manifests: regenerate
This commit is contained in:
@@ -15,11 +15,11 @@ spec:
|
||||
rules:
|
||||
- alert: KubePodCrashLooping
|
||||
annotations:
|
||||
description: Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container }}) is restarting {{ printf "%.2f" $value }} times / 5 minutes.
|
||||
description: Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container }}) is restarting {{ printf "%.2f" $value }} times / 10 minutes.
|
||||
runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/kubepodcrashlooping
|
||||
summary: Pod is crash looping.
|
||||
expr: |
|
||||
rate(kube_pod_container_status_restarts_total{job="kube-state-metrics"}[5m]) * 60 * 5 > 0
|
||||
rate(kube_pod_container_status_restarts_total{job="kube-state-metrics"}[10m]) * 60 * 5 > 0
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
@@ -499,11 +499,11 @@ spec:
|
||||
severity: critical
|
||||
- alert: AggregatedAPIErrors
|
||||
annotations:
|
||||
description: An aggregated API {{ $labels.name }}/{{ $labels.namespace }} has reported errors. The number of errors have increased for it in the past five minutes. High values indicate that the availability of the service changes too often.
|
||||
description: An aggregated API {{ $labels.name }}/{{ $labels.namespace }} has reported errors. It has appeared unavailable {{ $value | humanize }} times averaged over the past 10m.
|
||||
runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/aggregatedapierrors
|
||||
summary: An aggregated API has reported errors.
|
||||
expr: |
|
||||
sum by(name, namespace)(increase(aggregator_unavailable_apiservice_count[5m])) > 2
|
||||
sum by(name, namespace)(increase(aggregator_unavailable_apiservice_count[10m])) > 4
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: AggregatedAPIDown
|
||||
@@ -526,6 +526,16 @@ spec:
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critical
|
||||
- alert: KubeAPITerminatedRequests
|
||||
annotations:
|
||||
description: The apiserver has terminated {{ $value | humanizePercentage }} of its incoming requests.
|
||||
runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/kubeapiterminatedrequests
|
||||
summary: The apiserver has terminated {{ $value | humanizePercentage }} of its incoming requests.
|
||||
expr: |
|
||||
sum(rate(apiserver_request_terminations_total{job="apiserver"}[10m])) / ( sum(rate(apiserver_request_total{job="apiserver"}[10m])) + sum(rate(apiserver_request_terminations_total{job="apiserver"}[10m])) ) > 0.20
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
- name: kubernetes-system-kubelet
|
||||
rules:
|
||||
- alert: KubeNodeNotReady
|
||||
@@ -1102,77 +1112,80 @@ spec:
|
||||
verb: write
|
||||
record: apiserver_request:availability30d
|
||||
- expr: |
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="LIST",code=~"2.."}[30d]))
|
||||
avg_over_time(code_verb:apiserver_request_total:increase1h[30d]) * 24 * 30
|
||||
record: code_verb:apiserver_request_total:increase30d
|
||||
- expr: |
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"2.."}[30d]))
|
||||
record: code_verb:apiserver_request_total:increase30d
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="LIST",code=~"2.."}[1h]))
|
||||
record: code_verb:apiserver_request_total:increase1h
|
||||
- expr: |
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"2.."}[30d]))
|
||||
record: code_verb:apiserver_request_total:increase30d
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"2.."}[1h]))
|
||||
record: code_verb:apiserver_request_total:increase1h
|
||||
- expr: |
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"2.."}[30d]))
|
||||
record: code_verb:apiserver_request_total:increase30d
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"2.."}[1h]))
|
||||
record: code_verb:apiserver_request_total:increase1h
|
||||
- expr: |
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"2.."}[30d]))
|
||||
record: code_verb:apiserver_request_total:increase30d
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"2.."}[1h]))
|
||||
record: code_verb:apiserver_request_total:increase1h
|
||||
- expr: |
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="DELETE",code=~"2.."}[30d]))
|
||||
record: code_verb:apiserver_request_total:increase30d
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"2.."}[1h]))
|
||||
record: code_verb:apiserver_request_total:increase1h
|
||||
- expr: |
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="LIST",code=~"3.."}[30d]))
|
||||
record: code_verb:apiserver_request_total:increase30d
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="DELETE",code=~"2.."}[1h]))
|
||||
record: code_verb:apiserver_request_total:increase1h
|
||||
- expr: |
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"3.."}[30d]))
|
||||
record: code_verb:apiserver_request_total:increase30d
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="LIST",code=~"3.."}[1h]))
|
||||
record: code_verb:apiserver_request_total:increase1h
