Update the service tasks Grafana dashboard (#7038)

This commit is contained in:
Pierre Krieger
2020-09-08 11:59:37 +02:00
committed by GitHub
parent 03720ec08a
commit 7c7ad18d4e
@@ -44,14 +44,14 @@
{
"datasource": "$data_source",
"enable": true,
"expr": "increase(${metric_namespace}_tasks_ended_total{reason=\"panic\", instance=~\"${nodename}\"}[5m])",
"expr": "increase(${metric_namespace}_tasks_ended_total{reason=\"panic\", instance=~\"${nodename}\"}[10m])",
"hide": true,
"iconColor": "rgba(255, 96, 96, 1)",
"limit": 100,
"name": "Task panics",
"rawQuery": "SELECT\n extract(epoch from time_column) AS time,\n text_column as text,\n tags_column as tags\nFROM\n metric_table\nWHERE\n $__timeFilter(time_column)\n",
"showIn": 0,
"step": "",
"step": "10m",
"tags": [],
"textFormat": "{{instance}} - {{task_name}}",
"titleFormat": "Panic!",
@@ -60,12 +60,12 @@
{
"datasource": "$data_source",
"enable": true,
"expr": "changes(${metric_namespace}_process_start_time_seconds{instance=~\"${nodename}\"}[5m])",
"expr": "changes(${metric_namespace}_process_start_time_seconds{instance=~\"${nodename}\"}[10m])",
"hide": false,
"iconColor": "#8AB8FF",
"name": "Node reboots",
"showIn": 0,
"step": "",
"step": "10m",
"textFormat": "{{instance}}",
"titleFormat": "Reboots"
}
@@ -75,7 +75,7 @@
"gnetId": null,
"graphTooltip": 0,
"id": null,
"iteration": 1594822742772,
"iteration": 1599471940817,
"links": [],
"panels": [
{
@@ -87,220 +87,6 @@
"x": 0,
"y": 0
},
"id": 25,
"panels": [],
"title": "CPU & Memory",
"type": "row"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$data_source",
"fill": 0,
"fillGradient": 0,
"gridPos": {
"h": 6,
"w": 24,
"x": 0,
"y": 1
},
"hiddenSeries": false,
"id": 9,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [
{
"alias": "stddev-above",
"fillBelowTo": "stddev-below",
"hideTooltip": true,
"lines": false
},
{
"alias": "stddev-below",
"hideTooltip": true,
"lines": false
}
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "avg(${metric_namespace}_cpu_usage_percentage{instance=~\"${nodename}\"})",
"interval": "",
"legendFormat": "cpu-usage",
"refId": "A"
},
{
"expr": "avg(${metric_namespace}_cpu_usage_percentage{instance=~\"${nodename}\"}) - stddev(${metric_namespace}_cpu_usage_percentage{instance=~\"${nodename}\"})",
"interval": "",
"legendFormat": "stddev-below",
"refId": "B"
},
{
"expr": "avg(${metric_namespace}_cpu_usage_percentage{instance=~\"${nodename}\"}) + stddev(${metric_namespace}_cpu_usage_percentage{instance=~\"${nodename}\"})",
"interval": "",
"legendFormat": "stddev-above",
"refId": "C"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Average CPU usage and standard deviation",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "percent",
"label": null,
"logBase": 1,
"max": null,
"min": "0",
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$data_source",
"fill": 0,
"fillGradient": 0,
"gridPos": {
"h": 6,
"w": 24,
"x": 0,
"y": 7
},
"hiddenSeries": false,
"id": 20,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "${metric_namespace}_memory_usage_bytes{instance=~\"${nodename}\"}",
"interval": "",
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Memory usage",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "decbytes",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"collapsed": false,
"datasource": null,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 13
},
"id": 29,
"panels": [],
"title": "Tasks",
@@ -318,19 +104,23 @@
"h": 6,
"w": 24,
"x": 0,
"y": 14
"y": 1
},
"hiddenSeries": false,
"id": 11,
"interval": "1m",
"legend": {
