Add summary to Alertmanager rules where missing - updated accoring to guidelines
This commit is contained in:
@@ -8,6 +8,7 @@ groups:
|
||||
severity: warning
|
||||
annotations:
|
||||
description: Reloading Prometheus' configuration has failed for {{$labels.namespace}}/{{$labels.pod}}
|
||||
summary: Reloading Promehteus' configuration failed
|
||||
|
||||
- alert: PrometheusNotificationQueueRunningFull
|
||||
expr: predict_linear(prometheus_notifications_queue_length[5m], 60 * 30) > prometheus_notifications_queue_capacity
|
||||
@@ -17,6 +18,7 @@ groups:
|
||||
annotations:
|
||||
description: Prometheus' alert notification queue is running full for {{$labels.namespace}}/{{
|
||||
$labels.pod}}
|
||||
summary: Prometheus' alert notification queue is running full
|
||||
|
||||
- alert: PrometheusErrorSendingAlerts
|
||||
expr: rate(prometheus_notifications_errors_total[5m]) / rate(prometheus_notifications_sent_total[5m])
|
||||
@@ -27,6 +29,7 @@ groups:
|
||||
annotations:
|
||||
description: Errors while sending alerts from Prometheus {{$labels.namespace}}/{{
|
||||
$labels.pod}} to Alertmanager {{$labels.Alertmanager}}
|
||||
summary: Errors while sending alert from Prometheus
|
||||
|
||||
- alert: PrometheusErrorSendingAlerts
|
||||
expr: rate(prometheus_notifications_errors_total[5m]) / rate(prometheus_notifications_sent_total[5m])
|
||||
@@ -37,6 +40,7 @@ groups:
|
||||
annotations:
|
||||
description: Errors while sending alerts from Prometheus {{$labels.namespace}}/{{
|
||||
$labels.pod}} to Alertmanager {{$labels.Alertmanager}}
|
||||
summary: Errors while sending alerts from Prometheus
|
||||
|
||||
- alert: PrometheusNotConnectedToAlertmanagers
|
||||
expr: prometheus_notifications_alertmanagers_discovered < 1
|
||||
@@ -46,6 +50,7 @@ groups:
|
||||
annotations:
|
||||
description: Prometheus {{ $labels.namespace }}/{{ $labels.pod}} is not connected
|
||||
to any Alertmanagers
|
||||
summary: Prometheus is not connected to any Alertmanagers
|
||||
|
||||
- alert: PrometheusTSDBReloadsFailing
|
||||
expr: increase(prometheus_tsdb_reloads_failures_total[2h]) > 0
|
||||
|
||||
Reference in New Issue
Block a user