From db493fbb394845630d164395f93948911abc3acd Mon Sep 17 00:00:00 2001 From: Michel Hollands Date: Thu, 27 Jul 2023 15:35:34 +0100 Subject: [PATCH] Add Mimir dashboards Signed-off-by: Michel Hollands --- .../mimir-alertmanager-resources.json | 836 +++ .../src/dashboards/mimir-alertmanager.json | 2703 ++++++++++ .../dashboards/mimir-compactor-resources.json | 940 ++++ .../src/dashboards/mimir-compactor.json | 2276 ++++++++ .../src/dashboards/mimir-config.json | 312 ++ .../src/dashboards/mimir-object-store.json | 938 ++++ .../src/dashboards/mimir-overrides.json | 266 + .../dashboards/mimir-overview-networking.json | 1135 ++++ .../dashboards/mimir-overview-resources.json | 1315 +++++ .../src/dashboards/mimir-overview.json | 1476 ++++++ .../src/dashboards/mimir-queries.json | 3201 +++++++++++ .../dashboards/mimir-reads-networking.json | 2134 ++++++++ .../src/dashboards/mimir-reads-resources.json | 2657 ++++++++++ .../src/dashboards/mimir-reads.json | 4683 +++++++++++++++++ .../mimir-remote-ruler-reads-resources.json | 1003 ++++ .../dashboards/mimir-remote-ruler-reads.json | 1177 +++++ .../dashboards/mimir-rollout-progress.json | 1448 +++++ .../src/dashboards/mimir-ruler.json | 2604 +++++++++ .../src/dashboards/mimir-scaling.json | 362 ++ .../src/dashboards/mimir-slow-queries.json | 323 ++ .../src/dashboards/mimir-tenants.json | 2817 ++++++++++ .../src/dashboards/mimir-top-tenants.json | 1467 ++++++ .../dashboards/mimir-writes-networking.json | 1135 ++++ .../dashboards/mimir-writes-resources.json | 1373 +++++ .../src/dashboards/mimir-writes.json | 2914 ++++++++++ .../templates/grafana/configmap-3.yaml | 19 + .../templates/grafana/configmap-4.yaml | 19 + .../templates/grafana/configmap-5.yaml | 19 + .../templates/grafana/configmap-6.yaml | 19 + .../templates/grafana/configmap-7.yaml | 19 + .../templates/grafana/dashboard.yaml | 46 +- .../templates/grafana/datasources.yaml | 2 +- .../templates/grafana/grafana.yaml | 40 +- 33 files changed, 41672 insertions(+), 6 deletions(-) create mode 100644 charts/meta-monitoring/src/dashboards/mimir-alertmanager-resources.json create mode 100644 charts/meta-monitoring/src/dashboards/mimir-alertmanager.json create mode 100644 charts/meta-monitoring/src/dashboards/mimir-compactor-resources.json create mode 100644 charts/meta-monitoring/src/dashboards/mimir-compactor.json create mode 100644 charts/meta-monitoring/src/dashboards/mimir-config.json create mode 100644 charts/meta-monitoring/src/dashboards/mimir-object-store.json create mode 100644 charts/meta-monitoring/src/dashboards/mimir-overrides.json create mode 100644 charts/meta-monitoring/src/dashboards/mimir-overview-networking.json create mode 100644 charts/meta-monitoring/src/dashboards/mimir-overview-resources.json create mode 100644 charts/meta-monitoring/src/dashboards/mimir-overview.json create mode 100644 charts/meta-monitoring/src/dashboards/mimir-queries.json create mode 100644 charts/meta-monitoring/src/dashboards/mimir-reads-networking.json create mode 100644 charts/meta-monitoring/src/dashboards/mimir-reads-resources.json create mode 100644 charts/meta-monitoring/src/dashboards/mimir-reads.json create mode 100644 charts/meta-monitoring/src/dashboards/mimir-remote-ruler-reads-resources.json create mode 100644 charts/meta-monitoring/src/dashboards/mimir-remote-ruler-reads.json create mode 100644 charts/meta-monitoring/src/dashboards/mimir-rollout-progress.json create mode 100644 charts/meta-monitoring/src/dashboards/mimir-ruler.json create mode 100644 charts/meta-monitoring/src/dashboards/mimir-scaling.json create mode 100644 charts/meta-monitoring/src/dashboards/mimir-slow-queries.json create mode 100644 charts/meta-monitoring/src/dashboards/mimir-tenants.json create mode 100644 charts/meta-monitoring/src/dashboards/mimir-top-tenants.json create mode 100644 charts/meta-monitoring/src/dashboards/mimir-writes-networking.json create mode 100644 charts/meta-monitoring/src/dashboards/mimir-writes-resources.json create mode 100644 charts/meta-monitoring/src/dashboards/mimir-writes.json create mode 100644 charts/meta-monitoring/templates/grafana/configmap-3.yaml create mode 100644 charts/meta-monitoring/templates/grafana/configmap-4.yaml create mode 100644 charts/meta-monitoring/templates/grafana/configmap-5.yaml create mode 100644 charts/meta-monitoring/templates/grafana/configmap-6.yaml create mode 100644 charts/meta-monitoring/templates/grafana/configmap-7.yaml diff --git a/charts/meta-monitoring/src/dashboards/mimir-alertmanager-resources.json b/charts/meta-monitoring/src/dashboards/mimir-alertmanager-resources.json new file mode 100644 index 0000000..821ec03 --- /dev/null +++ b/charts/meta-monitoring/src/dashboards/mimir-alertmanager-resources.json @@ -0,0 +1,836 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"alertmanager\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"alertmanager\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"alertmanager\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"alertmanager\",resource=\"cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "CPU", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"alertmanager\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"alertmanager\"} > 0)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"alertmanager\",resource=\"memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (workingset)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"alertmanager\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (go heap inuse)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Alertmanager", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?alertmanager.*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Receive bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?alertmanager.*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(instance, pod, device) (\n rate(\n node_disk_written_bytes_total[$__rate_interval]\n )\n)\n+\nignoring(pod) group_right() (\n label_replace(\n count by(\n instance,\n pod,\n device\n )\n (\n container_fs_writes_bytes_total{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n container=~\"alertmanager\",\n device!~\".*sda.*\"\n }\n ),\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ) * 0\n)\n\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}} - {{device}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Disk writes", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(instance, pod, device) (\n rate(\n node_disk_read_bytes_total[$__rate_interval]\n )\n) + ignoring(pod) group_right() (\n label_replace(\n count by(\n instance,\n pod,\n device\n )\n (\n container_fs_writes_bytes_total{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n container=~\"alertmanager\",\n device!~\".*sda.*\"\n }\n ),\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ) * 0\n)\n\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}} - {{device}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Disk reads", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Disk", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(persistentvolumeclaim) (\n kubelet_volume_stats_used_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"} /\n kubelet_volume_stats_capacity_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n)\nand\ncount by(persistentvolumeclaim) (\n kube_persistentvolumeclaim_labels{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n label_name=~\"(alertmanager).*\"\n }\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{persistentvolumeclaim}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Disk space utilization", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Alertmanager resources", + "uid": "a6883fb22799ac74479c7db872451092", + "version": 0 + } \ No newline at end of file diff --git a/charts/meta-monitoring/src/dashboards/mimir-alertmanager.json b/charts/meta-monitoring/src/dashboards/mimir-alertmanager.json new file mode 100644 index 0000000..c212767 --- /dev/null +++ b/charts/meta-monitoring/src/dashboards/mimir-alertmanager.json @@ -0,0 +1,2703 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "100px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "short", + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cluster_job_pod:cortex_alertmanager_alerts:sum{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Total alerts", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "short", + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cluster_job_pod:cortex_alertmanager_silences:sum{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Total silences", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "short", + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max(cortex_alertmanager_tenants_discovered{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Tenants", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Headlines", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "1xx": "#EAB839", + "2xx": "#7EB26D", + "3xx": "#6ED0E0", + "4xx": "#EF843C", + "5xx": "#E24D42", + "cancel": "#A9A9A9", + "error": "#E24D42", + "success": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "QPS", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"})) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A", + "step": 10 + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"})) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B", + "step": 10 + }, + { + "expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C", + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Alertmanager Distributor", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "failed": "#E24D42", + "successful": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cluster_job:cortex_alertmanager_alerts_received_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n-\nsum(cluster_job:cortex_alertmanager_alerts_invalid_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(cluster_job:cortex_alertmanager_alerts_invalid_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "failed", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "APS", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Alerts received", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "cortex_alertmanager_dispatcher_aggregation_groups{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "per pod Active Aggregation Groups", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Alerts grouping", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "failed": "#E24D42", + "successful": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cluster_job_integration:cortex_alertmanager_notifications_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n-\nsum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "failed", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "NPS", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "(\nsum(cluster_job_integration:cortex_alertmanager_notifications_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}) by(integration)\n-\nsum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}) by(integration)\n) > 0\nor on () vector(0)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "success - {{ integration }}", + "legendLink": null + }, + { + "expr": "sum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}) by(integration)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "failed - {{ integration }}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "NPS by integration", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_alertmanager_notification_latency_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_alertmanager_notification_latency_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_alertmanager_notification_latency_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_alertmanager_notification_latency_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Alert notifications", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 11, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Operations / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "max": 1, + "min": 0, + "noValue": "0", + "unit": "percentunit" + } + }, + "id": 12, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operation_failures_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\"}[$__rate_interval])) / sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\"}[$__rate_interval])) >= 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "title": "Error rate", + "type": "timeseries" + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 13, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"attributes\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"attributes\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: Attributes", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 14, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"exists\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"exists\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: Exists", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Alertmanager Configuration Object Store (Alertmanager accesses)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 15, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"get\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"get\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: Get", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 16, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"get_range\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"get_range\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: GetRange", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 17, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"upload\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"upload\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: Upload", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 18, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"delete\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"delete\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: Delete", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 19, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod) (cortex_alertmanager_tenants_owned{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Per pod tenants", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 20, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (cluster_job_pod:cortex_alertmanager_alerts:sum{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Per pod alerts", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 21, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (cluster_job_pod:cortex_alertmanager_silences:sum{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Per pod silences", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Replication", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "failed": "#E24D42", + "successful": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 22, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_alertmanager_sync_configs_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_alertmanager_sync_configs_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_alertmanager_sync_configs_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "failed", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Syncs/sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 23, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(reason) (rate(cortex_alertmanager_sync_configs_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{reason}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Syncs/sec (by reason)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 24, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum (rate(cortex_alertmanager_ring_check_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "errors", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Ring check errors/sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Tenant configuration sync", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 25, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(outcome) (rate(cortex_alertmanager_state_initial_sync_completed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "interval": "1m", + "intervalFactor": 2, + "legendFormat": "{{outcome}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Initial syncs /sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 26, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_alertmanager_state_initial_sync_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "interval": "1m", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_alertmanager_state_initial_sync_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "interval": "1m", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_alertmanager_state_initial_sync_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_alertmanager_state_initial_sync_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "interval": "1m", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Initial sync duration", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + "failed": "#E24D42", + "successful": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 27, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_alertmanager_state_fetch_replica_state_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_alertmanager_state_fetch_replica_state_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "interval": "1m", + "intervalFactor": 2, + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_alertmanager_state_fetch_replica_state_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "interval": "1m", + "intervalFactor": 2, + "legendFormat": "failed", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Fetch state from other alertmanagers /sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Sharding initial state sync", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "failed": "#E24D42", + "successful": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 28, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cluster_job:cortex_alertmanager_state_replication_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n-\nsum(cluster_job:cortex_alertmanager_state_replication_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(cluster_job:cortex_alertmanager_state_replication_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "failed", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Replicate state to other alertmanagers /sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + "failed": "#E24D42", + "successful": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 29, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cluster_job:cortex_alertmanager_partial_state_merges_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n-\nsum(cluster_job:cortex_alertmanager_partial_state_merges_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(cluster_job:cortex_alertmanager_partial_state_merges_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "failed", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Merge state from other alertmanagers /sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + "failed": "#E24D42", + "successful": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 30, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_alertmanager_state_persist_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_alertmanager_state_persist_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_alertmanager_state_persist_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "failed", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Persist state to remote storage /sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Sharding runtime state sync", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Alertmanager", + "uid": "b0d38d318bbddd80476246d4930f9e55", + "version": 0 + } \ No newline at end of file diff --git a/charts/meta-monitoring/src/dashboards/mimir-compactor-resources.json b/charts/meta-monitoring/src/dashboards/mimir-compactor-resources.json new file mode 100644 index 0000000..7eb5bfe --- /dev/null +++ b/charts/meta-monitoring/src/dashboards/mimir-compactor-resources.json @@ -0,0 +1,940 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\",resource=\"cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "CPU", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (go heap inuse)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU and memory", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod) (container_memory_rss{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\"} > 0)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\",resource=\"memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (RSS)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\"} > 0)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\",resource=\"memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (workingset)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?compactor.*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Receive bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?compactor.*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(instance, pod, device) (\n rate(\n node_disk_written_bytes_total[$__rate_interval]\n )\n)\n+\nignoring(pod) group_right() (\n label_replace(\n count by(\n instance,\n pod,\n device\n )\n (\n container_fs_writes_bytes_total{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n container=~\"compactor\",\n device!~\".*sda.*\"\n }\n ),\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ) * 0\n)\n\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}} - {{device}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Disk writes", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(instance, pod, device) (\n rate(\n node_disk_read_bytes_total[$__rate_interval]\n )\n) + ignoring(pod) group_right() (\n label_replace(\n count by(\n instance,\n pod,\n device\n )\n (\n container_fs_writes_bytes_total{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n container=~\"compactor\",\n device!~\".*sda.*\"\n }\n ),\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ) * 0\n)\n\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}} - {{device}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Disk reads", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(persistentvolumeclaim) (\n kubelet_volume_stats_used_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"} /\n kubelet_volume_stats_capacity_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n)\nand\ncount by(persistentvolumeclaim) (\n kube_persistentvolumeclaim_labels{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n label_name=~\"(compactor).*\"\n }\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{persistentvolumeclaim}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Disk space utilization", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Disk", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Compactor resources", + "uid": "09a5c49e9cdb2f2b24c6d184574a07fd", + "version": 0 + } \ No newline at end of file diff --git a/charts/meta-monitoring/src/dashboards/mimir-compactor.json b/charts/meta-monitoring/src/dashboards/mimir-compactor.json new file mode 100644 index 0000000..9857d15 --- /dev/null +++ b/charts/meta-monitoring/src/dashboards/mimir-compactor.json @@ -0,0 +1,2276 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "completed": "#7EB26D", + "failed": "#E24D42", + "started": "#34CCEB" + }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Per-instance runs\nNumber of times a compactor instance triggers a compaction across all tenants that it manages.\n\n", + "fill": 10, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": false, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_compactor_runs_started_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "started", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_compactor_runs_completed_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "completed", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_compactor_runs_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "failed", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Per-instance runs / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "description": "### Tenants compaction progress\nIn a multi-tenant cluster, display the progress of tenants that are compacted while compaction is running.\n\n", + "fieldConfig": { + "defaults": { + "max": 1, + "noValue": 1, + "unit": "percentunit" + } + }, + "id": 2, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "(\n cortex_compactor_tenants_processing_succeeded{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"} +\n cortex_compactor_tenants_processing_failed{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"} +\n cortex_compactor_tenants_skipped{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}\n)\n/\ncortex_compactor_tenants_discovered{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"} > 0\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Tenants compaction progress", + "type": "timeseries" + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Longest time since last successful run\nDisplays the amount of time since the most recent successful execution\nof the compactor.\nThe value shown will be for the compactor replica that has the longest time since its\nlast successful run.\nThe table to the right shows a summary for all compactor replicas.\n\nIf there is no time value, one of the following messages might appear:\n\n- If you see \"No compactor data\" in this panel, that means that no compactors are active yet.\n\n- If you see \"No successful runs\" in this panel, that means that compactors are active, but none\n of them were successfully executed yet.\n\nThese might be expected - for example, if you just recently restarted your compactors,\nthey might not have had a chance to complete their first compaction run.\nHowever, if these messages persist, you should check the health of your compactors.\n\n", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "decimals": 1, + "noValue": "No compactor data", + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Last run" + }, + "properties": [ + { + "id": "custom.width", + "value": 74 + }, + { + "id": "mappings", + "value": [ + { + "options": { + "from": "-Infinity", + "result": { + "color": "text", + "text": "No successful runs since startup yet" + }, + "to": 0 + }, + "type": "range" + } + ] + }, + { + "id": "color", + "value": { + "mode": "thresholds" + } + }, + { + "id": "thresholds", + "value": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "yellow", + "value": 7200 + }, + { + "color": "orange", + "value": 21600 + }, + { + "color": "red", + "value": 43200 + } + ] + } + } + ] + } + ] + }, + "fill": 1, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "reduceOptions": { + "calcs": [ + "first" + ], + "fields": "/^Last run$/", + "values": false + }, + "textMode": "value" + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod)\n(\n (time() * (max_over_time(cortex_compactor_last_successful_run_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[1h]) !=bool 0))\n -\n max_over_time(cortex_compactor_last_successful_run_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[1h])\n)\n", + "format": "table", + "instant": true, + "interval": "", + "intervalFactor": null, + "legendFormat": "", + "legendLink": null, + "step": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Longest time since last successful run", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transformations": [ + { + "id": "organize", + "options": { + "renameByName": { + "Value": "Last run", + "pod": "Compactor" + } + } + }, + { + "id": "sortBy", + "options": { + "sort": [ + { + "desc": true, + "field": "Last run" + } + ] + } + } + ], + "type": "stat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Last successful run per-compactor replica\nDisplays the compactor replicas, and for each, shows how long it has been since\nits last successful compaction run.\n\nThe value in the status column is based on how long it has been since the last successful compaction.\n\n- Okay: less than 2 hours\n- Delayed: more than 2 hours\n- Late: more than 6 hours\n- Very late: more than 12 hours\n\nIf the status of any compactor replicas are *Late* or *Very late*, check their health.\n\n", + "fieldConfig": { + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Status" + }, + "properties": [ + { + "id": "custom.displayMode", + "value": "color-background" + }, + { + "id": "mappings", + "value": [ + { + "options": { + "from": "-Infinity", + "result": { + "color": "transparent", + "text": "N/A" + }, + "to": 0 + }, + "type": "range" + }, + { + "options": { + "from": 0, + "result": { + "color": "green", + "text": "Ok" + }, + "to": 7200 + }, + "type": "range" + }, + { + "options": { + "from": 7200, + "result": { + "color": "yellow", + "text": "Delayed" + }, + "to": 21600 + }, + "type": "range" + }, + { + "options": { + "from": 21600, + "result": { + "color": "orange", + "text": "Late" + }, + "to": 43200 + }, + "type": "range" + }, + { + "options": { + "from": 43200, + "result": { + "color": "red", + "text": "Very late" + }, + "to": "Infinity" + }, + "type": "range" + }, + { + "options": { + "match": "null+nan", + "result": { + "color": "transparent", + "text": "Unknown" + } + }, + "type": "special" + } + ] + }, + { + "id": "custom.width", + "value": 86 + }, + { + "id": "custom.align", + "value": "center" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Last run" + }, + "properties": [ + { + "id": "unit", + "value": "s" + }, + { + "id": "custom.width", + "value": 74 + }, + { + "id": "mappings", + "value": [ + { + "options": { + "from": "-Infinity", + "result": { + "text": "Never" + }, + "to": 0 + }, + "type": "range" + } + ] + } + ] + } + ] + }, + "fill": 1, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod)\n(\n (time() * (max_over_time(cortex_compactor_last_successful_run_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[1h]) !=bool 0))\n -\n max_over_time(cortex_compactor_last_successful_run_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[1h])\n)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "Last run", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Last successful run per-compactor replica", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transformations": [ + { + "id": "organize", + "options": { + "renameByName": { + "Value": "Last run", + "pod": "Compactor" + } + } + }, + { + "id": "sortBy", + "options": { + "sort": [ + { + "desc": true, + "field": "Last run" + } + ] + } + }, + { + "id": "calculateField", + "options": { + "alias": "One", + "binary": { + "left": "Last run", + "operator": "/", + "right": "Last run" + }, + "mode": "binary", + "replaceFields": false + } + }, + { + "id": "calculateField", + "options": { + "alias": "Status", + "binary": { + "left": "Last run", + "operator": "*", + "right": "One" + }, + "mode": "binary", + "replaceFields": false + } + }, + { + "id": "filterFieldsByName", + "options": { + "include": { + "names": [ + "Compactor", + "Last run", + "Status" + ] + } + } + } + ], + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Summary", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### TSDB compactions / sec\nRate of TSDB compactions. Single TSDB compaction takes one or more input blocks and produces one or more (during \"split\" phase) output blocks.\n\n", + "fill": 1, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(prometheus_tsdb_compactions_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "compactions", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "TSDB compactions / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### TSDB compaction duration\nDisplay the amount of time that it has taken to run a single TSDB compaction.\n\n", + "fill": 1, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(prometheus_tsdb_compaction_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(prometheus_tsdb_compaction_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(prometheus_tsdb_compaction_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(prometheus_tsdb_compaction_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "TSDB compaction duration", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(max by(user) (cortex_bucket_blocks_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Average blocks / tenant", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Tenants with largest number of blocks\nThe 10 tenants with the largest number of blocks.