"avg": false,
"alignAsTable": true,
"avg": true,
"current": false,
"hideEmpty": false,
"hideZero": false,
"max": false,
"min": false,
"show": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
"values": true
},
"lines": true,
"linewidth": 2,
@@ -348,7 +138,7 @@
"steppedLine": true,
"targets": [
{
"expr": "avg(increase(${metric_namespace}_tasks_polling_duration_sum{instance=~\"${nodename}\"}[$__interval])) by (task_name) * 1000 / $__interval_ms",
"expr": "avg(irate(${metric_namespace}_tasks_polling_duration_sum{instance=~\"${nodename}\"}[10m])) by (task_name)",
"interval": "",
"legendFormat": "{{task_name}}",
"refId": "A"
@@ -407,7 +197,7 @@
"h": 6,
"w": 24,
"x": 0,
"y": 20
"y": 7
},
"hiddenSeries": false,
"id": 30,
@@ -416,6 +206,8 @@
"alignAsTable": true,
"avg": true,
"current": false,
"hideEmpty": false,
"hideZero": false,
"max": false,
"min": false,
"rightSide": true,
@@ -439,7 +231,7 @@
"steppedLine": true,
"targets": [
{
"expr": "avg(rate(${metric_namespace}_tasks_polling_duration_count{instance=~\"${nodename}\"}[5m])) by (task_name)",
"expr": "avg(irate(${metric_namespace}_tasks_polling_duration_count{instance=~\"${nodename}\"}[10m])) by (task_name)",
"interval": "",
"legendFormat": "{{task_name}}",
"refId": "A"
@@ -498,7 +290,7 @@
"h": 6,
"w": 24,
"x": 0,
"y": 26
"y": 13
},
"hiddenSeries": false,
"id": 31,
@@ -530,7 +322,7 @@
"steppedLine": true,
"targets": [
{
"expr": "max(rate(${metric_namespace}_tasks_polling_duration_count{instance=~\"${nodename}\"}[5m])) by (task_name)",
"expr": "max(irate(${metric_namespace}_tasks_polling_duration_count{instance=~\"${nodename}\"}[10m])) by (task_name)",
"interval": "",
"legendFormat": "{{task_name}}",
"refId": "A"
@@ -589,21 +381,21 @@
"h": 6,
"w": 24,
"x": 0,
"y": 32
"y": 19
},
"hiddenSeries": false,
"id": 15,
"interval": "",
"legend": {
"alignAsTable": false,
"avg": false,
"alignAsTable": true,
"avg": true,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
"values": true
},
"lines": true,
"linewidth": 1,
@@ -621,7 +413,7 @@
"steppedLine": true,
"targets": [
{
"expr": "avg by(task_name) (irate(${metric_namespace}_tasks_spawned_total{instance=~\"${nodename}\"}[5m]))",
"expr": "avg by(task_name) (irate(${metric_namespace}_tasks_spawned_total{instance=~\"${nodename}\"}[10m]))",
"interval": "",
"legendFormat": "{{task_name}}",
"refId": "A"
@@ -680,21 +472,21 @@
"h": 6,
"w": 24,
"x": 0,
"y": 38
"y": 25
},
"hiddenSeries": false,
"id": 16,
"interval": "",
"legend": {
"alignAsTable": false,
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"max": true,
"min": false,
"rightSide": false,
"show": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
"values": true
},
"lines": true,
"linewidth": 1,
@@ -712,7 +504,7 @@
"steppedLine": true,
"targets": [
{
"expr": "max by(task_name) (irate(${metric_namespace}_tasks_spawned_total{instance=~\"${nodename}\"}[5m]))",
"expr": "max by(task_name) (irate(${metric_namespace}_tasks_spawned_total{instance=~\"${nodename}\"}[10m]))",
"interval": "",
"legendFormat": "{{task_name}}",
"refId": "A"
@@ -771,21 +563,21 @@
"h": 6,
"w": 24,
"x": 0,
"y": 44
"y": 31
},
"hiddenSeries": false,
"id": 2,
"interval": "",
"legend": {
"alignAsTable": false,
"avg": false,
"alignAsTable": true,
"avg": true,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
"values": true
},
"lines": true,
"linewidth": 1,
@@ -862,21 +654,21 @@
"h": 6,
"w": 24,
"x": 0,
"y": 50
"y": 37
},
"hiddenSeries": false,
"id": 3,
"interval": "",
"legend": {
"alignAsTable": false,
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"max": true,
