Add dashboard to monitor Prometheus data
This is an adapted version of this dashboard:
https://grafana.com/grafana/dashboards/3681
Change-Id: I405f09f75698b940becd6994a7fc457853603756
diff --git a/dashboards/prometheus-overview.json b/dashboards/prometheus-overview.json
new file mode 100644
index 0000000..9f09754
--- /dev/null
+++ b/dashboards/prometheus-overview.json
@@ -0,0 +1,4669 @@
+{
+ "annotations": {
+ "list": [
+ {
+ "$$hashKey": "object:456",
+ "builtIn": 1,
+ "datasource": "-- Grafana --",
+ "enable": true,
+ "hide": true,
+ "iconColor": "rgba(0, 211, 255, 1)",
+ "name": "Annotations & Alerts",
+ "type": "dashboard"
+ }
+ ]
+ },
+ "description": "Dashboard providing insight to Prometheus monitoring system status and it's runtime info.",
+ "editable": true,
+ "gnetId": 3681,
+ "graphTooltip": 1,
+ "iteration": 1585226845807,
+ "links": [],
+ "panels": [
+ {
+ "content": "<img src=\"https://cdn.worldvectorlogo.com/logos/prometheus.svg\"/ height=\"140px\">",
+ "datasource": null,
+ "gridPos": {
+ "h": 5,
+ "w": 2,
+ "x": 0,
+ "y": 0
+ },
+ "height": "",
+ "id": 50,
+ "links": [],
+ "mode": "html",
+ "title": "",
+ "transparent": true,
+ "type": "text"
+ },
+ {
+ "cacheTimeout": null,
+ "columns": [],
+ "datasource": "Prometheus",
+ "fontSize": "100%",
+ "gridPos": {
+ "h": 5,
+ "w": 22,
+ "x": 2,
+ "y": 0
+ },
+ "id": 41,
+ "links": [],
+ "pageSize": null,
+ "scroll": true,
+ "showHeader": true,
+ "sort": {
+ "col": 3,
+ "desc": false
+ },
+ "styles": [
+ {
+ "$$hashKey": "object:832",
+ "alias": "",
+ "align": "auto",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "Time",
+ "thresholds": [],
+ "type": "hidden",
+ "unit": "short"
+ },
+ {
+ "$$hashKey": "object:833",
+ "alias": "Prometheus instance",
+ "align": "auto",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": true,
+ "linkTargetBlank": true,
+ "linkTooltip": "Link to the prometheus instance",
+ "linkUrl": "${__cell:raw}/graph",
+ "mappingType": 1,
+ "pattern": "instance",
+ "thresholds": [],
+ "type": "string",
+ "unit": "short"
+ },
+ {
+ "$$hashKey": "object:834",
+ "alias": "Uptime",
+ "align": "auto",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "Value #A",
+ "thresholds": [],
+ "type": "number",
+ "unit": "s"
+ },
+ {
+ "$$hashKey": "object:835",
+ "alias": "",
+ "align": "auto",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": false,
+ "mappingType": 1,
+ "pattern": "__name__",
+ "thresholds": [],
+ "type": "hidden",
+ "unit": "short"
+ },
+ {
+ "$$hashKey": "object:836",
+ "alias": "Build git branch",
+ "align": "auto",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": true,
+ "linkTargetBlank": true,
+ "linkTooltip": "Link to git branch of a build",
+ "linkUrl": "https://github.com/prometheus/prometheus/tree/${__cell}",
+ "mappingType": 1,
+ "pattern": "branch",
+ "thresholds": [],
+ "type": "string",
+ "unit": "short"
+ },
+ {
+ "$$hashKey": "object:837",
+ "alias": "",
+ "align": "auto",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "Value #B",
+ "thresholds": [],
+ "type": "hidden",
+ "unit": "short"
+ },
+ {
+ "$$hashKey": "object:838",
+ "alias": "Prometheus version",
+ "align": "auto",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": true,
+ "linkTargetBlank": true,
+ "linkTooltip": "Prometheus release page",
+ "linkUrl": "https://github.com/prometheus/prometheus/releases/tag/v${__cell}",
+ "mappingType": 1,
+ "pattern": "version",
+ "thresholds": [],
+ "type": "string",
+ "unit": "short"
+ },
+ {
+ "$$hashKey": "object:839",
+ "alias": "Go version",
+ "align": "auto",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": true,
+ "linkTargetBlank": true,
+ "linkTooltip": "Go release page",
+ "linkUrl": "https://github.com/golang/go/releases/tag/${__cell}",
+ "mappingType": 1,
+ "pattern": "goversion",
+ "thresholds": [],
+ "type": "string",
+ "unit": "short"
+ },
+ {
+ "$$hashKey": "object:840",
+ "alias": "Build git revision",
+ "align": "auto",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "link": true,
+ "linkTargetBlank": true,
+ "linkTooltip": "Link to git commit of a build",
+ "linkUrl": "https://github.com/prometheus/prometheus/commit/${__cell}",
+ "mappingType": 1,
+ "pattern": "revision",
+ "thresholds": [],
+ "type": "string",
+ "unit": "short"
+ },
+ {
+ "$$hashKey": "object:841",
+ "alias": "",
+ "align": "auto",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "job",
+ "thresholds": [],
+ "type": "hidden",
+ "unit": "short"
+ },
+ {
+ "$$hashKey": "object:842",
+ "alias": "",
+ "align": "auto",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 2,
+ "mappingType": 1,
+ "pattern": "",
+ "thresholds": [],
+ "type": "number",
+ "unit": "short"
+ },
+ {
+ "$$hashKey": "object:843",
+ "alias": "Last reload success",
+ "align": "auto",
+ "colorMode": "cell",
+ "colors": [
+ "#E02F44",
+ "#E02F44",
+ "rgba(50, 172, 45, 0)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 0,
+ "link": true,
+ "linkTargetBlank": true,
+ "linkTooltip": "Config page",
+ "linkUrl": "https://${__cell_1:raw}/config",
+ "mappingType": 1,
+ "pattern": "Value #C",
+ "thresholds": [
+ "0",
+ "1"
+ ],
+ "type": "number",
+ "unit": "none"
+ },
+ {
+ "$$hashKey": "object:844",
+ "alias": "Rules",
+ "align": "auto",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": 0,
+ "link": true,
+ "linkTargetBlank": true,
+ "linkTooltip": "Rules page",
+ "linkUrl": "https://${__cell_1:raw}/rules",
+ "mappingType": 1,
+ "pattern": "Value #D",
+ "thresholds": [],
+ "type": "number",
+ "unit": "short"
+ },
+ {
+ "$$hashKey": "object:845",
+ "alias": "Targets",
+ "align": "auto",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": null,
+ "link": true,
+ "linkTargetBlank": true,
+ "linkTooltip": "Targets page",
