nixcfg/cluster/prod/app/telemetry/dashboards/Nomad allocation details-1683628091383.json

2213 lines
56 KiB
JSON

{
"__inputs": [
{
"name": "DS_DS_PROMETHEUS",
"label": "DS_PROMETHEUS",
"description": "",
"type": "datasource",
"pluginId": "prometheus",
"pluginName": "Prometheus"
}
],
"__elements": {},
"__requires": [
{
"type": "grafana",
"id": "grafana",
"name": "Grafana",
"version": "9.5.1"
},
{
"type": "panel",
"id": "graph",
"name": "Graph (old)",
"version": ""
},
{
"type": "datasource",
"id": "prometheus",
"name": "Prometheus",
"version": "1.0.0"
},
{
"type": "panel",
"id": "stat",
"name": "Stat",
"version": ""
},
{
"type": "panel",
"id": "timeseries",
"name": "Time series",
"version": ""
}
],
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": {
"type": "datasource",
"uid": "grafana"
},
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"target": {
"limit": 100,
"matchAny": false,
"tags": [],
"type": "dashboard"
},
"type": "dashboard"
}
]
},
"description": "Nomad built-in telemetry scoped on allocation",
"editable": true,
"fiscalYearStartMonth": 0,
"gnetId": 3800,
"graphTooltip": 1,
"id": null,
"links": [],
"liveNow": false,
"panels": [
{
"collapsed": false,
"datasource": {
"type": "prometheus",
"uid": "cud-fxAMz"
},
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 0
},
"id": 20,
"panels": [],
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "cud-fxAMz"
},
"refId": "A"
}
],
"title": "Overall allocations status",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
}
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "Blocked"
},
"properties": [
{
"id": "color",
"value": {
"mode": "thresholds"
}
},
{
"id": "thresholds",
"value": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 1
}
]
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "Migrating"
},
"properties": [
{
"id": "thresholds",
"value": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "purple",
"value": 1
}
]
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "Pending"
},
"properties": [
{
"id": "thresholds",
"value": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "orange",
"value": 1
}
]
}
}
]
}
]
},
"gridPos": {
"h": 7,
"w": 6,
"x": 0,
"y": 1
},
"id": 1,
"links": [],
"options": {
"colorMode": "background",
"graphMode": "none",
"justifyMode": "center",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"text": {},
"textMode": "auto"
},
"pluginVersion": "9.5.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"expr": "sum(nomad_client_allocations_blocked{host=~\"$host\"})",
"format": "time_series",
"hide": false,
"instant": true,
"interval": "",
"intervalFactor": 2,
"legendFormat": "Blocked",
"refId": "A",
"step": 20
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"expr": "sum(nomad_client_allocations_migrating{host=~\"$host\"})",
"format": "time_series",
"instant": true,
"interval": "",
"intervalFactor": 2,
"legendFormat": "Migrating",
"refId": "B",
"step": 20
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"expr": "sum(nomad_client_allocations_pending{host=~\"$host\"})",
"format": "time_series",
"instant": true,
"interval": "",
"intervalFactor": 2,
"legendFormat": "Pending",
"refId": "C",
"step": 20
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"expr": "sum(nomad_client_allocations_running{host=~\"$host\"})",
"format": "time_series",
"instant": true,
"interval": "",
"intervalFactor": 2,
"legendFormat": "Running",
"refId": "D",
"step": 20
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"expr": "sum(nomad_client_allocations_terminal{host=~\"$host\"})",
"format": "time_series",
"instant": true,
"interval": "",
"intervalFactor": 2,
"legendFormat": "Terminal",
"refId": "E",
"step": 20
}
],
"title": "Current Allocation Status",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "Allocations",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 50,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 2,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "normal"
},
"thresholdsStyle": {
"mode": "off"
}
},
"decimals": 0,
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "short"
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "blocked"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "red",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "migrating"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "purple",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "pending"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "blue",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "running"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "green",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "terminal"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "yellow",
"mode": "fixed"
}
}
]
}
]
},
"gridPos": {
"h": 7,
"w": 6,
"x": 6,
"y": 1
},
"id": 24,
"links": [],
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": false
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "9.2.0",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"expr": "sum(nomad_client_allocations_blocked{host=~\"$host\"})",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 2,
"legendFormat": "blocked",
"refId": "A",
"step": 20
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"expr": "sum(nomad_client_allocations_migrating{host=~\"$host\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "migrating",
"refId": "B",
"step": 20
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"expr": "sum(nomad_client_allocations_pending{host=~\"$host\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "pending",
"refId": "C",
"step": 20
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"expr": "sum(nomad_client_allocations_running{host=~\"$host\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "running",
"refId": "D",
"step": 20
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"expr": "sum(nomad_client_allocations_terminal{host=~\"$host\"})",
"format": "time_series",
"interval": "",
"intervalFactor": 2,
"legendFormat": "terminal",
"refId": "E",
"step": 20
}
],
