DCGM exporter v3.x emits lowercase metric names (dcgm_gpu_utilization) but dashboards used the old uppercase format (DCGM_FI_DEV_GPU_UTIL). Fixed across 4 dashboard files: - foxhunt-cockpit.json (Infrastructure Cockpit) - foxhunt-training-cockpit.json (Training Cockpit) - foxhunt-gpu-training.json (GPU Training) - gpu-overview.json (GPU Overview) Replaced DCGM_FI_DEV_FB_TOTAL with (dcgm_fb_used + dcgm_fb_free) since DCGM v3 doesn't emit a total metric. Redeployed all dashboard ConfigMaps and restarted Grafana. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
841 lines
19 KiB
JSON
841 lines
19 KiB
JSON
{
|
|
"__inputs": [
|
|
{
|
|
"name": "DS_PROMETHEUS",
|
|
"label": "Prometheus",
|
|
"description": "",
|
|
"type": "datasource",
|
|
"pluginId": "prometheus"
|
|
}
|
|
],
|
|
"id": null,
|
|
"uid": "foxhunt-gpu-overview",
|
|
"title": "GPU Overview",
|
|
"description": "NVIDIA GPU metrics from DCGM exporter: utilization, memory, temperature, power",
|
|
"tags": [
|
|
"gpu",
|
|
"nvidia",
|
|
"dcgm",
|
|
"foxhunt"
|
|
],
|
|
"timezone": "browser",
|
|
"schemaVersion": 39,
|
|
"version": 1,
|
|
"refresh": "15s",
|
|
"time": {
|
|
"from": "now-1h",
|
|
"to": "now"
|
|
},
|
|
"fiscalYearStartMonth": 0,
|
|
"liveNow": false,
|
|
"weekStart": "",
|
|
"templating": {
|
|
"list": [
|
|
{
|
|
"name": "gpu",
|
|
"type": "query",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"query": "label_values(dcgm_gpu_utilization, gpu)",
|
|
"refresh": 2,
|
|
"includeAll": true,
|
|
"multi": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"selected": true,
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"sort": 1
|
|
},
|
|
{
|
|
"name": "instance",
|
|
"type": "query",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"query": "label_values(dcgm_gpu_utilization, instance)",
|
|
"refresh": 2,
|
|
"includeAll": true,
|
|
"multi": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"selected": true,
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"sort": 1
|
|
},
|
|
{
|
|
"name": "namespace",
|
|
"type": "query",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"query": "label_values(dcgm_gpu_utilization, exported_namespace)",
|
|
"refresh": 2,
|
|
"includeAll": true,
|
|
"multi": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"selected": true,
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"sort": 1
|
|
}
|
|
]
|
|
},
|
|
"panels": [
|
|
{
|
|
"id": 1,
|
|
"type": "row",
|
|
"title": "GPU Utilization",
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"collapsed": false,
|
|
"panels": []
|
|
},
|
|
{
|
|
"id": 2,
|
|
"type": "timeseries",
|
|
"title": "GPU Utilization %",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 1
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"fillOpacity": 20,
|
|
"gradientMode": "scheme",
|
|
"spanNulls": false,
|
|
"showPoints": "never",
|
|
"stacking": {
|
|
"mode": "none",
|
|
"group": "A"
|
|
},
|
|
"axisPlacement": "auto",
|
|
"lineWidth": 2
|
|
},
|
|
"unit": "percent",
|
|
"min": 0,
|
|
"max": 100,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 80
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 95
|
|
}
|
|
]
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"mappings": []
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
},
|
|
"legend": {
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"calcs": [
|
|
"mean",
|
|
"max",
|
|
"last"
|
|
]
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "dcgm_gpu_utilization{gpu=~\"$gpu\", instance=~\"$instance\"}",
|
|
"legendFormat": "GPU {{ gpu }} ({{ instance }})"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 3,
|
|
"type": "gauge",
|
|
"title": "Current GPU Utilization",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 1
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "blue",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "green",
|
|
"value": 20
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 80
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 95
|
|
}
|
|
]
|
|
},
|
|
"min": 0,
|
|
