monitoring-mixins-website/assets/apache-couchdb/alerts.yaml

groups:
- name: ApacheCouchDBAlerts
  rules:
  - alert: CouchDBUnhealthyCluster
    annotations:
      description: '{{$labels.couchdb_cluster}} has reported a value of {{ printf
        "%.0f" $value }} for its stability over the last 5 minutes, which is below
        the threshold of 1.'
      summary: At least one of the nodes in a cluster is reporting the cluster as
        being unstable.
    expr: |
      min by(job, couchdb_cluster) (couchdb_couch_replicator_cluster_is_stable) < 1      
    for: 5m
    labels:
      severity: critical
  - alert: CouchDBHigh4xxResponseCodes
    annotations:
      description: '{{ printf "%.0f" $value }} 4xx responses have been detected over
        the last 5 minutes on {{$labels.instance}}, which is above the threshold of
        5.'
      summary: There are a high number of 4xx responses for incoming requests to a
        node.
    expr: |
      sum by(job, instance) (increase(couchdb_httpd_status_codes{code=~"4.*"}[5m])) > 5      
    for: 5m
    labels:
      severity: warning
  - alert: CouchDBHigh5xxResponseCodes
    annotations:
      description: '{{ printf "%.0f" $value }} 5xx responses have been detected over
        the last 5 minutes on {{$labels.instance}}, which is above the threshold of
        0.'
      summary: There are a high number of 5xx responses for incoming requests to a
        node.
    expr: |
      sum by(job, instance) (increase(couchdb_httpd_status_codes{code=~"5.*"}[5m])) > 0      
    for: 5m
    labels:
      severity: critical
  - alert: CouchDBModerateRequestLatency
    annotations:
      description: 'An average of {{ printf "%.0f" $value }}ms of request latency
        has occurred over the last 5 minutes on {{$labels.instance}}, which is above
        the threshold of 500ms. '
      summary: There is a moderate level of request latency for a node.
    expr: |
      sum by(job, instance) (couchdb_request_time_seconds_sum / couchdb_request_time_seconds_count) > 500      
    for: 5m
    labels:
      severity: warning
  - alert: CouchDBHighRequestLatency
    annotations:
      description: 'An average of {{ printf "%.0f" $value }}ms of request latency
        has occurred over the last 5 minutes on {{$labels.instance}}, which is above
        the threshold of 1000ms. '
      summary: There is a high level of request latency for a node.
    expr: |
      sum by(job, instance) (couchdb_request_time_seconds_sum / couchdb_request_time_seconds_count) > 1000      
    for: 5m
    labels:
      severity: critical
  - alert: CouchDBManyReplicatorJobsPending
    annotations:
      description: '{{ printf "%.0f" $value }} replicator jobs are pending on {{$labels.instance}},
        which is above the threshold of 10. '
      summary: There is a high number of replicator jobs pending for a node.
    expr: |
      sum by(job, instance) (couchdb_couch_replicator_jobs_pending) > 10      
    for: 5m
    labels:
      severity: warning
  - alert: CouchDBReplicatorJobsCrashing
    annotations:
      description: '{{ printf "%.0f" $value }} replicator jobs have crashed over the
        last 5 minutes on {{$labels.instance}}, which is above the threshold of 0. '
      summary: There are replicator jobs crashing for a node.
    expr: |
      sum by(job, instance) (increase(couchdb_couch_replicator_jobs_crashes_total[5m])) > 0      
    for: 5m
    labels:
      severity: critical
  - alert: CouchDBReplicatorChangesQueuesDying
    annotations:
      description: '{{ printf "%.0f" $value }} replicator changes queue processes
        have died over the last 5 minutes on {{$labels.instance}}, which is above
        the threshold of 0. '
      summary: There are replicator changes queue process deaths for a node.
    expr: |
      sum by(job, instance) (increase(couchdb_couch_replicator_changes_queue_deaths_total[5m])) > 0      
    for: 5m
    labels:
      severity: warning
  - alert: CouchDBReplicatorConnectionOwnersCrashing
    annotations:
      description: '{{ printf "%.0f" $value }} replicator connection owner processes
        have crashed over the last 5 minutes on {{$labels.instance}}, which is above
        the threshold of 0. '
      summary: There are replicator connection owner process crashes for a node.
    expr: |
      sum by(job, instance) (increase(couchdb_couch_replicator_connection_owner_crashes_total[5m])) > 0      
    for: 5m
    labels:
      severity: warning
  - alert: CouchDBReplicatorConnectionWorkersCrashing
    annotations:
      description: '{{ printf "%.0f" $value }} replicator connection worker processes
        have crashed over the last 5 minutes on {{$labels.instance}}, which is above
        the threshold of 0. '
      summary: There are replicator connection worker process crashes for a node.
    expr: |
      sum by(job, instance) (increase(couchdb_couch_replicator_connection_worker_crashes_total[5m])) > 0      
    for: 5m
    labels:
      severity: warning