+ "linkUrl": "https://${__cell_1:raw}/rules",
+ "mappingType": 1,
+ "pattern": "Value #E",
+ "thresholds": [],
+ "type": "number",
+ "unit": "short"
+ },
+ {
+ "$$hashKey": "object:846",
+ "alias": "# series",
+ "align": "auto",
+ "colorMode": "cell",
+ "colors": [
+ "rgba(50, 172, 45, 0)",
+ "#FF780A",
+ "#C4162A"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": null,
+ "mappingType": 1,
+ "pattern": "Value #F",
+ "thresholds": [
+ "500000",
+ "1000000"
+ ],
+ "type": "number",
+ "unit": "short"
+ },
+ {
+ "$$hashKey": "object:847",
+ "alias": "Time Range",
+ "align": "auto",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": null,
+ "mappingType": 1,
+ "pattern": "Value #G",
+ "thresholds": [],
+ "type": "number",
+ "unit": "s"
+ },
+ {
+ "$$hashKey": "object:848",
+ "alias": "Data",
+ "align": "auto",
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "dateFormat": "YYYY-MM-DD HH:mm:ss",
+ "decimals": null,
+ "mappingType": 1,
+ "pattern": "Value #H",
+ "thresholds": [],
+ "type": "number",
+ "unit": "bytes"
+ }
+ ],
+ "targets": [
+ {
+ "expr": "max(time() - process_start_time_seconds{job=\"prometheus\"}) by (instance)",
+ "format": "table",
+ "instant": true,
+ "interval": "",
+ "legendFormat": "",
+ "refId": "A"
+ },
+ {
+ "expr": "max(prometheus_build_info{job=\"prometheus\"}) by (instance, branch, goversion, version, revision)",
+ "format": "table",
+ "instant": true,
+ "interval": "",
+ "legendFormat": "",
+ "refId": "B"
+ },
+ {
+ "expr": "max(prometheus_config_last_reload_successful{job=\"prometheus\"}) by (instance)",
+ "format": "table",
+ "instant": true,
+ "interval": "",
+ "legendFormat": "",
+ "refId": "C"
+ },
+ {
+ "expr": "max(sum(prometheus_rule_group_rules{job=\"prometheus\"}) by (instance) or prometheus_build_info{job=\"prometheus\"}*0) by (instance)",
+ "format": "table",
+ "instant": true,
+ "interval": "",
+ "legendFormat": "",
+ "refId": "D"
+ },
+ {
+ "expr": "max(sum(prometheus_sd_discovered_targets{job=\"prometheus\", name=\"scrape\"}) by (instance) or prometheus_build_info{job=\"prometheus\"}*0) by (instance)",
+ "format": "table",
+ "instant": true,
+ "interval": "",
+ "legendFormat": "",
+ "refId": "E"
+ },
+ {
+ "expr": "max(prometheus_tsdb_head_series{job=\"prometheus\"}) by (instance)",
+ "format": "table",
+ "instant": true,
+ "interval": "",
+ "legendFormat": "",
+ "refId": "F"
+ },
+ {
+ "expr": "time() - max(prometheus_tsdb_lowest_timestamp_seconds{job=\"prometheus\"}) by (instance)",
+ "format": "table",
+ "instant": true,
+ "interval": "",
+ "legendFormat": "",
+ "refId": "G"
+ },
+ {
+ "expr": "min(prometheus_tsdb_storage_blocks_bytes{job=\"prometheus\"}) by (instance)",
+ "format": "table",
+ "instant": true,
+ "interval": "",
+ "legendFormat": "",
+ "refId": "H"
+ }
+ ],
+ "title": "Build, uptime and runtime instance info",
+ "transform": "table",
+ "type": "table"
+ },
+ {
+ "collapsed": false,
+ "datasource": null,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 5
+ },
+ "id": 56,
+ "panels": [],
+ "repeat": null,
+ "title": "Main info",
+ "type": "row"
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "Prometheus",
+ "fill": 0,
+ "fillGradient": 1,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 0,
+ "y": 6
+ },
+ "hiddenSeries": false,
+ "id": 71,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "nullPointMode": "null",
+ "options": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 2,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "max(prometheus_tsdb_head_series{job=\"prometheus\"}) by (instance)",
+ "interval": "",
+ "legendFormat": "{{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": "$long_term_interval",
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Number of time series",
+ "tooltip": {
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ],
+ "yaxis": {
+ "align": false,
+ "alignLevel": null
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "Prometheus",
+ "description": "",
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "fillGradient": 0,
+ "grid": {},
+ "gridPos": {
+ "h": 7,
+ "w": 7,
+ "x": 8,
+ "y": 6
+ },
+ "hiddenSeries": false,
+ "id": 25,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "max": true,
+ "min": false,
+ "show": false,
+ "sort": "max",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 2,
+ "links": [],
+ "nullPointMode": "connected",
+ "options": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "prometheus_target_interval_length_seconds{job=\"prometheus\",quantile=\"$quantile\"}",
+ "interval": "",
+ "legendFormat": "job {{job}} should be {{interval}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "$quantile quantile of interval length between scrapes per job",
+ "tooltip": {
+ "msResolution": false,
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "decimals": null,
+ "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": true,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 6,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 9,
+ "x": 15,
+ "y": 6
+ },
+ "hiddenSeries": false,
+ "id": 13,
+ "legend": {
+ "alignAsTable": true,
+ "avg": true,
+ "current": true,
+ "hideEmpty": true,
+ "hideZero": true,
+ "max": true,
+ "min": false,
+ "rightSide": false,
+ "show": false,
+ "sort": "total",
+ "sortDesc": true,
+ "total": true,
+ "values": true
+ },
+ "lines": false,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "$$hashKey": "object:1744",
+ "alias": "/net_conntrack/"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(increase(label_replace({__name__=~\"(:?prometheus|net_conntrack)_.*(:?fail|duplicate|out_of|error|not_found|corrupt|dropped|missed|exceeded).*_total\", job=\"prometheus\"}, \"metric_name\", \"$1\", \"__name__\", \"(.*)\")[$aggregation_interval:20s])) by (instance,metric_name,alertmanager,name,mechanism,queue) > 0",
