Compare commits

...

7 Commits

Author SHA1 Message Date
Michel Hollands
e9aab491db Rename dashboard configmaps
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-08-02 17:15:40 +01:00
Michel Hollands
93cac45b2e Add tempo dashboards plus fixes
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-07-31 10:45:31 +01:00
Michel Hollands
6ce4be70e2 Merge pull request #8 from grafana/add_mimir_dashboards
Add Mimir dashboards
2023-07-28 09:46:17 +01:00
Michel Hollands
176312167c Merge pull request #7 from grafana/use_loki_ssd_dashboards
Use Loki SSD dashboards
2023-07-28 09:45:55 +01:00
Michel Hollands
07a336d9ed Merge pull request #6 from grafana/add_kube_state_metrics_scraping
Add scraping of kube state metrics
2023-07-28 09:42:16 +01:00
Michel Hollands
f4d5bcc018 Use Loki SSD dashboards
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-07-27 13:48:42 +01:00
Michel Hollands
18f0dc932a Add scraping of kube state metrics
Signed-off-by: Michel Hollands <michel.hollands@gmail.com>
2023-07-27 09:23:09 +01:00
27 changed files with 16250 additions and 224 deletions

View File

@@ -217,15 +217,15 @@
"renderer": "flot",
"seriesOverrides": [ ],
"spaceLength": 10,
"span": 6,
"span": 4,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(increase(loki_compactor_delete_requests_received_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[1d]))",
"expr": "(loki_compactor_delete_requests_received_total{cluster=~\"$cluster\", namespace=~\"$namespace\"} or on() vector(0)) - on () (loki_compactor_delete_requests_processed_total{cluster=~\"$cluster\", namespace=~\"$namespace\"} or on () vector(0))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "received",
"legendFormat": "in progress",
"legendLink": null,
"step": 10
}
@@ -233,7 +233,7 @@
"thresholds": [ ],
"timeFrom": null,
"timeShift": null,
"title": "Delete Requests Received / Day",
"title": "# of Delete Requests (received - processed) ",
"tooltip": {
"shared": true,
"sort": 2,
@@ -293,7 +293,83 @@
"renderer": "flot",
"seriesOverrides": [ ],
"spaceLength": 10,
"span": 6,
"span": 4,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(increase(loki_compactor_delete_requests_received_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[1d]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "received",
"legendLink": null,
"step": 10
}
],
"thresholds": [ ],
"timeFrom": null,
"timeShift": null,
"title": "Delete Requests Received / Day",
"tooltip": {
"shared": true,
"sort": 2,
"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": "$datasource",
"fill": 1,
"id": 5,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [ ],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [ ],
"spaceLength": 10,
"span": 4,
"stack": false,
"steppedLine": false,
"targets": [
@@ -361,7 +437,7 @@
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"id": 5,
"id": 6,
"legend": {
"avg": false,
"current": false,
@@ -381,7 +457,247 @@
"renderer": "flot",
"seriesOverrides": [ ],
"spaceLength": 10,
"span": 12,
"span": 4,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"compactor\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
"legendLink": null,
"step": 10
}
],
"thresholds": [ ],
"timeFrom": null,
"timeShift": null,
"title": "Compactor CPU usage",
"tooltip": {
"shared": true,
"sort": 2,
"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": "$datasource",
"fill": 1,
"id": 7,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [ ],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [ ],
"spaceLength": 10,
"span": 4,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"compactor\"} / 1024 / 1024 ",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": " {{pod}} ",
"legendLink": null,
"step": 10
}
],
"thresholds": [ ],
"timeFrom": null,
"timeShift": null,
"title": "Compactor memory usage (MiB)",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [ ]
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
},
{
"aliasColors": { },
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$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": "loki_boltdb_shipper_compact_tables_operation_duration_seconds{cluster=~\"$cluster\", namespace=~\"$namespace\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
"legendLink": null,
"step": 10
}
],
"thresholds": [ ],
"timeFrom": null,
"timeShift": null,
"title": "Compaction run duration (seconds)",
"tooltip": {
"shared": true,
"sort": 2,
"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": "Compactor",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
{
"aliasColors": { },
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"id": 9,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [ ],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [ ],
"spaceLength": 10,
"span": 6,
"stack": false,
"steppedLine": false,
"targets": [
@@ -429,19 +745,7 @@
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Failures",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
},
{
"aliasColors": { },
"bars": false,
@@ -449,7 +753,7 @@
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"id": 6,
"id": 10,
"legend": {
"avg": false,
"current": false,
@@ -469,7 +773,7 @@
"renderer": "flot",
"seriesOverrides": [ ],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": false,
"steppedLine": false,
"targets": [
@@ -523,7 +827,45 @@
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Deleted lines",
"title": "Deletion metrics",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
{
"datasource": "$loki_datasource",
"id": 11,
"span": 6,
"targets": [
{
"expr": "{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"compactor\"} |~ \"Started processing delete request|delete request for user marked as processed\" | logfmt | line_format \"{{.ts}} user={{.user}} delete_request_id={{.delete_request_id}} msg={{.msg}}\" ",
"refId": "A"
}
],
"title": "In progress/finished",
"type": "logs"
},
{
"datasource": "$loki_datasource",
"id": 12,
"span": 6,
"targets": [
{
"expr": "{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"compactor\"} |~ \"delete request for user added\" | logfmt | line_format \"{{.ts}} user={{.user}} query='{{.query}}'\"",
"refId": "A"
}
],
"title": "Requests",
"type": "logs"
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "List of deletion requests",
"titleSize": "h6"
}
],

