Add summary to Alertmanager rules where missing - updated accoring to guidelines

This commit is contained in:
Alexander Holte-Davidsen
2018-03-05 09:52:51 +01:00
parent c54468ab7b
commit 8b6ee5c18b
6 changed files with 34 additions and 0 deletions

View File

@@ -51,6 +51,7 @@ groups:
annotations:
description: the API server has a 99th percentile latency of {{ $value }} seconds
for {{$labels.verb}} {{$labels.resource}}
summary: API server high latency
- alert: APIServerLatencyHigh
expr: apiserver_latency_seconds:quantile{quantile="0.99",subresource!="log",verb!~"^(?:WATCH|WATCHLIST|PROXY|CONNECT)$"}
> 4
@@ -60,6 +61,7 @@ groups:
annotations:
description: the API server has a 99th percentile latency of {{ $value }} seconds
for {{$labels.verb}} {{$labels.resource}}
summary: API server high latency
- alert: APIServerErrorsHigh
expr: rate(apiserver_request_count{code=~"^(?:5..)$"}[5m]) / rate(apiserver_request_count[5m])
* 100 > 2
@@ -68,6 +70,7 @@ groups:
severity: warning
annotations:
description: API server returns errors for {{ $value }}% of requests
summary: API server request errors
- alert: APIServerErrorsHigh
expr: rate(apiserver_request_count{code=~"^(?:5..)$"}[5m]) / rate(apiserver_request_count[5m])
* 100 > 5
@@ -84,12 +87,14 @@ groups:
annotations:
description: No API servers are reachable or all have disappeared from service
discovery
summary: No API servers are reachable
- alert: K8sCertificateExpirationNotice
labels:
severity: warning
annotations:
description: Kubernetes API Certificate is expiring soon (less than 7 days)
summary: Kubernetes API Certificate is expiering soon
expr: sum(apiserver_client_certificate_expiration_seconds_bucket{le="604800"}) > 0
- alert: K8sCertificateExpirationNotice
@@ -97,4 +102,5 @@ groups:
severity: critical
annotations:
description: Kubernetes API Certificate is expiring in less than 1 day
summary: Kubernetes API Certificate is expiering
expr: sum(apiserver_client_certificate_expiration_seconds_bucket{le="86400"}) > 0