# 创建配置目录
mkdir -p /opt/prometheus/{config,data,rules}

# 编写配置
cat > /opt/prometheus/config/prometheus.yml <<EOF
global:
  scrape_interval: 15s

scrape_configs:
  - job_name: 'prometheus'
    static_configs:
      - targets: ['localhost:9090']
EOF

# 运行容器
docker run -d \
  --name=prometheus \
  --restart=unless-stopped \
  -p 9090:9090 \
  -v /opt/prometheus/config:/etc/prometheus:ro \
  -v /opt/prometheus/data:/prometheus \
  -v /opt/prometheus/rules:/etc/prometheus/rules:ro \
  prom/prometheus:v2.52.0 \
  --config.file=/etc/prometheus/prometheus.yml \
  --storage.tsdb.retention.time=30d \
  --web.enable-lifecycle

# docker-compose.yml
version: '3.8'

services:
  # Prometheus
  prometheus:
    image: prom/prometheus:v2.52.0
    container_name: prometheus
    restart: unless-stopped
    ports:
      - "9090:9090"
    volumes:
      - ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./prometheus/rules:/etc/prometheus/rules:ro
      - prometheus_data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.retention.time=30d'
      - '--storage.tsdb.retention.size=10GB'
      - '--web.enable-lifecycle'
      - '--web.enable-admin-api'
    networks:
      - monitoring

  # Alertmanager
  alertmanager:
    image: prom/alertmanager:v0.27.0
    container_name: alertmanager
    restart: unless-stopped
    ports:
      - "9093:9093"
    volumes:
      - ./alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
      - alertmanager_data:/alertmanager
    command:
      - '--config.file=/etc/alertmanager/alertmanager.yml'
      - '--storage.path=/alertmanager'
    networks:
      - monitoring

  # Grafana
  grafana:
    image: grafana/grafana:10.4.0
    container_name: grafana
    restart: unless-stopped
    ports:
      - "3000:3000"
    environment:
      - GF_SECURITY_ADMIN_USER=admin
      - GF_SECURITY_ADMIN_PASSWORD=admin
      - GF_USERS_ALLOW_SIGN_UP=false
    volumes:
      - grafana_data:/var/lib/grafana
      - ./grafana/provisioning:/etc/grafana/provisioning:ro
    networks:
      - monitoring

  # Node Exporter
  node-exporter:
    image: prom/node-exporter:v1.7.0
    container_name: node-exporter
    restart: unless-stopped
    ports:
      - "9100:9100"
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    command:
      - '--path.procfs=/host/proc'
      - '--path.sysfs=/host/sys'
      - '--path.rootfs=/rootfs'
      - '--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)'
    networks:
      - monitoring

  # cAdvisor (容器指标)
  cadvisor:
    image: gcr.io/cadvisor/cadvisor:v0.47.2
    container_name: cadvisor
    restart: unless-stopped
    ports:
      - "8080:8080"
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:ro
      - /sys:/sys:ro
      - /var/lib/docker/:/var/lib/docker:ro
      - /dev/disk/:/dev/disk:ro
    privileged: true
    devices:
      - /dev/kmsg
    networks:
      - monitoring

  # Blackbox Exporter
  blackbox-exporter:
    image: prom/blackbox-exporter:v0.24.0
    container_name: blackbox-exporter
    restart: unless-stopped
    ports:
      - "9115:9115"
    volumes:
      - ./blackbox/config.yml:/etc/blackbox_exporter/config.yml:ro
    networks:
      - monitoring

  # Pushgateway
  pushgateway:
    image: prom/pushgateway:v1.7.0
    container_name: pushgateway
    restart: unless-stopped
    ports:
      - "9091:9091"
    networks:
      - monitoring

volumes:
  prometheus_data:
  alertmanager_data:
  grafana_data:

networks:
  monitoring:
    driver: bridge

# prometheus/prometheus.yml
global:
  scrape_interval: 15s
  evaluation_interval: 15s

rule_files:
  - /etc/prometheus/rules/*.yml

alerting:
  alertmanagers:
    - static_configs:
        - targets:
            - alertmanager:9093

scrape_configs:
  - job_name: 'prometheus'
    static_configs:
      - targets: ['prometheus:9090']

  - job_name: 'node'
    static_configs:
      - targets: ['node-exporter:9100']

  - job_name: 'cadvisor'
    static_configs:
      - targets: ['cadvisor:8080']

  - job_name: 'pushgateway'
    honor_labels: true
    static_configs:
      - targets: ['pushgateway:9091']

  - job_name: 'blackbox-http'
    metrics_path: /probe
    params:
      module: [http_2xx]
    static_configs:
      - targets:
          - https://example.com
    relabel_configs:
      - source_labels: [__address__]
        target_label: __param_target
      - source_labels: [__param_target]
        target_label: instance
      - target_label: __address__
        replacement: blackbox-exporter:9115

docker compose up -d
docker compose ps
docker compose logs -f prometheus

# 添加 Helm 仓库
helm repo add prometheus-community https://prometheus-community.github.io/helm-charts
helm repo update

# 安装 kube-prometheus-stack（包含 Prometheus + Grafana + Alertmanager + Exporters）
helm install monitoring prometheus-community/kube-prometheus-stack \
  --namespace monitoring \
  --create-namespace \
  --set prometheus.prometheusSpec.retention=30d \
  --set prometheus.prometheusSpec.storageSpec.volumeClaimTemplate.spec.storageClassName=gp3 \
  --set prometheus.prometheusSpec.storageSpec.volumeClaimTemplate.spec.resources.requests.storage=50Gi \
  --set grafana.adminPassword=admin123

