neuron-device-plugin.yaml

# source: https://github.com/aws/aws-neuron-sdk/blob/master/docs/neuron-container-tools/k8s-neuron-device-plugin.yml
# https://kubernetes.io/docs/concepts/extend-kubernetes/compute-storage-net/device-plugins/
apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: neuron-device-plugin-daemonset
  namespace: kube-system
spec:
  selector:
    matchLabels:
      name:  neuron-device-plugin-ds
  updateStrategy:
    type: RollingUpdate
  template:
    metadata:
      annotations:
        scheduler.alpha.kubernetes.io/critical-pod: ""
      labels:
        name: neuron-device-plugin-ds
    spec:
      tolerations:
      - key: CriticalAddonsOnly
        operator: Exists
      - key: aws.amazon.com/neuron
        operator: Exists
        effect: NoSchedule
      # Mark this pod as a critical add-on; when enabled, the critical add-on
      # scheduler reserves resources for critical add-on pods so that they can
      # be rescheduled after a failure.
      # See https://kubernetes.io/docs/tasks/administer-cluster/guaranteed-scheduling-critical-addon-pods/
      priorityClassName: "system-node-critical"
      affinity:
        nodeAffinity:
          requiredDuringSchedulingIgnoredDuringExecution:
            nodeSelectorTerms:
              - matchExpressions:
                  - key: "beta.kubernetes.io/instance-type"
                    operator: In
                    values:
                      - inf1.xlarge
                      - inf1.2xlarge
                      - inf1.6xlarge
                      - inf1.24xlarge
                      - inf2.xlarge
                      - inf2.8xlarge
                      - inf2.24xlarge
                      - inf2.48xlarge
              - matchExpressions:
                  - key: "node.kubernetes.io/instance-type"
                    operator: In
                    values:
                      - inf1.xlarge
                      - inf1.2xlarge
                      - inf1.6xlarge
                      - inf1.24xlarge
                      - inf2.xlarge
                      - inf2.8xlarge
                      - inf2.24xlarge
                      - inf2.48xlarge
      containers:
        - image: 790709498068.dkr.ecr.us-west-2.amazonaws.com/neuron-device-plugin:1.0.9043.0
          imagePullPolicy: Always
          name: k8s-neuron-device-plugin-ctr
          securityContext:
            allowPrivilegeEscalation: false
            capabilities:
              drop: ["ALL"]
          volumeMounts:
            - name: device-plugin
              mountPath: /var/lib/kubelet/device-plugins
      volumes:
        - name: device-plugin
          hostPath:
            path: /var/lib/kubelet/device-plugins