容器化部署 prometheus/grafana/alertmanager/node_exporter/cadvisor

目录及结构

.
├── alertmanager
│   └── alertmanager.yml
├── docker-compose.yml
├── grafana
│   ├── dashboards
│   └── provisioning
│       └── datasources
│           └── prometheus.yml
├── prometheus
│   ├── prometheus.yml
│   └── rules
│       └── alert.yml

Alertmanager 告警配置

global:
  smtp_smarthost: 'localhost:587'
  smtp_from: '[email protected]'

route:
  group_by: ['alertname']
  group_wait: 10s
  group_interval: 10s
  repeat_interval: 1h
  receiver: 'web.hook'

receivers:
  - name: 'web.hook'
    webhook_configs:
      - url: 'http://127.0.0.1:5001/'

inhibit_rules:
  - source_match:
      severity: 'critical'
    target_match:
      severity: 'warning'
    equal: ['alertname', 'dev', 'instance']

Prometheus 配置文件

global:
  scrape_interval: 15s
  evaluation_interval: 15s

rule_files:
  - "rules/*.yml"

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

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

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

  - job_name: 'grafana'
    static_configs:
      - targets: ['grafana:3000']

  - job_name: 'alertmanager'
    static_configs:
      - targets: ['alertmanager:9093']

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

告警规则 alert.yml

groups:
  - name: node_alerts
    rules:
      - alert: InstanceDown
        expr: up == 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "Instance {{ $labels.instance }} down"
          description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 1 minute."

      - alert: HighCpuUsage
        expr: 100 - (avg by(instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
        for: 2m
        labels:
          severity: warning
        annotations:
          summary: "High CPU usage on {{ $labels.instance }}"
          description: "CPU usage is above 80% for more than 2 minutes on {{ $labels.instance }}"

docker-compose.yml

version: '3.8'

services:
  prometheus:
    image: prom/prometheus:latest
    container_name: prometheus
    restart: unless-stopped
    ports:
      - "9090:9090"
    volumes:
      - ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml
      - ./prometheus/rules:/etc/prometheus/rules
      - prometheus_data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--web.console.libraries=/etc/prometheus/console_libraries'
      - '--web.console.templates=/etc/prometheus/consoles'
      - '--storage.tsdb.retention.time=720h'
      - '--storage.tsdb.min-block-duration=2h'
      - '--storage.tsdb.max-block-duration=2h'
      - '--web.enable-lifecycle'
    networks:
      - monitoring

  alertmanager:
    image: prom/alertmanager:latest
    container_name: alertmanager
    restart: unless-stopped
    ports:
      - "9093:9093"
    volumes:
      - ./alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml
      - alertmanager_data:/alertmanager
    command:
      - '--config.file=/etc/alertmanager/alertmanager.yml'
      - '--storage.path=/alertmanager'
      - '--web.external-url=http://localhost:9093'
    networks:
      - monitoring

  grafana:
    image: grafana/grafana:latest
    container_name: grafana
    restart: unless-stopped
    ports:
      - "3000:3000"
    volumes:
      - grafana_data:/var/lib/grafana
      - ./grafana/provisioning:/etc/grafana/provisioning
      - ./grafana/dashboards:/var/lib/grafana/dashboards
    environment:
      - GF_SECURITY_ADMIN_USER=admin
      - GF_SECURITY_ADMIN_PASSWORD=admin123
      - GF_USERS_ALLOW_SIGN_UP=false
      - GF_INSTALL_PLUGINS=grafana-piechart-panel
    networks:
      - monitoring

  node-exporter:
    image: prom/node-exporter:latest
    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.rootfs=/rootfs'
      - '--path.sysfs=/host/sys'
      - '--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)'
    networks:
      - monitoring

  cadvisor:
    image: gcr.io/cadvisor/cadvisor:latest
    container_name: cadvisor
    restart: unless-stopped
    ports:
      - "8080:8080"
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:rw
      - /sys:/sys:ro
      - /var/lib/docker/:/var/lib/docker:ro
      - /dev/disk/:/dev/disk:ro
    privileged: true
    devices:
      - /dev/kmsg
    networks:
      - monitoring


networks:
  monitoring:
    driver: bridge

volumes:
  prometheus_data:
  grafana_data:
  alertmanager_data: