Prometheus 安装与配置

global:           # 全局默认值（可被各模块覆盖）
scrape_configs:   # 抓取目标定义（最重要）
rule_files:       # 规则文件路径
alerting:         # Alertmanager 配置
remote_write:     # 远程写入（长期存储）
remote_read:      # 远程读取（长期存储）

global:
  scrape_interval: 15s        # 抓取间隔。生产环境建议 15-30s
  scrape_timeout: 10s         # 抓取超时，必须 < scrape_interval
  evaluation_interval: 15s    # 规则评估间隔
  external_labels:            # 所有时间序列的外部标签（联邦/多集群识别）
    cluster: 'us-east-1'
    env: 'production'

scrape_configs:
  - job_name: 'my-service'          # 必填，会作为 job 标签加入每条指标

    # --- 抓取行为 ---
    scrape_interval: 30s            # 覆盖 global
    scrape_timeout: 10s             # 覆盖 global
    metrics_path: /metrics          # 指标路径，默认 /metrics
    scheme: https                   # http 或 https
    sample_limit: 20000             # 单次抓取可接受的样本数上限

    # --- 认证 ---
    basic_auth:
      username: 'admin'
      password_file: '/etc/prometheus/secrets/app-password'
    bearer_token_file: '/var/run/secrets/token'
    tls_config:
      ca_file: '/etc/prometheus/ca.crt'
      cert_file: '/etc/prometheus/client.crt'
      key_file: '/etc/prometheus/client.key'
      insecure_skip_verify: false

    # --- 目标发现（三选一或组合使用）---
    static_configs:                 # 静态列表（最简单）
      - targets: ['host1:8080', 'host2:8080']
        labels:
          env: 'production'
      - targets: ['host3:8080']
        labels:
          env: 'canary'

    # 或使用服务发现（见 05-标签重写与服务发现）
    # kubernetes_sd_configs: [...]
    # consul_sd_configs: [...]
    # file_sd_configs: [...]

    # --- 标签重写 ---
    relabel_configs: [...]          # 抓取前（目标发现标签操作）
    metric_relabel_configs: [...]   # 抓取后（指标标签操作）

global:
  scrape_interval: 30s
  scrape_timeout: 10s
  evaluation_interval: 30s
  external_labels:
    cluster: 'us-east-1'
    env: 'production'

rule_files:
  - '/etc/prometheus/rules/recording.yml'
  - '/etc/prometheus/rules/alerts.yml'

alerting:
  alertmanagers:
    - static_configs:
        - targets: ['alertmanager:9093']

scrape_configs:
  # 1. Prometheus 自监控
  - job_name: 'prometheus'
    scrape_interval: 15s
    static_configs:
      - targets: ['localhost:9090']

  # 2. 节点导出器
  - job_name: 'node'
    scrape_interval: 30s
    static_configs:
      - targets:
          - 'node1.example.com:9100'
          - 'node2.example.com:9100'
          - 'node3.example.com:9100'
        labels:
          dc: 'dc1'

  # 3. 自定义应用
  - job_name: 'backend'
    scrape_interval: 15s
    metrics_path: '/actuator/prometheus'
    scheme: https
    basic_auth:
      username: 'prometheus'
      password_file: '/etc/prometheus/secrets/backend'
    static_configs:
      - targets:
          - 'backend1:8443'
          - 'backend2:8443'

services:
  prometheus:
    image: prom/prometheus:latest
    ports: ["9090:9090"]
    volumes:
      - ./prometheus:/etc/prometheus
      - promdata:/prometheus

  node-exporter:
    image: prom/node-exporter:latest
    network_mode: host
    pid: host
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    command:
      - '--path.procfs=/host/proc'
      - '--path.sysfs=/host/sys'

  blackbox:
    image: prom/blackbox-exporter:latest
    ports: ["9115:9115"]
    volumes:
      - ./blackbox.yml:/etc/blackbox_exporter/config.yml

  alertmanager:
    image: prom/alertmanager:latest
    ports: ["9093:9093"]
    volumes:
      - ./alertmanager.yml:/etc/alertmanager/config.yml

  grafana:
    image: grafana/grafana:latest
    ports: ["3000:3000"]

volumes:
  promdata: {}