openstack-helm-infra/values_overrides/grafana/prometheus.yaml
Vladimir Kozhukalov 8b29037cec Move values overrides to a separate directory
This is the action item to implement the spec:
doc/source/specs/2025.1/chart_versioning.rst

Also add overrides env variables

- OSH_VALUES_OVERRIDES_PATH
- OSH_INFRA_VALUES_OVERRIDES_PATH

This commit temporarily disables all jobs that involve scripts
in the OSH git repo because they need to be updated to work
with the new values_overrides structure in the OSH-infra repo.
Once this is merged I4974785c904cf7c8730279854e3ad9b6b7c35498
all these disabled test jobs must be enabled.

Depends-On: I327103c18fc0e10e989a17f69b3bff9995c45eb4
Change-Id: I7bfdef3ea2128bbb4e26e3a00161fe30ce29b8e7
2024-12-13 12:04:44 -06:00

3711 lines
114 KiB
YAML

# NOTE(srwilkers): This overrides file provides a reference for a dashboard for
# Prometheus
---
conf:
dashboards:
lma:
prometheus: |-
{
"__inputs": [
{
"name": "DS_PROMETHEUS",
"label": "prometheus",
"description": "Prometheus which you want to monitor",
"type": "datasource",
"pluginId": "prometheus",
"pluginName": "Prometheus"
}
],
"__requires": [
{
"type": "grafana",
"id": "grafana",
"name": "Grafana",
"version": "4.6.0"
},
{
"type": "panel",
"id": "graph",
"name": "Graph",
"version": ""
},
{
"type": "datasource",
"id": "prometheus",
"name": "Prometheus",
"version": "1.0.0"
},
{
"type": "panel",
"id": "singlestat",
"name": "Singlestat",
"version": ""
},
{
"type": "panel",
"id": "text",
"name": "Text",
"version": ""
}
],
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": "-- Grafana --",
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
},
{
"datasource": "${DS_PROMETHEUS}",
"enable": true,
"expr": "count(sum(up{instance=\"$instance\"}) by (instance) < 1)",
"hide": false,
"iconColor": "rgb(250, 44, 18)",
"limit": 100,
"name": "downage",
"showIn": 0,
"step": "30s",
"tagKeys": "instance",
"textFormat": "prometheus down",
"titleFormat": "Downage",
"type": "alert"
},
{
"datasource": "${DS_PROMETHEUS}",
"enable": true,
"expr": "sum(changes(prometheus_config_last_reload_success_timestamp_seconds[10m])) by (instance)",
"hide": false,
"iconColor": "#fceaca",
"limit": 100,
"name": "Reload",
"showIn": 0,
"step": "5m",
"tagKeys": "instance",
"tags": [],
"titleFormat": "Reload",
"type": "tags"
}
]
},
"description": "Dashboard for monitoring of Prometheus v2.x.x",
"overwrite": true,
"editable": false,
"gnetId": 3681,
"graphTooltip": 1,
"id": 41,
"links": [
{
"icon": "info",
"tags": [],
"targetBlank": true,
"title": "Dashboard's Github ",
"tooltip": "Github repo of this dashboard",
"type": "link",
"url": "https://github.com/FUSAKLA/Prometheus2-grafana-dashboard"
},
{
"icon": "doc",
"tags": [],
"targetBlank": true,
"title": "Prometheus Docs",
"tooltip": "",
"type": "link",
"url": "http://prometheus.io/docs/introduction/overview/"
}
],
"panels": [
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 0
},
"id": 53,
"panels": [],
"repeat": null,
"title": "Header instance info",
"type": "row"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"#299c46",
"rgba(237, 129, 40, 0.89)",
"#bf1b00"
],
"datasource": "${DS_PROMETHEUS}",
"decimals": 1,
"format": "s",
"gauge": {
"maxValue": 1000000,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
"h": 5,
"w": 4,
"x": 0,
"y": 1
},
"id": 41,
"interval": null,
"links": [],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"options": {},
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "time() - process_start_time_seconds{instance=\"$instance\"}",
"format": "time_series",
"instant": false,
"intervalFactor": 2,
"refId": "A"
}
],
"thresholds": "",
"title": "Uptime",
"type": "singlestat",
"valueFontSize": "80%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "current"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": true,
"colors": [
"#299c46",
"rgba(237, 129, 40, 0.89)",
"#bf1b00"
],
"datasource": "${DS_PROMETHEUS}",
"format": "short",
"gauge": {
"maxValue": 1000000,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
"h": 5,
"w": 8,
"x": 4,
"y": 1
},
"id": 42,
"interval": null,
"links": [],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"options": {},
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": true
},
"tableColumn": "",
"targets": [
{
"expr": "prometheus_tsdb_head_series{instance=\"$instance\"}",
"format": "time_series",
"instant": false,
"intervalFactor": 2,
"refId": "A"
}
],
"thresholds": "500000,800000,1000000",
"title": "Total count of time series",
"type": "singlestat",
"valueFontSize": "150%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "current"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"#299c46",
"rgba(237, 129, 40, 0.89)",
"#d44a3a"
],
"datasource": "${DS_PROMETHEUS}",
