dcgm-exporter-karpenter.yaml

apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: "dcgm-exporter"
  labels:
    app.kubernetes.io/name: "dcgm-exporter"
    app.kubernetes.io/version: "2.6.5"
spec:
  updateStrategy:
    type: RollingUpdate
  selector:
    matchLabels:
      app.kubernetes.io/name: "dcgm-exporter"
      app.kubernetes.io/version: "2.6.5"
  template:
    metadata:
      labels:
        app.kubernetes.io/name: "dcgm-exporter"
        app.kubernetes.io/version: "2.6.5"
      name: "dcgm-exporter"
    spec:
      # nodeSelector:
      # nodeSelector:
      #   accelerator: nvidia-gpu
      # tolerations:
      # - key: "nvidia.com/gpu"
      #   value: "present"
      #   effect: "NoSchedule"
      # ---- Karpenter Scaler ----
      affinity:
        nodeAffinity:
          requiredDuringSchedulingIgnoredDuringExecution:
            nodeSelectorTerms:
            - matchExpressions:
              - key: beta.kubernetes.io/instance-type
                operator: In
                values:
                - p2.xlarge
                - p2.4xlarge
                - p2.8xlarge
                - g4dn.xlarge
      containers:
      - image: "nvcr.io/nvidia/k8s/dcgm-exporter:2.3.5-2.6.5-ubuntu20.04"
        env:
        - name: "DCGM_EXPORTER_LISTEN"
          value: ":9400"
        - name: "DCGM_EXPORTER_KUBERNETES"
          value: "true"
        name: "dcgm-exporter"
        ports:
        - name: "metrics"
          containerPort: 9400
        securityContext:
          runAsNonRoot: false
          runAsUser: 0
        volumeMounts:
        - name: "pod-gpu-resources"
          readOnly: true
          mountPath: "/var/lib/kubelet/pod-resources"
      volumes:
      - name: "pod-gpu-resources"
        hostPath:
          path: "/var/lib/kubelet/pod-resources"
---
kind: Service
apiVersion: v1
metadata:
  name: "dcgm-exporter"
  labels:
    app.kubernetes.io/name: "dcgm-exporter"
    app.kubernetes.io/version: "2.6.5"
spec:
  selector:
    app.kubernetes.io/name: "dcgm-exporter"
    app.kubernetes.io/version: "2.6.5"
  ports:
  - name: "metrics"
    port: 9400
---
apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
  name: "dcgm-exporter"
spec:
  selector:
    matchLabels:
      app.kubernetes.io/name: "dcgm-exporter"
  endpoints:
  - port: "metrics"
  - interval: "15s"