"max": 100,
|
|
"unit": "percent",
|
|
"mappings": [],
|
|
"color": {
|
|
"mode": "thresholds"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showThresholdLabels": false,
|
|
"showThresholdMarkers": true,
|
|
"orientation": "auto"
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "dcgm_gpu_utilization{gpu=~\"$gpu\", instance=~\"$instance\"}",
|
|
"legendFormat": "GPU {{ gpu }}",
|
|
"instant": true
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 10,
|
|
"type": "row",
|
|
"title": "GPU Memory",
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 9
|
|
},
|
|
"collapsed": false,
|
|
"panels": []
|
|
},
|
|
{
|
|
"id": 11,
|
|
"type": "timeseries",
|
|
"title": "GPU Memory Used",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 10
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"fillOpacity": 20,
|
|
"gradientMode": "scheme",
|
|
"spanNulls": false,
|
|
"showPoints": "never",
|
|
"stacking": {
|
|
"mode": "none",
|
|
"group": "A"
|
|
},
|
|
"axisPlacement": "auto",
|
|
"lineWidth": 2
|
|
},
|
|
"unit": "decmbytes",
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"mappings": []
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
},
|
|
"legend": {
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"calcs": [
|
|
"mean",
|
|
"max",
|
|
"last"
|
|
]
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "dcgm_fb_used{gpu=~\"$gpu\", instance=~\"$instance\"}",
|
|
"legendFormat": "GPU {{ gpu }} used"
|
|
},
|
|
{
|
|
"refId": "B",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "(dcgm_fb_used{gpu=~\"$gpu\", instance=~\"$instance\"} + dcgm_fb_free{gpu=~\"$gpu\", instance=~\"$instance\"})",
|
|
"legendFormat": "GPU {{ gpu }} total"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 12,
|
|
"type": "gauge",
|
|
"title": "GPU Memory Usage %",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 10
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 70
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 90
|
|
}
|
|
]
|
|
},
|
|
"min": 0,
|
|
"max": 100,
|
|
"unit": "percent",
|
|
"mappings": [],
|
|
"color": {
|
|
"mode": "thresholds"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showThresholdLabels": false,
|
|
"showThresholdMarkers": true,
|
|
"orientation": "auto"
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "(dcgm_fb_used{gpu=~\"$gpu\", instance=~\"$instance\"} / (dcgm_fb_used{gpu=~\"$gpu\", instance=~\"$instance\"} + dcgm_fb_free{gpu=~\"$gpu\", instance=~\"$instance\"})) * 100",
|
|
"legendFormat": "GPU {{ gpu }}",
|
|
"instant": true
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 20,
|
|
"type": "row",
|
|
"title": "GPU Temperature & Power",
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 18
|
|
},
|
|
"collapsed": false,
|
|
"panels": []
|
|
},
|
|
{
|
|
"id": 21,
|
|
"type": "timeseries",
|
|
"title": "GPU Temperature",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 19
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"fillOpacity": 10,
|
|
"gradientMode": "scheme",
|
|
"spanNulls": false,
|
|
"showPoints": "never",
|
|
"stacking": {
|
|
"mode": "none",
|
|
"group": "A"
|
|
},
|
|
"axisPlacement": "auto",
|
|
"lineWidth": 2
|
|
},
|
|
"unit": "celsius",
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "blue",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "green",
|
|
"value": 40
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 75
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 85
|
|
}
|
|
]
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"mappings": []
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
},
|
|
"legend": {
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"calcs": [
|
|
"mean",
|
|
"max",
|
|
"last"
|
|
]
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "dcgm_gpu_temp{gpu=~\"$gpu\", instance=~\"$instance\"}",
|
|
"legendFormat": "GPU {{ gpu }} ({{ instance }})"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 22,
|
|
"type": "timeseries",
|
|
"title": "GPU Power Usage",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 19