View File

@@ -6,7 +6,6 @@
"gnetId": null,
"graphTooltip": 0,
"hideControls": false,
"id": 8,
"iteration": 1583185057230,
"links": [
{
@@ -1070,4 +1069,4 @@
"title": "Loki / Logs",
"uid": "logs",
"version": 0
}
}

View File

@@ -1,41 +1,27 @@
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": "-- Grafana --",
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"target": {
"limit": 100,
"matchAny": false,
"tags": [ ],
"type": "dashboard"
},
"type": "dashboard"
},
{
"datasource": "${datasource}",
"enable": false,
"expr": "sum by (tenant) (changes(loki_ruler_wal_prometheus_tsdb_wal_truncations_total{tenant=~\"${tenant}\"}[$__rate_interval]))",
"iconColor": "red",
"name": "WAL Truncations",
"target": {
"queryType": "Azure Monitor",
"refId": "Anno"
},
"titleFormat": "{{tenant}}"
}
]
"list": [ ]
},
"editable": true,
"fiscalYearStartMonth": 0,
"gnetId": null,
"graphTooltip": 0,
"hideControls": false,
"iteration": 1635347545534,
"links": [ ],
"links": [
{
"asDropdown": true,
"icon": "external link",
"includeVars": true,
"keepTime": true,
"tags": [
"loki"
],
"targetBlank": false,
"title": "Loki Dashboards",
"type": "dashboards"
}
],
"liveNow": false,
"panels": [
{
@@ -599,59 +585,139 @@
"type": "timeseries"
}
],
"schemaVersion": 31,
"refresh": "10s",
"rows": [ ],
"schemaVersion": 14,
"style": "dark",
"tags": [ ],
"tags": [
"loki"
],
"templating": {
"list": [
{
"description": null,
"error": null,
"current": {
"text": "default",
"value": "default"
},
"hide": 0,
"includeAll": false,
"label": "Datasource",
"multi": false,
"label": "Data Source",
"name": "datasource",
"options": [ ],
"query": "prometheus",
"queryValue": "",
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"type": "datasource"
},
{
"allValue": null,
"datasource": "${datasource}",
"definition": "label_values(loki_ruler_wal_samples_appended_total, tenant)",
"description": null,
"error": null,
"current": {
"text": "prod",
"value": "prod"
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": "cluster",
"multi": false,
"name": "cluster",
"options": [ ],
"query": "label_values(loki_build_info, cluster)",
"refresh": 1,
"regex": "",
"sort": 2,
"tagValuesQuery": "",
"tags": [ ],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "prod",
"value": "prod"
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": "namespace",
"multi": false,
"name": "namespace",
"options": [ ],
"query": "label_values(loki_build_info{cluster=~\"$cluster\"}, namespace)",
"refresh": 1,
"regex": "",
"sort": 2,
"tagValuesQuery": "",
"tags": [ ],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"hide": 0,
"label": null,
"name": "loki_datasource",
"options": [ ],
"query": "loki",
"refresh": 1,
"regex": "",
"type": "datasource"
},
{
"allValue": ".+",
"current": { },
"datasource": "$datasource",
"hide": 0,
"includeAll": true,
"label": "Tenant",
"multi": true,
"label": null,
"multi": false,
"name": "tenant",
"options": [ ],
"query": {
"query": "label_values(loki_ruler_wal_samples_appended_total, tenant)",
"refId": "StandardVariableQuery"
},
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 0,
"type": "query"
"query": "query_result(sum by (id) (grafanacloud_logs_instance_info) and sum(label_replace(loki_tenant:active_streams{cluster=\"$cluster\",namespace=\"$namespace\"},\"id\",\"$1\",\"tenant\",\"(.*)\")) by(id))",
"refresh": 0,
"regex": "/\"([^\"]+)\"/",
"sort": 1,
"tagValuesQuery": "",
"tags": [ ],
"tagsQuery": "",
"type": "query",
"useTags": false
}
]
},
"time": {
"from": "now-6h",
"from": "now-1h",
"to": "now"
},
"timepicker": { },
"timezone": "",
"title": "Recording Rules",
"uid": "2xKA_ZK7k",
"version": 9,
"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": "Loki / Recording Rules",
"uid": "recording-rules",
"version": 0,
"weekStart": ""
}

View File

@@ -6,7 +6,6 @@
"gnetId": null,
"graphTooltip": 0,
"hideControls": false,
"id": 68,
"iteration": 1588704280892,
"links": [
{
@@ -567,17 +566,17 @@
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum by (le) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push\", cluster=~\"$cluster\"})) * 1e3",
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push\", cluster=~\"$cluster\"})) * 1e3",
"legendFormat": ".99",
"refId": "A"
},
{
"expr": "histogram_quantile(0.75, sum by (le) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push\", cluster=~\"$cluster\"})) * 1e3",
"expr": "histogram_quantile(0.75, sum by (le) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push\", cluster=~\"$cluster\"})) * 1e3",
"legendFormat": ".9",
"refId": "B"
},
{
"expr": "histogram_quantile(0.5, sum by (le) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push\", cluster=~\"$cluster\"})) * 1e3",
"expr": "histogram_quantile(0.5, sum by (le) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push\", cluster=~\"$cluster\"})) * 1e3",
"legendFormat": ".5",
"refId": "C"
}
@@ -673,17 +672,17 @@
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum by (le) (job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3",
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3",
"legendFormat": ".99",
"refId": "A"
},
{
"expr": "histogram_quantile(0.9, sum by (le) (job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3",
"expr": "histogram_quantile(0.9, sum by (le) (cluster_job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3",
"legendFormat": ".9",
"refId": "B"
},
{
"expr": "histogram_quantile(0.5, sum by (le) (job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3",
"expr": "histogram_quantile(0.5, sum by (le) (cluster_job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3",
"legendFormat": ".5",
"refId": "C"
}
@@ -779,7 +778,7 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\"}[5m])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\"}[5m])) by (route)",
"expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\"}[$__rate_interval])) by (route) > 0",
"interval": "",
"legendFormat": "{{route}}",
"refId": "A"
@@ -877,18 +876,18 @@
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum by (le) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\", cluster=~\"$cluster\"})) * 1e3",
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\", cluster=~\"$cluster\"})) * 1e3",
"legendFormat": ".99",
"refId": "A"
},
{
"expr": "histogram_quantile(0.9, sum by (le) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\", cluster=~\"$cluster\"})) * 1e3",
"expr": "histogram_quantile(0.9, sum by (le) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\", cluster=~\"$cluster\"})) * 1e3",
"hide": false,
"legendFormat": ".9",
"refId": "B"
},
{
"expr": "histogram_quantile(0.5, sum by (le) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\", cluster=~\"$cluster\"})) * 1e3",
"expr": "histogram_quantile(0.5, sum by (le) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\", cluster=~\"$cluster\"})) * 1e3",
"hide": false,
"legendFormat": ".5",
"refId": "C"
@@ -985,7 +984,7 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\", route=\"/logproto.Pusher/Push\"}[5m])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\"}[5m])) by (route)",
"expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\", route=\"/logproto.Pusher/Push\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\"}[$__rate_interval])) by (route) > 0",
"interval": "",
"legendFormat": "{{route}}",
"refId": "A"
@@ -1085,17 +1084,17 @@
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"}))",
"expr": "histogram_quantile(0.99, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"}))",
"legendFormat": "{{route}}-.99",
"refId": "A"
},
{
"expr": "histogram_quantile(0.9, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"}))",
"expr": "histogram_quantile(0.9, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"}))",
"legendFormat": "{{route}}-.9",
"refId": "B"
},
{
"expr": "histogram_quantile(0.5, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"}))",