+ "interval": "",
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Prometheus errors in $aggregation_interval",
+ "tooltip": {
+ "msResolution": false,
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:1755",
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:1756",
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ],
+ "yaxis": {
+ "align": false,
+ "alignLevel": null
+ }
+ },
+ {
+ "collapsed": false,
+ "datasource": null,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 13
+ },
+ "id": 58,
+ "panels": [],
+ "repeat": null,
+ "title": "Requests & queries",
+ "type": "row"
+ },
+ {
+ "aliasColors": {
+ "Chunks": "#1F78C1",
+ "Chunks to persist": "#508642",
+ "Max chunks": "#052B51",
+ "Max to persist": "#3F6833"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 0,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 0,
+ "y": 14
+ },
+ "hiddenSeries": false,
+ "id": 18,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "hideEmpty": true,
+ "hideZero": true,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "connected",
+ "options": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(increase(prometheus_http_requests_total{job=\"prometheus\"}[$aggregation_interval])) by (instance, handler)",
+ "interval": "",
+ "legendFormat": "{{ handler }} handler on {{ instance }}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "HTTP request count by handler in $aggregation_interval",
+ "tooltip": {
+ "msResolution": false,
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:1899",
+ "format": "none",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:1900",
+ "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": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 8,
+ "y": 14
+ },
+ "hiddenSeries": false,
+ "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": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "histogram_quantile($quantile, sum(increase(prometheus_http_request_duration_seconds_bucket{job=\"prometheus\"}[$aggregation_interval])) by (le,instance, handler))",
+ "interval": "",
+ "legendFormat": "{{ handler }} handler on {{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "$quantile quantile of HTTP 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": "s",
+ "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": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 16,
+ "y": 14
+ },
+ "hiddenSeries": false,
+ "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": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "histogram_quantile($quantile, sum(increase(prometheus_http_response_size_bytes_bucket{job=\"prometheus\"}[$aggregation_interval])) by (le,instance, handler)) > 0",
+ "interval": "",
+ "legendFormat": "{{ handler }} handler on {{ instance }}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "$quantile quantile of 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
+ }
+ },
+ {
+ "collapsed": false,
+ "datasource": null,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 21
+ },
+ "id": 64,
+ "panels": [],
+ "repeat": null,
+ "title": "Resources",
+ "type": "row"
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "Prometheus",
+ "decimals": 2,
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 0,
+ "y": 22
+ },
+ "hiddenSeries": false,
+ "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": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(rate(process_cpu_seconds_total{job=\"prometheus\"}[$aggregation_interval])) by (instance)",
+ "interval": "",
+ "legendFormat": "CPU usage of {{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "CPU usage",
+ "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
+ }
+ ],
+ "yaxis": {
+ "align": false,
+ "alignLevel": null
+ }
+ },
+ {
+ "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": "Prometheus",
+ "decimals": null,
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 8,
+ "y": 22
+ },
+ "hiddenSeries": false,
+ "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": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "//",
+ "fill": 0
+ },
+ {
+ "alias": "collector heap size",
+ "color": "#E0752D",
+ "linewidth": 2
+ },
+ {
+ "alias": "collector kubernetes memory limit",
+ "color": "#BF1B00",
+ "linewidth": 3
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(process_resident_memory_bytes{job=\"prometheus\"}) by (instance)",
+ "interval": "",
+ "legendFormat": "Resident memory of {{instance}}",
+ "refId": "A"
+ },
+ {
+ "expr": "sum(go_memstats_alloc_bytes{job=\"prometheus\"}) by (instance)",
+ "interval": "",
+ "legendFormat": "Total allocated bytes of {{instance}}",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Memory usage",
+ "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 to persist": "#3F6833",
+ "RSS": "#890F02"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 16,
+ "y": 22
+ },
+ "hiddenSeries": false,
+ "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": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "rate(go_memstats_alloc_bytes_total{job=\"prometheus\"}[$aggregation_interval])",
+ "interval": "",
+ "legendFormat": "Allocated Bytes of {{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Allocations per second in $aggregation_interval",
+ "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
+ }
+ },
+ {
+ "collapsed": false,
+ "datasource": null,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 29
+ },
+ "id": 61,
+ "panels": [],
+ "repeat": null,
+ "title": "TSDB stats",
+ "type": "row"
+ },
+ {
+ "aliasColors": {
+ "Chunks": "#1F78C1",
+ "Chunks to persist": "#508642",
+ "Max chunks": "#052B51",
