2442 lines
57 KiB
JSON
2442 lines
57 KiB
JSON
{
|
|
"annotations": {
|
|
"list": [
|
|
{
|
|
"builtIn": 1,
|
|
"datasource": {
|
|
"type": "grafana",
|
|
"uid": "-- Grafana --"
|
|
},
|
|
"enable": true,
|
|
"hide": true,
|
|
"iconColor": "rgba(0, 211, 255, 1)",
|
|
"name": "Annotations & Alerts",
|
|
"type": "dashboard"
|
|
}
|
|
]
|
|
},
|
|
"description": "Comprehensive Slurm monitoring using slurmctld native OpenMetrics endpoint (port 6817). Covers cluster summary, job trends, per-node resources, per-partition status, per-user workloads, and scheduler internals (backfill, RPC latency, threads).",
|
|
"editable": true,
|
|
"fiscalYearStartMonth": 0,
|
|
"graphTooltip": 1,
|
|
"id": null,
|
|
"links": [],
|
|
"panels": [
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"id": 100,
|
|
"panels": [],
|
|
"title": "Cluster Summary",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 1
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 3
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 3,
|
|
"x": 0,
|
|
"y": 1
|
|
},
|
|
"id": 1,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "none",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"percentChangeColorMode": "standard",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showPercentChange": false,
|
|
"textMode": "auto",
|
|
"wideLayout": true
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"expr": "slurm_jobs_running",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Running Jobs",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "orange",
|
|
"value": 1
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 10
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 3,
|
|
"x": 3,
|
|
"y": 1
|
|
},
|
|
"id": 2,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "none",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"percentChangeColorMode": "standard",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showPercentChange": false,
|
|
"textMode": "auto",
|
|
"wideLayout": true
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"expr": "slurm_jobs_pending",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Pending Jobs",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 3,
|
|
"x": 6,
|
|
"y": 1
|
|
},
|
|
"id": 3,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "none",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"percentChangeColorMode": "standard",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showPercentChange": false,
|
|
"textMode": "auto",
|
|
"wideLayout": true
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"expr": "slurm_jobs_cpus_alloc",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Allocated CPUs",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "blue",
|
|
"value": 0
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 3,
|
|
"x": 9,
|
|
"y": 1
|
|
},
|
|
"id": 4,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "none",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"percentChangeColorMode": "standard",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showPercentChange": false,
|
|
"textMode": "auto",
|
|
"wideLayout": true
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"expr": "sum(slurm_node_cpus)",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Total CPUs",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [],
|
|
"max": 1,
|
|
"min": 0,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 0.7
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 0.9
|
|
}
|
|
]
|
|
},
|
|
"unit": "percentunit"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 3,
|
|
"x": 12,
|
|
"y": 1
|
|
},
|
|
"id": 5,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "none",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"percentChangeColorMode": "standard",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showPercentChange": false,
|
|
"textMode": "auto",
|
|
"wideLayout": true
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"expr": "sum(slurm_node_cpus_alloc) / sum(slurm_node_cpus)",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "CPU Utilization",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [],
|
|
"max": 1,
|
|
"min": 0,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 0.7
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 0.9
|
|
}
|
|
]
|
|
},
|
|
"unit": "percentunit"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 3,
|
|
"x": 15,
|
|
"y": 1
|
|
},
|
|
"id": 6,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "none",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"percentChangeColorMode": "standard",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showPercentChange": false,
|
|
"textMode": "auto",
|
|
"wideLayout": true
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"expr": "sum(slurm_node_memory_alloc_bytes) / sum(slurm_node_memory_bytes)",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Memory Utilization",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 3,
|
|
"x": 18,
|
|
"y": 1
|
|
},
|
|
