taiji-AI-PAD/k8s/monitoring.yaml

apiVersion: apps/v1
kind: Deployment
metadata:
  name: prometheus
  namespace: taiji-ai
  labels:
    app: prometheus
    component: monitoring
spec:
  replicas: 1
  selector:
    matchLabels:
      app: prometheus
  template:
    metadata:
      labels:
        app: prometheus
        component: monitoring
    spec:
      containers:
      - name: prometheus
        image: prom/prometheus:latest
        ports:
        - containerPort: 9090
          name: http
        command:
        - '--config.file=/etc/prometheus/prometheus.yml'
        - '--storage.tsdb.path=/prometheus'
        - '--web.console.libraries=/etc/prometheus/console_libraries'
        - '--web.console.templates=/etc/prometheus/consoles'
        - '--web.enable-lifecycle'
        resources:
          requests:
            memory: "512Mi"
            cpu: "200m"
          limits:
            memory: "2Gi"
            cpu: "1000m"
        volumeMounts:
        - name: prometheus-config
          mountPath: /etc/prometheus/prometheus.yml
          subPath: prometheus.yml
        - name: prometheus-data
          mountPath: /prometheus
      volumes:
      - name: prometheus-config
        configMap:
          name: prometheus-config
      - name: prometheus-data
        persistentVolumeClaim:
          claimName: prometheus-pvc
---
apiVersion: v1
kind: Service
metadata:
  name: prometheus-service
  namespace: taiji-ai
  labels:
    app: prometheus
spec:
  type: ClusterIP
  ports:
  - port: 9090
    targetPort: 9090
    protocol: TCP
    name: http
  selector:
    app: prometheus
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: grafana
  namespace: taiji-ai
  labels:
    app: grafana
    component: monitoring
spec:
  replicas: 1
  selector:
    matchLabels:
      app: grafana
  template:
    metadata:
      labels:
        app: grafana
        component: monitoring
    spec:
      containers:
      - name: grafana
        image: grafana/grafana:latest
        ports:
        - containerPort: 3000
          name: http
        env:
        - name: GF_SECURITY_ADMIN_PASSWORD
          value: "admin"
        resources:
          requests:
            memory: "256Mi"
            cpu: "100m"
          limits:
            memory: "512Mi"
            cpu: "500m"
        volumeMounts:
        - name: grafana-data
          mountPath: /var/lib/grafana
      volumes:
      - name: grafana-data
        persistentVolumeClaim:
          claimName: grafana-pvc
---
apiVersion: v1
kind: Service
metadata:
  name: grafana-service
  namespace: taiji-ai
  labels:
    app: grafana
spec:
  type: ClusterIP
  ports:
  - port: 3000
    targetPort: 3000
    protocol: TCP
    name: http
  selector:
    app: grafana
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
  name: prometheus-pvc
  namespace: taiji-ai
spec:
  accessModes:
    - ReadWriteOnce
  resources:
    requests:
      storage: 50Gi
  storageClassName: managed-premium
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
  name: grafana-pvc
  namespace: taiji-ai
spec:
  accessModes:
    - ReadWriteOnce
  resources:
    requests:
      storage: 10Gi
  storageClassName: managed-premium
---
apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-config
  namespace: taiji-ai
data:
  prometheus.yml: |
    global:
      scrape_interval: 15s
      evaluation_interval: 15s
    
    scrape_configs:
      - job_name: 'mcp-server'
        kubernetes_sd_configs:
          - role: pod
            namespaces:
              names:
                - taiji-ai
        relabel_configs:
          - source_labels: [__meta_kubernetes_pod_label_app]
            action: keep
            regex: mcp-server
          - source_labels: [__meta_kubernetes_pod_ip]
            action: replace
            target_label: __address__
            replacement: $1:8000
      
      - job_name: 'data-ingestion'
        kubernetes_sd_configs:
          - role: pod
            namespaces:
              names:
                - taiji-ai
        relabel_configs:
          - source_labels: [__meta_kubernetes_pod_label_app]
            action: keep
            regex: data-ingestion
          - source_labels: [__meta_kubernetes_pod_ip]
            action: replace
            target_label: __address__
            replacement: $1:8000
      
      - job_name: 'litellm-gateway'
        kubernetes_sd_configs:
          - role: pod
            namespaces:
              names:
                - taiji-ai
        relabel_configs:
          - source_labels: [__meta_kubernetes_pod_label_app]
            action: keep
            regex: litellm-gateway
          - source_labels: [__meta_kubernetes_pod_ip]
            action: replace
            target_label: __address__
            replacement: $1:4000