+ "Max to persist": "#3F6833"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 0,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 12,
+ "x": 0,
+ "y": 30
+ },
+ "hiddenSeries": false,
+ "id": 89,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "time() - min(prometheus_tsdb_lowest_timestamp_seconds{job=\"prometheus\"}) by (instance)",
+ "interval": "",
+ "legendFormat": "Oldest data for {{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": "$long_term_interval",
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Oldest data",
+ "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": 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": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 0,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 12,
+ "x": 12,
+ "y": 30
+ },
+ "hiddenSeries": false,
+ "id": 88,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "max(prometheus_tsdb_storage_blocks_bytes{job=\"prometheus\"}) by (instance)",
+ "interval": "",
+ "legendFormat": "",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": "$long_term_interval",
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Size of the storage",
+ "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
+ }
+ },
+ {
+ "collapsed": false,
+ "datasource": null,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 37
+ },
+ "id": 75,
+ "panels": [],
+ "title": "Query engine & API",
+ "type": "row"
+ },
+ {
+ "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": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 0,
+ "y": 38
+ },
+ "hiddenSeries": false,
+ "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": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "$$hashKey": "object:2178",
+ "alias": "/Limit/",
+ "color": "#E02F44",
+ "dashLength": 3,
+ "dashes": true,
+ "fill": 0,
+ "nullPointMode": "connected"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(prometheus_engine_queries{job=\"prometheus\"}) by (instance)",
+ "instant": false,
+ "interval": "",
+ "legendFormat": "{{instance}}",
+ "refId": "A"
+ },
+ {
+ "expr": "sum(prometheus_engine_queries_concurrent_max{job=\"prometheus\"}) by (instance)",
+ "interval": "",
+ "legendFormat": "{{instance}} Limit",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Number of concurent queries and it's limit",
+ "tooltip": {
+ "msResolution": false,
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:2199",
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:2200",
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ],
+ "yaxis": {
+ "align": false,
+ "alignLevel": null
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 8,
+ "y": 38
+ },
+ "hiddenSeries": false,
+ "id": 15,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "prometheus_engine_query_duration_seconds{job=\"prometheus\", quantile=\"$quantile\"}",
+ "interval": "",
+ "legendFormat": "{{slice}} slice on {{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "$quantile quantile of query engine evaluation duration per slice",
+ "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": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 16,
+ "y": 38
+ },
+ "hiddenSeries": false,
+ "id": 95,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(prometheus_api_remote_read_queries{job=\"prometheus\"}) by (instance)",
+ "interval": "",
+ "legendFormat": "{{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Number of queries on remote read API",
+ "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
+ }
+ ],
+ "yaxis": {
+ "align": false,
+ "alignLevel": null
+ }
+ },
+ {
+ "collapsed": false,
+ "datasource": null,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 45
+ },
+ "id": 57,
+ "panels": [],
+ "repeat": null,
+ "title": "Rule evaluation",
+ "type": "row"
+ },
+ {
+ "aliasColors": {
+ "Chunks": "#1F78C1",
+ "Chunks to persist": "#508642",
+ "Max chunks": "#052B51",
+ "Max to persist": "#3F6833"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 0,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 9,
+ "x": 0,
+ "y": 46
+ },
+ "hiddenSeries": false,
+ "id": 77,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/LIMIT/",
+ "color": "#E02F44",
+ "dashLength": 3,
+ "dashes": true,
+ "fill": 0
+ },
+ {
+ "alias": "slow",
+ "color": "#C4162A",
+ "fill": 8
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "topk(20,max(prometheus_rule_group_last_duration_seconds{job=\"prometheus\"}) by (rule_group, instance) / min(prometheus_rule_group_interval_seconds{job=\"prometheus\"}) by (rule_group, instance))",
+ "interval": "",
+ "legendFormat": "Percentage of {{rule_group}} group evaluation interval on {{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Percentage rule group evaluation duration from the rule group evaluation interval (top 20)",
+ "tooltip": {
+ "msResolution": false,
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "percentunit",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": "0",
+ "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": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 9,
+ "y": 46
+ },
+ "hiddenSeries": false,
+ "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": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "Queue length",
+ "yaxis": 2
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(prometheus_rule_evaluation_duration_seconds{job=\"prometheus\", quantile=\"$quantile\"}) by (instance, quantile)",
+ "interval": "",
+ "legendFormat": "evaluation duration of {{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "$quantile quantile of rule evaulation duration",
+ "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": 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
+ }
+ },
+ {
+ "aliasColors": {
+ "Chunks": "#1F78C1",