\n\n", + "fill": 1, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "topk(10, max by(user) (cortex_bucket_blocks_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{user}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Tenants with largest number of blocks", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_compactor_blocks_marked_for_deletion_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "blocks", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Blocks marked for deletion / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + "failed": "#E24D42", + "successful": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_compactor_blocks_cleaned_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_compactor_block_cleanup_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "failed", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Blocks deletions / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Garbage collector", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "failed": "#E24D42", + "successful": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 11, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_compactor_meta_syncs_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_compactor_meta_sync_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_compactor_meta_sync_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "failed", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Metadata syncs / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_compactor_meta_sync_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_compactor_meta_sync_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_compactor_meta_sync_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_compactor_meta_sync_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Metadata sync duration", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Metadata sync", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 13, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Operations / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "max": 1, + "min": 0, + "noValue": "0", + "unit": "percentunit" + } + }, + "id": 14, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operation_failures_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\"}[$__rate_interval])) / sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\"}[$__rate_interval])) >= 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "title": "Error rate", + "type": "timeseries" + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 15, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"attributes\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"attributes\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: Attributes", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 16, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"exists\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"exists\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: Exists", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Object Store", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 17, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"get\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"get\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: Get", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 18, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"get_range\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"get_range\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: GetRange", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 19, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"upload\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"upload\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: Upload", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 20, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"delete\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"delete\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: Delete", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "1xx": "#EAB839", + "2xx": "#7EB26D", + "3xx": "#6ED0E0", + "4xx": "#EF843C", + "5xx": "#E24D42", + "cancel": "#A9A9A9", + "error": "#E24D42", + "success": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 21, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Requests / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 22, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Key-value store for compactors ring", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Compactor", + "uid": "1b3443aea86db629e6efdb7d05c53823", + "version": 0 + } \ No newline at end of file diff --git a/charts/meta-monitoring/src/dashboards/mimir-config.json b/charts/meta-monitoring/src/dashboards/mimir-config.json new file mode 100644 index 0000000..439d1ca --- /dev/null +++ b/charts/meta-monitoring/src/dashboards/mimir-config.json @@ -0,0 +1,312 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "count(cortex_config_hash{cluster=~\"$cluster\", namespace=~\"$namespace\"}) by (sha256)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "sha256:{{sha256}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Startup config file hashes", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "instances", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Startup config file", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "count(cortex_runtime_config_hash{cluster=~\"$cluster\", namespace=~\"$namespace\"}) by (sha256)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "sha256:{{sha256}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Runtime config file hashes", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "instances", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Runtime config file", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Config", + "uid": "5d9d0b4724c0f80d68467088ec61e003", + "version": 0 + } \ No newline at end of file diff --git a/charts/meta-monitoring/src/dashboards/mimir-object-store.json b/charts/meta-monitoring/src/dashboards/mimir-object-store.json new file mode 100644 index 0000000..2809123 --- /dev/null +++ b/charts/meta-monitoring/src/dashboards/mimir-object-store.json @@ -0,0 +1,938 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(component) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{component}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "RPS / component", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "max": 1, + "min": 0, + "noValue": "0", + "unit": "percentunit" + } + }, + "id": 2, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by(component) (rate(thanos_objstore_bucket_operation_failures_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) / sum by(component) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) >= 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{component}}", + "legendLink": null + } + ], + "title": "Error rate / component", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Components", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "RPS / operation", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "max": 1, + "min": 0, + "noValue": "0", + "unit": "percentunit" + } + }, + "id": 4, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operation_failures_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) / sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) >= 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "title": "Error rate / operation", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Operations", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"get\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"get\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Op: Get", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"get_range\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"get_range\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Op: GetRange", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"exists\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"exists\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Op: Exists", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"attributes\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"attributes\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Op: Attributes", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"upload\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"upload\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Op: Upload", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"delete\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"delete\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Op: Delete", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Object Store", + "uid": "e1324ee2a434f4158c00a9ee279d3292", + "version": 0 + } \ No newline at end of file diff --git a/charts/meta-monitoring/src/dashboards/mimir-overrides.json b/charts/meta-monitoring/src/dashboards/mimir-overrides.json new file mode 100644 index 0000000..2bfe440 --- /dev/null +++ b/charts/meta-monitoring/src/dashboards/mimir-overrides.json @@ -0,0 +1,266 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "${datasource}", + "id": 1, + "span": 12, + "targets": [ + { + "expr": "max by(limit_name) (cortex_limits_defaults{cluster=~\"$cluster\",namespace=~\"$namespace\"})", + "instant": true, + "legendFormat": "", + "refId": "A" + } + ], + "title": "Defaults", + "transformations": [ + { + "id": "labelsToFields", + "options": { } + }, + { + "id": "merge", + "options": { } + }, + { + "id": "organize", + "options": { + "excludeByName": { + "Time": true + }, + "indexByName": { + "Value": 1, + "limit_name": 0 + } + } + }, + { + "id": "sortBy", + "options": { + "fields": { }, + "sort": [ + { + "field": "limit_name" + } + ] + } + } + ], + "type": "table" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "${datasource}", + "id": 2, + "span": 12, + "targets": [ + { + "expr": "max by(user, limit_name) (cortex_limits_overrides{cluster=~\"$cluster\",namespace=~\"$namespace\",user=~\"${tenant_id}\"})", + "instant": true, + "legendFormat": "", + "refId": "A" + } + ], + "title": "Per-tenant overrides", + "transformations": [ + { + "id": "labelsToFields", + "options": { + "mode": "columns", + "valueLabel": "limit_name" + } + }, + { + "id": "merge", + "options": { } + }, + { + "id": "organize", + "options": { + "excludeByName": { + "Time": true + }, + "indexByName": { + "user": 0 + } + } + } + ], + "type": "table" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "current": { + "selected": true, + "text": ".*", + "value": ".*" + }, + "hide": 0, + "label": "Tenant ID", + "name": "tenant_id", + "options": [ + { + "selected": true, + "text": ".*", + "value": ".*" + } + ], + "query": ".*", + "type": "textbox" + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Overrides", + "uid": "1e2c358600ac53f09faea133f811b5bb", + "version": 0 + } \ No newline at end of file diff --git a/charts/meta-monitoring/src/dashboards/mimir-overview-networking.json b/charts/meta-monitoring/src/dashboards/mimir-overview-networking.json new file mode 100644 index 0000000..2e97c77 --- /dev/null +++ b/charts/meta-monitoring/src/dashboards/mimir-overview-networking.json @@ -0,0 +1,1135 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Receive bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "highest", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Inflight requests (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "TCP connections (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Writes", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Receive bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "highest", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Inflight requests (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "TCP connections (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Reads", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend).*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Receive bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend).*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 11, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend).*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend).*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "highest", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Inflight requests (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend).*\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend).*\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend).*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "TCP connections (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Backend", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Overview networking", + "uid": "e15c71d372cc541367a088f10d9fcd92", + "version": 0 + } \ No newline at end of file diff --git a/charts/meta-monitoring/src/dashboards/mimir-overview-resources.json b/charts/meta-monitoring/src/dashboards/mimir-overview-resources.json new file mode 100644 index 0000000..e253f9b --- /dev/null +++ b/charts/meta-monitoring/src/dashboards/mimir-overview-resources.json @@ -0,0 +1,1315 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor|ingester|mimir-write\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "CPU", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor|ingester|mimir-write\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (workingset)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor|ingester|mimir-write\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (go heap inuse)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Writes", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(instance, pod, device) (\n rate(\n node_disk_written_bytes_total[$__rate_interval]\n )\n)\n+\nignoring(pod) group_right() (\n label_replace(\n count by(\n instance,\n pod,\n device\n )\n (\n container_fs_writes_bytes_total{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n container=~\"distributor|ingester|mimir-write\",\n device!~\".*sda.*\"\n }\n ),\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ) * 0\n)\n\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}} - {{device}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Disk writes", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(instance, pod, device) (\n rate(\n node_disk_read_bytes_total[$__rate_interval]\n )\n) + ignoring(pod) group_right() (\n label_replace(\n count by(\n instance,\n pod,\n device\n )\n (\n container_fs_writes_bytes_total{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n container=~\"distributor|ingester|mimir-write\",\n device!~\".*sda.*\"\n }\n ),\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ) * 0\n)\n\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}} - {{device}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Disk reads", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(persistentvolumeclaim) (\n kubelet_volume_stats_used_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"} /\n kubelet_volume_stats_capacity_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n)\nand\ncount by(persistentvolumeclaim) (\n kube_persistentvolumeclaim_labels{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n label_name=~\"(distributor|ingester|mimir-write).*\"\n }\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{persistentvolumeclaim}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Disk space utilization", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "CPU", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (workingset)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (go heap inuse)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Reads", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "CPU", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 11, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (workingset)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (go heap inuse)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Backend", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 13, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(instance, pod, device) (\n rate(\n node_disk_written_bytes_total[$__rate_interval]\n )\n)\n+\nignoring(pod) group_right() (\n label_replace(\n count by(\n instance,\n pod,\n device\n )\n (\n container_fs_writes_bytes_total{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n container=~\"query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend\",\n device!~\".*sda.*\"\n }\n ),\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ) * 0\n)\n\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}} - {{device}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Disk writes", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 14, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(instance, pod, device) (\n rate(\n node_disk_read_bytes_total[$__rate_interval]\n )\n) + ignoring(pod) group_right() (\n label_replace(\n count by(\n instance,\n pod,\n device\n )\n (\n container_fs_writes_bytes_total{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n container=~\"query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend\",\n device!~\".*sda.*\"\n }\n ),\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ) * 0\n)\n\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}} - {{device}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Disk reads", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 15, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(persistentvolumeclaim) (\n kubelet_volume_stats_used_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"} /\n kubelet_volume_stats_capacity_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n)\nand\ncount by(persistentvolumeclaim) (\n kube_persistentvolumeclaim_labels{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n label_name=~\"(query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend).*\"\n }\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{persistentvolumeclaim}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Disk space utilization", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Overview resources", + "uid": "a9b92d3c4d1af325d872a9e9a7083d71", + "version": 0 + } \ No newline at end of file diff --git a/charts/meta-monitoring/src/dashboards/mimir-overview.json b/charts/meta-monitoring/src/dashboards/mimir-overview.json new file mode 100644 index 0000000..4c00736 --- /dev/null +++ b/charts/meta-monitoring/src/dashboards/mimir-overview.json @@ -0,0 +1,1476 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "content": "The 'Status' panel shows an overview on the cluster health over the time.\nTo investigate failures, see a specific dashboard:\n\n- Writes\n- Reads\n- Rule evaluations\n- Alerting notifications\n- Object storage\n", + "datasource": null, + "description": "", + "id": 1, + "mode": "markdown", + "span": 3, + "title": "", + "transparent": true, + "type": "text" + }, + { + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "#7EB26D", + "value": null + }, + { + "color": "#EAB839", + "value": 0.01 + }, + { + "color": "#E24D42", + "value": 0.050000000000000003 + } + ] + } + } + }, + "id": 2, + "options": { + "showValue": "never" + }, + "span": 6, + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": false, + "expr": "(\n # gRPC errors are not tracked as 5xx but \"error\".\n sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\",status_code=~\"5.*|error\"}[$__rate_interval]))\n or\n # Handle the case no failure has been tracked yet.\n vector(0)\n)\n/\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]))\n", + "instant": false, + "legendFormat": "Writes", + "range": true + }, + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": false, + "expr": "(\n sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\",status_code=~\"5.*\"}[$__rate_interval]))\n or\n # Handle the case no failure has been tracked yet.\n vector(0)\n)\n/\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]))\n", + "instant": false, + "legendFormat": "Reads", + "range": true + }, + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": false, + "expr": "(\n (\n sum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n +\n # Consider missed evaluations as failures.\n sum(rate(cortex_prometheus_rule_group_iterations_missed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n )\n or\n # Handle the case no failure has been tracked yet.\n vector(0)\n)\n/\nsum(rate(cortex_prometheus_rule_evaluations_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "instant": false, + "legendFormat": "Rule evaluations", + "range": true + }, + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": false, + "expr": "(\n # Failed notifications from ruler to Alertmanager (handling the case the ruler metrics are missing).\n ((sum(rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n) or vector(0))\n +\n # Failed notifications from Alertmanager to receivers (handling the case the alertmanager metrics are missing).\n ((sum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n) or vector(0))\n)\n/\n(\n # Total notifications from ruler to Alertmanager (handling the case the ruler metrics are missing).\n ((sum(rate(cortex_prometheus_notifications_sent_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n) or vector(0))\n +\n # Total notifications from Alertmanager to receivers (handling the case the alertmanager metrics are missing).\n ((sum(cluster_job_integration:cortex_alertmanager_notifications_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n) or vector(0))\n)\n", + "instant": false, + "legendFormat": "Alerting notifications", + "range": true + }, + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": false, + "expr": "sum(rate(thanos_objstore_bucket_operation_failures_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval]))\n/\nsum(rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval]))\n", + "instant": false, + "legendFormat": "Object storage", + "range": true + } + ], + "title": "Status", + "type": "state-timeline" + }, + { + "id": 3, + "options": { + "alertInstanceLabelFilter": "cluster=~\"$cluster\", namespace=~\"$namespace\"", + "alertName": "Mimir", + "dashboardAlerts": false, + "maxItems": 100, + "sortOrder": 3, + "stateFilter": { + "error": true, + "firing": true, + "noData": false, + "normal": false, + "pending": false + } + }, + "span": 3, + "title": "Firing alerts", + "type": "alertlist" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Mimir cluster health", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "content": "These panels show an overview on the write path. \nTo examine the write path in detail, see a specific dashboard:\n\n- Writes\n- Writes resources\n- Writes networking\n- Overview resources\n- Overview networking\n", + "datasource": null, + "description": "", + "id": 4, + "mode": "markdown", + "span": 3, + "title": "", + "transparent": true, + "type": "text" + }, + { + "aliasColors": { + "1xx": "#EAB839", + "2xx": "#7EB26D", + "3xx": "#6ED0E0", + "4xx": "#EF843C", + "5xx": "#E24D42", + "cancel": "#A9A9A9", + "error": "#E24D42", + "success": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Write requests / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A", + "step": 10 + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B", + "step": 10 + }, + { + "expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C", + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Write latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cluster_namespace_job:cortex_distributor_received_samples:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "samples / sec", + "legendLink": null + }, + { + "expr": "sum(cluster_namespace_job:cortex_distributor_received_exemplars:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "exemplars / sec", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Ingestion / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "cps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Writes", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "content": "These panels show an overview on the read path. \nTo examine the read path in detail, see a specific dashboard:\n\n- Reads\n- Reads resources\n- Reads networking\n- Overview resources\n- Overview networking\n- Queries\n- Compactor\n", + "datasource": null, + "description": "", + "id": 8, + "mode": "markdown", + "span": 3, + "title": "", + "transparent": true, + "type": "text" + }, + { + "aliasColors": { + "1xx": "#EAB839", + "2xx": "#7EB26D", + "3xx": "#6ED0E0", + "4xx": "#EF843C", + "5xx": "#E24D42", + "cancel": "#A9A9A9", + "error": "#E24D42", + "success": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Read requests / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A", + "step": 10 + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B", + "step": 10 + }, + { + "expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C", + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Read latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 11, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "instant queries", + "color": "#429D48" + }, + { + "alias": "range queries", + "color": "#F1C731" + }, + { + "alias": "\"label names\" queries", + "color": "#2A66CF" + }, + { + "alias": "\"label values\" queries", + "color": "#9E44C1" + }, + { + "alias": "series queries", + "color": "#FFAB57" + }, + { + "alias": "remote read queries", + "color": "#C79424" + }, + { + "alias": "metadata queries", + "color": "#84D586" + }, + { + "alias": "exemplar queries", + "color": "#A1C4FC" + }, + { + "alias": "other", + "color": "#C788DE" + } + ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_query\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "instant queries", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_query_range\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "range queries", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_labels\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "\"label names\" queries", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_label_name_values\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "\"label values\" queries", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_series\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "series queries", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_read\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "remote read queries", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_metadata\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "metadata queries", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_query_exemplars\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "exemplar queries", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_.*\",route!~\".*(query|query_range|label.*|series|read|metadata|query_exemplars)\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "other", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Queries / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Reads", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "content": "These panels show an overview on the recording and alerting rules evaluation.\nTo examine the rules evaluation and alerts notifications in detail, see a specific dashboard:\n\n- Ruler\n- Alertmanager\n- Alertmanager resources\n- Overview resources\n- Overview networking\n", + "datasource": null, + "description": "", + "id": 12, + "mode": "markdown", + "span": 3, + "title": "", + "transparent": true, + "type": "text" + }, + { + "aliasColors": { + "failed": "#E24D42", + "success": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 13, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_prometheus_rule_evaluations_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "success", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "failed", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_prometheus_rule_group_iterations_missed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "missed", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Rule evaluations / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 14, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum (rate(cortex_prometheus_rule_evaluation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum (rate(cortex_prometheus_rule_evaluation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "average", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Rule evaluations latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + "failed": "#E24D42", + "successful": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 15, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_prometheus_notifications_sent_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n -\nsum(rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "failed", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Alerting notifications sent to Alertmanager / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Recording and alerting rules", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "content": "These panels show an overview on the long-term storage (object storage).\nTo examine the storage in detail, see a specific dashboard:\n\n- Object store\n- Compactor\n", + "datasource": null, + "description": "", + "id": 16, + "mode": "markdown", + "span": 3, + "title": "", + "transparent": true, + "type": "text" + }, + { + "aliasColors": { + "failed": "#E24D42", + "successful": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 17, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval]))\n-\nsum(rate(thanos_objstore_bucket_operation_failures_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval]))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_failures_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval]))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "failed", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Requests / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 18, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "attributes", + "color": "#429D48" + }, + { + "alias": "delete", + "color": "#F1C731" + }, + { + "alias": "exists", + "color": "#2A66CF" + }, + { + "alias": "get", + "color": "#9E44C1" + }, + { + "alias": "get_range", + "color": "#FFAB57" + }, + { + "alias": "iter", + "color": "#C79424" + }, + { + "alias": "upload", + "color": "#84D586" + } + ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Operations / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 19, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(max by(user) (max_over_time(cortex_bucket_blocks_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[15m])))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "blocks", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Total number of blocks in the storage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Long-term storage (object storage)", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Overview", + "uid": "ffcd83628d7d4b5a03d1cafd159e6c9c", + "version": 0 + } \ No newline at end of file diff --git a/charts/meta-monitoring/src/dashboards/mimir-queries.json b/charts/meta-monitoring/src/dashboards/mimir-queries.json new file mode 100644 index 0000000..05475f1 --- /dev/null +++ b/charts/meta-monitoring/src/dashboards/mimir-queries.json @@ -0,0 +1,3201 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_query_frontend_queue_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_query_frontend_queue_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Queue duration", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_query_frontend_retries_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_query_frontend_retries_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_query_frontend_retries_sum{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_query_frontend_retries_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Retries", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (cortex_query_frontend_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Queue length (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "noValue": "0", + "unit": "short" + } + }, + "id": 4, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(user) (cortex_query_frontend_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{user}}", + "legendLink": null + } + ], + "title": "Queue length (per user)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query-frontend", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_query_scheduler_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_query_scheduler_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_query_scheduler_queue_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_query_scheduler_queue_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Queue duration", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (cortex_query_scheduler_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Queue length (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "noValue": "0", + "unit": "short" + } + }, + "id": 7, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(user) (cortex_query_scheduler_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{user}}", + "legendLink": null + } + ], + "title": "Queue length (per user)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query-scheduler", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Intervals per query\nThe average number of split queries (partitioned by time) executed a single input query.