2025-12-02 13:16:00 -03:00
|
|
|
# services/monitoring/grafana-dashboard-gpu.yaml
|
|
|
|
|
apiVersion: v1
|
|
|
|
|
kind: ConfigMap
|
|
|
|
|
metadata:
|
|
|
|
|
name: grafana-dashboard-gpu
|
|
|
|
|
labels:
|
|
|
|
|
grafana_dashboard: "1"
|
|
|
|
|
data:
|
|
|
|
|
atlas-gpu.json: |
|
|
|
|
|
{
|
|
|
|
|
"uid": "atlas-gpu",
|
|
|
|
|
"title": "Atlas GPU",
|
|
|
|
|
"folderUid": "atlas-internal",
|
|
|
|
|
"editable": true,
|
|
|
|
|
"panels": [
|
|
|
|
|
{
|
|
|
|
|
"id": 1,
|
|
|
|
|
"type": "piechart",
|
2025-12-02 14:41:39 -03:00
|
|
|
"title": "Namespace GPU Share",
|
2025-12-02 13:16:00 -03:00
|
|
|
"datasource": {
|
|
|
|
|
"type": "prometheus",
|
|
|
|
|
"uid": "atlas-vm"
|
|
|
|
|
},
|
|
|
|
|
"gridPos": {
|
|
|
|
|
"h": 8,
|
|
|
|
|
"w": 12,
|
|
|
|
|
"x": 0,
|
|
|
|
|
"y": 0
|
|
|
|
|
},
|
|
|
|
|
"targets": [
|
|
|
|
|
{
|
2025-12-02 20:28:35 -03:00
|
|
|
"expr": "100 * ( ( (sum by (namespace) (max_over_time(DCGM_FI_DEV_GPU_UTIL{namespace!=\"\",pod!=\"\"}[$__range]))) or on(namespace) (sum(rate(container_cpu_usage_seconds_total{namespace!=\"\",pod!=\"\",container!=\"\"}[5m])) by (namespace) * 0) ) and on(namespace) ( (topk(10, ( sum(rate(container_cpu_usage_seconds_total{namespace!=\"\",pod!=\"\",container!=\"\"}[5m])) by (namespace) ) + (sum(container_memory_working_set_bytes{namespace!=\"\",pod!=\"\",container!=\"\"}) by (namespace) / 1e9) + ((sum((kube_pod_container_resource_requests{namespace!=\"\",resource=\"nvidia.com/gpu\"} or kube_pod_container_resource_limits{namespace!=\"\",resource=\"nvidia.com/gpu\"})) by (namespace)) or on(namespace) (sum(rate(container_cpu_usage_seconds_total{namespace!=\"\",pod!=\"\",container!=\"\"}[5m])) by (namespace) * 0) * 100)) >= bool 0) ) ) / clamp_min(sum( ( (sum by (namespace) (max_over_time(DCGM_FI_DEV_GPU_UTIL{namespace!=\"\",pod!=\"\"}[$__range]))) or on(namespace) (sum(rate(container_cpu_usage_seconds_total{namespace!=\"\",pod!=\"\",container!=\"\"}[5m])) by (namespace) * 0) ) and on(namespace) ( (topk(10, ( sum(rate(container_cpu_usage_seconds_total{namespace!=\"\",pod!=\"\",container!=\"\"}[5m])) by (namespace) ) + (sum(container_memory_working_set_bytes{namespace!=\"\",pod!=\"\",container!=\"\"}) by (namespace) / 1e9) + ((sum((kube_pod_container_resource_requests{namespace!=\"\",resource=\"nvidia.com/gpu\"} or kube_pod_container_resource_limits{namespace!=\"\",resource=\"nvidia.com/gpu\"})) by (namespace)) or on(namespace) (sum(rate(container_cpu_usage_seconds_total{namespace!=\"\",pod!=\"\",container!=\"\"}[5m])) by (namespace) * 0) * 100)) >= bool 0) ) ), 1)",
|
2025-12-02 13:16:00 -03:00
|
|
|
"refId": "A",
|
|
|
|
|
"legendFormat": "{{namespace}}"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"fieldConfig": {
|
|
|
|
|
"defaults": {
|
|
|
|
|
"unit": "percent",
|
|
|
|
|
"color": {
|
|
|
|
|
"mode": "palette-classic"
|
|
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
"overrides": []
|
|
|
|
|
},
|
|
|
|
|
"options": {
|
|
|
|
|
"legend": {
|
|
|
|
|
"displayMode": "list",
|
|
|
|
|
"placement": "right"
|
|
|
|
|
},
|
|
|
|
|
"pieType": "pie",
|
|
|
|
|
"displayLabels": [
|
|
|
|
|
"percent"
|
|
|
|
|
],
|
|
|
|
|
"tooltip": {
|
|
|
|
|
"mode": "single"
|
|
|
|
|
},
|
|
|
|
|
"colorScheme": "interpolateSpectral",
