\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 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 }