node-problem-detector-config.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"
            }
        ]
    }
  readonly-monitor.json: |
    {
        "plugin": "kmsg",
        "logPath": "/dev/kmsg",
        "lookback": "5m",
        "bufferSize": 10,
        "source": "readonly-monitor",
        "metricsReporting": true,
        "conditions": [
            {
                "type": "ReadonlyFilesystem",
                "reason": "FilesystemIsNotReadOnly",
                "message": "Filesystem is not read-only"
            }
        ],
        "rules": [
            {
                "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