"format": "none",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
"h": 5,
"w": 4,
"x": 12,
"y": 1
},
"id": 48,
"interval": null,
"links": [],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"options": {},
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "version",
"targets": [
{
"expr": "prometheus_build_info{instance=\"$instance\"}",
"format": "table",
"instant": true,
"intervalFactor": 2,
"refId": "A"
}
],
"thresholds": "",
"title": "Version",
"type": "singlestat",
"valueFontSize": "80%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "avg"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"#299c46",
"rgba(237, 129, 40, 0.89)",
"#d44a3a"
],
"datasource": "${DS_PROMETHEUS}",
"decimals": 2,
"format": "ms",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
"h": 5,
"w": 4,
"x": 16,
"y": 1
},
"id": 49,
"interval": null,
"links": [],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"options": {},
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "prometheus_tsdb_head_max_time{instance=\"$instance\"} - prometheus_tsdb_head_min_time{instance=\"$instance\"}",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
"refId": "A"
}
],
"thresholds": "",
"title": "Actual head block length",
"type": "singlestat",
"valueFontSize": "80%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "current"
},
{
"content": "<img src=\"https://cdn.worldvectorlogo.com/logos/prometheus.svg\"/ height=\"140px\">",
"gridPos": {
"h": 5,
"w": 2,
"x": 20,
"y": 1
},
"height": "",
"id": 50,
"links": [],
"mode": "html",
"options": {},
"title": "",
"transparent": true,
"type": "text"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": true,
"colors": [
"#e6522c",
"rgba(237, 129, 40, 0.89)",
"#299c46"
],
"datasource": "${DS_PROMETHEUS}",
"decimals": 1,
"format": "none",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
"h": 5,
"w": 2,
"x": 22,
"y": 1
},
"id": 52,
"interval": null,
"links": [],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"options": {},
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "2",
"format": "time_series",
"intervalFactor": 2,
"refId": "A"
}
],
"thresholds": "10,20",
"title": "",
"transparent": true,
"type": "singlestat",
"valueFontSize": "200%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "avg"
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 6
},
"id": 54,
"panels": [],
"repeat": null,
"title": "Main info",
"type": "row"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"editable": true,
"error": false,
"fill": 1,
"gridPos": {
"h": 7,
"w": 8,
"x": 0,
"y": 7
},
"id": 15,
"legend": {
"avg": true,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "max(prometheus_engine_query_duration_seconds{instance=\"$instance\"}) by (instance, slice)",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "max duration for {{slice}}",
"metric": "prometheus_local_storage_rushed_mode",
"refId": "A",
"step": 900
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Query elapsed time",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "s",
"label": "",
"logBase": 1,
"max": null,
"min": "0",
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {
"Chunks": "#1F78C1",
"Chunks to persist": "#508642",
"Max chunks": "#052B51",
"Max to persist": "#3F6833"
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"editable": true,
"error": false,
"fill": 1,
"gridPos": {
"h": 7,
"w": 8,
"x": 8,
"y": 7
},
"id": 17,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(increase(prometheus_tsdb_head_series_created_total{instance=\"$instance\"}[$aggregation_interval])) by (instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "created on {{ instance }}",
"metric": "prometheus_local_storage_maintain_series_duration_seconds_count",
"refId": "A",
"step": 1800
},
{
"expr": "sum(increase(prometheus_tsdb_head_series_removed_total{instance=\"$instance\"}[$aggregation_interval])) by (instance) * -1",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "removed on {{ instance }}",
"refId": "B"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Head series created/deleted",
"tooltip": {
"msResolution": false,
"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": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {
"Chunks": "#1F78C1",
"Chunks to persist": "#508642",
"Max chunks": "#052B51",
"Max to persist": "#3F6833"
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"editable": true,
"error": false,
"fill": 1,
"gridPos": {
"h": 7,
"w": 8,
"x": 16,
"y": 7
},
"id": 13,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(increase(prometheus_target_scrapes_exceeded_sample_limit_total{instance=\"$instance\"}[$aggregation_interval])) by (instance) > 0",
"format": "time_series",
"interval": "",
"intervalFactor": 2,
