{
"__inputs": [],
"__elements": [],
"__requires": [
{
"type": "grafana",
"id": "grafana",
"name": "Grafana",
"version": "8.3.2"
},
{
"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": "text",
"name": "Text",
"version": ""
}
],
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": "-- 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": "Dashboard to view multiple servers",
"editable": true,
"fiscalYearStartMonth": 0,
"gnetId": 405,
"graphTooltip": 0,
"id": null,
"iteration": 1640761048436,
"links": [],
"liveNow": false,
"panels": [
{
"editable": true,
"error": false,
"gridPos": {
"h": 3,
"w": 24,
"x": 0,
"y": 0
},
"id": 11,
"maxPerRow": 6,
"options": {
"content": "",
"mode": "html"
},
"pluginVersion": "8.3.2",
"repeat": "node",
"style": {},
"title": "$node",
"type": "text"
},
{
"datasource": {
"uid": "hpc-prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [
{
"options": {
"match": "null",
"result": {
"text": "N/A"
}
},
"type": "special"
}
],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 3,
"w": 24,
"x": 0,
"y": 3
},
"id": 20,
"links": [],
"maxDataPoints": 100,
"options": {
"colorMode": "none",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"mean"
],
"fields": "",
"values": false
},
"textMode": "auto"
},
"pluginVersion": "8.3.2",
"repeat": "node",
"targets": [
{
"expr": "count(node_cpu_seconds_total{instance=~\"$node\", mode=\"system\"}) or count(node_cpu{instance=~\"$node\", mode=\"system\"})",
"instant": true,
"interval": "",
"intervalFactor": 2,
"legendFormat": "",
"metric": "",
"refId": "A",
"step": 14400,
"target": ""
}
],
"title": "CPU Cores",
"type": "stat"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"uid": "hpc-prometheus"
},
"decimals": 3,
"editable": true,
"error": false,
"fill": 10,
"fillGradient": 0,
"grid": {},
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 6
},
"hiddenSeries": false,
"id": 7,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": false,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 0,
"links": [],
"maxPerRow": 6,
"nullPointMode": "connected",
"options": {
"alertThreshold": true
},
"percentage": true,
"pluginVersion": "8.3.2",
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": "node",
"seriesOverrides": [],
"spaceLength": 10,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(node_cpu_seconds_total{mode=\"system\",instance=~'$node'}[5m])) or sum(irate(node_cpu{mode=\"system\",instance=~'$node'}[5m]))",
"interval": "",
"intervalFactor": 2,
"legendFormat": "system",
"metric": "",
"refId": "A",
"step": 1200,
"target": ""
},
{
"expr": "sum(irate(node_cpu_seconds_total{mode=\"user\",instance=~'$node'}[5m])) or sum(irate(node_cpu{mode=\"user\",instance=~'$node'}[5m]))",
"interval": "",
"intervalFactor": 2,
"legendFormat": "user",
"refId": "B",
"step": 1200
},
{
"expr": "sum(irate(node_cpu_seconds_total{mode=\"nice\",instance=~'$node'}[5m])) or sum(irate(node_cpu{mode=\"nice\",instance=~'$node'}[5m]))",
"interval": "",
"intervalFactor": 2,
"legendFormat": "nice",
"refId": "C",
"step": 1200
},
{
"expr": "sum(irate(node_cpu_seconds_total{mode=\"iowait\",instance=~'$node'}[5m])) or sum(irate(node_cpu{mode=\"iowait\",instance=~'$node'}[5m]))",
"interval": "",
"intervalFactor": 2,
"legendFormat": "iowait",
"refId": "E",
"step": 1200
},
{
"expr": "sum(irate(node_cpu_seconds_total{mode=\"steal\",instance=~'$node'}[5m])) or sum(irate(node_cpu{mode=\"steal\",instance=~'$node'}[5m]))",
"intervalFactor": 2,
"legendFormat": "steal",
"refId": "H",
"step": 1200
},
{
"expr": "sum(irate(node_cpu_seconds_total{mode=\"idle\",instance=~'$node'}[5m])) or sum(irate(node_cpu{mode=\"idle\",instance=~'$node'}[5m]))",
"interval": "",
"intervalFactor": 2,
"legendFormat": "idle",
"refId": "D",
"step": 1200
},
{