+ "Chunks to persist": "#508642",
+ "Max chunks": "#052B51",
+ "Max to persist": "#3F6833"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 3,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 7,
+ "x": 17,
+ "y": 46
+ },
+ "hiddenSeries": false,
+ "id": 76,
+ "interval": "",
+ "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": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "Queue length",
+ "yaxis": 2
+ }
+ ],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(topk(20,prometheus_rule_group_rules{job=\"prometheus\"})) by (instance, rule_group)",
+ "interval": "",
+ "legendFormat": "number of rules in {{rule_group}} rule group on {{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Number of rules per group (top 20 groups)",
+ "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": "0",
+ "show": true
+ }
+ ],
+ "yaxis": {
+ "align": false,
+ "alignLevel": null
+ }
+ },
+ {
+ "collapsed": false,
+ "datasource": null,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 53
+ },
+ "id": 59,
+ "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": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 0,
+ "y": 54
+ },
+ "hiddenSeries": false,
+ "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": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/capacity/",
+ "color": "#E02F44",
+ "dashLength": 3,
+ "dashes": true,
+ "fill": 0,
+ "nullPointMode": "connected"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(prometheus_notifications_queue_length{job=\"prometheus\"})by (instance)",
+ "interval": "",
+ "legendFormat": "Queue size of {{instance}}",
+ "refId": "A"
+ },
+ {
+ "expr": "sum(prometheus_notifications_queue_capacity{job=\"prometheus\"})by (instance)",
+ "interval": "",
+ "legendFormat": "Queue capacity of {{instance}}",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Notification queue size and capacity",
+ "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
+ }
+ },
+ {
+ "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": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 8,
+ "y": 54
+ },
+ "hiddenSeries": false,
+ "id": 78,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(increase(prometheus_notifications_sent_total{job=\"prometheus\"}[$aggregation_interval])) by (instance, alertmanager)",
+ "interval": "",
+ "legendFormat": "Sent notifications to {{alertmanager}} alertmanager from {{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Number of sent notifictions per alertmanager in $aggregation_interval",
+ "tooltip": {
+ "msResolution": false,
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": "0",
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ],
+ "yaxis": {
+ "align": false,
+ "alignLevel": null
+ }
+ },
+ {
+ "aliasColors": {
+ "Alert queue capacity on o collector": "#bf1b00",
+ "Alert queue capacity on o harvester": "#bf1b00",
+ "Chunks": "#1F78C1",
+ "Chunks to persist": "#508642",
+ "Max chunks": "#052B51",
+ "Max to persist": "#3F6833"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 16,
+ "y": 54
+ },
+ "hiddenSeries": false,
+ "id": 79,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "hideEmpty": true,
+ "hideZero": true,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "avg(prometheus_notifications_latency_seconds{job=\"prometheus\", quantile=\"$quantile\"}) by (instance, alertmanager)",
+ "interval": "",
+ "legendFormat": "Latency of notifications sent to {{alertmanager}} from {{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "$quantile of notification latency per alertmanager",
+ "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": 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,
+ "datasource": null,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 61
+ },
+ "id": 60,
+ "panels": [],
+ "repeat": null,
+ "title": "Service discovery",
+ "type": "row"
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "Prometheus",
+ "decimals": 0,
+ "fill": 5,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 0,
+ "y": 62
+ },
+ "hiddenSeries": false,
+ "id": 69,
+ "legend": {
+ "alignAsTable": true,
+ "avg": false,
+ "current": true,
+ "hideEmpty": true,
+ "hideZero": true,
+ "max": false,
+ "min": false,
+ "rightSide": true,
+ "show": false,
+ "sort": "current",
+ "sortDesc": true,
+ "total": false,
+ "values": true
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(prometheus_sd_discovered_targets{job=\"prometheus\", name=\"scrape\"}) by (instance, config,name)",
+ "interval": "",
+ "intervalFactor": 5,
+ "legendFormat": "Number of {{name}} type targets from config {{config}} on {{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Number of discovered targets per Type and config",
+ "tooltip": {
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:2495",
+ "decimals": 0,
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:2496",
+ "decimals": 0,
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ],
+ "yaxis": {
+ "align": false,
+ "alignLevel": null
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "Prometheus",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 8,
+ "y": 62
+ },
+ "hiddenSeries": false,
+ "id": 45,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(increase(prometheus_sd_refresh_duration_seconds_count{job=\"prometheus\"}[$aggregation_interval])) by (instance, mechanism)",
+ "interval": "",
+ "legendFormat": "Number of sync for {{mechanism}} SD mechanism on {{instance}}",
+ "refId": "A"
+ },
+ {
+ "expr": "sum(increase(prometheus_sd_consul_rpc_duration_seconds_count{job=\"prometheus\"}[$aggregation_interval])) by (instance)",
+ "interval": "",
+ "legendFormat": "Number of sync for consul SD mechanism on {{instance}}",
+ "refId": "B"
+ },
+ {
