kubernetes/monitoring/grafana/dashboard/kubernetes-cluster-monitoring (via Prometheus).json
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": "-- Grafana --",
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"description": "Monitors Kubernetes cluster using Prometheus. Shows overall cluster CPU / Memory / Filesystem usage as well as individual pod, containers, systemd services statistics. Uses cAdvisor metrics only.",
"editable": true,
"gnetId": 1621,
"graphTooltip": 0,
"id": 5,
"iteration": 1592320815140,
"links": [],
"panels": [
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 0
},
"id": 33,
"panels": [],
"title": "Network I/O pressure",
"type": "row"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "Prometheus",
"decimals": 2,
"editable": true,
"error": false,
"fill": 1,
"grid": {},
"gridPos": {
"h": 5,
"w": 24,
"x": 0,
"y": 1
},
"height": "200px",
"id": 32,
"isNew": true,
"legend": {
"alignAsTable": false,
"avg": true,
"current": true,
"max": false,
"min": false,
"rightSide": false,
"show": false,
"sideWidth": 200,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "connected",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum (rate (container_network_receive_bytes_total{kubernetes_io_hostname=~\"^$Node$\"}[1m]))",
"format": "time_series",
"interval": "10s",
"intervalFactor": 1,
"legendFormat": "Received",
"metric": "network",
"refId": "A",
"step": 10
},
{
"expr": "- sum (rate (container_network_transmit_bytes_total{kubernetes_io_hostname=~\"^$Node$\"}[1m]))",
"format": "time_series",
"interval": "10s",
"intervalFactor": 1,
"legendFormat": "Sent",
"metric": "network",
"refId": "B",
"step": 10
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Network I/O pressure",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 0,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 6
},
"id": 34,
"panels": [],
"title": "Total usage",
"type": "row"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": true,
"colors": [
"rgba(50, 172, 45, 0.97)",
"rgba(237, 129, 40, 0.89)",
"rgba(245, 54, 54, 0.9)"
],
"datasource": "Prometheus",
"editable": true,
"error": false,
"format": "percent",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": true,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
"h": 5,
"w": 8,
"x": 0,
"y": 7
},
"height": "180px",
"id": 4,
"interval": null,
"isNew": true,
"links": [],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"options": {},
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "sum (container_memory_working_set_bytes{id=\"/\",kubernetes_io_hostname=~\"^$Node$\"}) / sum (machine_memory_bytes{kubernetes_io_hostname=~\"^$Node$\"}) * 100",
"interval": "10s",
"intervalFactor": 1,
"refId": "A",
"step": 10
}
],
"thresholds": "65, 90",
"title": "Cluster memory usage",
"type": "singlestat",
"valueFontSize": "80%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "current"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": true,
"colors": [
"rgba(50, 172, 45, 0.97)",
"rgba(237, 129, 40, 0.89)",
"rgba(245, 54, 54, 0.9)"
],
"datasource": "Prometheus",
"decimals": 2,
"editable": true,
"error": false,
"format": "percent",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": true,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
"h": 5,
"w": 8,
"x": 8,
"y": 7
},
"height": "180px",
"id": 6,
"interval": null,
"isNew": true,
"links": [],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"options": {},
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "sum (rate (container_cpu_usage_seconds_total{id=\"/\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) / sum (machine_cpu_cores{kubernetes_io_hostname=~\"^$Node$\"}) * 100",
"format": "time_series",
"interval": "10s",
"intervalFactor": 1,
"refId": "A",
"step": 10
}
],
"thresholds": "65, 90",
"title": "Cluster CPU usage (2m avg)",
"type": "singlestat",
"valueFontSize": "80%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "current"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": true,
"colors": [
"rgba(50, 172, 45, 0.97)",
"rgba(237, 129, 40, 0.89)",
"rgba(245, 54, 54, 0.9)"
],
"datasource": "Prometheus",
"decimals": 2,
"editable": true,
"error": false,
"format": "percent",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": true,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
"h": 5,
"w": 8,
"x": 16,
"y": 7
},
"height": "180px",
"id": 7,
"interval": null,
"isNew": true,
"links": [],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"options": {},