"expr": "sum(irate(node_cpu_seconds_total{mode=\"irq\",instance=~'$node'}[5m])) or sum(irate(node_cpu{mode=\"irq\",instance=~'$node'}[5m]))",
"interval": "",
"intervalFactor": 2,
"legendFormat": "irq",
"refId": "F",
"step": 1200
},
{
"expr": "sum(irate(node_cpu_seconds_total{mode=\"softirq\",instance=~'$node'}[5m])) or sum(irate(node_cpu{mode=\"softirq\",instance=~'$node'}[5m]))",
"interval": "",
"intervalFactor": 2,
"legendFormat": "softirq",
"refId": "G",
"step": 1200
},
{
"expr": "sum(irate(node_cpu_seconds_total{mode=\"guest\",instance=~'$node'}[5m])) or sum(irate(node_cpu{mode=\"guest\",instance=~'$node'}[5m]))",
"interval": "",
"intervalFactor": 2,
"legendFormat": "guest",
"refId": "I",
"step": 1200
}
],
"thresholds": [
{
"colorMode": "custom",
"fill": true,
"fillColor": "rgba(216, 200, 27, 0.27)",
"op": "gt",
"value": 0
}
],
"timeRegions": [],
"title": "CPU",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"format": "short",
"label": "%",
"logBase": 1,
"max": 100,
"min": 0,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
},
{
"aliasColors": {
"Slab": "#E5A8E2",
"Swap": "#E24D42"
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"uid": "hpc-prometheus"
},
"decimals": 2,
"editable": true,
"error": false,
"fill": 1,
"fillGradient": 0,
"grid": {},
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 13
},
"hiddenSeries": false,
"id": 17,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [],
"maxPerRow": 6,
"nullPointMode": "connected",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "8.3.2",
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": "node",
"seriesOverrides": [
{
"alias": "/Apps|Buffers|Cached|Free|Slab|SwapCached|PageTables|VmallocUsed/",
"fill": 5,
"stack": true
},
{
"alias": "Swap",
"fill": 5,
"stack": true
}
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "( node_memory_MemTotal_bytes{instance=~'$node'} - node_memory_MemFree_bytes{instance=~'$node'} - node_memory_Buffers_bytes{instance=~'$node'} - node_memory_Cached_bytes{instance=~'$node'} - node_memory_SwapCached_bytes{instance=~'$node'} - node_memory_Slab_bytes{instance=~'$node'} - node_memory_PageTables_bytes{instance=~'$node'} - node_memory_VmallocUsed_bytes{instance=~'$node'} ) or ( node_memory_MemTotal{instance=~'$node'} - node_memory_MemFree{instance=~'$node'} - node_memory_Buffers{instance=~'$node'} - node_memory_Cached{instance=~'$node'} - node_memory_SwapCached{instance=~'$node'} - node_memory_Slab{instance=~'$node'} - node_memory_PageTables{instance=~'$node'} - node_memory_VmallocUsed{instance=~'$node'} )",
"interval": "",
"intervalFactor": 2,
"legendFormat": "Apps",
"metric": "",
"refId": "A",
"step": 1200,
"target": ""
},
{
"expr": "node_memory_Buffers_bytes{instance=~'$node'} or node_memory_Buffers{instance=~'$node'}",
"interval": "",
"intervalFactor": 2,
"legendFormat": "Buffers",
"refId": "B",
"step": 1200
},
{
"expr": "node_memory_Cached_bytes{instance=~'$node'} or node_memory_Cached{instance=~'$node'}",
"interval": "",
"intervalFactor": 2,
"legendFormat": "Cached",
"refId": "D",
"step": 1200
},
{
"expr": "node_memory_MemFree_bytes{instance=~'$node'} or node_memory_MemFree{instance=~'$node'}",
"hide": false,
"interval": "",
"intervalFactor": 2,
"legendFormat": "Free",
"refId": "E",
"step": 1200
},
{
"expr": "node_memory_Slab_bytes{instance=~'$node'} or node_memory_Slab{instance=~'$node'}",
"interval": "",
"intervalFactor": 2,
"legendFormat": "Slab",
"refId": "F",
"step": 1200
},
{
"expr": "node_memory_SwapCached_bytes{instance=~'$node'} or node_memory_SwapCached{instance=~'$node'}",
"interval": "",
"intervalFactor": 2,
"legendFormat": "SwapCached",
"refId": "G",
"step": 1200
},
{
"expr": "node_memory_PageTables_bytes{instance=~'$node'} or node_memory_PageTables{instance=~'$node'}",