+ "expr": "sum(increase(prometheus_sd_kubernetes_http_request_duration_seconds_count{job=\"prometheus\"}[$aggregation_interval])) by (instance)",
+ "interval": "",
+ "legendFormat": "Number of sync for kubernetes SD mechanism on {{instance}}",
+ "refId": "C"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Service discovery sync count by mechanism in $aggregation_interval",
+ "tooltip": {
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ],
+ "yaxis": {
+ "align": false,
+ "alignLevel": null
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "Prometheus",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 16,
+ "y": 62
+ },
+ "hiddenSeries": false,
+ "id": 43,
+ "legend": {
+ "alignAsTable": true,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": true,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "prometheus_sd_refresh_duration_seconds{job=\"prometheus\", quantile=\"$quantile\"}",
+ "interval": "",
+ "legendFormat": "Duration of sync for {{mechanism}} SD mechanism on {{instance}}",
+ "refId": "A"
+ },
+ {
+ "expr": "consul_rpc_duration_seconds{job=\"prometheus\", quantile=\"$quantile\"}",
+ "interval": "",
+ "legendFormat": "Number of sync for consul SD mechanism on {{instance}}",
+ "refId": "B"
+ },
+ {
+ "expr": "prometheus_sd_file_scan_duration_seconds{job=\"prometheus\", quantile=\"$quantile\"}",
+ "interval": "",
+ "legendFormat": "Duration of sync for file_scan SD mechanism on {{instance}}",
+ "refId": "C"
+ },
+ {
+ "expr": "prometheus_sd_kubernetes_http_request_duration_seconds_sum{job=\"prometheus\"} / prometheus_sd_kubernetes_http_request_duration_seconds_count{job=\"prometheus\"}",
+ "interval": "",
+ "legendFormat": "AVG Duration of sync for k8s SD mechanism on {{instance}}",
+ "refId": "D"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "$quantile quantile of refresh duration per SD mechanism",
+ "tooltip": {
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "s",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ],
+ "yaxis": {
+ "align": false,
+ "alignLevel": null
+ }
+ },
+ {
+ "collapsed": false,
+ "datasource": null,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 69
+ },
+ "id": 73,
+ "panels": [],
+ "title": "Compaction and retention",
+ "type": "row"
+ },
+ {
+ "aliasColors": {},
+ "bars": true,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "Prometheus",
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 0,
+ "y": 70
+ },
+ "hiddenSeries": false,
+ "id": 80,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": false,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 1,
+ "points": true,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "histogram_quantile($quantile, sum(rate(prometheus_tsdb_compaction_duration_seconds_bucket{job=\"prometheus\"}[$aggregation_interval])) by (instance, le))",
+ "interval": "",
+ "legendFormat": "Compaction duration on {{ instance }}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "$quantile quantile of compaction duration",
+ "tooltip": {
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "decimals": null,
+ "format": "s",
+ "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": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "Prometheus",
+ "fill": 3,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 8,
+ "y": 70
+ },
+ "hiddenSeries": false,
+ "id": 81,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": true,
+ "targets": [
+ {
+ "expr": "sum(increase(prometheus_tsdb_compactions_total{job=\"prometheus\"}[$aggregation_interval])) by (instance) > 0",
+ "interval": "",
+ "legendFormat": "Count of horizontal compactions on {{instance}}",
+ "refId": "A"
+ },
+ {
+ "expr": "sum(increase(prometheus_tsdb_vertical_compactions_total{job=\"prometheus\"}[$aggregation_interval])) by (instance) > 0",
+ "interval": "",
+ "legendFormat": "Count of vertical compactions on {{instance}}",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Number of vertical/horizontal compactions in last $aggregation_interval",
+ "tooltip": {
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "decimals": null,
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ],
+ "yaxis": {
+ "align": false,
+ "alignLevel": null
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "Prometheus",
+ "fill": 3,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 16,
+ "y": 70
+ },
+ "hiddenSeries": false,
+ "id": 82,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": true,
+ "targets": [
+ {
+ "expr": "sum(increase(prometheus_tsdb_size_retentions_total{job=\"prometheus\"}[$aggregation_interval])) by (instance) > 0",
+ "interval": "",
+ "legendFormat": "Number of size retention cutoffs on {{ instance }}",
+ "refId": "A"
+ },
+ {
+ "expr": "sum(increase(prometheus_tsdb_time_retentions_total{job=\"prometheus\"}[$aggregation_interval])) by (instance) > 0",
+ "interval": "",
+ "legendFormat": "Number of time retention cutoffs on {{ instance }}",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Number of time/size retention cutoffs in $aggregation_interval",
+ "tooltip": {
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "decimals": null,
+ "format": "s",
+ "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
+ }
+ },
+ {
+ "collapsed": false,
+ "datasource": null,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 77
+ },
+ "id": 62,
+ "panels": [],
+ "repeat": null,
+ "title": "Head block",
+ "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": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 0,
+ "y": 78
+ },
+ "hiddenSeries": false,
+ "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": {
+ "dataLinks": []
+ },
+ "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{job=\"prometheus\"}) by (instance)",
+ "interval": "",
