监控主机和端口06

添加节点监控

[root@10 prometheus]# vim prometheus.yml
- job_name: 'node_exporter_采集器'
    metrics_path: /probe
    params:
      module: [tcp_connect]
    static_configs:
      - targets: ['10.10.0.175:9100']
      - targets: ['10.10.0.176:9100']
      - targets: ['10.10.0.177:9100']
      - targets: ['10.10.0.178:9100']
      - targets: ['10.10.0.179:9100']
      - targets: ['10.10.0.180:9100']
      - targets: ['10.10.0.187:9100']
      - targets: ['10.10.0.186:9100']
      - targets: ['10.10.0.189:9100']
      - targets: ['10.10.0.190:9100']
      - targets: ['10.10.0.188:9100']
      - targets: ['10.10.0.191:9100']
      - targets: ['10.10.0.192:9100']
      - targets: ['10.10.0.193:9100']
      - targets: ['10.10.0.195:9100']
      - targets: ['10.10.0.194:9100']
      - targets: ['10.10.0.196:9100']
      - targets: ['10.10.0.197:9100']
      - targets: ['10.10.0.198:9100']
      - targets: ['10.10.0.199:9100']
      - targets: ['10.10.0.200:9100']
      - targets: ['10.10.0.201:9100']
      - targets: ['10.10.0.202:9100']
      - targets: ['10.10.0.208:9100']
      - targets: ['10.10.0.210:9100']
      - targets: ['10.10.0.208:9100']
      - targets: ['10.10.0.207:9100']
      - targets: ['10.10.0.209:9100']
      - targets: ['10.10.0.212:9100']
      - targets: ['10.10.0.211:9100']
      - targets: ['10.10.0.216:9100']
      - targets: ['10.11.0.217:9100']
      - targets: ['10.10.0.218:9100']
      - targets: ['10.10.0.219:9100']
      - targets: ['10.10.0.220:9100']
      - targets: ['10.10.0.222:9100']
      - targets: ['10.10.0.221:9100']
        labels:
          instance: 'port_status'
          group: 'node_exporter'
    relabel_configs:
      - source_labels: [__address__]
        target_label: __param_target
      - source_labels: [__param_target]
        target_label: instance
      - target_label: __address__
	  replacement: 10.11.0.217:9115

检查配置文件

[root@10 prometheus]# ./promtool check config prometheus.yml
Checking prometheus.yml
  SUCCESS: 1 rule files found
 
Checking rules.yml
  SUCCESS: 14 rules found
 
  [root@10 prometheus]# systemctl reload prometheus.service

报警规则

[root@10 prometheus]# vim rules.yml
groups:
- name: port
  rules:
  - alert: 应用端口监控 # 告警名称
    expr: probe_success == 0 # 告警的判定条件，参考Prometheus高级查询来设定
    for: 1s # 满足告警条件持续时间多久后，才会发送告警
    labels: #标签项
      status: 严重
    annotations: # 解析项，详细解释告警信息
      summary: "group:{{$labels.instance}} High Node port has been down "
      description: "group:{{$labels.instance}} 服务已停止使用 "

检查配置文件

[root@10 prometheus]# ./promtool check config prometheus.yml
Checking prometheus.yml
  SUCCESS: 1 rule files found
 
Checking rules.yml
  SUCCESS: 14 rules found
 
  [root@10 prometheus]# systemctl restart alertmanager.service