"legendFormat": "exceeded_sample_limit on {{ instance }}",
"metric": "prometheus_local_storage_chunk_ops_total",
"refId": "A",
"step": 1800
},
{
"expr": "sum(increase(prometheus_target_scrapes_sample_duplicate_timestamp_total{instance=\"$instance\"}[$aggregation_interval])) by (instance) > 0",
"format": "time_series",
"interval": "",
"intervalFactor": 2,
"legendFormat": "duplicate_timestamp on {{ instance }}",
"metric": "prometheus_local_storage_chunk_ops_total",
"refId": "B",
"step": 1800
},
{
"expr": "sum(increase(prometheus_target_scrapes_sample_out_of_bounds_total{instance=\"$instance\"}[$aggregation_interval])) by (instance) > 0",
"format": "time_series",
"interval": "",
"intervalFactor": 2,
"legendFormat": "out_of_bounds on {{ instance }}",
"metric": "prometheus_local_storage_chunk_ops_total",
"refId": "C",
"step": 1800
},
{
"expr": "sum(increase(prometheus_target_scrapes_sample_out_of_order_total{instance=\"$instance\"}[$aggregation_interval])) by (instance) > 0",
"format": "time_series",
"interval": "",
"intervalFactor": 2,
"legendFormat": "out_of_order on {{ instance }}",
"metric": "prometheus_local_storage_chunk_ops_total",
"refId": "D",
"step": 1800
},
{
"expr": "sum(increase(prometheus_rule_evaluation_failures_total{instance=\"$instance\"}[$aggregation_interval])) by (instance) > 0",
"format": "time_series",
"interval": "",
"intervalFactor": 2,
"legendFormat": "rule_evaluation_failure on {{ instance }}",
"metric": "prometheus_local_storage_chunk_ops_total",
"refId": "G",
"step": 1800
},
{
"expr": "sum(increase(prometheus_tsdb_compactions_failed_total{instance=\"$instance\"}[$aggregation_interval])) by (instance) > 0",
"format": "time_series",
"interval": "",
"intervalFactor": 2,
"legendFormat": "tsdb_compactions_failed on {{ instance }}",
"metric": "prometheus_local_storage_chunk_ops_total",
"refId": "K",
"step": 1800
},
{
"expr": "sum(increase(prometheus_tsdb_reloads_failures_total{instance=\"$instance\"}[$aggregation_interval])) by (instance) > 0",
"format": "time_series",
"interval": "",
"intervalFactor": 2,
"legendFormat": "tsdb_reloads_failures on {{ instance }}",
"metric": "prometheus_local_storage_chunk_ops_total",
"refId": "L",
"step": 1800
},
{
"expr": "sum(increase(prometheus_tsdb_head_series_not_found{instance=\"$instance\"}[$aggregation_interval])) by (instance) > 0",
"format": "time_series",
"interval": "",
"intervalFactor": 2,
"legendFormat": "head_series_not_found on {{ instance }}",
"metric": "prometheus_local_storage_chunk_ops_total",
"refId": "E",
"step": 1800
},
{
"expr": "sum(increase(prometheus_evaluator_iterations_missed_total{instance=\"$instance\"}[$aggregation_interval])) by (instance) > 0",
"format": "time_series",
"interval": "",
"intervalFactor": 2,
"legendFormat": "evaluator_iterations_missed on {{ instance }}",
"metric": "prometheus_local_storage_chunk_ops_total",
"refId": "O",
"step": 1800
},
{
"expr": "sum(increase(prometheus_evaluator_iterations_skipped_total{instance=\"$instance\"}[$aggregation_interval])) by (instance) > 0",
"format": "time_series",
"interval": "",
"intervalFactor": 2,
"legendFormat": "evaluator_iterations_skipped on {{ instance }}",
"metric": "prometheus_local_storage_chunk_ops_total",
"refId": "P",
"step": 1800
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Prometheus errors",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": "0",
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 14
},
"id": 55,
"panels": [],
"repeat": null,
"title": "Scrape & rule duration",
"type": "row"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"description": "",
"editable": true,
"error": false,
"fill": 1,
"grid": {},
"gridPos": {
"h": 7,
"w": 12,
"x": 0,
"y": 15
},
"id": 25,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"max": true,
"min": false,
"show": false,
"sort": "max",
"sortDesc": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "connected",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "prometheus_target_interval_length_seconds{instance=\"$instance\",quantile=\"0.99\"} - 60",
"format": "time_series",
"interval": "2m",
"intervalFactor": 1,
"legendFormat": "{{instance}}",
"metric": "",
"refId": "A",
"step": 300
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Scrape delay (counts with 1m scrape interval)",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 2,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "s",
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {
"Chunks": "#1F78C1",
"Chunks to persist": "#508642",
"Max chunks": "#052B51",
"Max to persist": "#3F6833"
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"editable": true,
"error": false,
"fill": 1,
"gridPos": {
"h": 7,
"w": 12,
"x": 12,
"y": 15
},
"id": 14,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [
{
"alias": "Queue length",
"yaxis": 2
}
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(prometheus_evaluator_duration_seconds{instance=\"$instance\"}) by (instance, quantile)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Queue length",
"metric": "prometheus_local_storage_indexing_queue_length",
"refId": "B",
"step": 1800
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Rule evaulation duration",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": "0",
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": "0",
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 22
},
"id": 56,
"panels": [],
"repeat": null,
"title": "Requests & queries",
"type": "row"
},
{
"aliasColors": {
"Chunks": "#1F78C1",
"Chunks to persist": "#508642",
"Max chunks": "#052B51",
"Max to persist": "#3F6833"
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"editable": true,
"error": false,
"fill": 1,
"gridPos": {
"h": 7,
"w": 6,
"x": 0,
"y": 23
},
"id": 18,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(increase(http_requests_total{instance=\"$instance\"}[$aggregation_interval])) by (instance, handler) > 0",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ handler }} on {{ instance }}",
"metric": "",
"refId": "A",
"step": 1800
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Request count",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "none",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {
"Chunks": "#1F78C1",
"Chunks to persist": "#508642",
"Max chunks": "#052B51",
"Max to persist": "#3F6833"
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"editable": true,
"error": false,
"fill": 1,
"gridPos": {
"h": 7,
"w": 6,
"x": 6,
"y": 23
},
"id": 16,
"legend": {
"avg": false,
"current": false,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "max(sum(http_request_duration_microseconds{instance=\"$instance\"}) by (instance, handler, quantile)) by (instance, handler) > 0",
"format": "time_series",
"hide": false,
"intervalFactor": 2,
"legendFormat": "{{ handler }} on {{ instance }}",
"refId": "B"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Request duration per handler",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "µs",
"label": null,
"logBase": 1,
"max": null,
"min": "0",
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {
"Chunks": "#1F78C1",
"Chunks to persist": "#508642",
"Max chunks": "#052B51",
"Max to persist": "#3F6833"
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"editable": true,
"error": false,
"fill": 1,
"gridPos": {
"h": 7,
"w": 6,
"x": 12,
"y": 23
},
"id": 19,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(increase(http_request_size_bytes{instance=\"$instance\", quantile=\"0.99\"}[$aggregation_interval])) by (instance, handler) > 0",
"format": "time_series",
"hide": false,
"intervalFactor": 2,
"legendFormat": "{{ handler }} in {{ instance }}",
"refId": "B"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Request size by handler",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "bytes",
"label": null,
"logBase": 1,
"max": null,
"min": "0",
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {
"Allocated bytes": "#F9BA8F",
"Chunks": "#1F78C1",
"Chunks to persist": "#508642",
"Max chunks": "#052B51",
"Max count collector": "#bf1b00",
"Max count harvester": "#bf1b00",
"Max to persist": "#3F6833",
"RSS": "#890F02"
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"editable": true,
"error": false,
"fill": 1,
"gridPos": {
"h": 7,
"w": 6,
"x": 18,
"y": 23
},
"id": 8,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [
{
"alias": "/Max.*/",
"fill": 0,
"linewidth": 2
}
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(prometheus_engine_queries{instance=\"$instance\"}) by (instance, handler)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Current count ",
"metric": "last",
"refId": "A",
"step": 1800
},
{
"expr": "sum(prometheus_engine_queries_concurrent_max{instance=\"$instance\"}) by (instance, handler)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Max count",
"metric": "last",
"refId": "B",
"step": 1800
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Cont of concurent queries",
"tooltip": {
"msResolution": false,
"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": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 30
},
"id": 57,
"panels": [],
"repeat": null,
"title": "Alerting",
"type": "row"
},
{
"aliasColors": {
"Alert queue capacity on o collector": "#bf1b00",
"Alert queue capacity on o harvester": "#bf1b00",
"Chunks": "#1F78C1",
"Chunks to persist": "#508642",
"Max chunks": "#052B51",
"Max to persist": "#3F6833"
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"editable": true,
"error": false,
"fill": 1,