# values.yaml
prometheus:
  prometheusSpec:
    retention: 30d
    resources:
      requests:
        cpu: 500m
        memory: 2Gi
      limits:
        cpu: "2"
        memory: 4Gi
    storageSpec:
      volumeClaimTemplate:
        spec:
          storageClassName: gp3
          resources:
            requests:
              storage: 100Gi
    additionalScrapeConfigs:
      - job_name: 'custom-app'
        kubernetes_sd_configs:
          - role: pod
        relabel_configs:
          - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
            action: keep
            regex: true

alertmanager:
  alertmanagerSpec:
    resources:
      requests:
        cpu: 100m
        memory: 256Mi
    storage:
      volumeClaimTemplate:
        spec:
          storageClassName: gp3
          resources:
            requests:
              storage: 10Gi
  config:
    global:
      resolve_timeout: 5m
    route:
      receiver: 'null'
      routes:
        - match:
            severity: critical
          receiver: 'critical'
    receivers:
      - name: 'null'
      - name: 'critical'
        webhook_configs:
          - url: 'http://webhook:8080/alert'

grafana:
  adminPassword: admin123
  persistence:
    enabled: true
    size: 10Gi
  dashboardProviders:
    dashboardproviders.yaml:
      apiVersion: 1
      providers:
        - name: 'custom'
          folder: 'Custom'
          type: file
          options:
            path: /var/lib/grafana/dashboards/custom
  dashboards:
    custom:
      node-exporter:
        gnetId: 1860
        revision: 33
        datasource: Prometheus

# 安装
helm install monitoring prometheus-community/kube-prometheus-stack \
  -n monitoring \
  -f values.yaml

# 升级
helm upgrade monitoring prometheus-community/kube-prometheus-stack \
  -n monitoring \
  -f values.yaml

# namespace.yml
apiVersion: v1
kind: Namespace
metadata:
  name: monitoring

---
# prometheus-configmap.yml
apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-config
  namespace: monitoring
data:
  prometheus.yml: |
    global:
      scrape_interval: 15s
    rule_files:
      - /etc/prometheus/rules/*.yml
    scrape_configs:
      - job_name: 'kubernetes-pods'
        kubernetes_sd_configs:
          - role: pod
        relabel_configs:
          - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
            action: keep
            regex: true

---
# prometheus-deployment.yml
apiVersion: apps/v1
kind: Deployment
metadata:
  name: prometheus
  namespace: monitoring
spec:
  replicas: 1
  selector:
    matchLabels:
      app: prometheus
  template:
    metadata:
      labels:
        app: prometheus
    spec:
      serviceAccountName: prometheus
      containers:
        - name: prometheus
          image: prom/prometheus:v2.52.0
          ports:
            - containerPort: 9090
          args:
            - '--config.file=/etc/prometheus/prometheus.yml'
            - '--storage.tsdb.retention.time=30d'
            - '--web.enable-lifecycle'
          volumeMounts:
            - name: config
              mountPath: /etc/prometheus
            - name: data
              mountPath: /prometheus
          resources:
            requests:
              cpu: 500m
              memory: 1Gi
            limits:
              cpu: "2"
              memory: 4Gi
      volumes:
        - name: config
          configMap:
            name: prometheus-config
        - name: data
          persistentVolumeClaim:
            claimName: prometheus-data

---
# prometheus-rbac.yml
apiVersion: v1
kind: ServiceAccount
metadata:
  name: prometheus
  namespace: monitoring

---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  name: prometheus
rules:
  - apiGroups: [""]
    resources: ["nodes", "nodes/proxy", "services", "endpoints", "pods"]
    verbs: ["get", "list", "watch"]
  - apiGroups: ["extensions", "networking.k8s.io"]
    resources: ["ingresses"]
    verbs: ["get", "list", "watch"]
  - nonResourceURLs: ["/metrics"]
    verbs: ["get"]

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

---
# prometheus-service.yml
apiVersion: v1
kind: Service
metadata:
  name: prometheus
  namespace: monitoring
spec:
  type: ClusterIP
  selector:
    app: prometheus
  ports:
    - port: 9090
      targetPort: 9090

containers:
  - name: prometheus
    livenessProbe:
      httpGet:
        path: /-/healthy
        port: 9090
      initialDelaySeconds: 30
      periodSeconds: 15
    readinessProbe:
      httpGet:
        path: /-/ready
        port: 9090
      initialDelaySeconds: 10
      periodSeconds: 10

# docker-compose.yml
services:
  prometheus:
    image: prom/prometheus:v2.52.0
    healthcheck:
      test: ["CMD", "wget", "-qO-", "http://localhost:9090/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 30s

volumes:
  prometheus_data:
    driver: local
    driver_opts:
      type: none
      o: bind
      device: /opt/data/prometheus

apiVersion: v1
kind: PersistentVolumeClaim
metadata:
  name: prometheus-data
  namespace: monitoring
spec:
  storageClassName: gp3
  accessModes:
    - ReadWriteOnce
  resources:
    requests:
      storage: 100Gi