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "sum (container_fs_usage_bytes{device=~\"^/dev/.*$\",id=\"/\",kubernetes_io_hostname=~\"^$Node$\"}) / sum (container_fs_limit_bytes{device=~\"^/dev/.*$\",id=\"/\",kubernetes_io_hostname=~\"^$Node$\"}) * 100",
"interval": "10s",
"intervalFactor": 1,
"legendFormat": "",
"metric": "",
"refId": "A",
"step": 10
}
],
"thresholds": "65, 90",
"title": "Cluster filesystem usage",
"type": "singlestat",
"valueFontSize": "80%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "current"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"rgba(50, 172, 45, 0.97)",
"rgba(237, 129, 40, 0.89)",
"rgba(245, 54, 54, 0.9)"
],
"datasource": "Prometheus",
"decimals": 2,
"editable": true,
"error": false,
"format": "bytes",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
"h": 3,
"w": 4,
"x": 0,
"y": 12
},
"height": "1px",
"id": 9,
"interval": null,
"isNew": true,
"links": [],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"options": {},
"postfix": "",
"postfixFontSize": "20%",
"prefix": "",
"prefixFontSize": "20%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "sum (container_memory_working_set_bytes{id=\"/\",kubernetes_io_hostname=~\"^$Node$\"})",
"interval": "10s",
"intervalFactor": 1,
"refId": "A",
"step": 10
}
],
"thresholds": "",
"title": "Used",
"type": "singlestat",
"valueFontSize": "50%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "current"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"rgba(50, 172, 45, 0.97)",
"rgba(237, 129, 40, 0.89)",
"rgba(245, 54, 54, 0.9)"
],
"datasource": "Prometheus",
"decimals": 2,
"editable": true,
"error": false,
"format": "bytes",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
"h": 3,
"w": 4,
"x": 4,
"y": 12
},
"height": "1px",
"id": 10,
"interval": null,
"isNew": true,
"links": [],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"options": {},
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "sum (machine_memory_bytes{kubernetes_io_hostname=~\"^$Node$\"})",
"interval": "10s",
"intervalFactor": 1,
"refId": "A",
"step": 10
}
],
"thresholds": "",
"title": "Total",
"type": "singlestat",
"valueFontSize": "50%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "current"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"rgba(50, 172, 45, 0.97)",
"rgba(237, 129, 40, 0.89)",
"rgba(245, 54, 54, 0.9)"
],
"datasource": "Prometheus",
"decimals": 2,
"editable": true,
"error": false,
"format": "none",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
"h": 3,
"w": 4,
"x": 8,
"y": 12
},
"height": "1px",
"id": 11,
"interval": null,
"isNew": true,
"links": [],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"options": {},
"postfix": " cores",
"postfixFontSize": "30%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "sum (rate (container_cpu_usage_seconds_total{id=\"/\",kubernetes_io_hostname=~\"^$Node$\"}[2m]))",
"format": "time_series",
"interval": "10s",
"intervalFactor": 1,
"refId": "A",
"step": 10
}
],
"thresholds": "",
"title": "Used",
"type": "singlestat",
"valueFontSize": "50%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "current"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"rgba(50, 172, 45, 0.97)",
"rgba(237, 129, 40, 0.89)",
"rgba(245, 54, 54, 0.9)"
],
"datasource": "Prometheus",
"decimals": 2,
"editable": true,
"error": false,
"format": "none",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
"h": 3,
"w": 4,
"x": 12,
"y": 12
},
"height": "1px",
"id": 12,
"interval": null,
"isNew": true,
"links": [],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"options": {},
"postfix": " cores",
"postfixFontSize": "30%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "sum (machine_cpu_cores{kubernetes_io_hostname=~\"^$Node$\"})",
"interval": "10s",
"intervalFactor": 1,
"refId": "A",
"step": 10
}
],
"thresholds": "",
"title": "Total",
"type": "singlestat",
"valueFontSize": "50%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "current"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"rgba(50, 172, 45, 0.97)",
"rgba(237, 129, 40, 0.89)",
"rgba(245, 54, 54, 0.9)"
],
"datasource": "Prometheus",
"decimals": 2,
"editable": true,
"error": false,
"format": "bytes",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
"h": 3,
"w": 4,
"x": 16,
"y": 12
},
"height": "1px",
"id": 13,
"interval": null,
"isNew": true,
"links": [],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"options": {},
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "sum (container_fs_usage_bytes{device=~\"^/dev/.*$\",id=\"/\",kubernetes_io_hostname=~\"^$Node$\"})",