"gridPos": {
"h": 7,
"w": 8,
"x": 0,
"y": 31
},
"id": 20,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [
{
"alias": "/.*capacity.*/",
"fill": 0,
"linewidth": 2
}
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(prometheus_notifications_queue_capacity{instance=\"$instance\"})by (instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Alert queue capacity ",
"metric": "prometheus_local_storage_checkpoint_last_size_bytes",
"refId": "A",
"step": 1800
},
{
"expr": "sum(prometheus_notifications_queue_length{instance=\"$instance\"})by (instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Alert queue size on ",
"metric": "prometheus_local_storage_checkpoint_last_size_bytes",
"refId": "B",
"step": 1800
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Alert queue size",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "bytes",
"label": null,
"logBase": 1,
"max": null,
"min": "0",
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {
"Chunks": "#1F78C1",
"Chunks to persist": "#508642",
"Max chunks": "#052B51",
"Max to persist": "#3F6833"
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"editable": true,
"error": false,
"fill": 1,
"gridPos": {
"h": 7,
"w": 8,
"x": 8,
"y": 31
},
"id": 21,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(prometheus_notifications_alertmanagers_discovered{instance=\"$instance\"}) by (instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Checkpoint chunks written/s",
"metric": "prometheus_local_storage_checkpoint_series_chunks_written_sum",
"refId": "A",
"step": 1800
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Count of discovered alertmanagers",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "none",
"label": null,
"logBase": 1,
"max": null,
"min": "0",
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {
"Chunks": "#1F78C1",
"Chunks to persist": "#508642",
"Max chunks": "#052B51",
"Max to persist": "#3F6833"
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"editable": true,
"error": false,
"fill": 1,
"gridPos": {
"h": 7,
"w": 8,
"x": 16,
"y": 31
},
"id": 39,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(increase(prometheus_notifications_dropped_total{instance=\"$instance\"}[$aggregation_interval])) by (instance) > 0",
"format": "time_series",
"interval": "",
"intervalFactor": 2,
"legendFormat": "notifications_dropped on {{ instance }}",
"metric": "prometheus_local_storage_chunk_ops_total",
"refId": "F",
"step": 1800
},
{
"expr": "sum(increase(prometheus_rule_evaluation_failures_total{rule_type=\"alerting\",instance=\"$instance\"}[$aggregation_interval])) by (rule_type,instance) > 0",
"format": "time_series",
"interval": "",
"intervalFactor": 2,
"legendFormat": "rule_evaluation_failures on {{ instance }}",
"metric": "prometheus_local_storage_chunk_ops_total",
"refId": "A",
"step": 1800
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Alerting errors",
"tooltip": {
"msResolution": false,
"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": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 38
},
"id": 58,
"panels": [],
"repeat": null,
"title": "Service discovery",
"type": "row"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"fill": 1,
"gridPos": {
"h": 7,
"w": 6,
"x": 0,
"y": 39
},
"id": 45,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "increase(prometheus_target_sync_length_seconds_count{scrape_job=\"kubernetes-service-endpoints\"}[$aggregation_interval])",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Count of target synces",
"refId": "A",
"step": 240
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
"title": "Kubernetes SD sync count",
"tooltip": {
"shared": true,
"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": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
"Chunks": "#1F78C1",
"Chunks to persist": "#508642",
"Max chunks": "#052B51",
"Max to persist": "#3F6833"
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"editable": true,
"error": false,
"fill": 1,
"gridPos": {
"h": 7,
"w": 6,
"x": 6,
"y": 39
},
"id": 46,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(increase(prometheus_target_scrapes_exceeded_sample_limit_total{instance=\"$instance\"}[$aggregation_interval])) by (instance) > 0",
"format": "time_series",
"interval": "",
"intervalFactor": 2,
"legendFormat": "exceeded_sample_limit on {{ instance }}",
"metric": "prometheus_local_storage_chunk_ops_total",
"refId": "A",
"step": 1800
},
{
"expr": "sum(increase(prometheus_sd_file_read_errors_total{instance=\"$instance\"}[$aggregation_interval])) by (instance) > 0",
"format": "time_series",
"interval": "",
"intervalFactor": 2,
"legendFormat": "sd_file_read_error on {{ instance }}",
"metric": "prometheus_local_storage_chunk_ops_total",