"title": "Allocation Status",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "memory",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 60,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "normal"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "decmbytes"
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "allocated"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "purple",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "reserved"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#58140C",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "unallocated"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "blue",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "utilization"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#FADE2A",
"mode": "fixed"
}
},
{
"id": "custom.fillOpacity",
"value": 0
},
{
"id": "custom.lineWidth",
"value": 0
},
{
"id": "custom.lineWidth",
"value": 3
},
{
"id": "custom.stacking",
"value": {
"group": false,
"mode": "normal"
}
}
]
}
]
},
"gridPos": {
"h": 7,
"w": 6,
"x": 12,
"y": 1
},
"id": 3,
"links": [],
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "9.2.0",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"expr": "sum(nomad_client_allocs_memory_usage{host=~\"$host\"}/1024/1024)",
"format": "time_series",
"interval": "",
"intervalFactor": 2,
"legendFormat": "utilization",
"refId": "B",
"step": 20
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"expr": "sum(nomad_client_allocated_memory{host=~\"$host\"})",
"format": "time_series",
"hide": false,
"intervalFactor": 2,
"legendFormat": "allocated",
"refId": "A",
"step": 20
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"expr": "sum(nomad_client_unallocated_memory{host=~\"$host\"})",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 2,
"legendFormat": "unallocated",
"refId": "C",
"step": 20
}
],
"title": "Cluster-level Memory Allocation ",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "allocated cpu Hz",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 60,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 0,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "normal"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "hertz"
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "allocated"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "orange",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "host actual"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#DEDAF7",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "host utilization normalized"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#508642",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "nomad reserved"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#58140C",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "unallocated"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "blue",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "utilization"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#E5AC0E",
"mode": "fixed"
}
},
{
"id": "custom.fillOpacity",
"value": 0
},
{
"id": "custom.lineWidth",
"value": 2
},
{
"id": "custom.stacking",
"value": {
"group": false,
"mode": "normal"
}
}
]
}
]
},
"gridPos": {
"h": 7,
"w": 6,
"x": 18,
"y": 1
},
"id": 2,
"links": [],
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "9.2.0",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"expr": "sum(nomad_client_allocated_cpu{host=~\"$host\"} * 1000 * 1000)",
"format": "time_series",
"hide": false,
"intervalFactor": 2,
"legendFormat": "allocated",
"refId": "A",
"step": 20
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"expr": "sum(nomad_client_unallocated_cpu{host=~\"$host\"} * 1000 * 1000)",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 2,
"legendFormat": "unallocated",
"refId": "C",
"step": 20
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"expr": "sum(nomad_client_allocs_cpu_total_percent{host=~\"$host\"} / 100)\n * (\n sum(nomad_client_allocated_cpu{host=~\"$host\"} * 1000 * 1000) +\n sum(nomad_client_unallocated_cpu{host=~\"$host\"} * 1000 * 1000)\n )",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 2,
"legendFormat": "utilization",
"refId": "F",
"step": 2
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"expr": "sum(nomad_client_allocs_cpu_total_percent{host=~\"$host\"})",
"format": "time_series",
"hide": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "B",
"step": 2
}
],
"title": "Cluster-level CPU Allocation ",
"type": "timeseries"
},
{
"collapsed": false,
"datasource": {
"type": "prometheus",
"uid": "cud-fxAMz"
},
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 8
},
"id": 32,
"panels": [],
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "cud-fxAMz"
},
"refId": "A"
}
],
"title": "Allocations and jobs details",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "Allocation CPU usage",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "bars",
"fillOpacity": 100,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "normal"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "percent"
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "allocated"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#BF1B00",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "host actual"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#DEDAF7",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "host utilization normalized"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#508642",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "idle"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "dark-green",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "nomad reserved"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#58140C",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "other"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "purple",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "system"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "orange",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "unallocated"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#1F78C1",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "user"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "blue",
