一键部署 Prometheus + Grafana + Alertmanager 教程（使用 Docker Compose）

1. 安装前准备

确保你已安装以下组件：

# 安装 Docker
curl -fsSL https://get.docker.com | bash

# 安装 Docker Compose
sudo curl -L "https://github.com/docker/compose/releases/download/1.29.2/docker-compose-$(uname -s)-$(uname -m)" \
  -o /usr/local/bin/docker-compose

sudo chmod +x /usr/local/bin/docker-compose
docker-compose --version

2. 创建项目目录结构

mkdir -p ~/prometheus-stack
cd ~/prometheus-stack

mkdir -p prometheus
mkdir -p alertmanager

3. 创建配置文件

nano docker-compose.yml

粘贴以下内容：

version: '3.3'

services:
  prometheus:
    image: prom/prometheus
    container_name: prometheus
    ports:
      - "9090:9090"
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml
      - ./prometheus:/etc/prometheus/rules
    restart: unless-stopped

  grafana:
    image: grafana/grafana-oss
    container_name: grafana
    ports:
      - "3001:3000"
    environment:
      - GF_SECURITY_ADMIN_USER=admin
      - GF_SECURITY_ADMIN_PASSWORD=admin
    volumes:
      - grafana-storage:/var/lib/grafana
    restart: unless-stopped

  alertmanager:
    image: prom/alertmanager
    container_name: alertmanager
    ports:
      - "9093:9093"
    volumes:
      - ./alertmanager.yml:/etc/alertmanager/alertmanager.yml
    command:
      - '--config.file=/etc/alertmanager/alertmanager.yml'
    restart: unless-stopped

volumes:
  grafana-storage:

nano prometheus.yml

内容如下

# my global config
global:
  scrape_interval: 15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
  evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
  # scrape_timeout is set to the global default (10s).

# Alertmanager configuration
alerting:
  alertmanagers:
    - static_configs:
        - targets:
          - "xxxxx:9093"

# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
  - "/etc/prometheus/rules/*.yml"
  # - "first_rules.yml"
  # - "second_rules.yml"

# A scrape configuration containing exactly one endpoint to scrape:
# Here it's Prometheus itself.
scrape_configs:
  # The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
  - job_name: "prometheus"

    # metrics_path defaults to '/metrics'
    # scheme defaults to 'http'.

    static_configs:
      - targets: ["localhost:9090"]
       # The label name is added as a label `label_name=<label_value>` to any timeseries scraped from this config.
        labels:
          app: "prometheus"
  - job_name: "agent_windows"
    static_configs:
      - targets: ["xxxx:9182"]
        labels:
          app: "windows"
          instance: "虚拟机"
  - job_name: "alertmanager"
    static_configs:
      - targets: ["localhost:9093"]
        labels:
          app: "alertmanager"
  - job_name: "node_exporter"
    static_configs:
      - targets: ["xxxx:9100"]
        labels:
           app: "node_exporter"
           instance: "阿里云测试服务器"
  - job_name: "process_exporter"
    static_configs:
      - targets: ["xxxx:9256"]
        labels:
           app: "process"
           instance: "阿里云测试服务器"
  - job_name: 'http_probe'
    metrics_path: /probe
    params:
      module: [http_2xx]
    static_configs:
      - targets:
          - https:XXXXXX
        labels:
          instance: "公司主页"
          app: webapp
      - targets:
          - http://xxxxxxxx:9997/docs#/
        labels:
          instance: "PDF合并"
          app: pdfservice
    relabel_configs:
      - source_labels: [__address__]
        target_label: __param_target
      #- source_labels: [__param_target]
      #  target_label: url   
      # 保留 static_configs 里的 instance 标签，不覆盖
      # 也可以注释掉下一行，避免覆盖instance标签
      # - source_labels: [__param_target]
      #   target_label: instance
      - target_label: __address__
        replacement: xxxxxxx:9115

nano alertmanager.yml

route:
  group_by: ['alertname'] # 按 alertname 标签分组告警（相同告警合并通知）
  group_wait: 30s # 第一次告警延迟30秒再发送，防止太快触发
  group_interval: 5m  # 同一组告警发送间隔至少5分钟（防止频繁通知）
  repeat_interval: 1h # 告警持续存在，重复通知间隔1小时
  receiver: 'webhook_receiver'  # 默认发送接收器名称

receivers:
  - name: 'webhook_receiver'
    webhook_configs:
      - url: 'http://xxxx:5012/alertmanager_to_feishu'
        send_resolved: true 

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

剩下的配置文件就可以添加到prometheus/文件夹下

4. 启动服务

docker-compose up -d