"interval": "10s",
"intervalFactor": 1,
"refId": "A",
"step": 10
}
],
"thresholds": "",
"title": "Used",
"type": "singlestat",
"valueFontSize": "50%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "current"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"rgba(50, 172, 45, 0.97)",
"rgba(237, 129, 40, 0.89)",
"rgba(245, 54, 54, 0.9)"
],
"datasource": "Prometheus",
"decimals": 2,
"editable": true,
"error": false,
"format": "bytes",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
"h": 3,
"w": 4,
"x": 20,
"y": 12
},
"height": "1px",
"id": 14,
"interval": null,
"isNew": true,
"links": [],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"options": {},
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "sum (container_fs_limit_bytes{device=~\"^/dev/.*$\",id=\"/\",kubernetes_io_hostname=~\"^$Node$\"})",
"interval": "10s",
"intervalFactor": 1,
"refId": "A",
"step": 10
}
],
"thresholds": "",
"title": "Total",
"type": "singlestat",
"valueFontSize": "50%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "current"
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 15
},
"id": 35,
"panels": [],
"title": "Pods CPU usage",
"type": "row"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "Prometheus",
"decimals": 3,
"editable": true,
"error": false,
"fill": 0,
"grid": {},
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 16
},
"height": "",
"id": 17,
"isNew": true,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "connected",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": true,
"targets": [
{
"expr": "sum (rate (container_cpu_usage_seconds_total{image!=\"\",name=~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[1m])) by (pod)",
"format": "time_series",
"interval": "10s",
"intervalFactor": 1,
"legendFormat": "{{ pod }}",
"metric": "container_cpu",
"refId": "A",
"step": 10
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Pods CPU usage (1m avg)",
"tooltip": {
"msResolution": true,
"shared": true,
"sort": 2,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "none",
"label": "cores",
"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": true,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 23
},
"id": 36,
"panels": [
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "Prometheus",
"decimals": 3,
"editable": true,
"error": false,
"fill": 0,
"grid": {},
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 24
},
"height": "",
"id": 23,
"isNew": true,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "connected",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": true,
"targets": [
{
"expr": "sum (rate (container_cpu_usage_seconds_total{systemd_service_name!=\"\",kubernetes_io_hostname=~\"^$Node$\"}[1m])) by (systemd_service_name)",
"format": "time_series",
"hide": false,
"interval": "10s",
"intervalFactor": 1,
"legendFormat": "{{ systemd_service_name }}",
"metric": "container_cpu",
"refId": "A",
"step": 10
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "System services CPU usage (1m avg)",
"tooltip": {
"msResolution": true,
"shared": true,
"sort": 2,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "none",
"label": "cores",
"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
}
}
],
"title": "System services CPU usage",
"type": "row"
},
{
"collapsed": true,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 24
},
"id": 37,
"panels": [
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "Prometheus",
"decimals": 3,
"editable": true,
"error": false,
"fill": 0,
"grid": {},
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 25
},
"height": "",
"id": 24,
"isNew": true,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"hideEmpty": false,
"hideZero": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "connected",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": true,
"targets": [
{
"expr": "sum (rate (container_cpu_usage_seconds_total{image!=\"\",name=~\"^k8s_.*\",container_name!=\"POD\",kubernetes_io_hostname=~\"^$Node$\"}[1m])) by (container, pod)",
"format": "time_series",
"hide": false,
"interval": "10s",
"intervalFactor": 1,
"legendFormat": "pod: {{ pod }} | {{ container }}",
"metric": "container_cpu",
"refId": "A",
"step": 10
},
{
"expr": "sum (rate (container_cpu_usage_seconds_total{image!=\"\",name!~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[1m])) by (kubernetes_io_hostname, name, image)",
"format": "time_series",
"hide": false,
"interval": "10s",
"intervalFactor": 1,
