使用docker部署并配置grafana+prometheus

---

一、安装docker和docker-compose

root@tjsc:~# apt install docker.io docker-compose -y

完成后可查看docker及docker-compose 版本

root@tjsc:~# docker -v
Docker version 24.0.5, build 24.0.5-0ubuntu1~20.04.1
root@tjsc:~# docker-compose -v
docker-compose version 1.25.0, build unknown

二、容器编排

创建docker-compose.yml文件

root@tjsc:~# touch docker-compose.yml

将下列内容复制到该文件中

version: '2'

services:
  node-exporter:
    image: prom/node-exporter:latest
    container_name: node-exporter
    ports:
      - "9100:9100"
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    restart: always
  prometheus:
    image: prom/prometheus
    container_name: prometheus
    hostname: prometheus
    restart: always
    volumes:
      - ./prometheus/conf/:/etc/prometheus/
    ports:
      - '9090:9090'
  cadvisor:
    image: google/cadvisor:latest
    container_name: cadvisor
    hostname: cadvisor
    restart: always
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:rw
      - /sys:/sys:ro
      - /var/lib/docker/:/var/lib/docker:ro
    ports:
      - '8080:8080'
  grafana:
    image: grafana/grafana:latest
    container_name: grafana
    hostname: grafana
    restart: always
    volumes:
      - ./grafana/grafana-storage:/var/lib/grafana
    ports:
      - '13000:3000'
  alertmanager:
    image: prom/alertmanager:latest
    container_name: alertmanager
    hostname: alertmanager
    restart: always
    volumes:
      - ./prometheus/conf/alertmanager.yml:/etc/alertmanager/alertmanager.yml
      - ./prometheus/template:/etc/alertmanager/template
    ports:
      - '9093:9093'
  blackbox-exporter:
    image: prom/blackbox-exporter:latest
    container_name: blackbox-exporter
    hostname: blackbox-exporter
    restart: always
    ports:
      - '9115:9115'

在同一文件夹下，使用docker-compose up -d 后台启动容器

root@tjsc:~# docker-compose up -d

关闭容器的方法
root@tjsc:~# docker-compose down

二、初始配置

1. 目录结构如下（可自行创建）如docker-compose up -d 命令运行失败或报错，请检查目录权限
   
2. 初始配置，文件位置见图片
   2.1 Prometheus.yml （该文件配置要监控的主机、指定规则文件等）

global:
  scrape_interval:     15s 
  evaluation_interval: 15s 
alerting:       #指定alertmanager报警组件地址
  alertmanagers:
  - static_configs:
    - targets: [ '192.168.136.100:9093']
 
rule_files:  #指定报警规则文件
  - "rules.yml"
 
scrape_configs:
  - job_name: 'nodehost'   
    static_configs:
      - targets: ['192.168.136.100:9100','192.168.136.100:8080']
        labels:
          appname: 'Node1'
  - job_name: 'prometheus'
    static_configs:
      - targets: [ '192.168.136.100:9090']
        labels:
          appname: 'prometheus'
  - job_name: 'prometheus_port_status'
    metrics_path: /probe
    params:
      module: [tcp_connect]
    static_configs:
      - targets: ['192.168.136.100:12345']
        labels:
          instance: 'port_status'
          group: 'tcp'
    relabel_configs:  #此处为blackbox-exporter配置
      - source_labels: [__address__]
        target_label: __param_target
      - source_labels: [__param_target]
        target_label: instance
      - target_label: __address__
        replacement: 192.168.136.100:9115

2.2 rules.yml （该文件配置报警规则）

groups:
- name: example #定义规则组
  rules:
  - alert: InstanceDown  #定义报警名称
    expr: probe_success == 0   #Promql语句，触发规则
    for: 30s           
    labels:       #标签定义报警的级别和主机
      name: instance
      severity: Critical
    annotations: 
      summary: " {{ $labels.appname }}" #报警摘要，取报警信息的appname名称
      description: " 服务停止运行 "   #报警信息
      value: "{{ $value }}%"  # 当前报警状态值

2.3 alertmanager.yml（该文件配置报警方式）

global:
  resolve_timeout: 5m
  wechat_api_url: 'https://qyapi.weixin.qq.com/cgi-bin/'
templates:
- '/etc/alertmanager/template/wechat.tmpl'
route:
  group_by: ['alertname']
  group_wait: 10s
  group_interval: 10s
  repeat_interval: 5m
  receiver: 'wechat'
receivers:
- name: 'wechat'
  wechat_configs:
  - corp_id: <企业ID>    #此处为企业微信的企业ID
    to_party: '1'        #此处为企业微信的部门ID
    agent_id: '1000002'  #此处为企业微信应用的AgentId
    api_secret: <secret> #此处为企业微信应用的secret
    send_resolved: true