Prometheus Alertmanager Grafana 监控警报

Prometheus Alertmanager Grafana 监控警报

#node-exporter, Linux系统信息采集组件
#prometheus , 抓取、储存监控数据,供查询指标
#alertmanager , 发送警报通知
#grafana , web图形展示

#环境 centos7+docker
#单机模式,快速搭建测试环境


#安装node-exporter

 #docker安装方式
docker rm -f node-exporter
docker run -d -p 9100:9100 \
--name node-exporter \
-h $(hostname) \
-v "/proc:/host/proc:ro" \
-v "/sys:/host/sys:ro" \
-v "/:/rootfs:ro" \
--net="host" \
--pid="host" \
--cap-add=SYS_TIME \
  --cpus 0.1 \
  --memory 32M \
  --restart always \
prom/node-exporter \
--path.rootfs /rootfs \
--path.procfs /host/proc \
--path.sysfs /host/sys \
--collector.filesystem.ignored-mount-points "^/(sys|proc|dev|host|etc)($|/)"

 #非docker方式,正式环境推荐
 #curl -s http://files.elven.vip/download/node_exporter.sh |bash
 
 #默认端口9100 可浏览器访问查看文本数据 IP:9100/metrics

#安装prometheus

 ##prometheus配置文件
 # mkdir -p /data/prometheus/
 # vi /data/prometheus/prometheus.yml

 #prometheus.yml
global:
  scrape_interval:     15s # 设定抓取数据的周期,默认为1min
  evaluation_interval: 15s # 设定更新rules文件的周期,默认为1min
  scrape_timeout: 15s      # 设定抓取数据的超时时间,默认为10s

 # Alertmanager配置
alerting:
  alertmanagers:
  - static_configs:
    - targets: ["localhost:9093"]
 # rule配置 
rule_files:
- "/prometheus/rules.*yml"

scrape_configs:
  - job_name: 'node-exporter'
    static_configs:
      - targets: ['localhost:9100']
 ##警告规则
 # vi /data/prometheus/rules.linux.yml

 #rules
groups:
 - name: test-rules
   rules:
   - alert: InstanceDown  #告警名称
     expr: up == 0  #告警判定条件
     for: 3s  #持续多久后,才发送
     labels:  #标签
      team: test
     annotations: ##警报信息
      summary: "{{$labels.instance}}: has been down"
      description: "{{$labels.instance}}: job {{$labels.job}} has been down "
 #启动prometheus
docker rm -f prometheus
Dir=/data/prometheus
docker run -dit \
-u root --restart=always \
-h prometheus  --name prometheus \
--net="host" \
-v /etc/localtime:/etc/localtime:ro \
-v $Dir:/prometheus \
-v $Dir/prometheus.yml:/etc/prometheus/prometheus.yml \
--cpus 0.5 --memory 1024M \
prom/prometheus --web.enable-lifecycle

 #浏览器访问 IP:9090
 #修改配置后 curl -X POST http://localhost:9090/-/reload

#安装alertmanager
 #配置文件
 # mkdir -p /data/prometheus/alertmanager
 # vi /data/prometheus/alertmanager/alertmanager.yml

 # 全局配置项
global:
  resolve_timeout: 5m #超时,默认5min
  #邮箱smtp服务
  smtp_smarthost: 'smtp.qq.com:587'
  smtp_from: 'report@elven.vip'
  smtp_auth_username: 'report@elven.vip'
  smtp_auth_password: 'xxx密码'
  smtp_hello: 'qq.com'

 # 路由
route:
  group_by: ['alertname'] # 报警分组依据
  group_wait: 20s #组等待时间
  group_interval: 20s # 发送前等待时间
  repeat_interval: 10m #重复周期10分钟
  receiver: 'email' # 默认警报接收者

 # 警报接收者
receivers:
- name: 'email' # 警报名称
  email_configs:
  - to: '228@elven.vip'  # 接收警报的email

 #关于email、微信发送模板,后面单独讲
 #启动alertmanager 
docker rm -f alertmanager
Dir=/data/prometheus/alertmanager
docker run -dit \
-u root --restart=always \
-h alertmanager  --name alertmanager \
--net="host" \
-v /etc/localtime:/etc/localtime:ro \
-v $Dir:/alertmanager \
-v $Dir/alertmanager.yml:/etc/alertmanager/alertmanager.yml \
--cpus 0.2 --memory 128M \
prom/alertmanager

 #浏览器访问 IP:9093

#关闭node-exporter测试
# docker stop node-exporter
# netstat -lntp |grep 9100

#查看prometheus点击Alerts查看rules生效
#查看alertmanager是否收到,等待邮件通知……


#grafana
docker rm -f grafana
docker run -dit --name grafana \
-h grafana -u root  \
--restart always \
--cpus 0.2 --memory 128M \
-v /etc/localtime:/etc/localtime:ro \
-v /data/grafana:/var/lib/grafana \
--net="host" \
grafana/grafana

 # 浏览器访问 ip:3000 默认登录用户密码 admin
 #添加数据源Add data sources选 Prometheus 

 #可以参考这个grafana模板
 #https://grafana.com/grafana/dashboards/8919
 #导入 左边+按钮 -> Import -> 8919 -> prometheus选择源 -> Import

posted @ 2019-09-02 00:04 子隐 阅读(...) 评论(...) 编辑 收藏