"id": 7,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "none",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"percentChangeColorMode": "standard",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showPercentChange": false,
|
|
"textMode": "auto",
|
|
"wideLayout": true
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"editorMode": "code",
|
|
"expr": "slurm_nodes_idle",
|
|
"legendFormat": "idle",
|
|
"range": true,
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"editorMode": "code",
|
|
"expr": "slurm_nodes_mixed",
|
|
"legendFormat": "mix",
|
|
"range": true,
|
|
"refId": "B"
|
|
},
|
|
{
|
|
"editorMode": "code",
|
|
"expr": "slurm_nodes_alloc",
|
|
"legendFormat": "alloc",
|
|
"range": true,
|
|
"refId": "C"
|
|
},
|
|
{
|
|
"editorMode": "code",
|
|
"expr": "slurm_nodes_down",
|
|
"legendFormat": "down",
|
|
"range": true,
|
|
"refId": "D"
|
|
}
|
|
],
|
|
"title": "Nodes (idle/mix/alloc/down)",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 100
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 3,
|
|
"x": 21,
|
|
"y": 1
|
|
},
|
|
"id": 8,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "none",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"percentChangeColorMode": "standard",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showPercentChange": false,
|
|
"textMode": "auto",
|
|
"wideLayout": true
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"expr": "slurm_slurmdbd_queue_size",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "DBD Queue",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 5
|
|
},
|
|
"id": 101,
|
|
"panels": [],
|
|
"title": "Job Trends",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 20,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 2,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": [
|
|
{
|
|
"matcher": {
|
|
"id": "byName",
|
|
"options": "running"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "color",
|
|
"value": {
|
|
"fixedColor": "green",
|
|
"mode": "fixed"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"matcher": {
|
|
"id": "byName",
|
|
"options": "pending"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "color",
|
|
"value": {
|
|
"fixedColor": "orange",
|
|
"mode": "fixed"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"matcher": {
|
|
"id": "byName",
|
|
"options": "completing"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "color",
|
|
"value": {
|
|
"fixedColor": "blue",
|
|
"mode": "fixed"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 6
|
|
},
|
|
"id": 10,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"expr": "slurm_jobs_running",
|
|
"legendFormat": "running",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "slurm_jobs_pending",
|
|
"legendFormat": "pending",
|
|
"refId": "B"
|
|
},
|
|
{
|
|
"expr": "slurm_jobs_completing",
|
|
"legendFormat": "completing",
|
|
"refId": "C"
|
|
},
|
|
{
|
|
"expr": "slurm_jobs_suspended",
|
|
"legendFormat": "suspended",
|
|
"refId": "D"
|
|
},
|
|
{
|
|
"expr": "slurm_jobs_configuring",
|
|
"legendFormat": "configuring",
|
|
"refId": "E"
|
|
}
|
|
],
|
|
"title": "Job State Trends",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 20,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 2,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 6
|
|
},
|
|
"id": 11,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"expr": "rate(slurm_sdiag_jobs_completed[5m])*60",
|
|
"legendFormat": "completed",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "rate(slurm_sdiag_jobs_started[5m])*60",
|
|
"legendFormat": "started",
|
|
"refId": "B"
|
|
},
|
|
{
|
|
"expr": "rate(slurm_sdiag_jobs_submitted[5m])*60",
|
|
"legendFormat": "submitted",
|
|
"refId": "C"
|
|
},
|
|
{
|
|
"expr": "rate(slurm_sdiag_jobs_failed[5m])*60",
|
|
"legendFormat": "failed",
|
|
"refId": "D"
|
|
},
|
|
{
|
|
"expr": "rate(slurm_sdiag_jobs_canceled[5m])*60",
|
|
"legendFormat": "cancelled",
|
|
"refId": "E"
|
|
}
|
|
],
|
|
"title": "Job Throughput (rate/min)",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 14
|
|
},
|
|
"id": 102,
|
|
"panels": [],
|
|
"title": "Per-Node Resources",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 30,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 2,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 15
|
|
},
|
|
"id": 20,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"expr": "slurm_node_cpus_alloc",
|
|
"legendFormat": "{{node}} (alloc)",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "slurm_node_cpus",
|
|
"legendFormat": "{{node}} (total)",
|
|
"refId": "B"
|
|
}
|
|
],
|
|
"title": "CPU Allocation by Node",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 30,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 2,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
},
|
|
"unit": "bytes"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 15
|
|
},
|
|
"id": 21,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"expr": "slurm_node_memory_alloc_bytes",
|
|
