prometheus采集cadvisor数据：
添加cadvisor
root@master:~# vim /usr/local/prometheus/prometheus.yml
  - job_name: 'prometheus--cadvisor'
    static_configs:
    - targets: ['192.168.200.206:8080','192.168.200.207:8080']
重启prometheus：
root@master:~#systemctl restart prometheus
导入镜像
root@master:~# docker load -i cadvisor_v0.33.0.tar.gz 
打标签
root@master:~# docker tag gcr.io/google-containers/cadvisor:v0.33.0 harbor.wyh.net/baseimages/cadvisor:v0.33.0

上传镜像
root@master:~# docker push harbor.wyh.net/baseimages/cadvisor:v0.33.0
启动cadvisor容器：
docker run \
--volume=/:/rootfs:ro \
--volume=/var/run:/var/run:rw \
--volume=/sys:/sys:ro \
--volume=/var/lib/docker/:/var/lib/docker:ro \
--volume=/dev/disk/:/dev/disk:ro \
--publish=8080:8080 \
--detach=true \
--name=cadvisor \
harbor.wyh.net/baseimages/cadvisor:v0.33.0

验证cadvisor web界面：
访问node节点的cadvisor监听端口

image.png

image.png

查看已经监控上了

grafana添加pod监控模板：
395 893 容器模板ID
395模板

image.png

查看pod信息

prometheus报警设置：
prometheus触发一条告警的过程：
prometheus--->触发阈值--->超出持续时间--->alertmanager--->分组|抑制|静默--->媒体类型--->邮件|钉钉|微信
等。

分组(group): 将类似性质的警报合并为单个通知。
静默(silences): 是一种简单的特定时间静音的机制，例如：服务器要升级维护可以先设置这个时间段告警静
默。
抑制(inhibition): 当警报发出后，停止重复发送由此警报引发的其他警报，可以消除冗余告警
解压
root@master2:/usr/local/src# tar xf alertmanager-0.19.0.linux-amd64.tar.gz 
做个软连接
root@master2:/usr/local/src# ln -sv /usr/local/src/alertmanager-0.19.0.linux-amd64 /usr/local/alertmanager
设置启动脚本
root@master2:/usr/local/alertmanager# vim /etc/systemd/system/alertmanager.service
[Unit]
Description=Prometheus Server
Documentation=https://prometheus.io/docs/introduction/overview/
After=network.target
[Service]
Restart=on-faiure
ExecStart=/usr/local/alertmanager/alertmanager --config.file=/usr/local/alertmanager/alertmanager.yml
[Install]
WantedBy=multi-user.target

配置alertmanager：
root@master2:/usr/local/alertmanager# cat alertmanager.yml  | grep ^[^'#']
global:
  resolve_timeout: 5m
  smtp_smarthost: 'smtp.qq.com:465'
  smtp_from: '50589143@qq.com'
  smtp_auth_username: '50589143@qq.com'
  smtp_auth_password: 'pzjypoauatdvcadh'
  smtp_hello: '@qq.com'
  smtp_require_tls: false
route:
  group_by: ['alertname']
  group_wait: 10s
  group_interval: 10s
  repeat_interval: 60s
  receiver: 'web.hook'
receivers:
- name: 'web.hook'
  email_configs:
    - to: '2973707860@qq.com'
inhibit_rules:
  - source_match:
      severity: 'critical'
    target_match:
      severity: 'warning'
    equal: ['alertname', 'dev', 'instance']
重启服务
root@master2:/usr/local/alertmanager# systemctl restart alertmanager
查看端口
root@master2:/usr/local/alertmanager# ss -tnl | grep 9093
LISTEN  0         128                         *:9093                   *:*    
验证是否会报警
root@master2:/usr/local/alertmanager# ./amtool alert --alertmanager.url=http://192.168.200.197:9093
Alertname  Starts At  Summary  
配置prometheus报警规则：
root@master:/etc/ansible# vim /usr/local/prometheus/prometheus.yml
  8 alerting:
  9   alertmanagers:
 10   - static_configs:
 11     - targets:
 12       - 192.168.200.197:9093
 13       # - alertmanager:9093
 14 
 15 # Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
 16 rule_files:
 17   - "/usr/local/prometheus/rule-linux37.yml"

root@master:/etc/ansible# vim /usr/local/prometheus/rule-linux37.yml

groups:
  - name: linux37_pod.rules
    rules:
    - alert: Pod_all_cpu_usage
      expr: (sum by(name)(rate(container_cpu_usage_seconds_total{image!=""}[5m]))*100) > 10
      for: 5m
      labels:
        severity: critical
        service: pods
      annotations:
        description: 容器 {{ $labels.name }} CPU 资源利用率大于 75% , (current value is {{ $value }})
        summary: Dev CPU 负载告警
    - alert: Pod_all_memory_usage
      expr: sort_desc(avg by(name)(irate(container_memory_usage_bytes{name!=""}[5m]))*100) > 1024*10^3*2
      for: 10m
      labels:
        severity: critical
      annotations:
        description: 容器 {{ $labels.name }} Memory 资源利用率大于 2G , (current value is {{ $value }})
        summary: Dev Memory 负载告警
    - alert: Pod_all_network_receive_usage
      expr: sum by (name)(irate(container_network_receive_bytes_total{container_name="POD"}[1m])) > 1024*1024*50
      for: 10m
      labels:
        severity: critical
      annotations:
        description: 容器 {{ $labels.name }} network_receive 资源利用率大于 50M , (current value is {{ $value }})


root@master:/etc/ansible# systemctl restart prometheus

查看状态

调整为5个

然后这个就变成红色的

查看邮件已经发送了

image.png

修改为%25

root@master:/usr/local/prometheus# vim rule-linux37.yml 
 11         description: 容器 {{ $labels.name }} CPU 资源利用率大于 25% , (current value is {{ $value }})
root@master:/usr/local/prometheus# systemctl restart prometheus

停止服务

root@master:/usr/local/prometheus# systemctl stop prometheus
root@master2:~# systemctl stop alertmanager.service 
prometheus监控haproxy：
部署haproxy_exporter：
root@harbor:/usr/local/src# ln -sv /usr/local/src/haproxy_exporter-0.10.0.linux-amd64 /usr/local/harbor_exporter
启动服务
./haproxy_exporter --haproxy.scrape-uri=unix:/run/haproxy/admin.sock

root@master:~# vim /usr/local/prometheus/prometheus.yml
  - job_name: 'prometheus--haproxy'
    static_configs:
    - targets: ['192.168.200.200:9101']

root@master:~# systemctl restart prometheus.service 

查看haproxy的

grafana添加模板

image.png