# RocketMQ Alert Rules for Prometheus

groups:
  - name: rocketmq
    interval: 30s
    rules:
      # NameServer告警
      - alert: RocketMQNameServerDown
        expr: up{job="rocketmq-namesrv"} == 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "RocketMQ NameServer 实例 {{ $labels.instance }} 宕机"
          description: "RocketMQ NameServer 已经宕机超过1分钟"

      # Broker告警
      - alert: RocketMQBrokerDown
        expr: up{job="rocketmq-broker"} == 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "RocketMQ Broker {{ $labels.instance }} 宕机"
          description: "RocketMQ Broker 已经宕机超过1分钟"

      # 消费堆积告警
      - alert: RocketMQConsumerLag
        expr: rocketmq_consumer_tps > 0 and (rocketmq_consumer_tps - rocketmq_producer_tps) > 1000
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "RocketMQ 消费堆积 - {{ $labels.group }}"
          description: "消费者组 {{ $labels.group }} 在主题 {{ $labels.topic }} 上消费堆积"

      # 生产者发送失败告警
      - alert: RocketMQProducerSendFailed
        expr: rate(rocketmq_producer_send_failed_total[5m]) > 10
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "RocketMQ 生产者发送失败率升高"
          description: "消息发送失败率超过阈值"

      # 内存使用率告警
      - alert: RocketMQMemoryUsageHigh
        expr: (rocketmq_memory_used / rocketmq_memory_total) > 0.85
        for: 10m
        labels:
          severity: warning
        annotations:
          summary: "RocketMQ 内存使用率过高 - {{ $labels.instance }}"
          description: "实例 {{ $labels.instance }} 内存使用率超过85%"

      # 磁盘使用率告警
      - alert: RocketMQDiskUsageHigh
        expr: (rocketmq_disk_used / rocketmq_disk_total) > 0.80
        for: 10m
        labels:
          severity: warning
        annotations:
          summary: "RocketMQ 磁盘使用率过高 - {{ $labels.instance }}"
          description: "实例 {{ $labels.instance }} 磁盘使用率超过80%"