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"fillOpacity": 10,
|
|
"gradientMode": "scheme",
|
|
"spanNulls": false,
|
|
"showPoints": "never",
|
|
"stacking": {
|
|
"mode": "none",
|
|
"group": "A"
|
|
},
|
|
"axisPlacement": "auto",
|
|
"lineWidth": 2
|
|
},
|
|
"unit": "watt",
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"mappings": []
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
},
|
|
"legend": {
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"calcs": [
|
|
"mean",
|
|
"max",
|
|
"last"
|
|
]
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "dcgm_power_usage{gpu=~\"$gpu\", instance=~\"$instance\"}",
|
|
"legendFormat": "GPU {{ gpu }} ({{ instance }})"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 30,
|
|
"type": "row",
|
|
"title": "GPU Clocks & Per-Pod Usage",
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 27
|
|
},
|
|
"collapsed": false,
|
|
"panels": []
|
|
},
|
|
{
|
|
"id": 31,
|
|
"type": "timeseries",
|
|
"title": "GPU Memory Clock",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 28
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"fillOpacity": 10,
|
|
"gradientMode": "none",
|
|
"spanNulls": false,
|
|
"showPoints": "never",
|
|
"stacking": {
|
|
"mode": "none",
|
|
"group": "A"
|
|
},
|
|
"axisPlacement": "auto",
|
|
"lineWidth": 2
|
|
},
|
|
"unit": "hertz",
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"mappings": [],
|
|
"custom.transform": "negative-Y"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
},
|
|
"legend": {
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"calcs": [
|
|
"mean",
|
|
"max",
|
|
"last"
|
|
]
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "dcgm_memory_clock{gpu=~\"$gpu\", instance=~\"$instance\"} * 1000000",
|
|
"legendFormat": "GPU {{ gpu }} mem clock"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 32,
|
|
"type": "timeseries",
|
|
"title": "Per-Pod GPU Utilization",
|
|
"description": "GPU utilization broken down by pod. Requires DCGM exporter pod-level labels (exported_pod, exported_namespace).",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 28
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"fillOpacity": 15,
|
|
"gradientMode": "none",
|
|
"spanNulls": false,
|
|
"showPoints": "never",
|
|
"stacking": {
|
|
"mode": "none",
|
|
"group": "A"
|
|
},
|
|
"axisPlacement": "auto",
|
|
"lineWidth": 2
|
|
},
|
|
"unit": "percent",
|
|
"min": 0,
|
|
"max": 100,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"mappings": []
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
},
|
|
"legend": {
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"calcs": [
|
|
"mean",
|
|
"max",
|
|
"last"
|
|
]
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "dcgm_gpu_utilization{exported_namespace=~\"$namespace\", gpu=~\"$gpu\", instance=~\"$instance\"}",
|
|
"legendFormat": "{{ exported_namespace }}/{{ exported_pod }} GPU {{ gpu }}"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"id": 33,
|
|
"type": "timeseries",
|
|
"title": "Per-Pod GPU Memory Used",
|
|
"description": "GPU framebuffer memory used per pod. Requires DCGM exporter pod-level labels.",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 36
|
|
},
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "smooth",
|
|
"fillOpacity": 15,
|
|
"gradientMode": "none",
|
|
"spanNulls": false,
|
|
"showPoints": "never",
|
|
"stacking": {
|
|
"mode": "none",
|
|
"group": "A"
|
|
},
|
|
"axisPlacement": "auto",
|
|
"lineWidth": 2
|
|
},
|
|
"unit": "decmbytes",
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"mappings": []
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
},
|
|
"legend": {
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"calcs": [
|
|
"mean",
|
|
"max",
|
|
"last"
|
|
]
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "dcgm_fb_used{exported_namespace=~\"$namespace\", gpu=~\"$gpu\", instance=~\"$instance\"}",
|
|
"legendFormat": "{{ exported_namespace }}/{{ exported_pod }} GPU {{ gpu }}"
|
|
}
|
|
]
|
|
}
|
|
]
|
|
} |