部署

docker-compose.yml

version: '3'

services:
  prometheus:
    image: prom/prometheus:latest
    container_name: prometheus
    hostname: prometheus
    restart: always
    user: "1000:1000"  # 使用适当的用户ID
    volumes:
      - /etc/localtime:/etc/localtime:ro
      - /app/minio/prometheus:/prometheus
      - ./prometheus.yml:/prometheus/prometheus.yml
      - ./prometheus.yml:/etc/prometheus/prometheus.yml
      - ./node_down.yml:/etc/prometheus/node_down.yml
      - ./web.config.yml:/etc/prometheus/web.config.yml  # 挂载认证配置
    ports:
      - "9090:9090"
    command:
      - '--web.config.file=/etc/prometheus/web.config.yml'
      - '--web.enable-remote-write-receiver'

  node-exporter:
    image: node-exporter:latest
    container_name: node-exporter
    hostname: node-exporter
    restart: always
    ports:
      - "9100:9100"

prometheus.yml

global:
  scrape_interval:     15s # 设置间隔15s，默认1分钟.
  evaluation_interval: 15s # 每15秒评估一次规则， 默认1分钟.

 
# 加载规则一次，并根据全局规则定期对其进行评估'evaluation_interval'.
rule_files:
  - "node_down.yml"
  # - "first_rules.yml"
  # - "second_rules.yml"
 
# 监控配置:
scrape_configs:
  - job_name: 'minio1'
    static_configs:
    - targets: ['{ip:port}']

  - job_name: 'minio2'
    scrape_interval: 8s
    static_configs:
    - targets: ['{ip:port}']

node_down.yml

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

web.config.yml

htpasswd -nBC 12 '' | tr -d ':\n'

将生成的密码填入到下方即可

basic_auth_users:
  admin: {passwd}