"mode": "fixed"
}
}
]
}
]
},
"gridPos": {
"h": 9,
"w": 24,
"x": 0,
"y": 9
},
"id": 34,
"links": [],
"options": {
"legend": {
"calcs": [
"lastNotNull",
"max"
],
"displayMode": "table",
"placement": "right",
"showLegend": true,
"sortBy": "Max",
"sortDesc": true
},
"tooltip": {
"mode": "multi",
"sort": "none"
}
},
"pluginVersion": "9.2.0",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"exemplar": true,
"expr": "avg(nomad_client_allocs_cpu_total_percent{host=~\"$host\", exported_job!~\".*periodic.*\", exported_job=~\"$job\"}) by (exported_job, task_group, task, host)",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 3,
"legendFormat": "{{ exported_job }} | {{ task_group }} ({{ task}}) on {{host}}",
"refId": "B",
"step": 20
}
],
"title": "CPU usage details per allocation",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "Allocation memory usage",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 80,
"gradientMode": "opacity",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 2,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "normal"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "bytes"
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "allocated"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#BF1B00",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "host actual"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#DEDAF7",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "host utilization normalized"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#508642",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "idle"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "dark-green",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "nomad reserved"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#58140C",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "other"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "purple",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "system"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "orange",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "unallocated"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#1F78C1",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "user"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "blue",
"mode": "fixed"
}
}
]
}
]
},
"gridPos": {
"h": 10,
"w": 24,
"x": 0,
"y": 18
},
"id": 35,
"links": [],
"options": {
"legend": {
"calcs": [
"lastNotNull",
"max"
],
"displayMode": "table",
"placement": "right",
"showLegend": true,
"sortBy": "Max",
"sortDesc": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "9.2.0",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"exemplar": true,
"expr": "avg(nomad_client_allocs_memory_usage{host=~\"$host\", exported_job!~\".*periodic.*\", exported_job=~\"$job\"}) by (exported_job, task_group, task, host)",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 3,
"legendFormat": "{{ exported_job }} | {{ task_group }} ({{ task}}) on {{host}}",
"refId": "B",
"step": 20
}
],
"title": "RAM usage details per allocation",
"type": "timeseries"
},
{
"collapsed": true,
"datasource": {
"type": "prometheus",
"uid": "cud-fxAMz"
},
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 28
},
"id": 37,
"panels": [
{
"aliasColors": {
"allocated": "#BF1B00",
"host actual": "#DEDAF7",
"host utilization normalized": "#508642",
"idle": "dark-green",
"nomad reserved": "#58140C",
"other": "purple",
"system": "orange",
"unallocated": "#1F78C1",
"user": "blue"
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"fill": 6,
"fillGradient": 8,
"gridPos": {
"h": 8,
"w": 7,
"x": 0,
"y": 29
},
"height": "",
"hiddenSeries": false,
"id": 38,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": true,
"min": false,
"rightSide": true,
"show": false,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "null",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "9.2.0",
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": true,
"steppedLine": false,
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"exemplar": true,
"expr": "avg(nomad_client_allocs_memory_rss{host=~\"$host\", exported_job!~\".*periodic.*\", exported_job=~\"$job\", task=~\"$task\"}) by (exported_job, task_group, task, host)",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 3,
"legendFormat": "{{ exported_job }} | {{ task_group }} ({{ task}}) on {{host}}",
"refId": "B",
"step": 20
}
],
"thresholds": [],
"timeRegions": [],
"title": "Allocation RAM RSS usage",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"$$hashKey": "object:478",
"format": "bytes",
"label": "Allocation memory usage",
"logBase": 1,
"min": "0",
"show": true
},
{
"$$hashKey": "object:479",
"format": "percent",
"label": "",
"logBase": 1,
"min": "0",
"show": false
}
],
"yaxis": {
"align": false
}
},
{
"aliasColors": {
"allocated": "#BF1B00",
"host actual": "#DEDAF7",
"host utilization normalized": "#508642",
"idle": "dark-green",
"nomad reserved": "#58140C",
"other": "purple",
"system": "orange",
"unallocated": "#1F78C1",
"user": "blue"
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"fill": 6,
"fillGradient": 8,
"gridPos": {
"h": 8,
"w": 7,
"x": 7,
"y": 29
},
"height": "",
"hiddenSeries": false,
"id": 39,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": true,
"min": false,
"rightSide": true,
"show": false,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "null",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "9.2.0",
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": true,
"steppedLine": false,
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"exemplar": true,
"expr": "avg(nomad_client_allocs_memory_cache{host=~\"$host\", exported_job!~\".*periodic.*\", exported_job=~\"$job\", task=~\"$task\"}) by (exported_job, task_group, task, host)",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 3,
"legendFormat": "{{ exported_job }} | {{ task_group }} ({{ task}}) on {{host}}",
"refId": "B",
"step": 20
}
],
"thresholds": [],
"timeRegions": [],