\n\n", + "fill": 1, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_frontend_split_queries_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) / sum(rate(cortex_frontend_query_range_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", method=\"split_by_interval_and_results_cache\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "splitting rate", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Intervals per query", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "# Query the new metric introduced in Mimir 2.10.\n(\n sum by(request_type) (rate(cortex_frontend_query_result_cache_hits_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))\n /\n sum by(request_type) (rate(cortex_frontend_query_result_cache_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))\n)\n# Otherwise fallback to the previous general-purpose metrics.\nor\n(\n label_replace(\n # Query metrics before and after migration to new memcached backend.\n sum (\n rate(cortex_cache_hits{name=~\"frontend.+\", cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n or\n rate(thanos_cache_memcached_hits_total{name=\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n )\n /\n sum (\n rate(cortex_cache_fetched_keys{name=~\"frontend.+\", cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n or\n rate(thanos_cache_memcached_requests_total{name=~\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n ),\n \"request_type\", \"query_range\", \"\", \"\")\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{request_type}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Query results cache hit ratio", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Query results cache skipped\nThe % of queries whose results could not be cached.\nIt is tracked for each split query when the splitting by interval is enabled.\n\n", + "fill": 10, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_frontend_query_result_cache_skipped_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (reason) /\nignoring (reason) group_left sum(rate(cortex_frontend_query_result_cache_attempted_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{reason}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Query results cache skipped", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query-frontend - query splitting and results cache", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Sharded queries ratio\nThe % of queries that have been successfully rewritten and executed in a shardable way.\nThis panel only takes into account the type of queries that are supported by query sharding (eg. range queries).\n\n", + "fill": 1, + "id": 11, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_frontend_query_sharding_rewrites_succeeded_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) /\nsum(rate(cortex_frontend_query_sharding_rewrites_attempted_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "sharded queries ratio", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Sharded queries ratio", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Number of sharded queries per query\nThe number of sharded queries that have been executed for a single input query. It only tracks queries that\nhave been successfully rewritten in a shardable way.\n\n", + "fill": 1, + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_frontend_sharded_queries_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_frontend_sharded_queries_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_frontend_sharded_queries_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_frontend_sharded_queries_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Number of sharded queries per query", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query-frontend - query sharding", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 13, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job:cortex_ingester_queried_series_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})) * 1", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A", + "step": 10 + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job:cortex_ingester_queried_series_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})) * 1", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B", + "step": 10 + }, + { + "expr": "1 * sum(cluster_job:cortex_ingester_queried_series_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}) / sum(cluster_job:cortex_ingester_queried_series_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C", + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Series per query", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 14, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job:cortex_ingester_queried_samples_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})) * 1", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A", + "step": 10 + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job:cortex_ingester_queried_samples_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})) * 1", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B", + "step": 10 + }, + { + "expr": "1 * sum(cluster_job:cortex_ingester_queried_samples_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}) / sum(cluster_job:cortex_ingester_queried_samples_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C", + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Samples per query", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 15, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job:cortex_ingester_queried_exemplars_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})) * 1", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A", + "step": 10 + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job:cortex_ingester_queried_exemplars_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})) * 1", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B", + "step": 10 + }, + { + "expr": "1 * sum(cluster_job:cortex_ingester_queried_exemplars_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}) / sum(cluster_job:cortex_ingester_queried_exemplars_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C", + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Exemplars per query", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ingester", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 16, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_querier_storegateway_instances_hit_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_querier_storegateway_instances_hit_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_querier_storegateway_instances_hit_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_querier_storegateway_instances_hit_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Number of store-gateways hit per query", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 17, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_querier_storegateway_refetches_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_querier_storegateway_refetches_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_querier_storegateway_refetches_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_querier_storegateway_refetches_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Refetches of missing blocks per query", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + "Failure Rate": "#E24D42" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 18, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_querier_blocks_consistency_checks_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) / sum(rate(cortex_querier_blocks_consistency_checks_total{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Failure Rate", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Consistency checks failed", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Rejected queries\nThe proportion of all queries received by queriers that were rejected for some reason.\n\n", + "fill": 1, + "id": 19, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (reason) (rate(cortex_querier_queries_rejected_total{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) / ignoring (reason) group_left sum(rate(cortex_querier_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_query(_range)?\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{reason}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Rejected queries", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Querier", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 20, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max(cortex_bucket_index_loaded{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Max", + "legendLink": null + }, + { + "expr": "min(cortex_bucket_index_loaded{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Min", + "legendLink": null + }, + { + "expr": "avg(cortex_bucket_index_loaded{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Bucket indexes loaded (per querier)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + "failed": "#E24D42", + "successful": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 21, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_bucket_index_loads_total{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) - sum(rate(cortex_bucket_index_load_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_bucket_index_load_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "failed", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Bucket indexes load / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 22, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_bucket_index_load_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_bucket_index_load_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_bucket_index_load_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_bucket_index_load_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Bucket indexes load latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 23, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_bucket_store_series_blocks_queried_sum{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "blocks", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Blocks queried / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 24, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(data_type) (\n # Exclude \"chunks refetched\".\n rate(cortex_bucket_store_series_data_size_fetched_bytes_sum{component=\"store-gateway\", stage!=\"refetched\", cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{data_type}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Data fetched / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "binBps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 25, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(data_type) (\n # Exclude \"chunks processed\" to only count \"chunks returned\", other than postings and series.\n rate(cortex_bucket_store_series_data_size_touched_bytes_sum{component=\"store-gateway\", stage!=\"processed\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{data_type}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Data touched / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "binBps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Store-gateway", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 26, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(stage) (rate(cortex_bucket_store_series_request_stage_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n/\nsum by(stage) (rate(cortex_bucket_store_series_request_stage_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{stage}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Series request average latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 27, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by(stage, le) (rate(cortex_bucket_store_series_request_stage_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{stage}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Series request 99th percentile latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Series batch preloading efficiency\nThis panel shows the % of time reduced by preloading, for Series() requests which have been\nsplit to 2+ batches. If a Series() request is served within a single batch, then preloading\nis not triggered, and thus not counted in this measurement.\n\n", + "fill": 1, + "id": 28, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "# Clamping min to 0 because if preloading not useful at all, then the actual value we get is\n# slightly negative because of the small overhead introduced by preloading.\nclamp_min(1 - (\n sum(rate(cortex_bucket_store_series_batch_preloading_wait_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\n sum(rate(cortex_bucket_store_series_batch_preloading_load_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n), 0)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "% of time reduced by preloading", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Series batch preloading efficiency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 29, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "cortex_bucket_store_blocks_loaded{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Blocks currently loaded", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + "failed": "#E24D42", + "successful": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 30, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_bucket_store_block_loads_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) - sum(rate(cortex_bucket_store_block_load_failures_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_bucket_store_block_load_failures_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "failed", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Blocks loaded / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + "failed": "#E24D42", + "successful": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 31, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_bucket_store_block_drops_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) - sum(rate(cortex_bucket_store_block_drop_failures_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_bucket_store_block_drop_failures_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "failed", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Blocks dropped / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 32, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "cortex_bucket_store_indexheader_lazy_load_total{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"} - cortex_bucket_store_indexheader_lazy_unload_total{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Lazy loaded index-headers", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 33, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_bucket_store_indexheader_lazy_load_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_bucket_store_indexheader_lazy_load_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_bucket_store_indexheader_lazy_load_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_bucket_store_indexheader_lazy_load_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Index-header lazy load duration", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Index-header lazy load gate latency\nTime spent waiting for a turn to load an index header. This time is not included in \"Index-header lazy load duration.\"\n\n", + "fill": 1, + "id": 34, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_bucket_stores_gate_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",gate=\"index_header\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_bucket_stores_gate_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",gate=\"index_header\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_bucket_stores_gate_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",gate=\"index_header\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_bucket_stores_gate_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",gate=\"index_header\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Index-header lazy load gate latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 35, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_bucket_store_series_hash_cache_hits_total{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n/\nsum(rate(cortex_bucket_store_series_hash_cache_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "hit ratio", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Series hash cache hit ratio", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 36, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(thanos_store_index_cache_hits_total{item_type=\"ExpandedPostings\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n/\nsum(rate(thanos_store_index_cache_requests_total{item_type=\"ExpandedPostings\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "hit ratio", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "ExpandedPostings cache hit ratio", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 37, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_cache_memory_hits_total{name=\"chunks-attributes-cache\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n/\nsum(rate(cortex_cache_memory_requests_total{name=\"chunks-attributes-cache\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "hit ratio", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Chunks attributes in-memory cache hit ratio", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Queries", + "uid": "b3abe8d5c040395cc36615cb4334c92d", + "version": 0 + } \ No newline at end of file diff --git a/charts/meta-monitoring/src/dashboards/mimir-reads-networking.json b/charts/meta-monitoring/src/dashboards/mimir-reads-networking.json new file mode 100644 index 0000000..ca0843e --- /dev/null +++ b/charts/meta-monitoring/src/dashboards/mimir-reads-networking.json @@ -0,0 +1,2134 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Receive bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "highest", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Inflight requests (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "TCP connections (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Summary", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-frontend.*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Receive bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-frontend.*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-frontend.*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-frontend.*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "highest", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Inflight requests (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-frontend.*\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-frontend.*\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-frontend.*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "TCP connections (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query-frontend", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-scheduler.*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Receive bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-scheduler.*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 11, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-scheduler.*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-scheduler.*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "highest", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Inflight requests (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-scheduler.*\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-scheduler.*\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-scheduler.*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "TCP connections (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query-scheduler", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 13, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?querier.*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Receive bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 14, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?querier.*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 15, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?querier.*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?querier.*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "highest", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Inflight requests (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 16, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?querier.*\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?querier.*\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?querier.*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "TCP connections (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Querier", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 17, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?store-gateway.*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Receive bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 18, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?store-gateway.*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 19, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?store-gateway.*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?store-gateway.*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "highest", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Inflight requests (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 20, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?store-gateway.*\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?store-gateway.*\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?store-gateway.*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "TCP connections (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Store-gateway", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 21, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler.*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Receive bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 22, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler.*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 23, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler.*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler.*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "highest", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Inflight requests (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 24, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler.*\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler.*\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler.*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "TCP connections (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ruler", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Reads networking", + "uid": "54b2a0a4748b3bd1aefa92ce5559a1c2", + "version": 0 + } \ No newline at end of file diff --git a/charts/meta-monitoring/src/dashboards/mimir-reads-resources.json b/charts/meta-monitoring/src/dashboards/mimir-reads-resources.json new file mode 100644 index 0000000..ea744fb --- /dev/null +++ b/charts/meta-monitoring/src/dashboards/mimir-reads-resources.json @@ -0,0 +1,2657 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "CPU", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (workingset)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (go heap inuse)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Summary", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend\",resource=\"cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "CPU", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend\"} > 0)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend\",resource=\"memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (workingset)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (go heap inuse)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query-frontend", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-scheduler\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-scheduler\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-scheduler\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-scheduler\",resource=\"cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "CPU", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-scheduler\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-scheduler\"} > 0)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-scheduler\",resource=\"memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (workingset)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-scheduler\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (go heap inuse)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query-scheduler", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"querier\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"querier\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"querier\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"querier\",resource=\"cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "CPU", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 11, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"querier\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"querier\"} > 0)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"querier\",resource=\"memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (workingset)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"querier\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (go heap inuse)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Querier", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 13, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\",resource=\"cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "CPU", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 14, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (go heap inuse)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ingester", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 15, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod) (container_memory_rss{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"} > 0)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\",resource=\"memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (RSS)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 16, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"} > 0)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\",resource=\"memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (workingset)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 17, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Rules", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 18, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler\",resource=\"cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "CPU", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ruler", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 19, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler\"} > 0)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler\",resource=\"memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (workingset)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 20, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (go heap inuse)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 21, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"store-gateway\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"store-gateway\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"store-gateway\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"store-gateway\",resource=\"cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "CPU", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 22, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"store-gateway\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (go heap inuse)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Store-gateway", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 23, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod) (container_memory_rss{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"store-gateway\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"store-gateway\"} > 0)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"store-gateway\",resource=\"memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (RSS)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 24, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"store-gateway\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"store-gateway\"} > 0)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"store-gateway\",resource=\"memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (workingset)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 25, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(instance, pod, device) (\n rate(\n node_disk_written_bytes_total[$__rate_interval]\n )\n)\n+\nignoring(pod) group_right() (\n label_replace(\n count by(\n instance,\n pod,\n device\n )\n (\n container_fs_writes_bytes_total{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n container=~\"store-gateway\",\n device!~\".*sda.*\"\n }\n ),\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ) * 0\n)\n\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}} - {{device}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Disk writes", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 26, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(instance, pod, device) (\n rate(\n node_disk_read_bytes_total[$__rate_interval]\n )\n) + ignoring(pod) group_right() (\n label_replace(\n count by(\n instance,\n pod,\n device\n )\n (\n container_fs_writes_bytes_total{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n container=~\"store-gateway\",\n device!~\".*sda.*\"\n }\n ),\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ) * 0\n)\n\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}} - {{device}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Disk reads", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 27, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(persistentvolumeclaim) (\n kubelet_volume_stats_used_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"} /\n kubelet_volume_stats_capacity_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n)\nand\ncount by(persistentvolumeclaim) (\n kube_persistentvolumeclaim_labels{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n label_name=~\"(store-gateway).*\"\n }\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{persistentvolumeclaim}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Disk space utilization", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Reads resources", + "uid": "cc86fd5aa9301c6528986572ad974db9", + "version": 0 + } \ No newline at end of file diff --git a/charts/meta-monitoring/src/dashboards/mimir-reads.json b/charts/meta-monitoring/src/dashboards/mimir-reads.json new file mode 100644 index 0000000..690bb3a --- /dev/null +++ b/charts/meta-monitoring/src/dashboards/mimir-reads.json @@ -0,0 +1,4683 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "175px", + "panels": [ + { + "content": "