"expr": "histogram_quantile(0.5, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"}))",
"legendFormat": "{{route}}-.5",
"refId": "C"
}
@@ -1191,17 +1190,17 @@
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"})) * 1e3",
"expr": "histogram_quantile(0.99, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"})) * 1e3",
"legendFormat": ".99-{{route}}",
"refId": "A"
},
{
"expr": "histogram_quantile(0.9, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"})) * 1e3",
"expr": "histogram_quantile(0.9, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"})) * 1e3",
"legendFormat": ".9-{{route}}",
"refId": "B"
},
{
"expr": "histogram_quantile(0.5, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"})) * 1e3",
"expr": "histogram_quantile(0.5, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"})) * 1e3",
"legendFormat": ".5-{{route}}",
"refId": "C"
}
@@ -1297,7 +1296,7 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\", status_code!~\"5[0-9]{2}\"}[5m])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\"}[5m])) by (route)",
"expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\", status_code!~\"5[0-9]{2}\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\"}[$__rate_interval])) by (route) > 0",
"interval": "",
"legendFormat": "{{route}}",
"refId": "A"
@@ -1396,17 +1395,17 @@
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\", cluster=\"$cluster\"})) * 1e3",
"expr": "histogram_quantile(0.99, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\", cluster=\"$cluster\"})) * 1e3",
"legendFormat": ".99-{{route}}",
"refId": "A"
},
{
"expr": "histogram_quantile(0.9, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\", cluster=\"$cluster\"})) * 1e3",
"expr": "histogram_quantile(0.9, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\", cluster=\"$cluster\"})) * 1e3",
"legendFormat": ".9-{{route}}",
"refId": "B"
},
{
"expr": "histogram_quantile(0.5, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\", cluster=\"$cluster\"})) * 1e3",
"expr": "histogram_quantile(0.5, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\", cluster=\"$cluster\"})) * 1e3",
"legendFormat": ".5-{{route}}",
"refId": "C"
}
@@ -1502,7 +1501,7 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}[5m])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}[5m])) by (route)",
"expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}[$__rate_interval])) by (route) > 0",
"interval": "",
"legendFormat": "{{route}}",
"refId": "A"
@@ -2049,7 +2048,7 @@
"panels": [ ],
"targets": [
{
"expr": "{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\"} | logfmt | level=\"error\"",
"expr": "{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\"} |= \"level=error\"",
"refId": "A"
}
],
@@ -2100,7 +2099,7 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\"}[5m])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\"}[5m])) by (route)",
"expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\"}[$__rate_interval])) by (route) > 0",
"interval": "",
"intervalFactor": 1,
"legendFormat": "{{route}}",
@@ -2190,9 +2189,9 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(loki_distributor_ingester_append_failures_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (ingester)",
"expr": "sum(rate(loki_distributor_ingester_append_failures_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (pod)",
"intervalFactor": 1,
"legendFormat": "{{ingester}}",
"legendFormat": "{{pod}}",
"refId": "A"
}
],
@@ -3256,7 +3255,7 @@
"panels": [ ],
"targets": [
{
"expr": "{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\"} | logfmt | level=\"error\"",
"expr": "{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\"} |= \"level=error\"",
"refId": "A"
}
],
@@ -3307,7 +3306,7 @@
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\", status_code!~\"5[0-9]{2}\"}[1m])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\"}[1m])) by (route)",
"expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\", status_code!~\"5[0-9]{2}\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\"}[$__rate_interval])) by (route) > 0",
"interval": "",
"intervalFactor": 1,
"legendFormat": "{{route}}",