+ "legendFormat": "Head block chunk count on {{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "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
+ }
+ ],
+ "yaxis": {
+ "align": false,
+ "alignLevel": null
+ }
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 8,
+ "y": 78
+ },
+ "hiddenSeries": false,
+ "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": {
+ "dataLinks": []
+ },
+ "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{job=\"prometheus\"}[$aggregation_interval])) by (instance)",
+ "interval": "",
+ "legendFormat": "Appended samples/s on {{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Samples Appended per second in $aggregation_interval",
+ "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
+ }
+ ],
+ "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": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 0,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 16,
+ "y": 78
+ },
+ "hiddenSeries": false,
+ "id": 3,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "prometheus_tsdb_head_series{job=\"prometheus\"}",
+ "interval": "",
+ "legendFormat": "Time series count of {{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Time series total count",
+ "tooltip": {
+ "msResolution": false,
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:262",
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": "0",
+ "show": true
+ },
+ {
+ "$$hashKey": "object:263",
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ],
+ "yaxis": {
+ "align": false,
+ "alignLevel": null
+ }
+ },
+ {
+ "collapsed": false,
+ "datasource": null,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 85
+ },
+ "id": 84,
+ "panels": [],
+ "title": "WAL",
+ "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": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 0,
+ "y": 86
+ },
+ "hiddenSeries": false,
+ "id": 85,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(prometheus_tsdb_wal_fsync_duration_seconds{job=\"prometheus\",quantile=\"$quantile\"}) by (instance)",
+ "interval": "",
+ "legendFormat": "Duration of WAL fsync on {{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "$quantile quantile of WAL fsync duration",
+ "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": 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",
+ "To persist": "#9AC48A"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 0,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 8,
+ "y": 86
+ },
+ "hiddenSeries": false,
+ "id": 86,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(increase(prometheus_tsdb_wal_completed_pages_total{job=\"prometheus\"}[$aggregation_interval])) by (instance)",
+ "interval": "",
+ "legendFormat": "Completed WAL pages count of {{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Number of completed pages in $aggregation_interval",
+ "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
+ }
+ },
+ {
+ "aliasColors": {
+ "Chunks": "#1F78C1",
+ "Chunks to persist": "#508642",
+ "Max chunks": "#052B51",
+ "Max to persist": "#3F6833",
+ "To persist": "#9AC48A"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 16,
+ "y": 86
+ },
+ "hiddenSeries": false,
+ "id": 87,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(prometheus_tsdb_wal_truncate_duration_seconds_sum{job=\"prometheus\"} /prometheus_tsdb_wal_truncate_duration_seconds_count{job=\"prometheus\"}) by (instance)",
+ "interval": "",
+ "legendFormat": "Duration of WAL truncation on {{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Average duration of WAL truncation",
+ "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": 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,
+ "datasource": null,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 93
+ },
+ "id": 99,
+ "panels": [],
+ "title": "Go 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": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 0,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 0,
+ "y": 94
+ },
+ "hiddenSeries": false,
+ "id": 100,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(go_goroutines{job=\"prometheus\"}) by (instance)",
+ "interval": "",
+ "legendFormat": "Gorutines count of {{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Number of gorutines",
+ "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
+ }
+ },
+ {
+ "aliasColors": {
+ "Chunks": "#1F78C1",
+ "Chunks to persist": "#508642",
+ "Max chunks": "#052B51",
+ "Max to persist": "#3F6833",
+ "To persist": "#9AC48A"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 0,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 8,
+ "y": 94
+ },
+ "hiddenSeries": false,
+ "id": 101,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "max(go_gc_duration_seconds{job=\"prometheus\"}) by (instance)",
+ "interval": "",
+ "legendFormat": "GC duration on {{instance}}",
+ "refId": "A"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Duration of Go garbage collection",
+ "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": 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",
+ "To persist": "#9AC48A"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 5,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 8,
+ "x": 16,
+ "y": 94
+ },
+ "hiddenSeries": false,
+ "id": 102,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "max(go_memstats_mspan_sys_bytes{job=\"prometheus\"}) by (instance)",
+ "interval": "",
+ "legendFormat": "mspan {{instance}}",
+ "refId": "A"
+ },
+ {
+ "expr": "max(go_memstats_mcache_sys_bytes{job=\"prometheus\"}) by (instance)",
+ "interval": "",
+ "legendFormat": "mcache {{instance}}",
+ "refId": "B"
+ },
+ {
+ "expr": "max(go_memstats_buck_hash_sys_bytes{job=\"prometheus\"}) by (instance)",
+ "interval": "",