\n This dashboard shows health metrics for the read path.\n It is broken into sections for each service on the read path, and organized by the order in which the read request flows.\n
\n Incoming queries travel from the gateway → query frontend → query scheduler → querier → ingester and/or store-gateway (depending on the time range of the query).\n
\n For each service, there are 3 panels showing (1) requests per second to that service, (2) average, median, and p99 latency of requests to that service, and (3) p99 latency of requests to each instance of that service.\n

\n

\n The dashboard also shows metrics for the 4 optional caches that can be deployed:\n the query results cache, the metadata cache, the chunks cache, and the index cache.\n
\n These panels will show “no data” if the caches are not deployed.\n

\n

\n Lastly, it also includes metrics for how the ingester and store-gateway interact with object storage.\n

\n", + "datasource": null, + "description": "", + "id": 1, + "mode": "markdown", + "span": 12, + "title": "", + "transparent": true, + "type": "text" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Reads dashboard description", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "100px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Instant queries per second\nRate of instant queries per second being made to the system.\nIncludes both queries made to the /prometheus API as\nwell as queries from the ruler.\n\n", + "fill": 1, + "format": "reqps", + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n rate(\n cortex_request_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",\n route=~\"(prometheus|api_prom)_api_v1_query\"\n }[$__rate_interval]\n )\n or\n rate(\n cortex_prometheus_rule_evaluations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n)\n", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Instant queries / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Range queries per second\nRate of range queries per second being made to\nMimir via the /prometheus API.\n\n", + "fill": 1, + "format": "reqps", + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_query_range\"}[$__rate_interval]))", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Range queries / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### \"Label names\" queries per second\nRate of \"label names\" endpoint queries per second being made to\nMimir via the /prometheus API.\n\n", + "fill": 1, + "format": "reqps", + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_labels\"}[$__rate_interval]))", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Label names queries / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### \"Label values\" queries per second\nRate of specific \"label values\" endpoint queries per second being made to\nMimir via the /prometheus API.\n\n", + "fill": 1, + "format": "reqps", + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_label_name_values\"}[$__rate_interval]))", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Label values queries / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Series queries per second\nRate of series queries per second being made to\nMimir via the /prometheus API.\n\n", + "fill": 1, + "format": "reqps", + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_series\"}[$__rate_interval]))", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Series queries / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Headlines", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "1xx": "#EAB839", + "2xx": "#7EB26D", + "3xx": "#6ED0E0", + "4xx": "#EF843C", + "5xx": "#E24D42", + "cancel": "#A9A9A9", + "error": "#E24D42", + "success": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Requests / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A", + "step": 10 + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B", + "step": 10 + }, + { + "expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C", + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 9, + "links": [ ], + "options": { + "legend": { + "displayMode": "hidden", + "showLegend": false + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "exemplar": true, + "expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval])))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "legendLink": null + } + ], + "title": "Per pod p99 latency", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query-frontend", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "content": "

\n The query scheduler is an optional service that moves\n the internal queue from the query-frontend into a\n separate component.\n If this service is not deployed,\n these panels will show \"No data.\"\n

\n", + "datasource": null, + "description": "", + "id": 10, + "mode": "markdown", + "span": 4, + "title": "", + "transparent": true, + "type": "text" + }, + { + "aliasColors": { + "1xx": "#EAB839", + "2xx": "#7EB26D", + "3xx": "#6ED0E0", + "4xx": "#EF843C", + "5xx": "#E24D42", + "cancel": "#A9A9A9", + "error": "#E24D42", + "success": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 11, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_query_scheduler_queue_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Requests / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_query_scheduler_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_query_scheduler_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_query_scheduler_queue_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_query_scheduler_queue_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency (Time in Queue)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query-scheduler", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 13, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum (\n rate(thanos_memcached_operations_total{name=\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_operations_total{name=\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Requests/s", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Requests / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 14, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n) by (le)) * 1e3\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A", + "step": 10 + }, + { + "expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n) by (le)) * 1e3\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C", + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Cache – query results", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "1xx": "#EAB839", + "2xx": "#7EB26D", + "3xx": "#6ED0E0", + "4xx": "#EF843C", + "5xx": "#E24D42", + "cancel": "#A9A9A9", + "error": "#E24D42", + "success": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 15, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_querier_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Requests / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 16, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A", + "step": 10 + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B", + "step": 10 + }, + { + "expr": "1e3 * sum(cluster_job_route:cortex_querier_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}) / sum(cluster_job_route:cortex_querier_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C", + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 17, + "links": [ ], + "options": { + "legend": { + "displayMode": "hidden", + "showLegend": false + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "exemplar": true, + "expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_querier_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval])))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "legendLink": null + } + ], + "title": "Per pod p99 latency", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Querier", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "1xx": "#EAB839", + "2xx": "#7EB26D", + "3xx": "#6ED0E0", + "4xx": "#EF843C", + "5xx": "#E24D42", + "cancel": "#A9A9A9", + "error": "#E24D42", + "success": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 18, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\",route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Requests / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 19, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"})) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A", + "step": 10 + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"})) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B", + "step": 10 + }, + { + "expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C", + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 20, + "links": [ ], + "options": { + "legend": { + "displayMode": "hidden", + "showLegend": false + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "exemplar": true, + "expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/Query(Stream)?|/cortex.Ingester/MetricsForLabelMatchers|/cortex.Ingester/LabelValues|/cortex.Ingester/MetricsMetadata\"}[$__rate_interval])))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "legendLink": null + } + ], + "title": "Per pod p99 latency", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ingester", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "1xx": "#EAB839", + "2xx": "#7EB26D", + "3xx": "#6ED0E0", + "4xx": "#EF843C", + "5xx": "#E24D42", + "cancel": "#A9A9A9", + "error": "#E24D42", + "success": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 21, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",route=~\"/gatewaypb.StoreGateway/.*\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Requests / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 22, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"})) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A", + "step": 10 + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"})) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B", + "step": 10 + }, + { + "expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C", + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 23, + "links": [ ], + "options": { + "legend": { + "displayMode": "hidden", + "showLegend": false + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "exemplar": true, + "expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"}[$__rate_interval])))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "legendLink": null + } + ], + "title": "Per pod p99 latency", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Store-gateway", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Replicas\nThe maximum, and current number of querier replicas.\nPlease note that the current number of replicas can still show 1 replica even when scaled to 0.\nSince HPA never reports 0 replicas, the query will report 0 only if the HPA is not active.\n\n", + "fill": 1, + "id": 24, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/Max .+/", + "dashes": true, + "fill": 0 + }, + { + "alias": "/Current .+/", + "fill": 0 + } + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "kube_horizontalpodautoscaler_spec_max_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-querier\"}\n# Add the scaletargetref_name label which is more readable than \"kube-hpa-...\"\n+ on (cluster, namespace, horizontalpodautoscaler) group_left (scaletargetref_name)\n 0*kube_horizontalpodautoscaler_info{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-querier\"}\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Max {{ scaletargetref_name }}", + "legendLink": null + }, + { + "expr": "kube_horizontalpodautoscaler_status_current_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-querier\"}\n# HPA doesn't go to 0 replicas, so we multiply by 0 if the HPA is not active.\n* on (cluster, namespace, horizontalpodautoscaler)\n kube_horizontalpodautoscaler_status_condition{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-querier\", condition=\"ScalingActive\", status=\"true\"}\n# Add the scaletargetref_name label which is more readable than \"kube-hpa-...\"\n+ on (cluster, namespace, horizontalpodautoscaler) group_left (scaletargetref_name)\n 0*kube_horizontalpodautoscaler_info{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-querier\"}\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Current {{ scaletargetref_name }}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Replicas", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Scaling metric (desired replicas)\nThis panel shows the result scaling metric exposed by KEDA divided by the target/threshold used.\nIt should represent the desired number of replicas, ignoring the min/max constraints which are applied later.\n\n", + "fill": 1, + "id": 25, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "Target per replica", + "yaxis": 2 + } + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "keda_metrics_adapter_scaler_metrics_value\n/\non(metric) group_left\nlabel_replace(\n kube_horizontalpodautoscaler_spec_target_metric{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-querier\"},\n \"metric\", \"$1\", \"metric_name\", \"(.+)\"\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ scaledObject }}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Scaling metric (desired replicas)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Autoscaler failures rate\nThe rate of failures in the KEDA custom metrics API server. Whenever an error occurs, the KEDA custom\nmetrics server is unable to query the scaling metric from Prometheus so the autoscaler woudln't work properly.\n\n", + "fill": 1, + "id": 26, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(metric) (rate(keda_metrics_adapter_scaler_errors[$__rate_interval])) +\non(metric) group_left\nlabel_replace(\n kube_horizontalpodautoscaler_spec_target_metric{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-querier\"}\n * 0, \"metric\", \"$1\", \"metric_name\", \"(.+)\"\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{metric}} failures", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Autoscaler failures rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Querier - autoscaling", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "1xx": "#EAB839", + "2xx": "#7EB26D", + "3xx": "#6ED0E0", + "4xx": "#EF843C", + "5xx": "#E24D42", + "cancel": "#A9A9A9", + "error": "#E24D42", + "success": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 27, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Requests / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 28, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Store-gateway – key-value store for store-gateways ring", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 29, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(operation) (\n # Backwards compatibility\n rate(\n thanos_memcached_operations_total{\n component=\"store-gateway\",\n name=\"index-cache\",\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n or ignoring(backend)\n rate(\n thanos_cache_operations_total{\n component=\"store-gateway\",\n name=\"index-cache\",\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Requests / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 30, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A", + "step": 10 + }, + { + "expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C", + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency (getmulti)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Hit ratio\nEven if you do not set up memcached for the blocks index cache, you will still see data in this panel because the store-gateway by default has an\nin-memory blocks index cache.\n\n", + "fill": 1, + "id": 31, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(item_type) (\n rate(\n thanos_store_index_cache_hits_total{\n component=\"store-gateway\",\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n)\n/\nsum by(item_type) (\n rate(\n thanos_store_index_cache_requests_total{\n component=\"store-gateway\",\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{item_type}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Hit ratio", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memcached – block index cache (store-gateway accesses)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 32, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(operation) (\n # Backwards compatibility\n rate(thanos_memcached_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Requests / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 33, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A", + "step": 10 + }, + { + "expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C", + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency (getmulti)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 34, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n # Backwards compatibility\n rate(thanos_cache_memcached_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n)\n/\nsum(\n # Backwards compatibility\n rate(thanos_cache_memcached_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "items", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Hit ratio", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memcached – chunks cache (store-gateway accesses)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 35, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(operation) (\n # Backwards compatibility\n rate(thanos_memcached_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Requests / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 36, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A", + "step": 10 + }, + { + "expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C", + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency (getmulti)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 37, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n # Backwards compatibility\n rate(thanos_cache_memcached_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n/\nsum(\n # Backwards compatibility\n rate(thanos_cache_memcached_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "items", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Hit ratio", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memcached – metadata cache (store-gateway accesses)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 38, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(operation) (\n # Backwards compatibility\n rate(thanos_memcached_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Requests / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 39, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A", + "step": 10 + }, + { + "expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C", + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency (getmulti)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 40, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n # Backwards compatibility\n rate(thanos_cache_memcached_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n/\nsum(\n # Backwards compatibility\n rate(thanos_cache_memcached_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "items", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Hit ratio", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memcached – metadata cache (querier accesses)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 41, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Operations / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "max": 1, + "min": 0, + "noValue": "0", + "unit": "percentunit" + } + }, + "id": 42, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operation_failures_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\"}[$__rate_interval])) / sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\"}[$__rate_interval])) >= 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "title": "Error rate", + "type": "timeseries" + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 43, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"attributes\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"attributes\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: Attributes", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 44, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"exists\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"exists\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: Exists", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Blocks object store (store-gateway accesses)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 45, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"get\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"get\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: Get", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 46, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"get_range\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"get_range\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: GetRange", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 47, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"upload\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"upload\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: Upload", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 48, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"delete\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"delete\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: Delete", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 49, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Operations / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "max": 1, + "min": 0, + "noValue": "0", + "unit": "percentunit" + } + }, + "id": 50, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operation_failures_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\"}[$__rate_interval])) / sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\"}[$__rate_interval])) >= 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "title": "Error rate", + "type": "timeseries" + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 51, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"attributes\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"attributes\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: Attributes", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 52, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"exists\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"exists\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: Exists", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Blocks object store (querier accesses)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 53, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"get\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"get\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: Get", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 54, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"get_range\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"get_range\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: GetRange", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 55, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"upload\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"upload\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: Upload", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 56, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"delete\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"delete\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: Delete", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Reads", + "uid": "e327503188913dc38ad571c647eef643", + "version": 0 + } \ No newline at end of file diff --git a/charts/meta-monitoring/src/dashboards/mimir-remote-ruler-reads-resources.json b/charts/meta-monitoring/src/dashboards/mimir-remote-ruler-reads-resources.json new file mode 100644 index 0000000..4620ab0 --- /dev/null +++ b/charts/meta-monitoring/src/dashboards/mimir-remote-ruler-reads-resources.json @@ -0,0 +1,1003 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-frontend\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-frontend\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-frontend\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-frontend\",resource=\"cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "CPU", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-frontend\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-frontend\"} > 0)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-frontend\",resource=\"memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (workingset)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-frontend\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (go heap inuse)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query-frontend (dedicated to ruler)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-scheduler\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-scheduler\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-scheduler\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-scheduler\",resource=\"cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "CPU", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-scheduler\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-scheduler\"} > 0)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-scheduler\",resource=\"memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (workingset)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-scheduler\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (go heap inuse)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query-scheduler (dedicated to ruler)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-querier\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-querier\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-querier\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-querier\",resource=\"cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "CPU", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-querier\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-querier\"} > 0)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-querier\",resource=\"memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (workingset)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-querier\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (go heap inuse)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Querier (dedicated to ruler)", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Remote ruler reads resources", + "uid": "1940f6ef765a506a171faa2056c956c3", + "version": 0 + } \ No newline at end of file diff --git a/charts/meta-monitoring/src/dashboards/mimir-remote-ruler-reads.json b/charts/meta-monitoring/src/dashboards/mimir-remote-ruler-reads.json new file mode 100644 index 0000000..743b5de --- /dev/null +++ b/charts/meta-monitoring/src/dashboards/mimir-remote-ruler-reads.json @@ -0,0 +1,1177 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "175px", + "panels": [ + { + "content": "