"interval": "",
"intervalFactor": 2,
"legendFormat": "PageTables",
"refId": "H",
"step": 1200
},
{
"expr": "node_memory_VmallocUsed_bytes{instance=~'$node'} or node_memory_VmallocUsed{instance=~'$node'}",
"interval": "",
"intervalFactor": 2,
"legendFormat": "VmallocUsed",
"metric": "",
"refId": "I",
"step": 1200
},
{
"expr": "(node_memory_SwapTotal_bytes{instance=~'$node'} - node_memory_SwapFree{instance=~'$node'}) or (node_memory_SwapTotal{instance=~'$node'} - node_memory_SwapFree{instance=~'$node'})",
"interval": "",
"intervalFactor": 2,
"legendFormat": "Swap",
"metric": "",
"refId": "C",
"step": 1200
},
{
"expr": "node_memory_Committed_AS_bytes{instance=~'$node'} or node_memory_Committed_AS{instance=~'$node'}",
"interval": "",
"intervalFactor": 2,
"legendFormat": "Committed",
"metric": "",
"refId": "J",
"step": 1200
},
{
"expr": "node_memory_Mapped_bytes{instance=~'$node'} or node_memory_Mapped{instance=~'$node'}",
"interval": "",
"intervalFactor": 2,
"legendFormat": "Mapped",
"refId": "K",
"step": 1200
},
{
"expr": "node_memory_Active_bytes{instance=~'$node'} or node_memory_Active{instance=~'$node'}",
"interval": "",
"intervalFactor": 2,
"legendFormat": "Active",
"metric": "",
"refId": "L",
"step": 1200
},
{
"expr": "node_memory_Inactive_bytes{instance=~'$node'} or node_memory_Inactive{instance=~'$node'}",
"interval": "",
"intervalFactor": 2,
"legendFormat": "Inactive",
"metric": "",
"refId": "M",
"step": 1200
}
],
"thresholds": [],
"timeRegions": [],
"title": "Memory",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"format": "bytes",
"label": "GB",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"uid": "hpc-prometheus"
},
"editable": true,
"error": false,
"fill": 1,
"fillGradient": 0,
"grid": {},
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 20
},
"hiddenSeries": false,
"id": 13,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [],
"maxPerRow": 6,
"nullPointMode": "connected",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "8.3.2",
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": "node",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "node_load1{instance=~\"$node\"}",
"interval": "",
"intervalFactor": 2,
"legendFormat": "load",
"metric": "",
"refId": "A",
"step": 1200,
"target": ""
}
],
"thresholds": [],
"timeRegions": [],
"title": "Load",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 0,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"format": "short",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
},
{
"aliasColors": {},
"bars": false,
"datasource": {
"uid": "hpc-prometheus"
},
"decimals": 3,
"editable": true,
"error": false,
"fill": 1,
"grid": {},
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 27
},
"id": 9,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [],
"maxPerRow": 6,
"nullPointMode": "connected",
"percentage": false,
"pluginVersion": "8.3.2",
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": "node",
"seriesOverrides": [],
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "100.0 - 100 * (node_filesystem_avail_bytes{instance=~'$node',device !~'tmpfs',device!~'by-uuid'} / node_filesystem_size_bytes{instance=~'$node',device !~'tmpfs',device!~'by-uuid'}) or 100.0 - 100 * (node_filesystem_avail{instance=~'$node',device !~'tmpfs',device!~'by-uuid'} / node_filesystem_size{instance=~'$node',device !~'tmpfs',device!~'by-uuid'})",
"interval": "",
"intervalFactor": 2,
"legendFormat": "{{mountpoint}}",
"metric": "",
"refId": "A",
"step": 1200,
"target": ""
}
],
"thresholds": [],
"title": "Disk Space Used",
"tooltip": {
"msResolution": true,
"shared": true,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"show": true
},
"yaxes": [
{
"format": "percent",