"min": false,
"rightSide": false,
"show": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
"values": true
},
"lines": true,
"linewidth": 1,
@@ -947,13 +739,14 @@
"dashLength": 10,
"dashes": false,
"datasource": "$data_source",
"decimals": null,
"fill": 0,
"fillGradient": 0,
"gridPos": {
"h": 6,
"w": 24,
"x": 0,
"y": 56
"y": 43
},
"hiddenSeries": false,
"id": 7,
@@ -987,7 +780,7 @@
"steppedLine": true,
"targets": [
{
"expr": "avg(\n rate(${metric_namespace}_tasks_polling_duration_bucket{instance=~\"${nodename}\", le=\"+Inf\"}[1m])\n - ignoring(le)\n rate(${metric_namespace}_tasks_polling_duration_bucket{instance=~\"${nodename}\", le=\"1.024\"}[1m])\n) by (task_name) > 0",
"expr": "avg(\n irate(${metric_namespace}_tasks_polling_duration_bucket{instance=~\"${nodename}\", le=\"+Inf\"}[10m])\n - ignoring(le)\n irate(${metric_namespace}_tasks_polling_duration_bucket{instance=~\"${nodename}\", le=\"1.024\"}[10m])\n) by (task_name) > 0",
"interval": "",
"legendFormat": "{{task_name}}",
"refId": "A"
@@ -1013,6 +806,7 @@
},
"yaxes": [
{
"decimals": null,
"format": "cps",
"label": "Calls to `Future::poll`/second",
"logBase": 1,
@@ -1041,7 +835,7 @@
"h": 1,
"w": 24,
"x": 0,
"y": 62
"y": 49
},
"id": 27,
"panels": [],
@@ -1060,18 +854,20 @@
"h": 7,
"w": 24,
"x": 0,
"y": 63
"y": 50
},
"hiddenSeries": false,
"id": 23,
"id": 32,
"legend": {
"avg": false,
"alignAsTable": true,
"avg": true,
"current": false,
"max": false,
"max": true,
"min": false,
"show": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
"values": true
},
"lines": true,
"linewidth": 1,
@@ -1089,17 +885,17 @@
"steppedLine": false,
"targets": [
{
"expr": "${metric_namespace}_threads{instance=~\"${nodename}\"}",
"expr": "avg(${metric_namespace}_unbounded_channel_len{instance=~\"${nodename}\", action = \"send\"} - ignoring(action) ${metric_namespace}_unbounded_channel_len{instance=~\"${nodename}\", action = \"received\"}) by (entity)",
"interval": "",
"legendFormat": "{{instance}}",
"refId": "A"
"legendFormat": "{{entity}}",
"refId": "B"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Number of threads",
"title": "Unbounded channels size (average per node)",
"tooltip": {
"shared": true,
"sort": 2,
@@ -1135,9 +931,99 @@
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$data_source",
"fill": 0,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 57
},
"hiddenSeries": false,
"id": 33,
"legend": {
"alignAsTable": true,
"avg": true,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "avg(irate(${metric_namespace}_unbounded_channel_len{instance=~\"${nodename}\", action = \"send\"}[10m])) by (entity)",
"interval": "",
"legendFormat": "{{entity}}",
"refId": "B"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Unbounded channels rate (average per node)",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "cps",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
}
],
"refresh": "30s",
"refresh": false,
"schemaVersion": 22,
"style": "dark",
"tags": [],
@@ -1147,7 +1033,7 @@
"allValue": null,
"current": {},
"datasource": "$data_source",
"definition": "${metric_namespace}_cpu_usage_percentage",
"definition": "${metric_namespace}_process_start_time_seconds",
"hide": 0,
"includeAll": true,
"index": -1,
@@ -1155,7 +1041,7 @@
"multi": true,
"name": "nodename",
"options": [],
"query": "${metric_namespace}_cpu_usage_percentage",
"query": "${metric_namespace}_process_start_time_seconds",
"refresh": 1,
"regex": "/instance=\"(.*?)\"/",
"skipUrlSync": false,
@@ -1228,5 +1114,5 @@
"variables": {
"list": []
},
"version": 44
"version": 52
}