|
|
|
|
|
"colorBy": "value",
|
|
|
|
|
"reduceOptions": {
|
|
|
|
|
"calcs": [
|
|
|
|
|
"lastNotNull"
|
|
|
|
|
],
|
|
|
|
|
"fields": "",
|
|
|
|
|
"values": false
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"id": 2,
|
|
|
|
|
"type": "timeseries",
|
2025-12-02 14:41:39 -03:00
|
|
|
"title": "GPU Util by Namespace",
|
2025-12-02 13:16:00 -03:00
|
|
|
"datasource": {
|
|
|
|
|
"type": "prometheus",
|
|
|
|
|
"uid": "atlas-vm"
|
|
|
|
|
},
|
|
|
|
|
"gridPos": {
|
|
|
|
|
"h": 8,
|
|
|
|
|
"w": 12,
|
|
|
|
|
"x": 12,
|
|
|
|
|
"y": 0
|
|
|
|
|
},
|
|
|
|
|
"targets": [
|
|
|
|
|
{
|
|
|
|
|
"expr": "sum(DCGM_FI_DEV_GPU_UTIL{namespace!=\"\",pod!=\"\"}) by (namespace)",
|
|
|
|
|
"refId": "A",
|
|
|
|
|
"legendFormat": "{{namespace}}"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"fieldConfig": {
|
|
|
|
|
"defaults": {
|
|
|
|
|
"unit": "percent"
|
|
|
|
|
},
|
|
|
|
|
"overrides": []
|
|
|
|
|
},
|
|
|
|
|
"options": {
|
|
|
|
|
"legend": {
|
|
|
|
|
"displayMode": "table",
|
|
|
|
|
"placement": "right"
|
|
|
|
|
},
|
|
|
|
|
"tooltip": {
|
|
|
|
|
"mode": "multi"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"id": 3,
|
|
|
|
|
"type": "timeseries",
|
2025-12-02 14:41:39 -03:00
|
|
|
"title": "GPU Util by Node",
|
2025-12-02 13:16:00 -03:00
|
|
|
"datasource": {
|
|
|
|
|
"type": "prometheus",
|
|
|
|
|
"uid": "atlas-vm"
|
|
|
|
|
},
|
|
|
|
|
"gridPos": {
|
|
|
|
|
"h": 8,
|
|
|
|
|
"w": 12,
|
|
|
|
|
"x": 0,
|
|
|
|
|
"y": 8
|
|
|
|
|
},
|
|
|
|
|
"targets": [
|
|
|
|
|
{
|
|
|
|
|
"expr": "sum by (Hostname) (DCGM_FI_DEV_GPU_UTIL{pod!=\"\"})",
|
|
|
|
|
"refId": "A",
|
|
|
|
|
"legendFormat": "{{Hostname}}"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"fieldConfig": {
|
|
|
|
|
"defaults": {
|
|
|
|
|
"unit": "percent"
|
|
|
|
|
},
|
|
|
|
|
"overrides": []
|
|
|
|
|
},
|
|
|
|
|
"options": {
|
|
|
|
|
"legend": {
|
|
|
|
|
"displayMode": "table",
|
|
|
|
|
"placement": "right"
|
|
|
|
|
},
|
|
|
|
|
"tooltip": {
|
|
|
|
|
"mode": "multi"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"id": 4,
|
|
|
|
|
"type": "table",
|
2025-12-02 14:41:39 -03:00
|
|
|
"title": "Top Pods by GPU Util",
|
2025-12-02 13:16:00 -03:00
|
|
|
"datasource": {
|
|
|
|
|
"type": "prometheus",
|
|
|
|
|
"uid": "atlas-vm"
|
|
|
|
|
},
|
|
|
|
|
"gridPos": {
|
|
|
|
|
"h": 8,
|
|
|
|
|
"w": 12,
|
|
|
|
|
"x": 12,
|
|
|
|
|
"y": 8
|
|
|
|
|
},
|
|
|
|
|
"targets": [
|
|
|
|
|
{
|
|
|
|
|
"expr": "topk(10, sum(DCGM_FI_DEV_GPU_UTIL{pod!=\"\"}) by (namespace,pod,Hostname))",
|
|
|
|
|
"refId": "A"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"fieldConfig": {
|
|
|
|
|
"defaults": {
|
|
|
|
|
"unit": "percent"
|
|
|
|
|
},
|
|
|
|
|
"overrides": []
|
|
|
|
|
},
|
|
|
|
|
"options": {
|
|
|
|
|
"showHeader": true
|
|
|
|
|
},
|
|
|
|
|
"transformations": [
|
|
|
|
|
{
|
|
|
|
|
"id": "labelsToFields",
|
|
|
|
|
"options": {}
|
|
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"time": {
|
|
|
|
|
"from": "now-12h",
|
|
|
|
|
"to": "now"
|
|
|
|
|
},
|
|
|
|
|
"annotations": {
|
|
|
|
|
"list": []
|
|
|
|
|
},
|
|
|
|
|
"schemaVersion": 39,
|
|
|
|
|
"style": "dark",
|
|
|
|
|
"tags": [
|
|
|
|
|
"atlas",
|
|
|
|
|
"gpu"
|
|
|
|
|
]
|
|
|
|
|
}
|