AlertManager配置示例

# alertmanager.yml

route:
  # When a new group of alerts is created by an incoming alert, wait at
  # least 'group_wait' to send the initial notification.
  # This way ensures that you get multiple alerts for the same group that start
  # firing shortly after another are batched together on the first
  # notification.
  group_wait: 10s

  # When the first notification was sent, wait 'group_interval' to send a batch
  # of new alerts that started firing for that group.
  group_interval: 30s

  # If an alert has successfully been sent, wait 'repeat_interval' to
  # resend them.
  repeat_interval: 30m

  # A default receiver
  receiver: "slack"

  # All the above attributes are inherited by all child routes and can
  # overwritten on each.
  routes:
    - receiver: "slack"
      group_wait: 10s
      match_re:
        severity: critical|warning
      continue: true

    - receiver: "pager"
      group_wait: 10s
      match_re:
        severity: critial
      continue: true

receivers:
  - name: "slack"
    slack_configs:
      - api_url: 'https://hooks.slack.com/services/XXXXXXXXX/XXXXXXXXX/xxxxxxxxxxxxxxxxxxxxxxxxxxx'
        send_resolved: true
        channel: 'monitoring'
        text: "{{ range .Alerts }}<!channel> {{ .Annotations.summary }}\n{{ .Annotations.description }}\n{{ end }}"

  - name: "pager"
    webhook_config:
      - url: http://a.b.c.d:8080/send/sms
        send_resolved: true

故障排除
如果通知的触发时间过长，请检查以下延迟：

scrape_interval = 20s  #(prometheus.yml)
evaluation_interval = 20s  #(prometheus.yml)
increase(mysql_global_status_slow_queries[1m]) > 0  #(alerts/example-mysql.yml)
for: 5m  #(alerts/example-mysql.yml)
group_wait = 10s  #(alertmanager.yml)