"legendFormat": "docker: {{ kubernetes_io_hostname }} | {{ image }} ({{ name }})",
"metric": "container_cpu",
"refId": "B",
"step": 10
},
{
"expr": "sum (rate (container_cpu_usage_seconds_total{rkt_container_name!=\"\",kubernetes_io_hostname=~\"^$Node$\"}[1m])) by (kubernetes_io_hostname, rkt_container_name)",
"format": "time_series",
"interval": "10s",
"intervalFactor": 1,
"legendFormat": "rkt: {{ kubernetes_io_hostname }} | {{ rkt_container_name }}",
"metric": "container_cpu",
"refId": "C",
"step": 10
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Containers CPU usage (1m avg)",
"tooltip": {
"msResolution": true,
"shared": true,
"sort": 2,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "none",
"label": "cores",
"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
}
}
],
"title": "Containers CPU usage",
"type": "row"
},
{
"collapsed": true,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 25
},
"id": 38,
"panels": [
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "Prometheus",
"decimals": 3,
"editable": true,
"error": false,
"fill": 0,
"grid": {},
"gridPos": {
"h": 13,
"w": 24,
"x": 0,
"y": 26
},
"id": 20,
"isNew": true,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "connected",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": true,
"targets": [
{
"expr": "sum (rate (container_cpu_usage_seconds_total{id!=\"/\",kubernetes_io_hostname=~\"^$Node$\"}[1m])) by (id)",
"format": "time_series",
"hide": false,
"interval": "10s",
"intervalFactor": 1,
"legendFormat": "{{ id }}",
"metric": "container_cpu",
"refId": "A",
"step": 10
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "All processes CPU usage (1m avg)",
"tooltip": {
"msResolution": true,
"shared": true,
"sort": 2,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "none",
"label": "cores",
"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
}
}
],
"repeat": null,
"title": "All processes CPU usage",
"type": "row"
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 26
},
"id": 39,
"panels": [],
"title": "Pods memory usage",
"type": "row"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "Prometheus",
"decimals": 2,
"editable": true,
"error": false,
"fill": 0,
"grid": {},
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 27
},
"id": 25,
"isNew": true,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "connected",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": true,
"targets": [
{
"expr": "sum (container_memory_working_set_bytes{image!=\"\",name=~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}) by (pod)",
"format": "time_series",
"interval": "10s",
"intervalFactor": 1,
"legendFormat": "{{ pod }}",
"metric": "container_memory_usage:sort_desc",
"refId": "A",
"step": 10
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Pods memory usage",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 2,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "bytes",
"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": true,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 34
},
"id": 40,
"panels": [
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "Prometheus",
"decimals": 2,
"editable": true,
"error": false,
"fill": 0,
"grid": {},
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 35
},
"id": 26,
"isNew": true,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": 200,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "connected",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": true,
"targets": [
{
"expr": "sum (container_memory_working_set_bytes{systemd_service_name!=\"\",kubernetes_io_hostname=~\"^$Node$\"}) by (systemd_service_name)",
"interval": "10s",
"intervalFactor": 1,
"legendFormat": "{{ systemd_service_name }}",
"metric": "container_memory_usage:sort_desc",
"refId": "A",
"step": 10
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "System services memory usage",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 2,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "bytes",
"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
}
}
],
"title": "System services memory usage",
"type": "row"
},
{
"collapsed": true,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 35
},
"id": 41,
"panels": [
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "Prometheus",
"decimals": 2,
"editable": true,
"error": false,
"fill": 0,
"grid": {},
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 36
},
"id": 27,
"isNew": true,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": 200,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "connected",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": true,
