nvidia-ds.yaml

  
apiVersion: extensions/v1beta1
kind: DaemonSet
metadata:
  name: nvidia-device-plugin-daemonset
spec:
  updateStrategy:
    type: RollingUpdate
  template:
    metadata:
      # 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.  This annotation works in tandem with the toleration below.
      annotations:
        scheduler.alpha.kubernetes.io/critical-pod: ""
      labels:
        name: nvidia-device-plugin-ds
    spec:
      tolerations:
      # Allow this pod to be rescheduled while the node is in "critical add-ons only" mode.
      # This, along with the annotation above marks this pod as a critical add-on.
      - key: CriticalAddonsOnly
        operator: Exists
      - key: nvidia.com/gpu
        operator: Exists
        effect: NoSchedule
      containers:
      - image: nvidia/k8s-device-plugin:1.0.0-beta
        name: nvidia-device-plugin-ctr
        env:
        # Disable healthchecking as GTX 660 does not support NVML for monitoring
        - name: DP_DISABLE_HEALTHCHECKS
          value: xids
        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

---

# Source: loki-stack/charts/promtail/templates/daemonset.yaml
apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: loki-promtail
  labels:
    app: promtail
    chart: promtail-0.8.0
    release: loki
    heritage: Tiller
  annotations:
    {}

spec:
  selector:
    matchLabels:
      app: promtail
      release: loki
  updateStrategy:
    type: RollingUpdate
  template:
    metadata:
      labels:
        app: promtail
        release: loki
      annotations:
        checksum/config: 5a6e52debf233e73d6641c660ff09b8d41c712b4d4d4821f2314b55922cb1768
        prometheus.io/port: http-metrics
        prometheus.io/scrape: "true"

    spec:
      serviceAccountName: loki-promtail
      containers:
        - name: promtail
          image: "grafana/promtail:v0.1.0"
          imagePullPolicy: IfNotPresent
          args:
            - "-config.file=/etc/promtail/promtail.yaml"
            - "-client.url=http://loki:3100/api/prom/push"
          volumeMounts:
            - name: config
              mountPath: /etc/promtail
            - name: run
              mountPath: /run/promtail
            - mountPath: /var/lib/docker/containers
              name: docker
              readOnly: true
            - mountPath: /var/log/pods
              name: pods
              readOnly: true

          env:
          - name: HOSTNAME
            valueFrom:
              fieldRef:
                fieldPath: spec.nodeName
          ports:
            - containerPort: 3101
              name: http-metrics
          securityContext:
            readOnlyRootFilesystem: true
            runAsGroup: 0
            runAsUser: 0

          readinessProbe:
            failureThreshold: 5
            httpGet:
              path: /ready
              port: http-metrics
            initialDelaySeconds: 10
            periodSeconds: 10
            successThreshold: 1
            timeoutSeconds: 1

          resources:
            {}

      nodeSelector:
        {}

      affinity:
        {}

      tolerations:
        - effect: NoSchedule
          key: node-role.kubernetes.io/master

      volumes:
        - name: config
          configMap:
            name: loki-promtail
        - name: run
          hostPath:
            path: /run/promtail
        - hostPath:
            path: /var/lib/docker/containers
          name: docker
        - hostPath:
            path: /var/log/pods
          name: pods