\n This dashboard shows health metrics for the ruler read path when remote operational mode is enabled.\n It is broken into sections for each service on the ruler read path, and organized by the order in which the read request flows.\n
\n For each service, there are three panels showing (1) requests per second to that service, (2) average, median, and p99 latency of requests to that service, and (3) p99 latency of requests to each instance of that service.\n

\n", + "datasource": null, + "description": "", + "id": 1, + "mode": "markdown", + "span": 12, + "title": "", + "transparent": true, + "type": "text" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Remote ruler reads dashboard description", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "100px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Evaluations per second\nRate of rule expressions evaluated per second.\n\n", + "fill": 1, + "format": "reqps", + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n rate(\n cortex_request_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\",\n route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"\n }[$__rate_interval]\n )\n)\n", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Evaluations / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Headlines", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "1xx": "#EAB839", + "2xx": "#7EB26D", + "3xx": "#6ED0E0", + "4xx": "#EF843C", + "5xx": "#E24D42", + "cancel": "#A9A9A9", + "error": "#E24D42", + "success": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\", route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Requests / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\", route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"})) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A", + "step": 10 + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\", route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"})) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B", + "step": 10 + }, + { + "expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\", route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\", route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C", + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 5, + "links": [ ], + "options": { + "legend": { + "displayMode": "hidden", + "showLegend": false + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "exemplar": true, + "expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\", route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"}[$__rate_interval])))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "legendLink": null + } + ], + "title": "Per pod p99 latency", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query-frontend (dedicated to ruler)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "1xx": "#EAB839", + "2xx": "#7EB26D", + "3xx": "#6ED0E0", + "4xx": "#EF843C", + "5xx": "#E24D42", + "cancel": "#A9A9A9", + "error": "#E24D42", + "success": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_query_scheduler_queue_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Requests / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_query_scheduler_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_query_scheduler_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_query_scheduler_queue_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_query_scheduler_queue_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency (time in queue)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query-scheduler (dedicated to ruler)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "1xx": "#EAB839", + "2xx": "#7EB26D", + "3xx": "#6ED0E0", + "4xx": "#EF843C", + "5xx": "#E24D42", + "cancel": "#A9A9A9", + "error": "#E24D42", + "success": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_querier_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-querier.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Requests / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-querier.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A", + "step": 10 + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-querier.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B", + "step": 10 + }, + { + "expr": "1e3 * sum(cluster_job_route:cortex_querier_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-querier.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}) / sum(cluster_job_route:cortex_querier_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-querier.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C", + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 10, + "links": [ ], + "options": { + "legend": { + "displayMode": "hidden", + "showLegend": false + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "exemplar": true, + "expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_querier_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-querier.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval])))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "legendLink": null + } + ], + "title": "Per pod p99 latency", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Querier (dedicated to ruler)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Replicas\nThe minimum, maximum, and current number of querier replicas.\n\n", + "fill": 1, + "id": 11, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "kube_horizontalpodautoscaler_spec_min_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=\"keda-hpa-ruler-querier\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Min", + "legendLink": null + }, + { + "expr": "kube_horizontalpodautoscaler_spec_max_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=\"keda-hpa-ruler-querier\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Max", + "legendLink": null + }, + { + "expr": "kube_horizontalpodautoscaler_status_current_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=\"keda-hpa-ruler-querier\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Current", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Replicas", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Scaling metric\nThis panel shows the result of the query that is used as the scaling metric, and the target and threshold used.\nThe desired number of replicas is computed by HPA as: / .\n\n", + "fill": 1, + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "Target per replica", + "yaxis": 2 + } + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "keda_metrics_adapter_scaler_metrics_value +\non(metric) group_left\nlabel_replace(\n kube_horizontalpodautoscaler_spec_target_metric{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\"}\n * 0, \"metric\", \"$1\", \"metric_name\", \"(.+)\"\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Scaling metric", + "legendLink": null + }, + { + "expr": "kube_horizontalpodautoscaler_spec_target_metric{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=\"keda-hpa-ruler-querier\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Target per replica", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Scaling metric", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Autoscaler failures rate\nThe rate of failures in the KEDA custom metrics API server. Whenever an error occurs, the KEDA custom\nmetrics server is unable to query the scaling metric from Prometheus so the autoscaler does not work properly.\n\n", + "fill": 1, + "id": 13, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(metric) (rate(keda_metrics_adapter_scaler_errors[$__rate_interval])) +\non(metric) group_left\nlabel_replace(\n kube_horizontalpodautoscaler_spec_target_metric{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\"}\n * 0, \"metric\", \"$1\", \"metric_name\", \"(.+)\"\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{metric}} failures", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Autoscaler failures rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Querier (dedicated to ruler) - autoscaling", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Remote ruler reads", + "uid": "f103238f7f5ab2f1345ce650cbfbfe2f", + "version": 0 + } \ No newline at end of file diff --git a/charts/meta-monitoring/src/dashboards/mimir-rollout-progress.json b/charts/meta-monitoring/src/dashboards/mimir-rollout-progress.json new file mode 100644 index 0000000..9face76 --- /dev/null +++ b/charts/meta-monitoring/src/dashboards/mimir-rollout-progress.json @@ -0,0 +1,1448 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "custom": { + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "fillOpacity": 80, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineWidth": 1, + "scaleDistribution": { + "type": "linear" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [ ], + "max": 1, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "percentunit" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Ready" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "green", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Updated" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "blue", + "mode": "fixed" + } + } + ] + } + ] + }, + "gridPos": { + "h": 13, + "w": 10, + "x": 0, + "y": 0 + }, + "id": 1, + "links": [ ], + "options": { + "barRadius": 0, + "barWidth": 0.96999999999999997, + "fullHighlight": false, + "groupWidth": 0.69999999999999996, + "legend": { + "calcs": [ ], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "orientation": "horizontal", + "showValue": "auto", + "stacking": "none", + "tooltip": { + "mode": "multi", + "sort": "none" + }, + "xField": "Workload", + "xTickLabelRotation": 0, + "xTickLabelSpacing": 0 + }, + "targets": [ + { + "expr": "(\n sum by(cortex_service) (\n label_replace(\n label_replace(\n label_replace(\n {__name__=~\"kube_(deployment|statefulset)_status_replicas_updated\", cluster=~\"$cluster\", namespace=~\"$namespace\"},\n \"cortex_service\", \"$1\", \"deployment\", \"(.+)\"\n ),\n \"cortex_service\", \"$1\", \"statefulset\", \"(.+)\"\n ),\n # Strip the -zone-X suffix, if there is one\n \"cortex_service\", \"$1\", \"cortex_service\", \"(.*?)(?:-zone-[a-z])?\"\n )\n )\n /\n sum by(cortex_service) (\n label_replace(\n label_replace(\n label_replace(\n {__name__=~\"kube_(deployment|statefulset)_status_replicas\", cluster=~\"$cluster\", namespace=~\"$namespace\"},\n \"cortex_service\", \"$1\", \"deployment\", \"(.+)\"\n ),\n \"cortex_service\", \"$1\", \"statefulset\", \"(.+)\"\n ),\n # Strip the -zone-X suffix, if there is one\n \"cortex_service\", \"$1\", \"cortex_service\", \"(.*?)(?:-zone-[a-z])?\"\n )\n )\n) and (\n sum by(cortex_service) (\n label_replace(\n label_replace(\n label_replace(\n {__name__=~\"kube_(deployment|statefulset)_status_replicas\", cluster=~\"$cluster\", namespace=~\"$namespace\"},\n \"cortex_service\", \"$1\", \"deployment\", \"(.+)\"\n ),\n \"cortex_service\", \"$1\", \"statefulset\", \"(.+)\"\n ),\n # Strip the -zone-X suffix, if there is one\n \"cortex_service\", \"$1\", \"cortex_service\", \"(.*?)(?:-zone-[a-z])?\"\n )\n )\n > 0\n)\n", + "format": "table", + "instant": true, + "intervalFactor": null, + "legendFormat": "__auto", + "legendLink": null, + "step": null + }, + { + "expr": "(\n sum by(cortex_service) (\n label_replace(\n label_replace(\n label_replace(\n {__name__=~\"kube_(deployment|statefulset)_status_replicas_ready\", cluster=~\"$cluster\", namespace=~\"$namespace\"},\n \"cortex_service\", \"$1\", \"deployment\", \"(.+)\"\n ),\n \"cortex_service\", \"$1\", \"statefulset\", \"(.+)\"\n ),\n # Strip the -zone-X suffix, if there is one\n \"cortex_service\", \"$1\", \"cortex_service\", \"(.*?)(?:-zone-[a-z])?\"\n )\n )\n /\n sum by(cortex_service) (\n label_replace(\n label_replace(\n label_replace(\n {__name__=~\"kube_(deployment|statefulset)_status_replicas\", cluster=~\"$cluster\", namespace=~\"$namespace\"},\n \"cortex_service\", \"$1\", \"deployment\", \"(.+)\"\n ),\n \"cortex_service\", \"$1\", \"statefulset\", \"(.+)\"\n ),\n # Strip the -zone-X suffix, if there is one\n \"cortex_service\", \"$1\", \"cortex_service\", \"(.*?)(?:-zone-[a-z])?\"\n )\n )\n) and (\n sum by(cortex_service) (\n label_replace(\n label_replace(\n label_replace(\n {__name__=~\"kube_(deployment|statefulset)_status_replicas\", cluster=~\"$cluster\", namespace=~\"$namespace\"},\n \"cortex_service\", \"$1\", \"deployment\", \"(.+)\"\n ),\n \"cortex_service\", \"$1\", \"statefulset\", \"(.+)\"\n ),\n # Strip the -zone-X suffix, if there is one\n \"cortex_service\", \"$1\", \"cortex_service\", \"(.*?)(?:-zone-[a-z])?\"\n )\n )\n > 0\n)\n", + "format": "table", + "instant": true, + "intervalFactor": null, + "legendFormat": "__auto", + "legendLink": null, + "step": null + } + ], + "title": "Rollout progress", + "transformations": [ + { + "id": "joinByField", + "options": { + "byField": "cortex_service", + "mode": "outer" + } + }, + { + "id": "organize", + "options": { + "excludeByName": { + "Time 1": true, + "Time 2": true + }, + "renameByName": { + "Value #A": "Updated", + "Value #B": "Ready", + "cortex_service": "Workload" + } + } + }, + { + "id": "sortBy", + "options": { + "sort": [ + { + "field": "Workload" + } + ] + } + } + ], + "type": "barchart" + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "decimals": 1, + "noValue": "", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "fill": 1, + "gridPos": { + "h": 4, + "w": 2, + "x": 10, + "y": 0 + }, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\",status_code=~\"2.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]))\n", + "format": null, + "instant": false, + "interval": "", + "intervalFactor": null, + "legendFormat": "", + "legendLink": null, + "step": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Writes - 2xx", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "stat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "decimals": 1, + "noValue": "", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "orange", + "value": 0.20000000000000001 + }, + { + "color": "red", + "value": 0.5 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "fill": 1, + "gridPos": { + "h": 4, + "w": 2, + "x": 12, + "y": 0 + }, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\",status_code=~\"4.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]))\n", + "format": null, + "instant": false, + "interval": "", + "intervalFactor": null, + "legendFormat": "", + "legendLink": null, + "step": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Writes - 4xx", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "stat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "decimals": 1, + "noValue": "", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 0.01 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "fill": 1, + "gridPos": { + "h": 4, + "w": 2, + "x": 14, + "y": 0 + }, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\",status_code=~\"5.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]))\n", + "format": null, + "instant": false, + "interval": "", + "intervalFactor": null, + "legendFormat": "", + "legendLink": null, + "step": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Writes - 5xx", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "stat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "decimals": 1, + "noValue": "", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "orange", + "value": 0.20000000000000001 + }, + { + "color": "red", + "value": 0.5 + } + ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "fill": 1, + "gridPos": { + "h": 4, + "w": 8, + "x": 16, + "y": 0 + }, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}))\n", + "format": null, + "instant": false, + "interval": "", + "intervalFactor": null, + "legendFormat": "", + "legendLink": null, + "step": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Writes 99th latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "stat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "decimals": 1, + "noValue": "", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "fill": 1, + "gridPos": { + "h": 4, + "w": 2, + "x": 10, + "y": 4 + }, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\",status_code=~\"2.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]))\n", + "format": null, + "instant": false, + "interval": "", + "intervalFactor": null, + "legendFormat": "", + "legendLink": null, + "step": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Reads - 2xx", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "stat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "decimals": 1, + "noValue": "", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "orange", + "value": 0.01 + }, + { + "color": "red", + "value": 0.050000000000000003 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "fill": 1, + "gridPos": { + "h": 4, + "w": 2, + "x": 12, + "y": 4 + }, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\",status_code=~\"4.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]))\n", + "format": null, + "instant": false, + "interval": "", + "intervalFactor": null, + "legendFormat": "", + "legendLink": null, + "step": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Reads - 4xx", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "stat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "decimals": 1, + "noValue": "", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 0.01 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "fill": 1, + "gridPos": { + "h": 4, + "w": 2, + "x": 14, + "y": 4 + }, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\",status_code=~\"5.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]))\n", + "format": null, + "instant": false, + "interval": "", + "intervalFactor": null, + "legendFormat": "", + "legendLink": null, + "step": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Reads - 5xx", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "stat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "decimals": 1, + "noValue": "", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "orange", + "value": 1 + }, + { + "color": "red", + "value": 2.5 + } + ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "fill": 1, + "gridPos": { + "h": 4, + "w": 8, + "x": 16, + "y": 4 + }, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}))\n", + "format": null, + "instant": false, + "interval": "", + "intervalFactor": null, + "legendFormat": "", + "legendLink": null, + "step": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Reads 99th latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "stat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "decimals": 0, + "noValue": "All healthy", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "orange", + "value": 1 + }, + { + "color": "red", + "value": 2 + } + ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "fill": 1, + "gridPos": { + "h": 3, + "w": 10, + "x": 0, + "y": 13 + }, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "text": { + "titleSize": 14, + "valueSize": 14 + }, + "textMode": "value_and_name" + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "kube_deployment_status_replicas_unavailable{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n> 0\n", + "format": null, + "instant": true, + "interval": "", + "intervalFactor": null, + "legendFormat": "{{deployment}}", + "legendLink": null, + "step": null + }, + { + "expr": "kube_statefulset_status_replicas_current{cluster=~\"$cluster\", namespace=~\"$namespace\"} -\nkube_statefulset_status_replicas_ready {cluster=~\"$cluster\", namespace=~\"$namespace\"}\n> 0\n", + "format": null, + "instant": true, + "interval": "", + "intervalFactor": null, + "legendFormat": "{{statefulset}}", + "legendLink": null, + "step": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Unhealthy pods", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "stat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "overrides": [ + { + "matcher": { + "id": "byRegexp", + "options": "r.*" + }, + "properties": [ + { + "id": "custom.align", + "value": "center" + } + ] + } + ] + }, + "gridPos": { + "h": 8, + "w": 6, + "x": 10, + "y": 8 + }, + "id": 11, + "targets": [ + { + "expr": "count by(container, version) (\n label_replace(\n kube_pod_container_info{cluster=~\"$cluster\", namespace=~\"$namespace\"},\n \"version\", \"$1\", \"image\", \".*:(.*)\"\n )\n)\n", + "instant": true, + "legendFormat": "", + "refId": "A" + } + ], + "title": "Pods count per version", + "transformations": [ + { + "id": "labelsToFields", + "options": { + "valueLabel": "version" + } + }, + { + "id": "organize", + "options": { + "excludeByName": { + "Time": true + }, + "indexByName": { + "Time": 0, + "container": 1 + } + } + }, + { + "id": "sortBy", + "options": { + "fields": { }, + "sort": [ + { + "field": "container" + } + ] + } + } + ], + "type": "table" + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "gridPos": { + "h": 8, + "w": 8, + "x": 16, + "y": 8 + }, + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "1 - (\n avg_over_time(histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"} offset 24h))[1h:])\n /\n avg_over_time(histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}))[1h:])\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "writes", + "legendLink": null + }, + { + "expr": "1 - (\n avg_over_time(histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"} offset 24h))[1h:])\n /\n avg_over_time(histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}))[1h:])\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "reads", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency vs 24h ago", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "refresh": "10s", + "rows": null, + "schemaVersion": 27, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Rollout progress", + "uid": "7f0b5567d543a1698e695b530eb7f5de", + "version": 0 + } \ No newline at end of file diff --git a/charts/meta-monitoring/src/dashboards/mimir-ruler.json b/charts/meta-monitoring/src/dashboards/mimir-ruler.json new file mode 100644 index 0000000..bbde06a --- /dev/null +++ b/charts/meta-monitoring/src/dashboards/mimir-ruler.json @@ -0,0 +1,2604 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "100px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "short", + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cortex_ruler_managers_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Active configurations", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "short", + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Total rules", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Read from ingesters - QPS\nNote: Even while operating in Remote ruler mode you will still see values for this panel.\n\nThis is because the metrics are inclusive of intermediate services and are showing the requests that ultimately reach the ingesters.\n\nFor a more detailed view of the read path when using remote ruler mode, see the Remote ruler reads dashboard.\n\n", + "fill": 1, + "format": "reqps", + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval]))", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Read from ingesters - QPS", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "reqps", + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval]))", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Write to ingesters - QPS", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Headlines", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "failed": "#E24D42", + "success": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_prometheus_rule_evaluations_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "success", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "failed", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_prometheus_rule_group_iterations_missed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "missed", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Evaluations per second", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum (rate(cortex_prometheus_rule_evaluation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum (rate(cortex_prometheus_rule_evaluation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "average", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rule evaluations global", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "1xx": "#EAB839", + "2xx": "#7EB26D", + "3xx": "#6ED0E0", + "4xx": "#EF843C", + "5xx": "#E24D42", + "cancel": "#A9A9A9", + "error": "#E24D42", + "success": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "QPS", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_ingester_client_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_ingester_client_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_ingester_client_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Writes (ingesters)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "1xx": "#EAB839", + "2xx": "#7EB26D", + "3xx": "#6ED0E0", + "4xx": "#EF843C", + "5xx": "#E24D42", + "cancel": "#A9A9A9", + "error": "#E24D42", + "success": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "QPS", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_ingester_client_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_ingester_client_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_ingester_client_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Reads (ingesters)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "1xx": "#EAB839", + "2xx": "#7EB26D", + "3xx": "#6ED0E0", + "4xx": "#EF843C", + "5xx": "#E24D42", + "cancel": "#A9A9A9", + "error": "#E24D42", + "success": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 11, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Requests / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ruler - key-value store for rulers ring", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 13, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_querier_storegateway_instances_hit_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_querier_storegateway_instances_hit_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_querier_storegateway_instances_hit_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_querier_storegateway_instances_hit_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Number of store-gateways hit per query", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 14, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_querier_storegateway_refetches_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_querier_storegateway_refetches_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_querier_storegateway_refetches_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_querier_storegateway_refetches_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Refetches of missing blocks per query", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + "Failures / sec": "#E24D42" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 15, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_querier_blocks_consistency_checks_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) / sum(rate(cortex_querier_blocks_consistency_checks_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Failures / sec", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Consistency checks failed", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ruler - blocks storage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "noValue": 0, + "unit": "short" + } + }, + "id": 16, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(user) (rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum by(user) (rate(cortex_prometheus_notifications_sent_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]) > 0)\n> 0\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ user }}", + "legendLink": null + } + ], + "title": "Delivery errors", + "type": "timeseries" + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "noValue": 0, + "unit": "percentunit" + } + }, + "fill": 1, + "id": 17, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(user) (rate(cortex_prometheus_notifications_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum by(user) (rate(cortex_prometheus_notifications_queue_capacity{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) > 0\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ user }}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Queue length", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "noValue": 0, + "unit": "short" + } + }, + "id": 18, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by (user) (increase(cortex_prometheus_notifications_dropped_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) > 0\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ user }}", + "legendLink": null + } + ], + "title": "Dropped", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Notifications", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 19, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(user) (rate(cortex_prometheus_rule_group_iterations_missed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ user }}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Missed iterations", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 20, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(cortex_prometheus_rule_group_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])\n /\nrate(cortex_prometheus_rule_group_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ user }}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 21, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(rule_group) (rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ rule_group }}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Failures", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Group evaluations", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 22, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(user) (rate(cortex_prometheus_rule_evaluation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum by(user) (rate(cortex_prometheus_rule_evaluation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ user }}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rule evaluation per user", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 23, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Operations / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "max": 1, + "min": 0, + "noValue": "0", + "unit": "percentunit" + } + }, + "id": 24, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operation_failures_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\"}[$__rate_interval])) / sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\"}[$__rate_interval])) >= 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "title": "Error rate", + "type": "timeseries" + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 25, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"attributes\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"attributes\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: Attributes", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 26, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"exists\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"exists\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: Exists", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ruler configuration object store (ruler accesses)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 27, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"get\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"get\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: Get", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 28, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"get_range\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"get_range\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: GetRange", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 29, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"upload\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"upload\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: Upload", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 30, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"delete\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"delete\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency of op: Delete", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Ruler", + "uid": "631e15d5d85afb2ca8e35d62984eeaa0", + "version": 0 + } \ No newline at end of file diff --git a/charts/meta-monitoring/src/dashboards/mimir-scaling.json b/charts/meta-monitoring/src/dashboards/mimir-scaling.json new file mode 100644 index 0000000..f92fd3c --- /dev/null +++ b/charts/meta-monitoring/src/dashboards/mimir-scaling.json @@ -0,0 +1,362 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "200px", + "panels": [ + { + "id": 1, + "options": { + "content": "This dashboard identifies scaling-related issues by suggesting services that you might want to scale up.\nThe table that follows contains a suggested number of replicas and the reason why.\nIf the system is failing and depending on the reason, try scaling up to the specified number.\nThe specified numbers are intended as helpful guidelines when things go wrong, rather than prescriptive guidelines.\n\nReasons:\n- **sample_rate**: There are not enough replicas to handle the\n sample rate. Applies to distributor and ingesters.\n- **active_series**: There are not enough replicas\n to handle the number of active series. Applies to ingesters.\n- **cpu_usage**: There are not enough replicas\n based on the CPU usage of the jobs vs the resource requests.\n Applies to all jobs.\n- **memory_usage**: There are not enough replicas based on the memory\n usage vs the resource requests. Applies to all jobs.\n- **active_series_limits**: There are not enough replicas to hold 60% of the\n sum of all the per tenant series limits.\n- **sample_rate_limits**: There are not enough replicas to handle 60% of the\n sum of all the per tenant rate limits.\n", + "mode": "markdown" + }, + "span": 12, + "title": "", + "type": "text" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Service scaling", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "400px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "sort": { + "col": 0, + "desc": false + }, + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Required Replicas", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "Cluster", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "__name__", + "thresholds": [ ], + "type": "hidden", + "unit": "short" + }, + { + "alias": "Cluster", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "cluster", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "Service", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "deployment", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "Namespace", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "namespace", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "Reason", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "reason", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sort_desc(\n cluster_namespace_deployment_reason:required_replicas:count{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n > ignoring(reason) group_left\n cluster_namespace_deployment:actual_replicas:count{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Workload-based scaling", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Scaling", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Scaling", + "uid": "64bbad83507b7289b514725658e10352", + "version": 0 + } \ No newline at end of file diff --git a/charts/meta-monitoring/src/dashboards/mimir-slow-queries.json b/charts/meta-monitoring/src/dashboards/mimir-slow-queries.json new file mode 100644 index 0000000..015e0fe --- /dev/null +++ b/charts/meta-monitoring/src/dashboards/mimir-slow-queries.json @@ -0,0 +1,323 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "${lokidatasource}", + "fieldConfig": { + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Time range" + }, + "properties": [ + { + "id": "mappings", + "value": [ + { + "from": "", + "id": 1, + "text": "Instant query", + "to": "", + "type": 1, + "value": "0" + } + ] + }, + { + "id": "unit", + "value": "s" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Step" + }, + "properties": [ + { + "id": "unit", + "value": "s" + } + ] + } + ] + }, + "id": 1, + "span": 12, + "targets": [ + { + "expr": "{cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | response_time > ${min_duration}", + "instant": false, + "legendFormat": "", + "range": true, + "refId": "A" + } + ], + "title": "Slow queries", + "transformations": [ + { + "id": "extractFields", + "options": { + "source": "labels" + } + }, + { + "id": "calculateField", + "options": { + "alias": "Time range", + "binary": { + "left": "param_end", + "operator": "-", + "reducer": "sum", + "right": "param_start" + }, + "mode": "binary", + "reduce": { + "reducer": "sum" + }, + "replaceFields": false + } + }, + { + "id": "organize", + "options": { + "excludeByName": { + "Line": true, + "Time": true, + "caller": true, + "cluster": true, + "container": true, + "host": true, + "id": true, + "job": true, + "labels": true, + "level": true, + "line": true, + "method": true, + "msg": true, + "name": true, + "namespace": true, + "param_end": true, + "param_start": true, + "param_time": true, + "path": true, + "pod": true, + "pod_template_hash": true, + "query_wall_time_seconds": true, + "stream": true, + "traceID": true, + "tsNs": true + }, + "indexByName": { + "Time range": 3, + "param_query": 2, + "param_step": 4, + "response_time": 5, + "ts": 0, + "user": 1 + }, + "renameByName": { + "org_id": "Tenant ID", + "param_query": "Query", + "param_step": "Step", + "response_time": "Duration" + } + } + } + ], + "type": "table" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "hide": 0, + "includeAll": false, + "label": "Logs datasource", + "multi": false, + "name": "lokidatasource", + "query": "loki", + "type": "datasource" + }, + { + "current": { + "selected": true, + "text": "5s", + "value": "5s" + }, + "hide": 0, + "label": "Min duration", + "name": "min_duration", + "options": [ + { + "selected": true, + "text": "5s", + "value": "5s" + } + ], + "query": "5s", + "type": "textbox" + }, + { + "current": { + "selected": true, + "text": ".*", + "value": ".*" + }, + "hide": 0, + "label": "Tenant ID", + "name": "tenant_id", + "options": [ + { + "selected": true, + "text": ".*", + "value": ".*" + } + ], + "query": ".*", + "type": "textbox" + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Slow queries", + "uid": "6089e1ce1e678788f46312a0a1e647e6", + "version": 0 + } \ No newline at end of file diff --git a/charts/meta-monitoring/src/dashboards/mimir-tenants.json b/charts/meta-monitoring/src/dashboards/mimir-tenants.json new file mode 100644 index 0000000..514b447 --- /dev/null +++ b/charts/meta-monitoring/src/dashboards/mimir-tenants.json @@ -0,0 +1,2817 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "25px", + "panels": [ + { + "content": "

