example.rules

###
# Sample prometheus rules/alerts for rocketmq.
#
# NOTE: Please review these carefully as thresholds and behavior may not meet
#       your SLOs or labels.
#

###
# Recording Rules


###
# Galera Alerts

groups:
- name: GaleraAlerts
  rules:
  - alert: RocketMQClusterProduceHigh
    expr: sum(rocketmq_producer_tps) by (cluster) >= 10
    for: 3m
    labels:
      severity: warning
    annotations:
      description: '{{$labels.cluster}} Sending tps too high.'
      summary: cluster send tps too high
  - alert: RocketMQClusterProduceLow
    expr: sum(rocketmq_producer_tps) by (cluster) < 1
    for: 3m
    labels:
      severity: warning
    annotations:
      description: '{{$labels.cluster}} Sending tps too low.'
      summary: cluster send tps too low
  - alert: RocketMQClusterConsumeHigh
    expr: sum(rocketmq_consumer_tps) by (cluster) >= 10
    for: 3m
    labels:
      severity: warning
    annotations:
      description: '{{$labels.cluster}} consuming tps too high.'
      summary: cluster consume tps too high
  - alert: RocketMQClusterConsumeLow
    expr: sum(rocketmq_consumer_tps) by (cluster) < 1
    for: 3m
    labels:
      severity: warning
    annotations:
      description: '{{$labels.cluster}} consuming tps too low.'
      summary: cluster consume tps too low
  - alert: ConsumerFallingBehind
    expr: (sum(rocketmq_producer_offset) by (topic) - on(topic)  group_right  sum(rocketmq_consumer_offset) by (group,topic)) - ignoring(group) group_left sum (avg_over_time(rocketmq_producer_tps[5m])) by (topic)*5*60 > 0
    for: 3m
    labels:
      severity: warning
    annotations:
      description: 'consumer {{$labels.group}} on {{$labels.topic}} lag behind
        and is falling behind (behind value {{$value}}).'
      summary: consumer lag behind
  - alert: GroupGetLatencyByStoretime
    expr: rocketmq_group_get_latency_by_storetime > 1000
    for: 3m
    labels:
      severity: warning
    annotations:
      description: 'consumer {{$labels.group}} on {{$labels.broker}}, {{$labels.topic}} consume time lag behind message store time
        and (behind value is {{$value}}).'
      summary: message consumes time lag behind message store time too much