"legendFormat": "{{node}} (alloc)",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "slurm_node_memory_bytes",
|
|
"legendFormat": "{{node}} (total)",
|
|
"refId": "B"
|
|
}
|
|
],
|
|
"title": "Memory Allocation by Node",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 20,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 2,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"max": 1,
|
|
"min": 0,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 0.7
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 0.9
|
|
}
|
|
]
|
|
},
|
|
"unit": "percentunit"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 23
|
|
},
|
|
"id": 22,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"expr": "slurm_node_cpus_alloc / slurm_node_cpus",
|
|
"legendFormat": "{{node}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "CPU Utilization by Node",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 20,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 2,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"max": 1,
|
|
"min": 0,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 0.7
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 0.9
|
|
}
|
|
]
|
|
},
|
|
"unit": "percentunit"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 23
|
|
},
|
|
"id": 23,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"expr": "slurm_node_memory_alloc_bytes / slurm_node_memory_bytes",
|
|
"legendFormat": "{{node}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Memory Utilization by Node",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 31
|
|
},
|
|
"id": 103,
|
|
"panels": [],
|
|
"title": "Per-Partition Status",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 30,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 2,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 8,
|
|
"x": 0,
|
|
"y": 32
|
|
},
|
|
"id": 30,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"expr": "slurm_partition_jobs_running",
|
|
"legendFormat": "{{partition}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Running Jobs by Partition",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 30,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 2,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 8,
|
|
"x": 8,
|
|
"y": 32
|
|
},
|
|
"id": 31,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"expr": "slurm_partition_jobs_pending",
|
|
"legendFormat": "{{partition}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Pending Jobs by Partition",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 30,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 2,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 8,
|
|
"x": 16,
|
|
"y": 32
|
|
},
|
|
"id": 32,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"expr": "slurm_partition_jobs_cpus_alloc",
|
|
"legendFormat": "{{partition}} (alloc)",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "slurm_partition_cpus",
|
|
"legendFormat": "{{partition}} (total)",
|
|
"refId": "B"
|
|
}
|
|
],
|
|
"title": "CPU Allocation by Partition",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 40
|
|
},
|
|
"id": 104,
|
|
"panels": [],
|
|
"title": "Per-User Workloads (DISABLED: not currently scraping /metrics/jobs-users-accts)",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 30,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 2,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "normal"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 41
|
|
},
|
|
"id": 40,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "table",
|
|
"placement": "right",
|
|
"showLegend": true,
|
|
"sortBy": "Last *",
|
|
"sortDesc": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"expr": "slurm_user_jobs_running{job=~\"slurm-native.*\"} > 0",
|
|
"legendFormat": "{{username}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Running Jobs by User",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 30,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 2,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "normal"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 41
|
|
},
|
|
"id": 41,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "table",
|
|
"placement": "right",
|
|
"showLegend": true,
|
|
"sortBy": "Last *",
|
|
"sortDesc": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"expr": "slurm_user_jobs_pending{job=~\"slurm-native.*\"} > 0",
|
|
"legendFormat": "{{username}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Pending Jobs by User",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 30,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 2,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "normal"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 49
|
|
},
|
|
"id": 42,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "table",
|
|
"placement": "right",
|
|
"showLegend": true,
|
|
"sortBy": "Last *",
|
|
"sortDesc": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"expr": "slurm_user_jobs_cpus_alloc{job=~\"slurm-native.*\"} > 0",
|
|