"logBase": 1,
"max": 100,
"min": 0,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
]
},
{
"aliasColors": {},
"bars": false,
"datasource": {
"uid": "hpc-prometheus"
},
"editable": true,
"error": false,
"fill": 1,
"grid": {},
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 34
},
"id": 19,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [],
"maxPerRow": 6,
"nullPointMode": "connected",
"percentage": false,
"pluginVersion": "8.3.2",
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": "node",
"seriesOverrides": [],
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "irate(node_disk_io_time_seconds_total{instance=~\"$node\"}[5m])*100 or irate(node_disk_io_time_ms{instance=~\"$node\"}[5m])/10",
"interval": "",
"intervalFactor": 2,
"legendFormat": "{{device}}",
"metric": "",
"refId": "A",
"step": 1200,
"target": ""
}
],
"thresholds": [],
"title": "Disk Utilization per Device",
"tooltip": {
"msResolution": false,
"shared": false,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"show": true
},
"yaxes": [
{
"format": "percent",
"logBase": 1,
"max": 100,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
]
},
{
"aliasColors": {},
"bars": false,
"datasource": {
"uid": "hpc-prometheus"
},
"editable": true,
"error": false,
"fill": 1,
"grid": {},
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 41
},
"id": 14,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [],
"maxPerRow": 6,
"nullPointMode": "connected",
"percentage": false,
"pluginVersion": "8.3.2",
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": "node",
"seriesOverrides": [
{
"alias": "/.*_read$/",
"transform": "negative-Y"
}
],
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "irate(node_disk_reads_completed_total{instance=~'$node'}[5m]) or irate(node_disk_reads_completed{instance=~'$node'}[5m])",
"interval": "",
"intervalFactor": 4,
"legendFormat": "{{device}}_read",
"metric": "",
"refId": "A",
"step": 2400,
"target": ""
},
{
"expr": "irate(node_disk_writes_completed_total{instance=~'$node'}[5m]) or irate(node_disk_writes_completed{instance=~'$node'}[5m])",
"intervalFactor": 2,
"legendFormat": "{{device}}_write",
"metric": "",
"refId": "B",
"step": 1200
}
],
"thresholds": [],
"title": "Disk IOs per Device",
"tooltip": {
"msResolution": false,
"shared": false,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"show": true
},
"yaxes": [
{
"format": "short",
"label": "IO/second read (-) / write (+)",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
]
},
{
"aliasColors": {},
"bars": false,
"datasource": {
"uid": "hpc-prometheus"
},
"editable": true,
"error": false,
"fill": 1,
"grid": {},
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 48
},
"id": 18,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [],
"maxPerRow": 6,
"nullPointMode": "connected",
"percentage": false,
"pluginVersion": "8.3.2",
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": "node",
"seriesOverrides": [
{
"alias": "/.*_read/",
"transform": "negative-Y"
}
],
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "irate(node_disk_read_bytes_total{instance=~'$node'}[5m]) or irate(node_disk_sectors_read{instance=~'$node'}[5m]) * 512",
"interval": "",
"intervalFactor": 4,
"legendFormat": "{{device}}_read",
"refId": "B",
"step": 2400
},
{
"expr": "irate(node_disk_written_bytes_total{instance=~'$node'}[5m]) or irate(node_disk_sectors_written{instance=~'$node'}[5m]) * 512",
"interval": "",
"intervalFactor": 4,
"legendFormat": "{{device}}_write",
"metric": "",
"refId": "A",
"step": 2400,
"target": ""
}
],
"thresholds": [],
"title": "Disk Throughput per Device",
"tooltip": {
"msResolution": false,
"shared": false,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"show": true
},
"yaxes": [
{