"title": "Allocation RAM cache usage",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"$$hashKey": "object:478",
"format": "bytes",
"label": "Allocation memory usage",
"logBase": 1,
"min": "0",
"show": true
},
{
"$$hashKey": "object:479",
"format": "percent",
"label": "",
"logBase": 1,
"min": "0",
"show": false
}
],
"yaxis": {
"align": false
}
},
{
"aliasColors": {
"allocated": "#BF1B00",
"host actual": "#DEDAF7",
"host utilization normalized": "#508642",
"idle": "dark-green",
"nomad reserved": "#58140C",
"other": "purple",
"system": "orange",
"unallocated": "#1F78C1",
"user": "blue"
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"fill": 6,
"fillGradient": 8,
"gridPos": {
"h": 8,
"w": 5,
"x": 14,
"y": 29
},
"height": "",
"hiddenSeries": false,
"id": 40,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": true,
"min": false,
"rightSide": true,
"show": false,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "null",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "9.2.0",
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": true,
"steppedLine": false,
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"exemplar": true,
"expr": "avg(nomad_client_allocs_cpu_system{host=~\"$host\", exported_job!~\".*periodic.*\", exported_job=~\"$job\", task=~\"$task\"}) by (exported_job, task_group, task, host)",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 2,
"legendFormat": "{{ exported_job }} | {{ task_group }} ({{ task}}) on {{host}}",
"refId": "B",
"step": 20
}
],
"thresholds": [],
"timeRegions": [],
"title": "CPU system usage",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"$$hashKey": "object:478",
"format": "percent",
"label": "Allocation memory usage",
"logBase": 1,
"min": "0",
"show": true
},
{
"$$hashKey": "object:479",
"format": "percent",
"label": "",
"logBase": 1,
"show": false
}
],
"yaxis": {
"align": false
}
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "Allocation memory usage",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 80,
"gradientMode": "opacity",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 2,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "normal"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green"
},
{
"color": "red",
"value": 80
}
]
},
"unit": "percent"
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "allocated"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#BF1B00",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "host actual"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#DEDAF7",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "host utilization normalized"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#508642",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "idle"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "dark-green",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "nomad reserved"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#58140C",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "other"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "purple",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "system"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "orange",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "unallocated"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "#1F78C1",
"mode": "fixed"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "user"
},
"properties": [
{
"id": "color",
"value": {
"fixedColor": "blue",
"mode": "fixed"
}
}
]
}
]
},
"gridPos": {
"h": 8,
"w": 5,
"x": 19,
"y": 29
},
"id": 41,
"links": [],
"options": {
"legend": {
"calcs": [
"lastNotNull",
"max"
],
"displayMode": "list",
"placement": "right",
"showLegend": false
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"pluginVersion": "9.2.0",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"exemplar": true,
"expr": "avg(nomad_client_allocs_cpu_user{host=~\"$host\", exported_job!~\".*periodic.*\", exported_job=~\"$job\", task=~\"$task\"}) by (exported_job, task_group, task, host)",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 2,
"legendFormat": "{{ exported_job }} | {{ task_group }} ({{ task}}) on {{host}}",
"refId": "B",
"step": 20
}
],
"title": "CPU user usage",
"type": "timeseries"
}
],
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "cud-fxAMz"
},
"refId": "A"
}
],
"title": "Allocation details",
"type": "row"
}
],
"refresh": "10s",
"schemaVersion": 38,
"style": "dark",
"tags": [],
"templating": {
"list": [
{
"allValue": ".*",
"current": {},
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"definition": "label_values(host)",
"hide": 0,
"includeAll": true,
"multi": false,
"name": "host",
"options": [],
"query": {
"query": "label_values(host)",
"refId": "Prometheus-host-Variable-Query"
},
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"sort": 0,
"tagValuesQuery": "",
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"current": {},
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"definition": "label_values(nomad_client_allocs_cpu_total_percent, exported_job)",
"description": "Nomad Job name",
"hide": 0,
"includeAll": true,
"label": "Job",
"multi": true,
"name": "job",
"options": [],
"query": {
"query": "label_values(nomad_client_allocs_cpu_total_percent, exported_job)",
"refId": "StandardVariableQuery"
},
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"tagValuesQuery": "",
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"current": {},
"datasource": {
"type": "prometheus",
"uid": "${DS_DS_PROMETHEUS}"
},
"definition": "label_values(nomad_client_allocs_cpu_total_percent{exported_job=~\"$job\"}, task)",
"description": "Nomad task",
"hide": 0,
"includeAll": false,
"label": "Task",
"multi": true,
"name": "task",
"options": [],
"query": {
"query": "label_values(nomad_client_allocs_cpu_total_percent{exported_job=~\"$job\"}, task)",
"refId": "StandardVariableQuery"
},
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"type": "query"
}
]
},
"time": {
"from": "now-30m",
"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": "",
"title": "Nomad allocation details",
"uid": "er3YdrrMz",
"version": 3,
"weekStart": ""
}