"refId": "E",
"step": 1800
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
"title": "Service discovery errors",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": "0",
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 46
},
"id": 59,
"panels": [],
"repeat": null,
"title": "TSDB stats",
"type": "row"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"fill": 1,
"gridPos": {
"h": 7,
"w": 6,
"x": 0,
"y": 47
},
"id": 36,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(increase(prometheus_tsdb_reloads_total{instance=\"$instance\"}[30m])) by (instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ instance }}",
"refId": "A"
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
"title": "Reloaded block from disk",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
"Chunks": "#1F78C1",
"Chunks to persist": "#508642",
"Max chunks": "#052B51",
"Max to persist": "#3F6833"
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"editable": true,
"error": false,
"fill": 1,
"gridPos": {
"h": 7,
"w": 6,
"x": 6,
"y": 47
},
"id": 5,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(prometheus_tsdb_blocks_loaded{instance=\"$instance\"}) by (instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Loaded data blocks",
"metric": "prometheus_local_storage_memory_chunkdescs",
"refId": "A",
"step": 1800
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
"title": "Loaded data blocks",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": "0",
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
"Chunks": "#1F78C1",
"Chunks to persist": "#508642",
"Max chunks": "#052B51",
"Max to persist": "#3F6833"
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"editable": true,
"error": false,
"fill": 1,
"gridPos": {
"h": 7,
"w": 6,
"x": 12,
"y": 47
},
"id": 3,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "prometheus_tsdb_head_series{instance=\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Time series count",
"metric": "prometheus_local_storage_memory_series",
"refId": "A",
"step": 1800
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
"title": "Time series total count",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": "0",
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"editable": true,
"error": false,
"fill": 1,
"gridPos": {
"h": 7,
"w": 6,
"x": 18,
"y": 47
},
"id": 1,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(prometheus_tsdb_head_samples_appended_total{instance=\"$instance\"}[$aggregation_interval])) by (instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "samples/s {{instance}}",
"metric": "prometheus_local_storage_ingested_samples_total",
"refId": "A",
"step": 1800
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
"title": "Samples Appended per second",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "short",
"label": "",
"logBase": 1,
"max": null,
"min": "0",
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 54
},
"id": 60,
"panels": [],
"repeat": null,
"title": "Head block stats",
"type": "row"
},
{
"aliasColors": {
"Chunks": "#1F78C1",
"Chunks to persist": "#508642",
"Max chunks": "#052B51",
"Max to persist": "#3F6833",
"To persist": "#9AC48A"
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"editable": true,
"error": false,
"fill": 1,
"gridPos": {
"h": 7,
"w": 8,
"x": 0,
"y": 55
},
"id": 2,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [
{
"alias": "/Max.*/",
"fill": 0
}
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(prometheus_tsdb_head_chunks{instance=\"$instance\"}) by (instance)",
"format": "time_series",
"hide": false,
"intervalFactor": 2,
"legendFormat": "Head chunk count",
"metric": "prometheus_local_storage_memory_chunks",
"refId": "A",
"step": 1800
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
"title": "Head chunks count",
"tooltip": {
"msResolution": false,
"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": true
}
]
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"fill": 1,
"gridPos": {
"h": 7,
"w": 8,
"x": 8,
"y": 55
},
"id": 35,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "max(prometheus_tsdb_head_max_time{instance=\"$instance\"}) by (instance) - min(prometheus_tsdb_head_min_time{instance=\"$instance\"}) by (instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ instance }}",
"refId": "A"
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
"title": "Length of head block",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "ms",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
"Chunks": "#1F78C1",
"Chunks to persist": "#508642",
"Max chunks": "#052B51",
"Max to persist": "#3F6833"
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"editable": true,
"error": false,
"fill": 1,
"gridPos": {
"h": 7,
"w": 8,