"format": "bytes",
"label": "Bytes/second read (-) / write (+)",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
]
},
{
"aliasColors": {},
"bars": false,
"datasource": {
"uid": "hpc-prometheus"
},
"editable": true,
"error": false,
"fill": 1,
"grid": {},
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 55
},
"id": 25,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [],
"maxPerRow": 6,
"nullPointMode": "connected",
"percentage": false,
"pluginVersion": "8.3.2",
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": "node",
"seriesOverrides": [],
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "node_disk_io_now{instance=~\"$node\"}",
"interval": "",
"intervalFactor": 1,
"legendFormat": "{{device}}",
"metric": "",
"refId": "A",
"step": 1200,
"target": ""
}
],
"thresholds": [],
"title": "Disk Queue Length",
"tooltip": {
"msResolution": false,
"shared": true,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"show": true
},
"yaxes": [
{
"format": "short",
"logBase": 1,
"min": 0,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
]
},
{
"aliasColors": {},
"bars": false,
"datasource": {
"uid": "hpc-prometheus"
},
"editable": true,
"error": false,
"fill": 1,
"grid": {},
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 62
},
"id": 22,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [],
"maxPerRow": 6,
"nullPointMode": "connected",
"percentage": false,
"pluginVersion": "8.3.2",
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": "node",
"seriesOverrides": [],
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "irate(node_context_switches_total{instance=~\"$node\"}[5m]) or irate(node_context_switches{instance=~\"$node\"}[5m])",
"interval": "",
"intervalFactor": 2,
"legendFormat": "context switches",
"metric": "",
"refId": "A",
"step": 1200,
"target": ""
}
],
"thresholds": [],
"title": "Context Switches",
"tooltip": {
"msResolution": false,
"shared": true,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"show": true
},
"yaxes": [
{
"format": "short",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
]
},
{
"aliasColors": {},
"bars": false,
"datasource": {
"uid": "hpc-prometheus"
},
"editable": true,
"error": false,
"fill": 1,
"grid": {},
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 69
},
"id": 12,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [],
"maxPerRow": 6,
"nullPointMode": "connected",
"percentage": false,
"pluginVersion": "8.3.2",
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": "node",
"seriesOverrides": [
{
"alias": "/.*_in/",
"transform": "negative-Y"
}
],
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "irate(node_network_receive_bytes_total{instance=~'$node'}[5m])*8 or irate(node_network_receive_bytes{instance=~'$node'}[5m])*8",
"interval": "",
"intervalFactor": 2,
"legendFormat": "{{device}}_in",
"metric": "",
"refId": "A",
"step": 1200,
"target": ""
},
{
"expr": "irate(node_network_transmit_bytes_total{instance=~'$node'}[5m])*8 or irate(node_network_transmit_bytes{instance=~'$node'}[5m])*8",
"interval": "",
"intervalFactor": 2,
"legendFormat": "{{device}}_out",
"refId": "B",
"step": 1200
}
],
"thresholds": [],
"title": "Network Traffic",
"tooltip": {
"msResolution": false,
"shared": true,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"show": true
},
"yaxes": [
{
"format": "bits",
"label": "bits in (-) / bits out (+)",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
]
},
{
"aliasColors": {},
"bars": false,
"datasource": {
"uid": "hpc-prometheus"
},
"editable": true,
"error": false,
"fill": 1,
"grid": {},
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 76
},
"id": 21,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [],
"maxPerRow": 6,
"nullPointMode": "connected",
"percentage": false,
