搭建监控系统 （Node exporter、Grafana、Prometheus、Alertmanager）

global:                  
  scrape_interval:     15s 
  external_labels:   
    monitor: 'codelab-monitor'
# Alertmanager配置
alerting:
 alertmanagers:
 - static_configs:
   - targets: ["192.168.50.100:9093"] # 设定alertmanager和prometheus交互的接口，即alertmanager监听的ip地址和端口
rule_files: 
  - '/tmp/prometheus/prometheus_rules.yml'
  - '/tmp/prometheus/alertmanager/alertmanager_rules.yml' 
scrape_configs: 
  - job_name: 'prometheus' 
    # 覆盖全局的 scrape_interval
    scrape_interval: 5s
    static_configs:  
      - targets: ['192.168.50.100:9090']
  - job_name: 'node'
    scrape_interval: 10s
    metrics_path: "/metrics"
    static_configs:
      - targets: ['192.168.50.100:9100']  # 本机 node_exporter 的 endpoint 这里若配置成127.0.0.1 会出现gramtheus访问node不通问题

(base) mengfaniaodeMBP:prometheus mengfanxiao$ cat prometheus_rules.yml 
groups:
- name: example   #报警规则的名字
  rules:
  # Alert for any instance that is unreachable for >5 minutes.
  - alert: InstanceDown     #检测job的状态，持续1分钟metrices不能访问会发给altermanager进行报警
    expr: up == 0
    for: 1m    #持续时间
    labels:
      serverity: page
    annotations:
      summary: "Instance {{ $labels.instance }} down"
      description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 5 minutes."
  #- alert: "it's has problem"  #报警的名字
  #  expr: "test_tomcat{exported_instance="uat",exported_job="uat-app-status",host="test",instance="uat",job="uat-apps-status"} -  test_tomcat{exported_instance="uat",exported_job="uat-app-status",host="test",instance="uat",job="uat-apps-status"} offset 1w > 5"   # 这个意思是监控该表达式查询出来的值与一周前的值进行比较，大于5且持续10m钟就发送给altermanager进行报警
  #  for: 1m  #持续时间
  #  labels:
 #     serverity: warning
  #  annotations:
  #    summary: "{{ $labels.type }}趋势增高"
  #    description: "机器:{{ $labels.host }} tomcat_id:{{ $labels.id }} 类型:{{ $labels.type }} 与一周前的差值大于5,当前的差值为:{{ $value }}"    #自定义的报警内容

(base) mengfaniaodeMBP:alermanager mengfanxiao$ cat alertmanager_rules.yml 
groups:
 - name: test-rules
   rules:
   - alert: InstanceDown # 告警名称
     expr: up == 0 # 告警的判定条件，参考Prometheus高级查询来设定
     for: 2m # 满足告警条件持续时间多久后，才会发送告警
     labels: #标签项
      team: node
     annotations: # 解析项，详细解释告警信息
      summary: "{{$labels.instance}}: has been down"
      description: "{{$labels.instance}}: job {{$labels.job}} has been down "
      value: {{$value}}
(base) mengfaniaodeMBP:alermanager mengfanxiao$ ls
alertmanager.ymlalertmanager_rules.ymlconfig.ymltemplate
(base) mengfaniaodeMBP:alermanager mengfanxiao$ 
(base) mengfaniaodeMBP:alermanager mengfanxiao$ cat alertmanager_rules.yml 
groups:
 - name: test-rules
   rules:
   - alert: InstanceDown # 告警名称
     expr: up == 0 # 告警的判定条件，参考Prometheus高级查询来设定
     for: 2m # 满足告警条件持续时间多久后，才会发送告警
     labels: #标签项
      team: node
     annotations: # 解析项，详细解释告警信息
      summary: "{{$labels.instance}}: has been down"
      description: "{{$labels.instance}}: job {{$labels.job}} has been down "
   #   value: {{$value}}

(base) mengfaniaodeMBP:alermanager mengfanxiao$ cat alertmanager.yml 
# 全局配置项
global: 
  resolve_timeout: 5m #处理超时时间，默认为5min
  smtp_smarthost: 'smtp.sina.com:25' # 邮箱smtp服务器代理
  smtp_from: '******@sina.com' # 发送邮箱名称
  smtp_auth_username: '******@sina.com' # 邮箱名称
  smtp_auth_password: '******' # 邮箱密码或授权码
  wechat_api_url: 'https://qyapi.weixin.qq.com/cgi-bin/' # 企业微信地址
# 定义模板信心
templates:
  - 'template/*.tmpl'
# 定义路由树信息
route:
  group_by: ['alertname'] # 报警分组依据
  group_wait: 10s # 最初即第一次等待多久时间发送一组警报的通知
  group_interval: 10s # 在发送新警报前的等待时间
  repeat_interval: 1m # 发送重复警报的周期 对于email配置中，此项不可以设置过低，否则将会由于邮件发送太多频繁，被smtp服务器拒绝
  receiver: 'email' # 发送警报的接收者的名称，以下receivers name的名称
# 定义警报接收者信息
receivers:
  - name: 'email' # 警报
    email_configs: # 邮箱配置
    - to: '******@163.com'  # 接收警报的email配置
      html: '{{ template "test.html" . }}' # 设定邮箱的内容模板
      headers: { Subject: "[WARN] 报警邮件"} # 接收邮件的标题
    # 第三方开发配置
     #webhook_configs: # webhook配置
    #- url: 'http://127.0.0.1:5001'
    #send_resolved: true
    #wechat_configs: # 企业微信报警配置
    #- send_resolved: true
     #to_party: '1' # 接收组的id
      #agent_id: '1000002' # (企业微信-->自定应用-->AgentId)
      #corp_id: '******' # 企业信息(我的企业-->CorpId[在底部])
      #api_secret: '******' # 企业微信(企业微信-->自定应用-->Secret)
      #message: '{{ template "test_wechat.html" . }}' # 发送消息模板的设定
# 一个inhibition规则是在与另一组匹配器匹配的警报存在的条件下，使匹配一组匹配器的警报失效的规则。两个警报必须具有一组相同的标签。 
inhibit_rules: 
  - source_match: 
     severity: 'critical' 
    target_match: 
     severity: 'warning' 
    equal: ['alertname', 'dev', 'instance']

(base) mengfaniaodeMBP:template mengfanxiao$ cat test.tmpl 
{{ define "test.html" }}
<table border="1">
        <tr>
                <td>报警项</td>
                <td>实例</td>
                <td>报警阀值</td>
                <td>开始时间</td>
        </tr>
        {{ range $i, $alert := .Alerts }}
                <tr>
                        <td>{{ index $alert.Labels "alertname" }}</td>
                        <td>{{ index $alert.Labels "instance" }}</td>
                        <td>{{ index $alert.Annotations "value" }}</td>
                        <td>{{ $alert.StartsAt }}</td>
                </tr>
        {{ end }}
</table>
{{ end }}