aitsc/k8s/monitoring.yaml

apiVersion: apps/v1
kind: Deployment
metadata:
  name: flask-monitor
  labels:
    app: flask-monitor
spec:
  replicas: 1
  selector:
    matchLabels:
      app: flask-monitor
  template:
    metadata:
      labels:
        app: flask-monitor
    spec:
      containers:
      - name: monitor
        image: flask-prompt-master-monitor:latest
        env:
        - name: APP_URL
          value: "http://flask-prompt-master-service:80"
        - name: MONITOR_INTERVAL
          value: "30"
        resources:
          requests:
            memory: "128Mi"
            cpu: "100m"
          limits:
            memory: "256Mi"
            cpu: "200m"
        volumeMounts:
        - name: logs
          mountPath: /app/logs
        livenessProbe:
          exec:
            command:
            - python
            - -c
            - "import requests; requests.get('$APP_URL/health')"
          initialDelaySeconds: 60
          periodSeconds: 60
      volumes:
      - name: logs
        persistentVolumeClaim:
          claimName: logs-pvc
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: flask-log-manager
  labels:
    app: flask-log-manager
spec:
  replicas: 1
  selector:
    matchLabels:
      app: flask-log-manager
  template:
    metadata:
      labels:
        app: flask-log-manager
    spec:
      containers:
      - name: log-manager
        image: flask-prompt-master-log-manager:latest
        resources:
          requests:
            memory: "64Mi"
            cpu: "50m"
          limits:
            memory: "128Mi"
            cpu: "100m"
        volumeMounts:
        - name: logs
          mountPath: /app/logs
      volumes:
      - name: logs
        persistentVolumeClaim:
          claimName: logs-pvc
---
apiVersion: batch/v1
kind: CronJob
metadata:
  name: log-maintenance
spec:
  schedule: "0 2 * * *"  # 每天凌晨2点执行
  jobTemplate:
    spec:
      template:
        spec:
          containers:
          - name: log-maintenance
            image: flask-prompt-master-log-manager:latest
            command: ["python", "log_manager.py"]
            volumeMounts:
            - name: logs
              mountPath: /app/logs
          volumes:
          - name: logs
            persistentVolumeClaim:
              claimName: logs-pvc
          restartPolicy: OnFailure
---
apiVersion: v1
kind: ConfigMap
metadata:
  name: monitor-config
data:
  monitor-interval: "30"
  alert-threshold: "2.0"
  retention-days: "30"
  max-file-size: "10485760"  # 10MB