"targets": [
{
"expr": "sum (container_memory_working_set_bytes{image!=\"\",name=~\"^k8s_.*\",container_name!=\"POD\",kubernetes_io_hostname=~\"^$Node$\"}) by (container, pod)",
"format": "time_series",
"interval": "10s",
"intervalFactor": 1,
"legendFormat": "pod: {{ pod }} | {{ container }}",
"metric": "container_memory_usage:sort_desc",
"refId": "A",
"step": 10
},
{
"expr": "sum (container_memory_working_set_bytes{image!=\"\",name!~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}) by (kubernetes_io_hostname, name, image)",
"format": "time_series",
"interval": "10s",
"intervalFactor": 1,
"legendFormat": "docker: {{ kubernetes_io_hostname }} | {{ image }} ({{ name }})",
"metric": "container_memory_usage:sort_desc",
"refId": "B",
"step": 10
},
{
"expr": "sum (container_memory_working_set_bytes{rkt_container_name!=\"\",kubernetes_io_hostname=~\"^$Node$\"}) by (kubernetes_io_hostname, rkt_container_name)",
"format": "time_series",
"interval": "10s",
"intervalFactor": 1,
"legendFormat": "rkt: {{ kubernetes_io_hostname }} | {{ rkt_container_name }}",
"metric": "container_memory_usage:sort_desc",
"refId": "C",
"step": 10
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Containers memory usage",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 2,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "bytes",
"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
}
}
],
"title": "Containers memory usage",
"type": "row"
},
{
"collapsed": true,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 36
},
"id": 42,
"panels": [
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "Prometheus",
"decimals": 2,
"editable": true,
"error": false,
"fill": 0,
"grid": {},
"gridPos": {
"h": 13,
"w": 24,
"x": 0,
"y": 44
},
"id": 28,
"isNew": true,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": 200,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "connected",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": true,
"targets": [
{
"expr": "sum (container_memory_working_set_bytes{id!=\"/\",kubernetes_io_hostname=~\"^$Node$\"}) by (id)",
"interval": "10s",
"intervalFactor": 1,
"legendFormat": "{{ id }}",
"metric": "container_memory_usage:sort_desc",
"refId": "A",
"step": 10
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "All processes memory usage",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 2,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "bytes",
"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
}
}
],
"title": "All processes memory usage",
"type": "row"
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 37
},
"id": 43,
"panels": [],
"title": "Pods network I/O",
"type": "row"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "Prometheus",
"decimals": 2,
"editable": true,
"error": false,
"fill": 1,
"grid": {},
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 38
},
"id": 16,
"isNew": true,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "connected",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum (rate (container_network_receive_bytes_total{image!=\"\",name=~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[1m])) by (pod)",
"format": "time_series",
"interval": "10s",
"intervalFactor": 1,
"legendFormat": "-> {{ pod }}",
"metric": "network",
"refId": "A",
"step": 10
},
{
"expr": "- sum (rate (container_network_transmit_bytes_total{image!=\"\",name=~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[1m])) by (pod)",
"format": "time_series",
"interval": "10s",
"intervalFactor": 1,
"legendFormat": "<- {{ pod }}",
"metric": "network",
"refId": "B",
"step": 10
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Pods network I/O (1m avg)",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 2,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "Bps",
"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": true,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 45
},
"id": 44,
"panels": [
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "Prometheus",
"decimals": 2,
"editable": true,
"error": false,
"fill": 1,
"grid": {},
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 46
},
"id": 30,
"isNew": true,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": 200,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "connected",
"options": {},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum (rate (container_network_receive_bytes_total{image!=\"\",name=~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[1m])) by (container, pod)",
