1.使用二进制方式安装Alertmanager

• 下载安装包

wget https://github.com/prometheus/alertmanager/releases/download/v0.25.0/alertmanager-0.25.0.linux-amd64.tar.gz

• 将安装包解压至/data目录

[root@alert ~]# mkdir /data
[root@alert ~]# tar xf alertmanager-0.25.0.linux-amd64.tar.gz -C /data/
[root@alert ~]# cd /data/
[root@alert data]# ln -s alertmanager-0.25.0.linux-amd64/ alertmanager

• 添加Alertmanager为系统服务

    vi /usr/lib/systemd/system/alertmanager.service 
  

[Unit]
Description=Prometheus Alertmanager Service daemon
After=network.target

[Service]
Type=simple
User=root
Group=root
ExecStart=/data/alertmanager/alertmanager\
          --config.file=/data/alertmanager/alertmanager.yml\
          --storage.path=/data/alertmanager/data/\
          --data.retention=120h\
          --web.external-url=http://192.168.10.5:9093\
          --web.listen-address=:9093
Restart=on-failure

[Install]
WantedBy=multi-user.target

[root@alert system]# systemctl daemon-reload 
[root@alert system]# systemctl start alertmanager
[root@alert system]# systemctl enable alertmanager.service 

• 可以在浏览器查看状态：IP:9093/#/status
  

2.Alertmanager配置

• 修改alertmanager配置文件

    vim /data/alertmanager/alertmanager.yml
  

global:
  resolve_timeout: 5m
  smtp_smarthost: 'smtp.163.com:465'
  smtp_from: '自己邮箱@163.com'
  smtp_auth_username: '自己邮箱@163.com'
  smtp_auth_password: 'PLAPPSJXJCQABYAF'
  smtp_require_tls: false
templates:
  - 'template/*.tmpl'
route:
  group_by: ['alertname']
  group_wait: 30s
  group_interval: 5m
  repeat_interval: 20m
  receiver: 'email'

receivers:
  - name: 'email'
    email_configs:
      - to: '接收人邮箱@qq.com'
        html: '{{ template "test.html" . }}'
        send_resolved: true

注意：上文中的test.hml要和下文define中的名字一样

• 创建告警模板

[root@alert ~]# cd /data/alertmanager
[root@alert alertmanager]# mkdir template
[root@alert alertmanager]# vim test.tmpl

{{ define "test.html" }}
{{- if gt (len .Alerts.Firing) 0 -}}
{{- range $index, $alert := .Alerts -}}
========= ERROR ==========<br>
告警名称：{{ .Labels.alertname }}<br>
告警级别：{{ .Labels.severity }}<br>
告警机器：{{ .Labels.instance }} {{ .Labels.device }}<br>
告警详情：{{ .Annotations.summary }}<br>
告警时间：{{ (.StartsAt.Add 28800e9).Format "2006-01-02 15:04:05" }}<br>
========= END ==========<br>
{{- end }}
{{- end }}
{{- if gt (len .Alerts.Resolved) 0 -}}
{{- range $index, $alert := .Alerts -}}
========= INFO ==========<br>
告警名称：{{ .Labels.alertname }}<br>
告警级别：{{ .Labels.severity }}<br>
告警机器：{{ .Labels.instance }}<br>
告警详情：{{ .Annotations.summary }}<br>
告警时间：{{ (.StartsAt.Add 28800e9).Format "2006-01-02 15:04:05" }}<br>
恢复时间：{{ (.EndsAt.Add 28800e9).Format "2006-01-02 15:04:05" }}<br>
========= END ==========<br>
{{- end }}
{{- end }}
{{- end }}

[root@alert ~]# systemctl restart alertmanager

3.alert接入prometheus

• 修改Prometheus配置文件：prometheus.yml以下内容加入到配置文件的合适位置

alerting:
  alertmanagers:
    - static_configs:
        - targets:
          - 192.168.10.5:9093
rule_files:
  - "/data/prometheus/rules/*_rules.yml"
  
  - job_name: "alertmanager"
    static_configs:
      - targets: ["192.168.10.5:9093"]

4.创建告警配置文件（在prometheus服务器）

• 创建目录

mkdir -p /data/prometheus/rules

• 创建告警规则，以node为例

    vim /data/prometheus/rules/node_rules.yml
  

groups:
  - name: node_status
    rules:
    - alert: status
      expr: up == 0
      for: 1m
      labels:
        severity: critical
      annotations:
        discription: "Node has been down for more than 2 minutes"
        summary: "Node Down"

5.测试告警

• 重启Prometheus服务，关闭一个node节点测试

[root@localhost rules]# systemctl restart prometheus.service

• 此时收到一个node 挂掉的邮件
  

• 将节点恢复，然后会收到一个恢复邮件
  

• 此部分内容为简单实现基于alertmanager的邮件告警。