node-problem-detector.yaml

---
apiVersion: v1
data:
  kernel-monitor.json: |
    {
        "plugin": "kmsg",
        "logPath": "/dev/kmsg",
        "lookback": "5m",
        "bufferSize": 10,
        "source": "kernel-monitor",
        "conditions": [
            {
                "type": "KernelDeadlock",
                "reason": "KernelHasNoDeadlock",
                "message": "kernel has no deadlock"
            },
            {
                "type": "ReadonlyFilesystem",
                "reason": "FilesystemIsNotReadOnly",
                "message": "Filesystem is not read-only"
            }
        ],
        "rules": [
            {
                "type": "temporary",
                "reason": "OOMKilling",
                "pattern": "Kill process \\d+ (.+) score \\d+ or sacrifice child\\nKilled process \\d+ (.+) total-vm:\\d+kB, anon-rss:\\d+kB, file-rss:\\d+kB.*"
            },
            {
                "type": "temporary",
                "reason": "TaskHung",
                "pattern": "task \\S+:\\w+ blocked for more than \\w+ seconds\\."
            },
            {
                "type": "temporary",
                "reason": "UnregisterNetDevice",
                "pattern": "unregister_netdevice: waiting for \\w+ to become free. Usage count = \\d+"
            },
            {
                "type": "temporary",
                "reason": "KernelOops",
                "pattern": "BUG: unable to handle kernel NULL pointer dereference at .*"
            },
            {
                "type": "temporary",
                "reason": "KernelOops",
                "pattern": "divide error: 0000 \\[#\\d+\\] SMP"
            },
            {
    			"type": "temporary",
    			"reason": "MemoryReadError",
    			"pattern": "CE memory read error .*"
            },
            {
                "type": "permanent",
                "condition": "KernelDeadlock",
                "reason": "DockerHung",
                "pattern": "task docker:\\w+ blocked for more than \\w+ seconds\\."
            },
            {
                "type": "permanent",
                "condition": "ReadonlyFilesystem",
                "reason": "FilesystemIsReadOnly",
                "pattern": "Remounting filesystem read-only"
            }
        ]
    }
  docker-monitor.json: |
    {
        "plugin": "journald",
        "pluginConfig": {
            "source": "dockerd"
        },
        "logPath": "/var/log/journal",
        "lookback": "5m",
        "bufferSize": 10,
        "source": "docker-monitor",
        "conditions": [],
        "rules": [
            {
                "type": "temporary",
                "reason": "CorruptDockerImage",
                "pattern": "Error trying v2 registry: failed to register layer: rename /var/lib/docker/image/(.+) /var/lib/docker/image/(.+): directory not empty.*"
            }
        ]
    }
kind: ConfigMap
metadata:
  name: node-problem-detector-config
  namespace: kube-system
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: node-problem-detector
  namespace: kube-system
  labels:
    app: node-problem-detector
spec:
  selector:
    matchLabels:
      app: node-problem-detector
  template:
    metadata:
      labels:
        app: node-problem-detector
    spec:
      affinity:
        nodeAffinity:
          requiredDuringSchedulingIgnoredDuringExecution:
            nodeSelectorTerms:
              - matchExpressions:
                  - key: kubernetes.io/os
                    operator: In
                    values:
                      - linux
      containers:
      - name: node-problem-detector
        command:
        - /node-problem-detector
        - --logtostderr
        - --config.system-log-monitor=/config/kernel-monitor.json,/config/docker-monitor.json
        - --config.custom-plugin-monitor=/config/health-checker-kubelet.json
        image: k8s.gcr.io/node-problem-detector/node-problem-detector:v0.8.6
        resources:
          limits:
            cpu: 10m
            memory: 80Mi
          requests:
            cpu: 10m
            memory: 80Mi
        imagePullPolicy: Always
        securityContext:
          privileged: true
        env:
        - name: NODE_NAME
          valueFrom:
            fieldRef:
              fieldPath: spec.nodeName
        volumeMounts:
        - name: log
          mountPath: /var/log
          readOnly: true
        - name: kmsg
          mountPath: /dev/kmsg
          readOnly: true
        # Make sure node problem detector is in the same timezone
        # with the host.
        - name: localtime
          mountPath: /etc/localtime
          readOnly: true
        - name: config
          mountPath: /config
          readOnly: true
        - mountPath: /etc/machine-id
          name: machine-id
          readOnly: true
        - mountPath: /run/systemd/system
          name: systemd
        - mountPath: /var/run/dbus/
          name: dbus
          mountPropagation: Bidirectional
      volumes:
      - name: log
        # Config `log` to your system log directory
        hostPath:
          path: /var/log/
      - name: kmsg
        hostPath:
          path: /dev/kmsg
      - name: localtime
        hostPath:
          path: /etc/localtime
      - name: config
        configMap:
          name: node-problem-detector-config
          items:
          - key: kernel-monitor.json
            path: kernel-monitor.json
          - key: docker-monitor.json
            path: docker-monitor.json
      - name: machine-id
        hostPath:
          path: /etc/machine-id
          type: "File"
      - name: systemd
        hostPath:
          path: /run/systemd/system/
          type: ""
      - name: dbus
        hostPath:
          path: /var/run/dbus/
          type: ""
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: node-problem-detector
  namespace: kube-system
  labels:
    app: node-problem-detector
spec:
  selector:
    matchLabels:
      app: node-problem-detector
  template:
    metadata:
      labels:
        app: node-problem-detector
    spec:
      affinity:
        nodeAffinity:
          requiredDuringSchedulingIgnoredDuringExecution:
            nodeSelectorTerms:
              - matchExpressions:
                  - key: kubernetes.io/os
                    operator: In
                    values:
                      - linux
      containers:
      - name: node-problem-detector
        command:
        - /node-problem-detector
        - --logtostderr
        - --config.system-log-monitor=/config/kernel-monitor.json,/config/docker-monitor.json
        image: k8s.gcr.io/node-problem-detector/node-problem-detector:v0.8.7
        resources:
          limits:
            cpu: 10m
            memory: 80Mi
          requests:
            cpu: 10m
            memory: 80Mi
        imagePullPolicy: Always
        securityContext:
          privileged: true
        env:
        - name: NODE_NAME
          valueFrom:
            fieldRef:
              fieldPath: spec.nodeName
        volumeMounts:
        - name: log
          mountPath: /var/log
          readOnly: true
        - name: kmsg
          mountPath: /dev/kmsg
          readOnly: true
        # Make sure node problem detector is in the same timezone
        # with the host.
        - name: localtime
          mountPath: /etc/localtime
          readOnly: true
        - name: config
          mountPath: /config
          readOnly: true
      volumes:
      - name: log
        # Config `log` to your system log directory
        hostPath:
          path: /var/log/
      - name: kmsg
        hostPath:
          path: /dev/kmsg
      - name: localtime
        hostPath:
          path: /etc/localtime
      - name: config
        configMap:
          name: node-problem-detector-config
          items:
          - key: kernel-monitor.json
            path: kernel-monitor.json
          - key: docker-monitor.json
            path: docker-monitor.json
      tolerations:
        - effect: NoSchedule
          operator: Exists
        - effect: NoExecute
          operator: Exists