+ "legendFormat": "buck_hash {{instance}}",
+ "refId": "C"
+ },
+ {
+ "expr": "max(go_memstats_gc_sys_bytes{job=\"prometheus\"}) by (instance)",
+ "interval": "",
+ "legendFormat": "gc {{instance}}",
+ "refId": "D"
+ },
+ {
+ "expr": "max(go_memstats_other_sys_bytes{job=\"prometheus\"}) by (instance)",
+ "interval": "",
+ "legendFormat": "other {{instance}}",
+ "refId": "E"
+ },
+ {
+ "expr": "max(go_memstats_stack_sys_bytes{job=\"prometheus\"}) by (instance)",
+ "format": "time_series",
+ "hide": false,
+ "intervalFactor": 1,
+ "legendFormat": "stack {{instance}}",
+ "metric": "prometheus_local_storage_memory_chunks",
+ "refId": "F"
+ },
+ {
+ "expr": "max(go_memstats_heap_sys_bytes{job=\"prometheus\"}) by (instance)",
+ "interval": "",
+ "legendFormat": "heap {{instance}}",
+ "refId": "G"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Go system memory allocations",
+ "tooltip": {
+ "msResolution": false,
+ "shared": true,
+ "sort": 2,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "$$hashKey": "object:2633",
+ "format": "bytes",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "$$hashKey": "object:2634",
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ],
+ "yaxis": {
+ "align": false,
+ "alignLevel": null
+ }
+ },
+ {
+ "collapsed": false,
+ "datasource": null,
+ "gridPos": {
+ "h": 1,
+ "w": 24,
+ "x": 0,
+ "y": 101
+ },
+ "id": 68,
+ "panels": [],
+ "repeat": null,
+ "title": "Network",
+ "type": "row"
+ },
+ {
+ "aliasColors": {
+ "Chunks": "#1F78C1",
+ "Chunks to persist": "#508642",
+ "Max chunks": "#052B51",
+ "Max to persist": "#3F6833"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 12,
+ "x": 0,
+ "y": 102
+ },
+ "hiddenSeries": false,
+ "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": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/closed/",
+ "transform": "negative-Y"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(increase(net_conntrack_listener_conn_accepted_total{job=\"prometheus\"}[$aggregation_interval])) by (instance, listener_name) > 0",
+ "interval": "",
+ "legendFormat": "{{listener_name}} accepted connections on {{instance}}",
+ "refId": "A"
+ },
+ {
+ "expr": "sum(increase(net_conntrack_listener_conn_closed_total{job=\"prometheus\"}[$aggregation_interval])) by (instance, listener_name) > 0",
+ "interval": "",
+ "legendFormat": "{{listener_name}} closed connections on {{instance}}",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Accepted/closed inbound connections per listener",
+ "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": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "fillGradient": 0,
+ "gridPos": {
+ "h": 7,
+ "w": 12,
+ "x": 12,
+ "y": 102
+ },
+ "hiddenSeries": false,
+ "id": 90,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null",
+ "options": {
+ "dataLinks": []
+ },
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "/closed/",
+ "stack": "B",
+ "transform": "negative-Y"
+ },
+ {
+ "alias": "/established/",
+ "stack": "A"
+ }
+ ],
+ "spaceLength": 10,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(increase(net_conntrack_dialer_conn_established_total{job=\"prometheus\"}[$aggregation_interval])) by (instance, dialer_name) > 0",
+ "interval": "",
+ "legendFormat": "{{dialer_name}} established connections on {{instance}}",
+ "refId": "A"
+ },
+ {
+ "expr": "sum(increase(net_conntrack_dialer_conn_closed_total{job=\"prometheus\"}[$aggregation_interval])) by (instance, dialer_name) > 0",
+ "interval": "",
+ "legendFormat": "{{dialer_name}} closed connections on {{instance}}",
+ "refId": "B"
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeRegions": [],
+ "timeShift": null,
+ "title": "Established/closed outbound connections per dialer ",
+ "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
+ }
+ }
+ ],
+ "refresh": "1m",
+ "schemaVersion": 22,
+ "style": "dark",
+ "tags": [
+ "prometheus",
+ "monitoring"
+ ],
+ "templating": {
+ "list": [
+ {
+ "auto": true,
+ "auto_count": 300,
+ "auto_min": "1m",
+ "current": {
+ "selected": false,
+ "text": "1d",
+ "value": "1d"
+ },
+ "hide": 0,
+ "label": "Aggregation intarval",
+ "name": "aggregation_interval",
+ "options": [
+ {
+ "selected": false,
+ "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": true,
+ "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": {
+ "text": "0.99",
+ "value": "0.99"
+ },
+ "datasource": "Prometheus",
+ "definition": "query_result({__name__=~\"prometheus_.*_seconds\"})",
+ "hide": 0,
+ "includeAll": false,
+ "index": -1,
+ "label": "Quantile",
+ "multi": false,
+ "name": "quantile",
+ "options": [],
+ "query": "query_result({__name__=~\"prometheus_.*_seconds\"})",
+ "refresh": 2,
+ "regex": "/quantile=\"([^\"]+)\"/",
+ "skipUrlSync": false,
+ "sort": 1,
+ "tagValuesQuery": "",
+ "tags": [],
+ "tagsQuery": "",
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "auto": false,
+ "auto_count": 30,
+ "auto_min": "10s",
+ "current": {
+ "selected": false,
+ "text": "3d",
+ "value": "3d"
+ },
+ "hide": 0,
+ "label": null,
+ "name": "long_term_interval",
+ "options": [
+ {
+ "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": true,
+ "text": "3d",
+ "value": "3d"
+ },
+ {
+ "selected": false,
+ "text": "1w",
+ "value": "1w"
+ },
+ {
+ "selected": false,
+ "text": "4w",
+ "value": "4w"
+ },
+ {
+ "selected": false,
+ "text": "12w",
+ "value": "12w"
+ },
+ {
+ "selected": false,
+ "text": "1y",
+ "value": "1y"
+ }
+ ],
+ "query": "10m,30m,1h,6h,12h,1d,3d,1w,4w,12w,1y",
+ "refresh": 2,
+ "skipUrlSync": false,
+ "type": "interval"
+ }
+ ]
+ },
+ "time": {
+ "from": "now-7d",
+ "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": "Prometheus",
+ "uid": "iLC3yp9Zz",
+ "variables": {
+ "list": []
+ },
+ "version": 3
+}