tencent cloud

apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: elastic-gpu-exporter
  namespace: kube-system
  labels:
    app: elastic-gpu-exporter
spec:
  updateStrategy:
    type: RollingUpdate
  selector:
    matchLabels:
      name: gpu-manager-ds
      app: nano-gpu-exporter
  template:
    metadata:
      name: elastic-gpu-exporter
      labels:
        name: gpu-manager-ds
        app: nano-gpu-exporter
    spec:
      nodeSelector:
        qgpu-device-enable: enable
      serviceAccount: elastic-gpu-exporter
      hostNetwork: true
      hostPID: true
      hostIPC: true
      containers:
        - image: ccr.ccs.tencentyun.com/tkeimages/elastic-gpu-exporter:v1.0.8
          imagePullPolicy: Always
          args:
            - --node=$(NODE_NAME)
          env:
            - name: "PORT"
              value: "5678"
            - name: "NODE_NAME"
              valueFrom:
                fieldRef:
                  fieldPath: spec.nodeName
          name: elastic-gpu-exporter
          securityContext:
            capabilities:
              add: ["SYS_ADMIN"]
          volumeMounts:
            - name: cgroup
              readOnly: true
              mountPath: "/host/sys"
      volumes:
        - name: cgroup
          hostPath:
            type: Directory
            path: "/sys"
---
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
metadata:
  name: elastic-gpu-exporter
rules:
  - apiGroups:
      - ""
    resources:
      - nodes
    verbs:
      - get
      - list
      - watch
  - apiGroups:
      - ""
    resources:
      - events
    verbs:
      - create
      - patch
  - apiGroups:
      - ""
    resources:
      - pods
    verbs:
      - update
      - patch
      - get
      - list
      - watch
  - apiGroups:
      - ""
    resources:
      - bindings
      - pods/binding
    verbs:
      - create
  - apiGroups:
      - ""
    resources:
      - configmaps
    verbs:
      - get
      - list
      - watch
---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: elastic-gpu-exporter
  namespace: kube-system
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1
metadata:
  name: elastic-gpu-exporter
  namespace: kube-system
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: elastic-gpu-exporter
subjects:
  - kind: ServiceAccount
    name: elastic-gpu-exporter
    namespace: kube-system
---
apiVersion: v1
kind: Service
metadata:
  name: elastic-gpu-exporter
  namespace: kube-system
  annotations:
    prometheus.io/scrape: "true"
  labels:
    kubernetes.io/cluster-service: "true"
spec:
  clusterIP: None
  ports:
    - name: elastic-gpu-exporter
      port: 5678
      protocol: TCP
      targetPort: 5678
  selector:
    app: nano-gpu-exporter


NAME                   DESIRED   CURRENT   READY   UP-TO-DATE   AVAILABLE   NODE SELECTOR   AGE
elastic-gpu-exporter   1         1         1       1            1           <none>          3m36s

NAME                        READY   STATUS    RESTARTS   AGE
elastic-gpu-exporter-dblqm  1/1     Running   0          6s

$ curl NodeIP:5678/metrics

gpu_core_usage{card="0",node="10.0.66.4"} 0

pod_core_usage{namespace="default",node="10.0.66.4",pod="7a2fa737-eef1-4801-8937-493d7efb16b7"} 0

container_gpu_utilization{container="cuda",namespace="default",node="10.0.66.4",pod="cuda"} 0