"pluginVersion": "8.3.2",
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": "node",
"seriesOverrides": [],
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "node_netstat_Tcp_CurrEstab{instance=~'$node'}",
"intervalFactor": 2,
"legendFormat": "established",
"refId": "A",
"step": 1200,
"target": ""
}
],
"thresholds": [],
"title": "Netstat",
"tooltip": {
"msResolution": false,
"shared": true,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"show": true
},
"yaxes": [
{
"format": "short",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
]
},
{
"aliasColors": {},
"bars": false,
"datasource": {
"uid": "hpc-prometheus"
},
"editable": true,
"error": false,
"fill": 1,
"grid": {},
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 83
},
"id": 23,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [],
"maxPerRow": 6,
"nullPointMode": "connected",
"percentage": false,
"pluginVersion": "8.3.2",
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": "node",
"seriesOverrides": [
{
"alias": "/.*Out.*/",
"transform": "negative-Y"
},
{
"alias": "Udp_NoPorts",
"yaxis": 2
}
],
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "irate(node_netstat_Udp_InDatagrams{instance=~\"$node\"}[5m])",
"intervalFactor": 2,
"legendFormat": "Udp_InDatagrams",
"refId": "A",
"step": 1200,
"target": ""
},
{
"expr": "irate(node_netstat_Udp_InErrors{instance=~\"$node\"}[5m])",
"intervalFactor": 2,
"legendFormat": "Udp_InErrors",
"refId": "B",
"step": 1200
},
{
"expr": "irate(node_netstat_Udp_OutDatagrams{instance=~\"$node\"}[5m])",
"interval": "",
"intervalFactor": 2,
"legendFormat": "Udp_OutDatagrams",
"refId": "C",
"step": 1200
},
{
"expr": "irate(node_netstat_Udp_NoPorts{instance=~\"$node\"}[5m])",
"intervalFactor": 2,
"legendFormat": "Udp_NoPorts",
"refId": "D",
"step": 1200
}
],
"thresholds": [],
"title": "UDP Stats",
"tooltip": {
"msResolution": false,
"shared": true,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"show": true
},
"yaxes": [
{
"format": "short",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
]
},
{
"aliasColors": {},
"bars": false,
"datasource": {
"uid": "hpc-prometheus"
},
"editable": true,
"error": false,
"fill": 1,
"grid": {},
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 90
},
"id": 24,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [],
"maxPerRow": 6,
"nullPointMode": "connected",
"percentage": false,
"pluginVersion": "8.3.2",
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": "node",
"seriesOverrides": [],
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "node_nf_conntrack_entries_limit{instance=~\"$node\"} - node_nf_conntrack_entries{instance=~\"$node\"}",
"intervalFactor": 2,
"legendFormat": "free",
"refId": "A",
"step": 1200,
"target": ""
}
],
"thresholds": [],
"title": "Conntrack",
"tooltip": {
"msResolution": false,
"shared": true,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"show": true
},
"yaxes": [
{
"format": "short",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
]
}
],
"schemaVersion": 33,
"style": "dark",
"tags": [
"prometheus"
],
"templating": {
"list": [
{
"allFormat": "glob",
"current": {},
"datasource": {
"uid": "hpc-prometheus"
},
"definition": "",
"hide": 0,
"includeAll": false,
"label": "",
"multi": true,
"multiFormat": "regex values",
"name": "node",
"options": [],
"query": {
"query": "label_values(node_exporter_build_info, instance)",
"refId": "hpc-prometheus-node-Variable-Query"
},
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"type": "query"
}
]
},
"time": {
"from": "now-7d",
"to": "now"
},
"timepicker": {
"now": true,
"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": "SLURM - Node Exporter Server Metrics",
"uid": "67UjInAnk",
"version": 1,
"weekStart": ""
}