"format": "time_series",
"hide": false,
"interval": "10s",
"intervalFactor": 1,
"legendFormat": "-> pod: {{ pod }} | {{ container }}",
"metric": "network",
"refId": "B",
"step": 10
},
{
"expr": "- sum (rate (container_network_transmit_bytes_total{image!=\"\",name=~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[1m])) by (container, pod)",
"format": "time_series",
"hide": false,
"interval": "10s",
"intervalFactor": 1,
"legendFormat": "<- pod: {{ pod }} | {{ container }}",
"metric": "network",
"refId": "D",
"step": 10
},
{
"expr": "sum (rate (container_network_receive_bytes_total{image!=\"\",name!~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[1m])) by (kubernetes_io_hostname, name, image)",
"format": "time_series",
"hide": false,
"interval": "10s",
"intervalFactor": 1,
"legendFormat": "-> docker: {{ kubernetes_io_hostname }} | {{ image }} ({{ name }})",
"metric": "network",
"refId": "A",
"step": 10
},
{
"expr": "- sum (rate (container_network_transmit_bytes_total{image!=\"\",name!~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[1m])) by (kubernetes_io_hostname, name, image)",
"format": "time_series",
"hide": false,
"interval": "10s",
"intervalFactor": 1,
"legendFormat": "<- docker: {{ kubernetes_io_hostname }} | {{ image }} ({{ name }})",
"metric": "network",
"refId": "C",
"step": 10
},
{
"expr": "sum (rate (container_network_transmit_bytes_total{rkt_container_name!=\"\",kubernetes_io_hostname=~\"^$Node$\"}[1m])) by (kubernetes_io_hostname, rkt_container_name)",
"format": "time_series",
"hide": false,
"interval": "10s",
"intervalFactor": 1,
"legendFormat": "-> rkt: {{ kubernetes_io_hostname }} | {{ rkt_container_name }}",
"metric": "network",
"refId": "E",
"step": 10
},
{
"expr": "- sum (rate (container_network_transmit_bytes_total{rkt_container_name!=\"\",kubernetes_io_hostname=~\"^$Node$\"}[1m])) by (kubernetes_io_hostname, rkt_container_name)",
"format": "time_series",
"hide": false,
"interval": "10s",
"intervalFactor": 1,
"legendFormat": "<- rkt: {{ kubernetes_io_hostname }} | {{ rkt_container_name }}",
"metric": "network",
"refId": "F",
"step": 10
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Containers network I/O (1m avg)",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 2,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "Bps",
"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
}
}
],
"title": "Containers network I/O",
"type": "row"
},
{
"collapsed": true,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 46
},
"id": 45,
"panels": [
{
"aliasColors": {},
"bars": false,
"datasource": "Prometheus",
"decimals": 2,
"editable": true,
"error": false,
"fill": 1,
"grid": {},
"gridPos": {
"h": 13,
"w": 24,
"x": 0,
"y": 46
},
"id": 29,
"isNew": true,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": 200,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "connected",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum (rate (container_network_receive_bytes_total{id!=\"/\",kubernetes_io_hostname=~\"^$Node$\"}[1m])) by (id)",
"interval": "10s",
"intervalFactor": 1,
"legendFormat": "-> {{ id }}",
"metric": "network",
"refId": "A",
"step": 10
},
{
"expr": "- sum (rate (container_network_transmit_bytes_total{id!=\"/\",kubernetes_io_hostname=~\"^$Node$\"}[1m])) by (id)",
"interval": "10s",
"intervalFactor": 1,
"legendFormat": "<- {{ id }}",
"metric": "network",
"refId": "B",
"step": 10
}
],
"thresholds": [],
"timeFrom": null,
"timeShift": null,
"title": "All processes network I/O (1m avg)",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 2,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"show": true
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
}
],
"title": "All processes network I/O",
"type": "row"
}
],
"refresh": "10s",
"schemaVersion": 18,
"style": "dark",
"tags": [
"kubernetes"
],
"templating": {
"list": [
{
"allValue": ".*",
"current": {
"text": "All",
"value": "$__all"
},
"datasource": "Prometheus",
"definition": "",
"hide": 0,
"includeAll": true,
"label": null,
"multi": false,
"name": "Node",
"options": [],
"query": "label_values(kubernetes_io_hostname)",
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"sort": 0,
"tagValuesQuery": "",
"tags": [],
"tagsQuery": "",
"type": "query",
"useTags": false
}
]
},
"time": {
"from": "now-5m",
"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": "Kubernetes cluster monitoring (via Prometheus)",
"uid": "Zos5JpeWk",
"version": 2
}