Commit 5958772b authored by Pedro Eduardo Trujillo's avatar Pedro Eduardo Trujillo
Browse files

Merge branch 'dev' into 'master' 

Dev

See merge request redmic-project/metric/prometheus!30
parents a360b702 18f1dc70

deploy/rules/kafka.rules.yml

+13 −4
Original line number Diff line number Diff line
@@ -2,15 +2,24 @@ groups: 
- name: kafka

  rules:

  - alert: KafkaConsumerLagIncreasing

    expr: abs(delta(kafka_consumergroup_lag_sum[5m]) - avg_over_time(delta(kafka_consumergroup_lag_sum[5m])[1d:])) /

      stddev_over_time(delta(kafka_consumergroup_lag_sum[5m])[1d:]) > 1

    for: 15m

    expr: abs(rate(kafka_consumergroup_lag_sum[5m]) - avg_over_time(rate(kafka_consumergroup_lag_sum[5m])[1d:])) /

      stddev_over_time(rate(kafka_consumergroup_lag_sum[5m])[1d:]) > 3

    for: 5m

    labels:

      severity: warning

      severity: critical

    annotations:

      description: abs(z-score) for lag of consumer group '{{$labels.consumergroup}}' is at {{$value | printf "%.3f"}} for '{{$labels.topic}}' topic

      summary: Consuming ratio of Kafka consumer group '{{$labels.consumergroup}}' is not enough for '{{$labels.topic}}' (abs(z-score > 1)



  - alert: KafkaConsumerGroupIsEmpty

    expr: kafka_consumergroup_members == 0

    for: 10m

    labels:

      severity: critical

    annotations:

      description: Consumer group '{{$labels.consumergroup}}' has no active consumers

      summary: Kafka consumers from '{{$labels.consumergroup}}' group are not running



  - alert: KafkaConsumerTooHighLag

    expr: kafka_consumergroup_lag_sum > 1000000

    for: 1m