"x": 16,
"y": 55
},
"id": 4,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(prometheus_tsdb_head_chunks_created_total{instance=\"$instance\"}[$aggregation_interval])) by (instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "created on {{ instance }}",
"refId": "B"
},
{
"expr": "sum(rate(prometheus_tsdb_head_chunks_removed_total{instance=\"$instance\"}[$aggregation_interval])) by (instance) * -1",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "deleted on {{ instance }}",
"refId": "C"
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
"title": "Head Chunks Created/Deleted per second",
"tooltip": {
"msResolution": false,
"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": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 62
},
"id": 61,
"panels": [],
"repeat": null,
"title": "Data maintenance",
"type": "row"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"fill": 1,
"gridPos": {
"h": 7,
"w": 6,
"x": 0,
"y": 63
},
"id": 33,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "connected",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(increase(prometheus_tsdb_compaction_duration_sum{instance=\"$instance\"}[30m]) / increase(prometheus_tsdb_compaction_duration_count{instance=\"$instance\"}[30m])) by (instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ instance }}",
"refId": "B"
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
"title": "Compaction duration",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"fill": 1,
"gridPos": {
"h": 7,
"w": 6,
"x": 6,
"y": 63
},
"id": 34,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "connected",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(prometheus_tsdb_head_gc_duration_seconds{instance=\"$instance\"}) by (instance, quantile)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ quantile }} on {{ instance }}",
"refId": "A"
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
"title": "Go Garbage collection duration",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"fill": 1,
"gridPos": {
"h": 7,
"w": 6,
"x": 12,
"y": 63
},
"id": 37,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "connected",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(prometheus_tsdb_wal_truncate_duration_seconds{instance=\"$instance\"}) by (instance, quantile)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ quantile }} on {{ instance }}",
"refId": "A"
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
"title": "WAL truncate duration seconds",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"fill": 1,
"gridPos": {
"h": 7,
"w": 6,
"x": 18,
"y": 63
},
"id": 38,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "connected",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(tsdb_wal_fsync_duration_seconds{instance=\"$instance\"}) by (instance, quantile)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ quantile }} {{ instance }}",
"refId": "A"
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
"title": "WAL fsync duration seconds",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 70
},
"id": 62,
"panels": [],
"repeat": null,
"title": "RAM&CPU",
"type": "row"
},
{
"aliasColors": {
"Allocated bytes": "#7EB26D",
"Allocated bytes - 1m max": "#BF1B00",
"Allocated bytes - 1m min": "#BF1B00",
"Allocated bytes - 5m max": "#BF1B00",
"Allocated bytes - 5m min": "#BF1B00",
"Chunks": "#1F78C1",
"Chunks to persist": "#508642",
"Max chunks": "#052B51",
"Max to persist": "#3F6833",
"RSS": "#447EBC"
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"decimals": null,
"editable": true,
"error": false,
"fill": 1,
"gridPos": {
"h": 7,
"w": 8,
"x": 0,
"y": 71
},
"id": 6,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [
{
"alias": "/-/",
"fill": 0
},
{
"alias": "collector heap size",
"color": "#E0752D",
"fill": 0,
"linewidth": 2
},
{
"alias": "collector kubernetes memory limit",
"color": "#BF1B00",
"fill": 0,
"linewidth": 3
}
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(process_resident_memory_bytes{instance=\"$instance\"}) by (instance)",
"format": "time_series",
"hide": false,
"intervalFactor": 2,
"legendFormat": "Total resident memory - {{instance}}",
"metric": "process_resident_memory_bytes",
"refId": "B",
"step": 1800
},
{
"expr": "sum(go_memstats_alloc_bytes{instance=\"$instance\"}) by (instance)",
"format": "time_series",
"hide": false,
"intervalFactor": 2,
"legendFormat": "Total llocated bytes - {{instance}}",
"metric": "go_memstats_alloc_bytes",
"refId": "A",
"step": 1800
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
"title": "Memory",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "bytes",
"label": null,
"logBase": 1,
"max": null,
"min": "0",
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
"Allocated bytes": "#F9BA8F",