\n This dashboard shows various metrics detailed by tenant (user) selected above.\n

\n", + "datasource": null, + "description": "", + "id": 1, + "mode": "markdown", + "span": 12, + "title": "", + "transparent": true, + "type": "text" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Tenants dashboard description", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### All series\nNumber of active and in-memory series per user, and active series matching custom trackers (in parenthesis).\nNote that these counts include all series regardless of the type of data (counter, gauge, native histogram, etc.).\nNote that active series matching custom trackers are included in the total active series count.\n\n", + "fill": 1, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "limit", + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n (\n cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n - cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "in-memory", + "legendLink": null + }, + { + "expr": "max(cortex_limits_overrides{cluster=~\"$cluster\", job=~\"($namespace)/((overrides-exporter|mimir-backend.*))\", limit_name=\"max_global_series_per_user\", user=\"$user\"})\nor\nmax(cortex_limits_defaults{cluster=~\"$cluster\", job=~\"($namespace)/((overrides-exporter|mimir-backend.*))\", limit_name=\"max_global_series_per_user\"})\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "sum(\n cortex_ingester_active_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "active", + "legendLink": null + }, + { + "expr": "sum by (name) (\n cortex_ingester_active_series_custom_tracker{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n) > 0\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "active ({{ name }})", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "All series", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Native histogram series\nNumber of active native histogram series per user, and active native histogram series matching custom trackers (in parenthesis).\nNote that active series matching custom trackers are included in the total active series count.\n\n", + "fill": 1, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "limit", + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n cortex_ingester_active_native_histogram_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "active", + "legendLink": null + }, + { + "expr": "sum by (name) (\n cortex_ingester_active_native_histogram_series_custom_tracker{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n) > 0\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "active ({{ name }})", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Native histogram series", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Total number of buckets used by native histogram series\nTotal number of buckets in active native histogram series per user, and total active native histogram buckets matching custom trackers (in parenthesis).\n\n", + "fill": 1, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "limit", + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n cortex_ingester_active_native_histogram_buckets{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "buckets", + "legendLink": null + }, + { + "expr": "sum by (name) (\n cortex_ingester_active_native_histogram_buckets_custom_tracker{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n) > 0\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "buckets ({{ name }})", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Total number of buckets used by native histogram series", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Active series and native histograms", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Series with exemplars\nNumber of series with exemplars currently in storage.\n\n", + "fill": 1, + "id": 5, + "legend": { + "show": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n cortex_ingester_tsdb_exemplar_series_with_exemplars_in_storage{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "series", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Series with exemplars", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Newest seen sample age\nThe age of the newest received sample seen in the distributors.\n\n", + "fill": 1, + "id": 6, + "legend": { + "show": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "time() - max(cortex_distributor_latest_seen_sample_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"} > 0)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "age", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Newest seen sample age", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Oldest exemplar age\nThe age of the oldest exemplar stored in circular storage.\nUseful to check for what time range the current exemplar buffer limit allows.\nThis usually means the max age for all exemplars for a typical setup.\nThis is not true though if one of the series timestamp is in future compared to rest series.\n\n", + "fill": 1, + "id": 7, + "legend": { + "show": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "time() - min(cortex_ingester_tsdb_exemplar_last_exemplars_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"} > 0)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "age", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Oldest exemplar age", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Samples and exemplars", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Distributor requests incoming rate\nThe rate of requests that have come in to the distributor, including rejected requests.\n\n", + "fill": 1, + "id": 8, + "legend": { + "show": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_distributor_requests_in_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "rate", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Distributor requests incoming rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Distributor requests received (accepted) rate\nThe rate of received requests, excluding rejected requests.\n\n", + "fill": 1, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "limit", + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_distributor_received_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "rate", + "legendLink": null + }, + { + "expr": "max(cortex_limits_overrides{cluster=~\"$cluster\", job=~\"($namespace)/((overrides-exporter|mimir-backend.*))\", limit_name=\"request_rate\", user=\"$user\"})\nor\nmax(cortex_limits_defaults{cluster=~\"$cluster\", job=~\"($namespace)/((overrides-exporter|mimir-backend.*))\", limit_name=\"request_rate\"})\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Distributor requests received (accepted) rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Distributor discarded requests rate\nThe rate of each request's discarding reason.\n\n", + "fill": 1, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (reason) (rate(cortex_discarded_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ reason }}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Distributor discarded requests rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Distributor ingestion requests", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Distributor samples incoming rate\nThe rate of samples that have come in to the distributor, including rejected or deduped exemplars.\n\n", + "fill": 1, + "id": 11, + "legend": { + "show": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_distributor_samples_in_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "rate", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Distributor samples incoming rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Distributor samples received (accepted) rate\nThe rate of received samples, excluding rejected and deduped samples.\n\n", + "fill": 1, + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "limit", + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "rate", + "legendLink": null + }, + { + "expr": "max(cortex_limits_overrides{cluster=~\"$cluster\", job=~\"($namespace)/((overrides-exporter|mimir-backend.*))\", limit_name=\"ingestion_rate\", user=\"$user\"})\nor\nmax(cortex_limits_defaults{cluster=~\"$cluster\", job=~\"($namespace)/((overrides-exporter|mimir-backend.*))\", limit_name=\"ingestion_rate\"})\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Distributor samples received (accepted) rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Distributor deduplicated/non-HA\nThe rate of deduplicated samples and the rate of received samples for a user that has HA tracking turned on, but the sample didn't contain both HA labels.\n\n", + "fill": 1, + "id": 13, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_distributor_deduped_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "deduplicated", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_distributor_non_ha_samples_received_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "non-HA", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Distributor deduplicated/non-HA", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Distributor and ingester discarded samples rate\nThe rate of each sample's discarding reason.\n\n", + "fill": 1, + "id": 14, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (reason) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ reason }} (distributor)", + "legendLink": null + }, + { + "expr": "sum by (reason) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ reason }} (ingester)", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Distributor and ingester discarded samples rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Samples ingestion funnel", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Distributor exemplars incoming rate\nThe rate of exemplars that have come in to the distributor, including rejected or deduped exemplars.\n\n", + "fill": 1, + "id": 15, + "legend": { + "show": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_distributor_exemplars_in_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "rate", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Distributor exemplars incoming rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Distributor exemplars received (accepted) rate\nThe rate of received exemplars, excluding rejected and deduped exemplars.\nThis number can be sensibly lower than incoming rate because we dedupe the HA sent exemplars, and then reject based on time.\nSee discarded rate for reasons why exemplars are being discarded.\n\n", + "fill": 1, + "id": 16, + "legend": { + "show": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_distributor_received_exemplars_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "rate", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Distributor exemplars received (accepted) rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Distributor discarded exemplars rate\nThe rate of each exmplars' discarding reason.\n\n", + "fill": 1, + "id": 17, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (reason) (rate(cortex_discarded_exemplars_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ reason }}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Distributor discarded exemplars rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Ingester appended exemplars rate\nTotal number of exemplars appended in the ingesters.\nThis can be lower than ingested exemplars rate since TSDB does not append the same exemplar twice, and those can be frequent.\n\n", + "fill": 1, + "id": 18, + "legend": { + "show": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n rate(cortex_ingester_tsdb_exemplar_exemplars_appended_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval])\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "rate", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Ingester appended exemplars rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Exemplars ingestion funnel", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Symbol table size for loaded blocks\nSize of symbol table in memory for loaded blocks, averaged by ingester.\n\n", + "fill": 1, + "id": 19, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (job) (cortex_ingester_tsdb_symbol_table_size_bytes{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ job }}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Symbol table size for loaded blocks", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Space used by local blocks\nThe number of bytes that are currently used for local storage by all blocks.\n\n", + "fill": 1, + "id": 20, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (job) (cortex_ingester_tsdb_storage_blocks_bytes{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ job }}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Space used by local blocks", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ingesters' storage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Number of groups\nTotal number of rule groups for a tenant.\n\n", + "fill": 1, + "id": 21, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "limit", + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "count(sum by (rule_group) (cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "groups", + "legendLink": null + }, + { + "expr": "max(cortex_limits_overrides{cluster=~\"$cluster\", job=~\"($namespace)/((overrides-exporter|mimir-backend.*))\", limit_name=\"ruler_max_rule_groups_per_tenant\", user=\"$user\"})\nor\nmax(cortex_limits_defaults{cluster=~\"$cluster\", job=~\"($namespace)/((overrides-exporter|mimir-backend.*))\", limit_name=\"ruler_max_rule_groups_per_tenant\"})\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Number of groups", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Number of rules\nTotal number of rules for a tenant.\n\n", + "fill": 1, + "id": 22, + "legend": { + "show": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "rules", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Number of rules", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 23, + "legend": { + "show": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_prometheus_rule_evaluations_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "rate", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Total evaluations rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 24, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (rule_group) (rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval])) > 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ rule_group }}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Failed evaluations rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rules", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 25, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "sort": { + "col": 2, + "desc": true + }, + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "rules", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "topk($limit, sum by (rule_group) (cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $limit biggest groups", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 26, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "sort": { + "col": 2, + "desc": true + }, + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "seconds", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "topk($limit, sum by (rule_group) (cortex_prometheus_rule_group_last_duration_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $limit slowest groups (last evaluation)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Top rules", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 27, + "legend": { + "show": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_prometheus_notifications_sent_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "rate", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Sent notifications rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + "rate": "#E24D42" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 28, + "legend": { + "show": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "rate", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Failed notifications rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Notifications", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 29, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_query_frontend_queries_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Queries / Sec", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Read Requests - query-frontend", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 30, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cortex_query_scheduler_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\", user=\"$user\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Queue Length", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Number of Queries Queued - query-scheduler", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Read Path - Queries (User)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 31, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_query_frontend_queries_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Queries / Sec", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Read Requests - ruler-query-frontend", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 32, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cortex_query_scheduler_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\", user=\"$user\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Queue Length", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Number of Queries Queued - ruler-query-scheduler", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Read Path - Queries (Ruler)", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "user", + "multi": false, + "name": "user", + "options": [ ], + "query": "label_values(cortex_ingester_active_series{cluster=~\"$cluster\", namespace=~\"$namespace\"}, user)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "current": { + "selected": true, + "text": "10", + "value": "10" + }, + "hide": 0, + "includeAll": false, + "multi": false, + "name": "limit", + "options": [ + { + "selected": true, + "text": "10", + "value": "10" + }, + { + "selected": false, + "text": "50", + "value": "50" + }, + { + "selected": false, + "text": "100", + "value": "100" + }, + { + "selected": false, + "text": "500", + "value": "500" + }, + { + "selected": false, + "text": "1000", + "value": "1000" + } + ], + "type": "custom" + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Tenants", + "uid": "35fa247ce651ba189debf33d7ae41611", + "version": 0 + } \ No newline at end of file diff --git a/charts/meta-monitoring/src/dashboards/mimir-top-tenants.json b/charts/meta-monitoring/src/dashboards/mimir-top-tenants.json new file mode 100644 index 0000000..2760999 --- /dev/null +++ b/charts/meta-monitoring/src/dashboards/mimir-top-tenants.json @@ -0,0 +1,1467 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "25px", + "panels": [ + { + "content": "