|
||||
- expr: |
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"3.."}[30d]))
|
||||
record: code_verb:apiserver_request_total:increase30d
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"3.."}[1h]))
|
||||
record: code_verb:apiserver_request_total:increase1h
|
||||
- expr: |
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"3.."}[30d]))
|
||||
record: code_verb:apiserver_request_total:increase30d
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"3.."}[1h]))
|
||||
record: code_verb:apiserver_request_total:increase1h
|
||||
- expr: |
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"3.."}[30d]))
|
||||
record: code_verb:apiserver_request_total:increase30d
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"3.."}[1h]))
|
||||
record: code_verb:apiserver_request_total:increase1h
|
||||
- expr: |
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="DELETE",code=~"3.."}[30d]))
|
||||
record: code_verb:apiserver_request_total:increase30d
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"3.."}[1h]))
|
||||
record: code_verb:apiserver_request_total:increase1h
|
||||
- expr: |
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="LIST",code=~"4.."}[30d]))
|
||||
record: code_verb:apiserver_request_total:increase30d
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="DELETE",code=~"3.."}[1h]))
|
||||
record: code_verb:apiserver_request_total:increase1h
|
||||
- expr: |
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"4.."}[30d]))
|
||||
record: code_verb:apiserver_request_total:increase30d
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="LIST",code=~"4.."}[1h]))
|
||||
record: code_verb:apiserver_request_total:increase1h
|
||||
- expr: |
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"4.."}[30d]))
|
||||
record: code_verb:apiserver_request_total:increase30d
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"4.."}[1h]))
|
||||
record: code_verb:apiserver_request_total:increase1h
|
||||
- expr: |
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"4.."}[30d]))
|
||||
record: code_verb:apiserver_request_total:increase30d
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"4.."}[1h]))
|
||||
record: code_verb:apiserver_request_total:increase1h
|
||||
- expr: |
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"4.."}[30d]))
|
||||
record: code_verb:apiserver_request_total:increase30d
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"4.."}[1h]))
|
||||
record: code_verb:apiserver_request_total:increase1h
|
||||
- expr: |
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="DELETE",code=~"4.."}[30d]))
|
||||
record: code_verb:apiserver_request_total:increase30d
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"4.."}[1h]))
|
||||
record: code_verb:apiserver_request_total:increase1h
|
||||
- expr: |
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="LIST",code=~"5.."}[30d]))
|
||||
record: code_verb:apiserver_request_total:increase30d
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="DELETE",code=~"4.."}[1h]))
|
||||
record: code_verb:apiserver_request_total:increase1h
|
||||
- expr: |
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"5.."}[30d]))
|
||||
record: code_verb:apiserver_request_total:increase30d
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="LIST",code=~"5.."}[1h]))
|
||||
record: code_verb:apiserver_request_total:increase1h
|
||||
- expr: |
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"5.."}[30d]))
|
||||
record: code_verb:apiserver_request_total:increase30d
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="GET",code=~"5.."}[1h]))
|
||||
record: code_verb:apiserver_request_total:increase1h
|
||||
- expr: |
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"5.."}[30d]))
|
||||
record: code_verb:apiserver_request_total:increase30d
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="POST",code=~"5.."}[1h]))
|
||||
record: code_verb:apiserver_request_total:increase1h
|
||||
- expr: |
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"5.."}[30d]))
|
||||
record: code_verb:apiserver_request_total:increase30d
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PUT",code=~"5.."}[1h]))
|
||||
record: code_verb:apiserver_request_total:increase1h
|
||||
- expr: |
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="DELETE",code=~"5.."}[30d]))
|
||||
record: code_verb:apiserver_request_total:increase30d
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="PATCH",code=~"5.."}[1h]))
|
||||
record: code_verb:apiserver_request_total:increase1h
|
||||
- expr: |
|
||||
sum by (code, verb) (increase(apiserver_request_total{job="apiserver",verb="DELETE",code=~"5.."}[1h]))
|
||||
record: code_verb:apiserver_request_total:increase1h
|
||||
- expr: |
|
||||
sum by (code) (code_verb:apiserver_request_total:increase30d{verb=~"LIST|GET"})
|
||||
labels:
|
||||
|
||||
Reference in New Issue
Block a user