# Node Problem Detector 完整部署
# 建立者: Claude Code (首席架構師)
# 日期: 2026-03-28 (台北)
# 用途: 偵測節點問題 (OOM, 磁碟壓力, 內核問題等)

---
apiVersion: v1
kind: Namespace
metadata:
  name: node-problem-detector
  labels:
    app: node-problem-detector

---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: node-problem-detector
  namespace: node-problem-detector

---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  name: node-problem-detector
rules:
- apiGroups: [""]
  resources: ["nodes"]
  verbs: ["get"]
- apiGroups: [""]
  resources: ["nodes/status"]
  verbs: ["patch"]
- apiGroups: [""]
  resources: ["events"]
  verbs: ["create", "patch", "update"]

---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: node-problem-detector
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: node-problem-detector
subjects:
- kind: ServiceAccount
  name: node-problem-detector
  namespace: node-problem-detector

---
apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: node-problem-detector
  namespace: node-problem-detector
  labels:
    app: node-problem-detector
spec:
  selector:
    matchLabels:
      app: node-problem-detector
  template:
    metadata:
      labels:
        app: node-problem-detector
    spec:
      serviceAccountName: node-problem-detector
      containers:
      - name: node-problem-detector
        image: registry.k8s.io/node-problem-detector/node-problem-detector:v0.8.17
        command:
        - /node-problem-detector
        - --logtostderr
        - --config.system-log-monitor=/config/kernel-monitor.json,/config/docker-monitor.json
        resources:
          limits:
            cpu: 100m
            memory: 100Mi
          requests:
            cpu: 20m
            memory: 50Mi
        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
        - name: localtime
          mountPath: /etc/localtime
          readOnly: true
      tolerations:
      - operator: Exists
        effect: NoSchedule
      - operator: Exists
        effect: NoExecute
      volumes:
      - name: log
        hostPath:
          path: /var/log/
      - name: kmsg
        hostPath:
          path: /dev/kmsg
      - name: localtime
        hostPath:
          path: /etc/localtime