View File

@@ -53,6 +53,11 @@
"points": false,
"renderer": "flot",
"seriesOverrides": [
{
"alias": "request",
"color": "#FFC000",
"fill": 0
},
{
"alias": "limit",
"color": "#E02F44",
@@ -72,6 +77,14 @@
"legendLink": null,
"step": 10
},
{
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\", resource=\"cpu\"} > 0)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "request",
"legendLink": null,
"step": 10
},
{
"expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\"})",
"format": "time_series",
@@ -142,6 +155,11 @@
"points": false,
"renderer": "flot",
"seriesOverrides": [
{
"alias": "request",
"color": "#FFC000",
"fill": 0
},
{
"alias": "limit",
"color": "#E02F44",
@@ -161,6 +179,14 @@
"legendLink": null,
"step": 10
},
{
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\", resource=\"memory\"} > 0)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "request",
"legendLink": null,
"step": 10
},
{
"expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\"} > 0)",
"format": "time_series",
@@ -509,83 +535,6 @@
"show": false
}
]
},
{
"aliasColors": { },
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"gridPos": { },
"id": 7,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [ ],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [ ],
"spaceLength": 10,
"span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "loki_boltdb_shipper_query_readiness_duration_seconds{cluster=~\"$cluster\", namespace=~\"$namespace\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "duration",
"legendLink": null,
"step": 10
}
],
"thresholds": [ ],
"timeFrom": null,
"timeShift": null,
"title": "Query Readiness Duration",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [ ]
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
}
],
"repeat": null,
@@ -607,7 +556,7 @@
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"id": 8,
"id": 7,
"legend": {
"avg": false,
"current": false,
@@ -626,6 +575,11 @@
"points": false,
"renderer": "flot",
"seriesOverrides": [
{
"alias": "request",
"color": "#FFC000",
"fill": 0
},
{
"alias": "limit",
"color": "#E02F44",
@@ -645,6 +599,14 @@
"legendLink": null,
"step": 10
},
{
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\", resource=\"cpu\"} > 0)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "request",
"legendLink": null,
"step": 10
},
{
"expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"})",
"format": "time_series",
@@ -695,7 +657,7 @@
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"id": 9,
"id": 8,
"legend": {
"avg": false,
"current": false,
@@ -714,6 +676,11 @@
"points": false,
"renderer": "flot",
"seriesOverrides": [
{
"alias": "request",
"color": "#FFC000",
"fill": 0
},
{
"alias": "limit",
"color": "#E02F44",
@@ -733,6 +700,14 @@
"legendLink": null,
"step": 10
},
{
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\", resource=\"memory\"} > 0)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "request",
"legendLink": null,
"step": 10
},
{
"expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"} > 0)",
"format": "time_series",
@@ -783,7 +758,7 @@
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"id": 10,
"id": 9,
"legend": {
"avg": false,
"current": false,

