open-im-server/config/instance-down-rules.yml

groups:
  - name: instance_down
    rules:
      - alert: InstanceDown
        expr: up == 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "Instance {{ $labels.instance }} down"
          description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 1 minutes."

  - name: database_insert_failure_alerts
    rules:
      - alert: DatabaseInsertFailed
        expr: (increase(msg_insert_redis_failed_total[5m]) > 0) or (increase(msg_insert_mongo_failed_total[5m]) > 0)
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "Increase in MsgInsertRedisFailedCounter or MsgInsertMongoFailedCounter detected"
          description: "Either MsgInsertRedisFailedCounter or MsgInsertMongoFailedCounter has increased in the last 5 minutes, indicating failures in message insert operations to Redis or MongoDB,maybe the redis or mongodb is crash."

  - name: registrations_few
    rules:
      - alert: RegistrationsFew
        expr: increase(user_login_total[1h]) == 0
        for: 1m
        labels:
          severity: info
        annotations:
          summary: "Too few registrations within the time frame"
          description: "The number of registrations in the last hour is 0. There might be some issues."

  - name: messages_few
    rules:
      - alert: MessagesFew
        expr: (increase(single_chat_msg_process_success_total[1h])+increase(group_chat_msg_process_success_total[1h])) == 0
        for: 1m
        labels:
          severity: info
        annotations:
          summary: "Too few messages within the time frame"
          description: "The number of messages sent in the last hour is 0. There might be some issues."