\n This dashboard shows the top tenants based on multiple selection criterias.\n Rows are collapsed by default to avoid querying all of them.\n Use the templating variable \"limit\" above to select the amount of users to be shown.\n

\n", + "datasource": null, + "description": "", + "id": 1, + "mode": "markdown", + "span": 12, + "title": "", + "transparent": true, + "type": "text" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Top tenants dashboard description", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "sort": { + "col": 2, + "desc": true + }, + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "series", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "topk($limit,\n sum by (user) (\n cortex_ingester_active_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n )\n)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $limit users by active series", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "By active series", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "sort": { + "col": 2, + "desc": true + }, + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "series", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "topk($limit, sum by (user) (\n (\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} )\n -\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} )\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"} )\n)\n)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $limit users by in-memory series (series created - series removed)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "By in-memory series", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (user) (\n (\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} )\n -\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} )\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"} )\n)\n\nand\ntopk($limit, sum by (user) (\n (\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} @ end())\n -\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} @ end())\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"} @ end())\n)\n - sum by (user) (\n (\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} @ start())\n -\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} @ start())\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"} @ start())\n)\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ user }}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $limit users by in-memory series (series created - series removed) that grew the most between query range start and query range end", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "By in-memory series growth", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "sort": { + "col": 2, + "desc": true + }, + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "samples/s", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "topk($limit, sum by (user) (rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"}[5m])))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $limit users by received samples rate in last 5m", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "By samples rate", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (user) (rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))\nand\ntopk($limit,\n sum by (user) (rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval] @ end()))\n -\n sum by (user) (rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval] @ start()))\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ user }}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $limit users by received samples rate that grew the most between query range start and query range end", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "By samples rate growth", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "sort": { + "col": 2, + "desc": true + }, + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "samples/s", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "topk($limit, sum by (user) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*|distributor|cortex|mimir|mimir-write.*))\"}[5m])))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $limit users by discarded samples rate in last 5m", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "By discarded samples rate", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (user) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*|distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))\nand\ntopk($limit,\n sum by (user) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*|distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval] @ end()))\n -\n sum by (user) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*|distributor|cortex|mimir|mimir-write.*))\"}[$__rate_interval] @ start()))\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ user }}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $limit users by discarded samples rate that grew the most between query range start and query range end", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "By discarded samples rate growth", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "sort": { + "col": 2, + "desc": true + }, + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "series", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "topk($limit,\n sum by (user) (\n cortex_ingester_tsdb_exemplar_series_with_exemplars_in_storage{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n )\n)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $limit users by series with exemplars", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "By series with exemplars", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "sort": { + "col": 2, + "desc": true + }, + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "exemplars/s", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "topk($limit, sum by (user) (rate(cortex_distributor_received_exemplars_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"}[5m])))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $limit users by received exemplars rate in last 5m", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "By exemplars rate", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 11, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "sort": { + "col": 3, + "desc": true + }, + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "rules", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "topk($limit, sum by (rule_group, user) (cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $limit biggest groups", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "By rule group size", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "sort": { + "col": 3, + "desc": true + }, + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "seconds", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "topk($limit, sum by (rule_group, user) (cortex_prometheus_rule_group_last_duration_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $limit slowest groups (last evaluation)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "By rule group evaluation time", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "current": { + "selected": true, + "text": "10", + "value": "10" + }, + "hide": 0, + "includeAll": false, + "multi": false, + "name": "limit", + "options": [ + { + "selected": true, + "text": "10", + "value": "10" + }, + { + "selected": false, + "text": "50", + "value": "50" + }, + { + "selected": false, + "text": "100", + "value": "100" + } + ], + "type": "custom" + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Top tenants", + "uid": "bc6e12d4fe540e4a1785b9d3ca0ffdd9", + "version": 0 + } \ No newline at end of file diff --git a/charts/meta-monitoring/src/dashboards/mimir-writes-networking.json b/charts/meta-monitoring/src/dashboards/mimir-writes-networking.json new file mode 100644 index 0000000..da77885 --- /dev/null +++ b/charts/meta-monitoring/src/dashboards/mimir-writes-networking.json @@ -0,0 +1,1135 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Receive bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "highest", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Inflight requests (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "TCP connections (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Summary", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?distributor.*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Receive bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?distributor.*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?distributor.*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?distributor.*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "highest", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Inflight requests (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?distributor.*\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?distributor.*\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?distributor.*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "TCP connections (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Distributor", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ingester.*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Receive bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ingester.*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit bandwidth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 11, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ingester.*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ingester.*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "highest", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Inflight requests (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ingester.*\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ingester.*\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ingester.*\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "TCP connections (per pod)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ingester", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Writes networking", + "uid": "978c1cb452585c96697a238eaac7fe2d", + "version": 0 + } \ No newline at end of file diff --git a/charts/meta-monitoring/src/dashboards/mimir-writes-resources.json b/charts/meta-monitoring/src/dashboards/mimir-writes-resources.json new file mode 100644 index 0000000..07b7a80 --- /dev/null +++ b/charts/meta-monitoring/src/dashboards/mimir-writes-resources.json @@ -0,0 +1,1373 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor|ingester|mimir-write\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "CPU", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor|ingester|mimir-write\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (workingset)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor|ingester|mimir-write\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (go heap inuse)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Summary", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor\",resource=\"cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "CPU", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor\"} > 0)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor\",resource=\"memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (workingset)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (go heap inuse)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Distributor", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (cortex_ingester_memory_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "In-memory series", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\",resource=\"cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "CPU", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ingester", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod) (container_memory_rss{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"} > 0)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\",resource=\"memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (RSS)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "request", + "color": "#FFC000", + "dashLength": 5, + "dashes": true, + "fill": 0 + }, + { + "alias": "limit", + "color": "#E02F44", + "dashLength": 5, + "dashes": true, + "fill": 0 + } + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"} > 0)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\",resource=\"memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "request", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (workingset)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 11, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Memory (go heap inuse)", + "tooltip": { + "sort": 2 + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(instance, pod, device) (\n rate(\n node_disk_written_bytes_total[$__rate_interval]\n )\n)\n+\nignoring(pod) group_right() (\n label_replace(\n count by(\n instance,\n pod,\n device\n )\n (\n container_fs_writes_bytes_total{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n container=~\"ingester\",\n device!~\".*sda.*\"\n }\n ),\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ) * 0\n)\n\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}} - {{device}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Disk writes", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 13, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(instance, pod, device) (\n rate(\n node_disk_read_bytes_total[$__rate_interval]\n )\n) + ignoring(pod) group_right() (\n label_replace(\n count by(\n instance,\n pod,\n device\n )\n (\n container_fs_writes_bytes_total{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n container=~\"ingester\",\n device!~\".*sda.*\"\n }\n ),\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ) * 0\n)\n\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}} - {{device}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Disk reads", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 14, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(persistentvolumeclaim) (\n kubelet_volume_stats_used_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"} /\n kubelet_volume_stats_capacity_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n)\nand\ncount by(persistentvolumeclaim) (\n kube_persistentvolumeclaim_labels{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n label_name=~\"(ingester).*\"\n }\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{persistentvolumeclaim}}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Disk space utilization", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Writes resources", + "uid": "bc9160e50b52e89e0e49c840fea3d379", + "version": 0 + } \ No newline at end of file diff --git a/charts/meta-monitoring/src/dashboards/mimir-writes.json b/charts/meta-monitoring/src/dashboards/mimir-writes.json new file mode 100644 index 0000000..1bd405a --- /dev/null +++ b/charts/meta-monitoring/src/dashboards/mimir-writes.json @@ -0,0 +1,2914 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "125px", + "panels": [ + { + "content": "

\n This dashboard shows various health metrics for the write path.\n It is broken into sections for each service on the write path,\n and organized by the order in which the write request flows.\n
\n Incoming metrics data travels from the gateway → distributor → ingester.\n
\n For each service, there are 3 panels showing\n (1) requests per second to that service,\n (2) average, median, and p99 latency of requests to that service, and\n (3) p99 latency of requests to each instance of that service.\n

\n

\n It also includes metrics for the key-value (KV) stores used to manage\n the high-availability tracker and the ingesters.\n