View File

@@ -142,7 +142,7 @@
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\", cluster=~\"$cluster\"})) * 1e3",
"expr": "histogram_quantile(0.99, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\"})) * 1e3",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ route }} 99th Percentile",
@@ -150,7 +150,7 @@
"step": 10
},
{
"expr": "histogram_quantile(0.50, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\", cluster=~\"$cluster\"})) * 1e3",
"expr": "histogram_quantile(0.50, sum by (le,route) (cluster_job_route:loki_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\"})) * 1e3",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ route }} 50th Percentile",
@@ -158,7 +158,7 @@
"step": 10
},
{
"expr": "1e3 * sum(job_route:loki_request_duration_seconds_sum:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\", cluster=~\"$cluster\"}) by (route) / sum(job_route:loki_request_duration_seconds_count:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\", cluster=~\"$cluster\"}) by (route) ",
"expr": "1e3 * sum(cluster_job_route:loki_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\"}) by (route) / sum(cluster_job_route:loki_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\"}) by (route) ",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ route }} Average",

View File

@@ -52,6 +52,11 @@
"points": false,
"renderer": "flot",
"seriesOverrides": [
{
"alias": "request",
"color": "#FFC000",
"fill": 0
},
{
"alias": "limit",
"color": "#E02F44",
@@ -71,6 +76,14 @@
"legendLink": null,
"step": 10
},
{
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\", resource=\"cpu\"} > 0)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "request",
"legendLink": null,
"step": 10
},
{
"expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\"})",
"format": "time_series",
@@ -140,6 +153,11 @@
"points": false,
"renderer": "flot",
"seriesOverrides": [
{
"alias": "request",
"color": "#FFC000",
"fill": 0
},
{
"alias": "limit",
"color": "#E02F44",
@@ -159,6 +177,14 @@
"legendLink": null,
"step": 10
},
{
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\", resource=\"memory\"} > 0)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "request",
"legendLink": null,
"step": 10
},
{
"expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\"} > 0)",
"format": "time_series",
@@ -1534,4 +1560,4 @@
"title": "Loki / Retention",
"uid": "retention",
"version": 0
}
}

View File

@@ -128,6 +128,11 @@
"points": false,
"renderer": "flot",
"seriesOverrides": [
{
"alias": "request",
"color": "#FFC000",
"fill": 0
},
{
"alias": "limit",
"color": "#E02F44",
@@ -147,6 +152,14 @@
"legendLink": null,
"step": 10
},
{
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\", resource=\"cpu\"} > 0)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "request",
"legendLink": null,
"step": 10
},
{
"expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"})",
"format": "time_series",
@@ -217,6 +230,11 @@
"points": false,
"renderer": "flot",
"seriesOverrides": [
{
"alias": "request",
"color": "#FFC000",
"fill": 0
},
{
"alias": "limit",
"color": "#E02F44",
@@ -236,6 +254,14 @@
"legendLink": null,
"step": 10
},
{
"expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\", resource=\"memory\"} > 0)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "request",
"legendLink": null,
"step": 10
},
{
"expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"} > 0)",
"format": "time_series",

View File

@@ -142,7 +142,7 @@
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum by (le) (job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3",
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job:loki_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-write\"})) * 1e3",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "99th Percentile",
@@ -150,7 +150,7 @@
"step": 10
},
{
"expr": "histogram_quantile(0.50, sum by (le) (job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3",
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job:loki_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-write\"})) * 1e3",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "50th Percentile",
@@ -158,7 +158,7 @@
"step": 10
},
{
"expr": "1e3 * sum(job:loki_request_duration_seconds_sum:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"}) / sum(job:loki_request_duration_seconds_count:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})",
"expr": "1e3 * sum(cluster_job:loki_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-write\"}) / sum(cluster_job:loki_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-write\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Average",

