docker部署Prometheus

创建prometheus.yml

~]# vim prometheus.yml
global:
  scrape_interval:     60s
  evaluation_interval: 60s
alerting:
  alertmanagers:
  - static_configs:
    - targets: ["localhost:9093"]
rule_files:
  - "/data/docker/prometheus/rule.yml"
scrape_configs:
  - job_name: 'prometheus'
    static_configs:
    - targets: ["localhost:9091"]
  - job_name: 'node-exporter'
    static_configs:
    - targets: ["localhost:9100"]
  - job_name: 'alertmanager'
    static_configs:
    - targets: ["localhost:9093"]

运行Prometheus容器

docker run -d -p 9091:9090 --name prometheus --restart=always -v /data/docker/prometheus/data:/data  -v /data/docker/prometheus/prometheus.yml:/data/prometheus.yml -v /data/docker/prometheus/rule.yml:/data/rule.yml prom/prometheus --config.file=/data/prometheus.yml --web.enable-lifecycle --storage.tsdb.retention=90d

创建rule.yml

# 这里为例方便测试设置为up==1
~]# vim rule.yml 
groups:
- name: Hosts.rules
  rules:
  - alert: HostDown           
    expr: up{job=~"node-exporter|prometheus|grafana|alertmanager"} == 0
    for: 0m
    labels:
      severity: ERROR
    annotations:
      title: 'Instance down'
      summary: "{{$labels.instance}}"
      description: "主机: 【{{ $labels.instance }}】has been down for more than 1 minute"
## 注意==0为报警条件，当有服务宕机测会告警，如果测试需改为1

运行node-exporter容器

docker run -d --name node-exporter --restart=always -p 9100:9100 -v "/proc:/host/proc:ro" -v "/sys:/host/sys:ro" -v "/:/rootfs:ro" prom/node-exporter

创建告警配置文件

global:
  resolve_timeout: 5m 
  smtp_smarthost: 'smtp.qq.com:465'
  smtp_from: '1017096373@qq.com'
  smtp_auth_username: '1017096373@qq.com'  
  smtp_auth_password: 'xfjoexdzymztbjac'  # 注意不是邮件密码
  smtp_require_tls: false
  smtp_hello: 'qq.com'

route:
  group_by: ['alertname']
  group_wait: 5s
  group_interval: 5s
  repeat_interval: 5m
  receiver: 'email'
  
receivers:
  - name: 'email'
    email_configs:
    - to: '1017096373@qq.com'
      send_resolved: true

运行告警容器

docker run -d -p 9093:9093 --restart always --name alertmanager -v /data/docker/prometheus/alertmanager.yml:/etc/alertmanager/alertmanager.yml  prom/alertmanager