"legendFormat": "{{username}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "CPU Allocation by User",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 30,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 2,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "normal"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
},
|
|
"unit": "bytes"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 49
|
|
},
|
|
"id": 43,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "table",
|
|
"placement": "right",
|
|
"showLegend": true,
|
|
"sortBy": "Last *",
|
|
"sortDesc": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"expr": "slurm_user_jobs_memory_alloc{job=~\"slurm-native.*\"} > 0",
|
|
"legendFormat": "{{username}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Memory Allocation by User",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 57
|
|
},
|
|
"id": 105,
|
|
"panels": [],
|
|
"title": "Scheduler Performance",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 10,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 2,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
},
|
|
"unit": "µs"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 8,
|
|
"x": 0,
|
|
"y": 58
|
|
},
|
|
"id": 50,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"expr": "slurm_sched_mean_cycle",
|
|
"legendFormat": "main scheduler (mean)",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "slurm_schedule_cycle_last",
|
|
"legendFormat": "main scheduler (last)",
|
|
"refId": "B"
|
|
},
|
|
{
|
|
"expr": "slurm_bf_mean_cycle",
|
|
"legendFormat": "backfill (mean)",
|
|
"refId": "C"
|
|
},
|
|
{
|
|
"expr": "slurm_bf_cycle_last",
|
|
"legendFormat": "backfill (last)",
|
|
"refId": "D"
|
|
}
|
|
],
|
|
"title": "Scheduler Cycle Time",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 10,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 2,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 8,
|
|
"x": 8,
|
|
"y": 58
|
|
},
|
|
"id": 51,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"expr": "slurm_schedule_queue_len",
|
|
"legendFormat": "scheduler queue",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "slurm_bf_queue_len",
|
|
"legendFormat": "backfill queue",
|
|
"refId": "B"
|
|
},
|
|
{
|
|
"expr": "slurm_slurmdbd_queue_size",
|
|
"legendFormat": "slurmdbd queue",
|
|
"refId": "C"
|
|
},
|
|
{
|
|
"expr": "slurm_agent_queue_size",
|
|
"legendFormat": "agent queue",
|
|
"refId": "D"
|
|
}
|
|
],
|
|
"title": "Queue Lengths",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 10,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 2,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 8,
|
|
"x": 16,
|
|
"y": 58
|
|
},
|
|
"id": 52,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"expr": "rate(slurm_backfilled_jobs[5m])*60",
|
|
"legendFormat": "backfilled jobs/min",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "rate(slurm_bf_cycle_cnt[5m])*60",
|
|
"legendFormat": "bf cycles/min",
|
|
"refId": "B"
|
|
},
|
|
{
|
|
"expr": "slurm_bf_depth_mean",
|
|
"legendFormat": "bf depth (mean)",
|
|
"refId": "C"
|
|
},
|
|
{
|
|
"expr": "slurm_bf_table_size",
|
|
"legendFormat": "bf table size",
|
|
"refId": "D"
|
|
}
|
|
],
|
|
"title": "Backfill Statistics",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 10,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 2,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
},
|
|
"unit": "µs"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 66
|
|
},
|
|
"id": 53,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"expr": "slurm_sdiag_latency",
|
|
"legendFormat": "sdiag latency",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "RPC Latency",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "tier3-mimir"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"drawStyle": "line",
|
|
"fillOpacity": 10,
|
|
"gradientMode": "none",
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
},
|
|
"insertNulls": false,
|
|
"lineInterpolation": "linear",
|
|
"lineWidth": 2,
|
|
"pointSize": 5,
|
|
"scaleDistribution": {
|
|
"type": "linear"
|
|
},
|
|
"showPoints": "auto",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 66
|
|
},
|
|
"id": 54,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.1.1",
|
|
"targets": [
|
|
{
|
|
"expr": "slurm_server_thread_cnt",
|
|
"legendFormat": "slurmctld threads",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "slurm_agent_thread_cnt",
|
|
"legendFormat": "agent threads",
|
|
"refId": "B"
|
|
},
|
|
{
|
|
"expr": "slurm_agent_cnt",
|
|
"legendFormat": "agents",
|
|
"refId": "C"
|
|
}
|
|
],
|
|
"title": "Thread Count",
|
|
"type": "timeseries"
|
|
}
|
|
],
|
|
"preload": false,
|
|
"refresh": "",
|
|
"schemaVersion": 41,
|
|
"tags": [],
|
|
"templating": {
|
|
"list": []
|
|
},
|
|
"time": {
|
|
"from": "now-6h",
|
|
"to": "now"
|
|
},
|
|
"timepicker": {},
|
|
"timezone": "",
|
|
"title": "Slurm Native OpenMetrics Copy",
|
|
"uid": "cbb59c02-d5be-4375-bb46-0a0c658f239c",
|
|
"version": 1
|
|
}
|