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -63,6 +63,13 @@ data:
targets = discovery.relabel.rename_meta_labels.output
forward_to = [ {{ include "agent.prometheus_write_targets" . }} ]
}
{{- if .Values.kubeStateMetrics.enabled }}
prometheus.scrape "kubeStateMetrics" {
targets = [ { "__address__" = "{{ .Values.kubeStateMetrics.endpoint }}" } ]
forward_to = [ {{ include "agent.prometheus_write_targets" . }} ]
}
{{- end }}
{{- end }}
{{- if or .Values.local.traces.enabled .Values.cloud.traces.enabled }}

View File

@@ -1,16 +1,16 @@
{{- if or (or .Values.local.logs.enabled .Values.local.metrics.enabled) .Values.local.traces.enabled }}
{{- if or (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled) .Values.dashboards.traces.enabled }}
---
apiVersion: v1
kind: ConfigMap
metadata:
name: loki-dashboards-provisioning
name: dashboards-provisioning
namespace: {{ $.Release.Namespace }}
data:
dashboards.yaml: |
---
apiVersion: 1
providers:
{{- if .Values.local.logs.enabled }}
{{- if .Values.dashboards.logs.enabled }}
- disableDeletion: true
editable: false
folder: Loki
@@ -28,7 +28,7 @@ data:
orgId: 1
type: file
{{- end }}
{{- if .Values.local.metrics.enabled }}
{{- if .Values.dashboards.metrics.enabled }}
- disableDeletion: true
editable: false
folder: Mimir
@@ -70,4 +70,14 @@ data:
orgId: 1
type: file
{{- end }}
{{- if .Values.dashboards.traces.enabled }}
- disableDeletion: true
editable: false
folder: Tempo
name: tempo-1
options:
path: /var/lib/grafana/dashboards/tempo-1
orgId: 1
type: file
{{- end }}
{{- end }}

View File

@@ -65,15 +65,17 @@ spec:
name: grafana-pv
- mountPath: /etc/grafana/provisioning/datasources
name: datasources-provisioning
{{- if or (or .Values.dashboards.logs.enabled .Values.dashboards.metrics.enabled) .Values.dashboards.traces.enabled }}
- mountPath: /etc/grafana/provisioning/dashboards
name: loki-dashboards-provisioning
{{- if .Values.local.logs.enabled }}
name: dashboards-provisioning
{{- end }}
{{- if .Values.dashboards.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 }}
{{- if .Values.dashboards.metrics.enabled }}
- mountPath: /var/lib/grafana/dashboards/mimir-1
name: mimir-dashboards-1
- mountPath: /var/lib/grafana/dashboards/mimir-2
@@ -85,6 +87,10 @@ spec:
- mountPath: /var/lib/grafana/dashboards/mimir-5
name: mimir-dashboards-5
{{- end }}
{{- if .Values.dashboards.traces.enabled }}
- mountPath: /var/lib/grafana/dashboards/tempo-1
name: tempo-dashboards-1
{{- end }}
volumes:
- name: grafana-pv
persistentVolumeClaim:
@@ -92,10 +98,10 @@ spec:
- name: datasources-provisioning
configMap:
name: datasources-provisioning
{{- if .Values.local.logs.enabled }}
- name: loki-dashboards-provisioning
- name: dashboards-provisioning
configMap:
name: loki-dashboards-provisioning
name: dashboards-provisioning
{{- if .Values.dashboards.logs.enabled }}
- name: loki-dashboards-1
configMap:
name: loki-dashboards-1
@@ -103,10 +109,7 @@ spec:
configMap:
name: loki-dashboards-2
{{- end }}
{{- if .Values.local.metrics.enabled }}
- name: mimir-dashboards-provisioning
configMap:
name: mimir-dashboards-provisioning
{{- if .Values.dashboards.metrics.enabled }}
- name: mimir-dashboards-1
configMap:
name: mimir-dashboards-1
@@ -123,6 +126,11 @@ spec:
configMap:
name: mimir-dashboards-5
{{- end }}
{{- if .Values.dashboards.traces.enabled }}
- name: tempo-dashboards-1
configMap:
name: tempo-dashboards-1
{{- end }}
---
apiVersion: v1
@@ -138,4 +146,4 @@ spec:
app: grafana
sessionAffinity: None
type: ClusterIP # Make this configurable
{{- end }}
{{- end }}