\n", + "datasource": null, + "description": "", + "id": 1, + "mode": "markdown", + "span": 12, + "title": "", + "transparent": true, + "type": "text" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Writes dashboard description", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "100px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "short", + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cluster_namespace_job:cortex_distributor_received_samples:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Samples / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Exemplars / sec\nThe total number of received exemplars by the distributors, excluding rejected and deduped exemplars, but not necessarily ingested by the ingesters.\n\n", + "fill": 1, + "format": "short", + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cluster_namespace_job:cortex_distributor_received_exemplars:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Exemplars / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### In-memory series\nThe number of series not yet flushed to object storage that are held in ingester memory.\n\n", + "fill": 1, + "format": "short", + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cortex_ingester_memory_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}\n/ on(cluster, namespace) group_left\nmax by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"}))\n", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "In-memory series", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Exemplars in ingesters\nNumber of TSDB exemplars currently in ingesters' storage.\n\n", + "fill": 1, + "format": "short", + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cortex_ingester_tsdb_exemplar_exemplars_in_storage{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}\n/ on(cluster, namespace) group_left\nmax by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"}))\n", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Exemplars in ingesters", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "short", + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "count(count by(user) (cortex_ingester_active_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}))", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Tenants", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Headlines", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "1xx": "#EAB839", + "2xx": "#7EB26D", + "3xx": "#6ED0E0", + "4xx": "#EF843C", + "5xx": "#E24D42", + "cancel": "#A9A9A9", + "error": "#E24D42", + "success": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Requests / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A", + "step": 10 + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B", + "step": 10 + }, + { + "expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C", + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 9, + "links": [ ], + "options": { + "legend": { + "displayMode": "hidden", + "showLegend": false + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "exemplar": true, + "expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval])))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "legendLink": null + } + ], + "title": "Per pod p99 latency", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Distributor", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "1xx": "#EAB839", + "2xx": "#7EB26D", + "3xx": "#6ED0E0", + "4xx": "#EF843C", + "5xx": "#E24D42", + "cancel": "#A9A9A9", + "error": "#E24D42", + "success": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\",route=\"/cortex.Ingester/Push\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Requests / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 11, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"})) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A", + "step": 10 + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"})) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B", + "step": 10 + }, + { + "expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C", + "step": 10 + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 12, + "links": [ ], + "options": { + "legend": { + "displayMode": "hidden", + "showLegend": false + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "exemplar": true, + "expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"}[$__rate_interval])))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "legendLink": null + } + ], + "title": "Per pod p99 latency", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ingester", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Replicas\nThe maximum and current number of distributor replicas.\nNote: The current number of replicas can still show 1 replica even when scaled to 0.\nBecause HPA never reports 0 replicas, the query will report 0 only if the HPA is not active.\n\n", + "fill": 1, + "id": 13, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "/Max .+/", + "dashes": true, + "fill": 0 + }, + { + "alias": "/Current .+/", + "fill": 0 + } + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "kube_horizontalpodautoscaler_spec_max_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-distributor\"}\n# Add the scaletargetref_name label for readability\n+ on (cluster, namespace, horizontalpodautoscaler) group_left (scaletargetref_name)\n 0*kube_horizontalpodautoscaler_info{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-distributor\"}\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Max {{ scaletargetref_name }}", + "legendLink": null + }, + { + "expr": "kube_horizontalpodautoscaler_status_current_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-distributor\"}\n# HPA doesn't go to 0 replicas, so we multiply by 0 if the HPA is not active\n* on (cluster, namespace, horizontalpodautoscaler)\n kube_horizontalpodautoscaler_status_condition{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-distributor\", condition=\"ScalingActive\", status=\"true\"}\n# Add the scaletargetref_name label for readability\n+ on (cluster, namespace, horizontalpodautoscaler) group_left (scaletargetref_name)\n 0*kube_horizontalpodautoscaler_info{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-distributor\"}\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Current {{ scaletargetref_name }}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Replicas", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Scaling metric (CPU): Desired replicas\nThis panel shows the scaling metric exposed by KEDA divided by the target/threshold used.\nIt should represent the desired number of replicas, ignoring the min/max constraints applied later.\n\n", + "fill": 1, + "id": 14, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "keda_metrics_adapter_scaler_metrics_value{metric=~\".*cpu.*\"}\n/\non(metric) group_left label_replace(\n kube_horizontalpodautoscaler_spec_target_metric{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-distributor\"},\n \"metric\", \"$1\", \"metric_name\", \"(.+)\"\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ scaledObject }}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Scaling metric (CPU): Desired replicas", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Scaling metric (memory): Desired replicas\nThis panel shows the scaling metric exposed by KEDA divided by the target/threshold used.\nIt should represent the desired number of replicas, ignoring the min/max constraints applied later.\n\n", + "fill": 1, + "id": 15, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "keda_metrics_adapter_scaler_metrics_value{metric=~\".*memory.*\"}\n/\non(metric) group_left label_replace(\n kube_horizontalpodautoscaler_spec_target_metric{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-distributor\"},\n \"metric\", \"$1\", \"metric_name\", \"(.+)\"\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ scaledObject }}", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Scaling metric (memory): Desired replicas", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Autoscaler failures rate\nThe rate of failures in the KEDA custom metrics API server. Whenever an error occurs, the KEDA custom\nmetrics server is unable to query the scaling metric from Prometheus so the autoscaler woudln't work properly.\n\n", + "fill": 1, + "id": 16, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(metric) (rate(keda_metrics_adapter_scaler_errors[$__rate_interval])) +\non(metric) group_left\nlabel_replace(\n kube_horizontalpodautoscaler_spec_target_metric{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-distributor\"}\n * 0, \"metric\", \"$1\", \"metric_name\", \"(.+)\"\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{metric}} failures", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Autoscaler failures rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Distributor - autoscaling", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "1xx": "#EAB839", + "2xx": "#7EB26D", + "3xx": "#6ED0E0", + "4xx": "#EF843C", + "5xx": "#E24D42", + "cancel": "#A9A9A9", + "error": "#E24D42", + "success": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 17, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Requests / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 18, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Distributor - key-value store for high-availability (HA) deduplication", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "1xx": "#EAB839", + "2xx": "#7EB26D", + "3xx": "#6ED0E0", + "4xx": "#EF843C", + "5xx": "#E24D42", + "cancel": "#A9A9A9", + "error": "#E24D42", + "success": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 19, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Requests / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 20, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Distributor - key-value store for distributors ring", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "1xx": "#EAB839", + "2xx": "#7EB26D", + "3xx": "#6ED0E0", + "4xx": "#EF843C", + "5xx": "#E24D42", + "cancel": "#A9A9A9", + "error": "#E24D42", + "success": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 21, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Requests / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 22, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ingester - key-value store for the ingesters ring", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "failed": "#E24D42", + "successful": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Uploaded blocks / sec\nThe rate of blocks being uploaded from the ingesters\nto object storage.\n\n", + "fill": 10, + "id": 23, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_ingester_shipper_uploads_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) - sum(rate(cortex_ingester_shipper_upload_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_ingester_shipper_upload_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "failed", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Uploaded blocks / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Upload latency\nThe average, median (50th percentile), and 99th percentile time\nthe ingesters take to upload blocks to object storage.\n\n", + "fill": 1, + "id": 24, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\",component=\"ingester\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\",component=\"ingester\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\",component=\"ingester\",operation=\"upload\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\",component=\"ingester\",operation=\"upload\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Upload latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ingester - shipper", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "failed": "#E24D42", + "successful": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Compactions per second\nIngesters maintain a local TSDB per-tenant on disk. Each TSDB maintains a head block for each\nactive time series; these blocks get periodically compacted (by default, every 2h).\nThis panel shows the rate of compaction operations across all TSDBs on all ingesters.\n\n", + "fill": 10, + "id": 25, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_ingester_tsdb_compactions_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_ingester_tsdb_compactions_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "failed", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Compactions / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Compaction latency\nThe average, median (50th percentile), and 99th percentile time ingesters take to compact TSDB head blocks\non the local filesystem.\n\n", + "fill": 1, + "id": 26, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_ingester_tsdb_compaction_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_ingester_tsdb_compaction_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_ingester_tsdb_compaction_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_ingester_tsdb_compaction_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Compactions latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ingester - TSDB head", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + "failed": "#E24D42", + "successful": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### WAL truncations per second\nThe WAL is truncated each time a new TSDB block is written. This panel measures the rate of\ntruncations.\n\n", + "fill": 10, + "id": 27, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_ingester_tsdb_wal_truncations_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) - sum(rate(cortex_ingester_tsdb_wal_truncations_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_ingester_tsdb_wal_truncations_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "failed", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "WAL truncations / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + "failed": "#E24D42", + "successful": "#7EB26D" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Checkpoints created per second\nCheckpoints are created as part of the WAL truncation process.\nThis metric measures the rate of checkpoint creation.\n\n", + "fill": 10, + "id": 28, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_ingester_tsdb_checkpoint_creations_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) - sum(rate(cortex_ingester_tsdb_checkpoint_creations_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_ingester_tsdb_checkpoint_creations_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "failed", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Checkpoints created / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "description": "### WAL truncations latency (including checkpointing)\nAverage time taken to perform a full WAL truncation,\nincluding the time taken for the checkpointing to complete.\n\n", + "fieldConfig": { + "defaults": { + "noValue": "0", + "unit": "s" + } + }, + "id": 29, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(rate(cortex_ingester_tsdb_wal_truncate_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))\n/\nsum(rate(cortex_ingester_tsdb_wal_truncate_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) >= 0\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "avg", + "legendLink": null + } + ], + "title": "WAL truncations latency (includes checkpointing)", + "type": "timeseries" + }, + { + "aliasColors": { + "WAL": "#E24D42", + "mmap-ed chunks": "#E28A42" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 30, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_ingester_tsdb_wal_corruptions_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "WAL", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_ingester_tsdb_mmap_chunk_corruptions_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "mmap-ed chunks", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Corruptions / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ingester - TSDB write ahead log (WAL)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Distributor exemplars incoming rate\nThe rate of exemplars that have come in to the distributor, including rejected or deduped exemplars.\n\n", + "fill": 1, + "id": 31, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cluster_namespace_job:cortex_distributor_exemplars_in:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "incoming exemplars", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Distributor exemplars incoming rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ex/s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Distributor exemplars received rate\nThe rate of received exemplars, excluding rejected and deduped exemplars.\nThis number can be sensibly lower than incoming rate because we dedupe the HA sent exemplars, and then reject based on time, see `cortex_discarded_exemplars_total` for specific reasons rates.\n\n", + "fill": 1, + "id": 32, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cluster_namespace_job:cortex_distributor_received_exemplars:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "received exemplars", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Distributor exemplars received rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ex/s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Ingester ingested exemplars rate\nThe rate of exemplars ingested in the ingesters.\nEvery exemplar is sent to the replication factor number of ingesters, so the sum of rates from all ingesters is divided by the replication factor.\nThis ingested exemplars rate should match the distributor's received exemplars rate.\n\n", + "fill": 1, + "id": 33, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n cluster_namespace_job:cortex_ingester_ingested_exemplars:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "ingested exemplars", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Ingester ingested exemplars rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ex/s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Ingester appended exemplars rate\nThe rate of exemplars appended in the ingesters.\nThis can be lower than ingested exemplars rate since TSDB does not append the same exemplar twice, and those can be frequent.\n\n", + "fill": 1, + "id": 34, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n cluster_namespace_job:cortex_ingester_tsdb_exemplar_exemplars_appended:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor|cortex|mimir|mimir-write.*))\"})\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "appended exemplars", + "legendLink": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Ingester appended exemplars rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ex/s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Exemplars", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Writes", + "uid": "8280707b8f16e7b87b840fc1cc92d4c5", + "version": 0 + } \ No newline at end of file diff --git a/charts/meta-monitoring/templates/grafana/configmap-3.yaml b/charts/meta-monitoring/templates/grafana/configmap-3.yaml new file mode 100644 index 0000000..690b5b7 --- /dev/null +++ b/charts/meta-monitoring/templates/grafana/configmap-3.yaml @@ -0,0 +1,19 @@ +{{- if .Values.local.metrics.enabled }} +--- +apiVersion: v1 +kind: ConfigMap +metadata: + name: mimir-dashboards-1 + namespace: {{ $.Release.Namespace }} +data: + "mimir-alertmanager-resources.json": | + {{ $.Files.Get "src/dashboards/mimir-alertmanager-resources.json" | fromJson | toJson }} + "mimir-alertmanager.json": | + {{ $.Files.Get "src/dashboards/mimir-alertmanager.json" | fromJson | toJson }} + "mimir-compactor-resources.json": | + {{ $.Files.Get "src/dashboards/mimir-compactor-resources.json" | fromJson | toJson }} + "mimir-compactor.json": | + {{ $.Files.Get "src/dashboards/mimir-compactor.json" | fromJson | toJson }} + "mimir-config.json": | + {{ $.Files.Get "src/dashboards/mimir-config.json" | fromJson | toJson }} +{{- end }} \ No newline at end of file diff --git a/charts/meta-monitoring/templates/grafana/configmap-4.yaml b/charts/meta-monitoring/templates/grafana/configmap-4.yaml new file mode 100644 index 0000000..3aa861b --- /dev/null +++ b/charts/meta-monitoring/templates/grafana/configmap-4.yaml @@ -0,0 +1,19 @@ +{{- if .Values.local.metrics.enabled }} +--- +apiVersion: v1 +kind: ConfigMap +metadata: + name: mimir-dashboards-2 + namespace: {{ $.Release.Namespace }} +data: + "mimir-object-store.json": | + {{ $.Files.Get "src/dashboards/mimir-object-store.json" | fromJson | toJson }} + "mimir-overrides.json": | + {{ $.Files.Get "src/dashboards/mimir-overrides.json" | fromJson | toJson }} + "mimir-overview-networking.json": | + {{ $.Files.Get "src/dashboards/mimir-overview-networking.json" | fromJson | toJson }} + "mimir-overview-resources.json": | + {{ $.Files.Get "src/dashboards/mimir-overview-resources.json" | fromJson | toJson }} + "mimir-overview.json": | + {{ $.Files.Get "src/dashboards/mimir-overview.json" | fromJson | toJson }} +{{- end }} \ No newline at end of file diff --git a/charts/meta-monitoring/templates/grafana/configmap-5.yaml b/charts/meta-monitoring/templates/grafana/configmap-5.yaml new file mode 100644 index 0000000..1cc0105 --- /dev/null +++ b/charts/meta-monitoring/templates/grafana/configmap-5.yaml @@ -0,0 +1,19 @@ +{{- if .Values.local.metrics.enabled }} +--- +apiVersion: v1 +kind: ConfigMap +metadata: + name: mimir-dashboards-3 + namespace: {{ $.Release.Namespace }} +data: + "mimir-queries.json": | + {{ $.Files.Get "src/dashboards/mimir-queries.json" | fromJson | toJson }} + "mimir-reads-networking.json": | + {{ $.Files.Get "src/dashboards/mimir-reads-networking.json" | fromJson | toJson }} + "mimir-reads-resources.json": | + {{ $.Files.Get "src/dashboards/mimir-reads-resources.json" | fromJson | toJson }} + "mimir-reads.json": | + {{ $.Files.Get "src/dashboards/mimir-reads.json" | fromJson | toJson }} + "mimir-remote-ruler-reads-resources.json": | + {{ $.Files.Get "src/dashboards/mimir-remote-ruler-reads-resources.json" | fromJson | toJson }} +{{- end }} \ No newline at end of file diff --git a/charts/meta-monitoring/templates/grafana/configmap-6.yaml b/charts/meta-monitoring/templates/grafana/configmap-6.yaml new file mode 100644 index 0000000..898112f --- /dev/null +++ b/charts/meta-monitoring/templates/grafana/configmap-6.yaml @@ -0,0 +1,19 @@ +{{- if .Values.local.metrics.enabled }} +--- +apiVersion: v1 +kind: ConfigMap +metadata: + name: mimir-dashboards-4 + namespace: {{ $.Release.Namespace }} +data: + "mimir-remote-ruler-reads.json": | + {{ $.Files.Get "src/dashboards/mimir-remote-ruler-reads.json" | fromJson | toJson }} + "mimir-rollout-progress.json": | + {{ $.Files.Get "src/dashboards/mimir-rollout-progress.json" | fromJson | toJson }} + "mimir-ruler.json": | + {{ $.Files.Get "src/dashboards/mimir-ruler.json" | fromJson | toJson }} + "mimir-scaling.json": | + {{ $.Files.Get "src/dashboards/mimir-scaling.json" | fromJson | toJson }} + "mimir-slow-queries.json": | + {{ $.Files.Get "src/dashboards/mimir-slow-queries.json" | fromJson | toJson }} +{{- end }} \ No newline at end of file diff --git a/charts/meta-monitoring/templates/grafana/configmap-7.yaml b/charts/meta-monitoring/templates/grafana/configmap-7.yaml new file mode 100644 index 0000000..1c871a3 --- /dev/null +++ b/charts/meta-monitoring/templates/grafana/configmap-7.yaml @@ -0,0 +1,19 @@ +{{- if .Values.local.metrics.enabled }} +--- +apiVersion: v1 +kind: ConfigMap +metadata: + name: mimir-dashboards-5 + namespace: {{ $.Release.Namespace }} +data: + "mimir-tenants.json": | + {{ $.Files.Get "src/dashboards/mimir-tenants.json" | fromJson | toJson }} + "mimir-top-tenants.json": | + {{ $.Files.Get "src/dashboards/mimir-top-tenants.json" | fromJson | toJson }} + "mimir-writes-networking.json": | + {{ $.Files.Get "src/dashboards/mimir-writes-networking.json" | fromJson | toJson }} + "mimir-writes-resources.json": | + {{ $.Files.Get "src/dashboards/mimir-writes-resources.json" | fromJson | toJson }} + "mimir-writes.json": | + {{ $.Files.Get "src/dashboards/mimir-writes.json" | fromJson | toJson }} +{{- end }} diff --git a/charts/meta-monitoring/templates/grafana/dashboard.yaml b/charts/meta-monitoring/templates/grafana/dashboard.yaml index 0c2bfeb..106187a 100644 --- a/charts/meta-monitoring/templates/grafana/dashboard.yaml +++ b/charts/meta-monitoring/templates/grafana/dashboard.yaml @@ -1,4 +1,4 @@ -{{- if .Values.local.logs.enabled }} +{{- if or (or .Values.local.logs.enabled .Values.local.metrics.enabled) .Values.local.traces.enabled }} --- apiVersion: v1 kind: ConfigMap @@ -10,6 +10,7 @@ data: --- apiVersion: 1 providers: +{{- if .Values.local.logs.enabled }} - disableDeletion: true editable: false folder: Loki @@ -26,4 +27,47 @@ data: path: /var/lib/grafana/dashboards/loki-2 orgId: 1 type: file +{{- end }} +{{- if .Values.local.metrics.enabled }} + - disableDeletion: true + editable: false + folder: Mimir + name: mimir-1 + options: + path: /var/lib/grafana/dashboards/mimir-1 + orgId: 1 + type: file + - disableDeletion: true + editable: false + folder: Mimir + name: mimir-2 + options: + path: /var/lib/grafana/dashboards/mimir-2 + orgId: 1 + type: file + - disableDeletion: true + editable: false + folder: Mimir + name: mimir-3 + options: + path: /var/lib/grafana/dashboards/mimir-3 + orgId: 1 + type: file + - disableDeletion: true + editable: false + folder: Mimir + name: mimir-4 + options: + path: /var/lib/grafana/dashboards/mimir-4 + orgId: 1 + type: file + - disableDeletion: true + editable: false + folder: Mimir + name: mimir-5 + options: + path: /var/lib/grafana/dashboards/mimir-5 + orgId: 1 + type: file +{{- end }} {{- end }} \ No newline at end of file diff --git a/charts/meta-monitoring/templates/grafana/datasources.yaml b/charts/meta-monitoring/templates/grafana/datasources.yaml index 434b329..a532415 100644 --- a/charts/meta-monitoring/templates/grafana/datasources.yaml +++ b/charts/meta-monitoring/templates/grafana/datasources.yaml @@ -3,7 +3,7 @@ apiVersion: v1 kind: ConfigMap metadata: - name: loki-datasources-provisioning + name: datasources-provisioning namespace: {{ $.Release.Namespace }} data: datasources.yaml: | diff --git a/charts/meta-monitoring/templates/grafana/grafana.yaml b/charts/meta-monitoring/templates/grafana/grafana.yaml index 962443a..cee8b96 100644 --- a/charts/meta-monitoring/templates/grafana/grafana.yaml +++ b/charts/meta-monitoring/templates/grafana/grafana.yaml @@ -64,22 +64,34 @@ spec: - mountPath: /var/lib/grafana name: grafana-pv - mountPath: /etc/grafana/provisioning/datasources - name: loki-datasources-provisioning - {{- if .Values.local.logs.enabled }} + name: datasources-provisioning - mountPath: /etc/grafana/provisioning/dashboards name: loki-dashboards-provisioning + {{- if .Values.local.logs.enabled }} - mountPath: /var/lib/grafana/dashboards/loki-1 name: loki-dashboards-1 - mountPath: /var/lib/grafana/dashboards/loki-2 name: loki-dashboards-2 {{- end }} + {{- if .Values.local.metrics.enabled }} + - mountPath: /var/lib/grafana/dashboards/mimir-1 + name: mimir-dashboards-1 + - mountPath: /var/lib/grafana/dashboards/mimir-2 + name: mimir-dashboards-2 + - mountPath: /var/lib/grafana/dashboards/mimir-3 + name: mimir-dashboards-3 + - mountPath: /var/lib/grafana/dashboards/mimir-4 + name: mimir-dashboards-4 + - mountPath: /var/lib/grafana/dashboards/mimir-5 + name: mimir-dashboards-5 + {{- end }} volumes: - name: grafana-pv persistentVolumeClaim: claimName: grafana-pvc - - name: loki-datasources-provisioning + - name: datasources-provisioning configMap: - name: loki-datasources-provisioning + name: datasources-provisioning {{- if .Values.local.logs.enabled }} - name: loki-dashboards-provisioning configMap: @@ -91,6 +103,26 @@ spec: configMap: name: loki-dashboards-2 {{- end }} + {{- if .Values.local.metrics.enabled }} + - name: mimir-dashboards-provisioning + configMap: + name: mimir-dashboards-provisioning + - name: mimir-dashboards-1 + configMap: + name: mimir-dashboards-1 + - name: mimir-dashboards-2 + configMap: + name: mimir-dashboards-2 + - name: mimir-dashboards-3 + configMap: + name: mimir-dashboards-3 + - name: mimir-dashboards-4 + configMap: + name: mimir-dashboards-4 + - name: mimir-dashboards-5 + configMap: + name: mimir-dashboards-5 + {{- end }} --- apiVersion: v1