"Chunks": "#1F78C1",
"Chunks to persist": "#508642",
"Max chunks": "#052B51",
"Max to persist": "#3F6833",
"RSS": "#890F02"
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"editable": true,
"error": false,
"fill": 1,
"gridPos": {
"h": 7,
"w": 8,
"x": 8,
"y": 71
},
"id": 7,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "rate(go_memstats_alloc_bytes_total{instance=\"$instance\"}[$aggregation_interval])",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Allocated Bytes/s",
"metric": "go_memstats_alloc_bytes",
"refId": "A",
"step": 1800
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
"title": "Allocations per second",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "bytes",
"label": null,
"logBase": 1,
"max": null,
"min": "0",
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"decimals": 2,
"editable": true,
"error": false,
"fill": 1,
"gridPos": {
"h": 7,
"w": 8,
"x": 16,
"y": 71
},
"id": 9,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": false,
"max": false,
"min": false,
"rightSide": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(process_cpu_seconds_total{instance=\"$instance\"}[$aggregation_interval])) by (instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "CPU/s",
"metric": "prometheus_local_storage_ingested_samples_total",
"refId": "B",
"step": 1800
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
"title": "CPU per second",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
"avg"
]
},
"yaxes": [
{
"format": "none",
"label": null,
"logBase": 1,
"max": null,
"min": "0",
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 78
},
"id": 63,
"panels": [],
"repeat": null,
"title": "Contrac errors",
"type": "row"
},
{
"aliasColors": {
"Chunks": "#1F78C1",
"Chunks to persist": "#508642",
"Max chunks": "#052B51",
"Max to persist": "#3F6833"
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"editable": true,
"error": false,
"fill": 1,
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 79
},
"id": 47,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(increase(net_conntrack_dialer_conn_failed_total{instance=\"$instance\"}[$aggregation_interval])) by (instance) > 0",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 2,
"legendFormat": "conntrack_dialer_conn_failed on {{ instance }}",
"metric": "prometheus_local_storage_chunk_ops_total",
"refId": "M",
"step": 1800
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
"title": "Net errors",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": "0",
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
}
],
"refresh": "5m",
"schemaVersion": 18,
"style": "dark",
"tags": [
"prometheus"
],
"templating": {
"list": [
{
"auto": true,
"auto_count": 30,
"auto_min": "2m",
"current": {
"text": "auto",
"value": "$__auto_interval_aggregation_interval"
},
"hide": 0,
"label": "aggregation intarval",
"name": "aggregation_interval",
"options": [
{
"selected": true,
"text": "auto",
"value": "$__auto_interval_aggregation_interval"
},
{
"selected": false,
"text": "1m",
"value": "1m"
},
{
"selected": false,
"text": "10m",
"value": "10m"
},
{
"selected": false,
"text": "30m",
"value": "30m"
},
{
"selected": false,
"text": "1h",
"value": "1h"
},
{
"selected": false,
"text": "6h",
"value": "6h"
},
{
"selected": false,
"text": "12h",
"value": "12h"
},
{
"selected": false,
"text": "1d",
"value": "1d"
},
{
"selected": false,
"text": "7d",
"value": "7d"
},
{
"selected": false,
"text": "14d",
"value": "14d"
},
{
"selected": false,
"text": "30d",
"value": "30d"
}
],
"query": "1m,10m,30m,1h,6h,12h,1d,7d,14d,30d",
"refresh": 2,
"skipUrlSync": false,
"type": "interval"
},
{
"allValue": null,
"current": {},
"datasource": "${DS_PROMETHEUS}",
"definition": "",
"hide": 0,
"includeAll": false,
"label": "Instance",
"multi": false,
"name": "instance",
"options": [],
"query": "label_values(prometheus_build_info, instance)",
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 2,
"tagValuesQuery": "",
"tags": [],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"current": {
"text": "prometheus",
"value": "prometheus"
},
"hide": 0,
"includeAll": false,
"label": "Prometheus datasource",
"multi": false,
"name": "DS_PROMETHEUS",
"options": [],
"query": "prometheus",
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"type": "datasource"
},
{
"current": {
"text": "No data sources found",
"value": ""
},
"hide": 0,
"includeAll": false,
"label": "InfluxDB datasource",
"multi": false,
"name": "influx_datasource",
"options": [],
"query": "influxdb",
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"type": "datasource"
}
]
},
"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": "browser",
"title": "Prometheus2.0 (v1.0.0 by FUSAKLA)",
"version": 1
}
...