View File

@@ -1,4 +1,4 @@
{{- if .Values.local.logs.enabled }}
{{- if .Values.dashboards.logs.enabled }}
---
apiVersion: v1
kind: ConfigMap

View File

@@ -1,4 +1,4 @@
{{- if .Values.local.logs.enabled }}
{{- if .Values.dashboards.logs.enabled }}
---
apiVersion: v1
kind: ConfigMap

View File

@@ -1,4 +1,4 @@
{{- if .Values.local.metrics.enabled }}
{{- if .Values.dashboards.metrics.enabled }}
---
apiVersion: v1
kind: ConfigMap

View File

@@ -1,4 +1,4 @@
{{- if .Values.local.metrics.enabled }}
{{- if .Values.dashboards.metrics.enabled }}
---
apiVersion: v1
kind: ConfigMap

View File

@@ -1,4 +1,4 @@
{{- if .Values.local.metrics.enabled }}
{{- if .Values.dashboards.metrics.enabled }}
---
apiVersion: v1
kind: ConfigMap

View File

@@ -1,4 +1,4 @@
{{- if .Values.local.metrics.enabled }}
{{- if .Values.dashboards.metrics.enabled }}
---
apiVersion: v1
kind: ConfigMap

View File

@@ -1,4 +1,4 @@
{{- if .Values.local.metrics.enabled }}
{{- if .Values.dashboards.metrics.enabled }}
---
apiVersion: v1
kind: ConfigMap

View File

@@ -0,0 +1,21 @@
{{- if .Values.dashboards.traces.enabled }}
---
apiVersion: v1
kind: ConfigMap
metadata:
name: tempo-dashboards-1
namespace: {{ $.Release.Namespace }}
data:
"tempo-operational.json": |
{{ $.Files.Get "src/dashboards/tempo-operational.json" | fromJson | toJson }}
"tempo-reads.json": |
{{ $.Files.Get "src/dashboards/tempo-reads.json" | fromJson | toJson }}
"tempo-resources.json": |
{{ $.Files.Get "src/dashboards/tempo-resources.json" | fromJson | toJson }}
"tempo-rollout-progress.json": |
{{ $.Files.Get "src/dashboards/tempo-rollout-progress.json" | fromJson | toJson }}
"tempo-tenants.json": |
{{ $.Files.Get "src/dashboards/tempo-tenants.json" | fromJson | toJson }}
"tempo-writes.json": |
{{ $.Files.Get "src/dashboards/tempo-writes.json" | fromJson | toJson }}
{{- end }}

View File

@@ -14,7 +14,6 @@ local:
minio:
enabled: false # This should be set to true if any of the previous is enabled
cloud:
logs:
enabled: true
@@ -41,11 +40,28 @@ logs:
# source: "" # Empty uses the log message
# replace: "*****""
# Set enabled = true to add the default logs/metrics/traces dashboards to the local Grafana
dashboards:
logs:
enabled: true
metrics:
enabled: true
traces:
enabled: true
global:
minio:
rootUser: "rootuser"
rootPassword: "rootpassword"
kubeStateMetrics:
# Scrape https://github.com/kubernetes/kube-state-metrics by default
enabled: true
# This endpoint is created when the helm chart from
# https://artifacthub.io/packages/helm/prometheus-community/kube-state-metrics/
# is used. Change this if kube-state-metrics is installed somewhere else.
endpoint: kube-state-metrics.kube-state-metrics.svc.cluster.local:8080
# The following are configuration for the dependencies.
# These should not be changed.