fix labels

This commit is contained in:
Dmitry Verkhoturov
2018-11-06 16:41:01 +03:00
parent 3e70847581
commit 681a18ef3a

View File

@@ -688,7 +688,7 @@ spec:
severity: warning severity: warning
- alert: KubeCronJobRunning - alert: KubeCronJobRunning
annotations: annotations:
message: CronJob {{ $labels.namespaces }}/{{ $labels.cronjob }} is taking message: CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is taking
more than 1h to complete. more than 1h to complete.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecronjobrunning runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecronjobrunning
expr: | expr: |
@@ -698,7 +698,7 @@ spec:
severity: warning severity: warning
- alert: KubeJobCompletion - alert: KubeJobCompletion
annotations: annotations:
message: Job {{ $labels.namespaces }}/{{ $labels.job }} is taking more than message: Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking more than
one hour to complete. one hour to complete.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobcompletion runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobcompletion
expr: | expr: |
@@ -708,7 +708,7 @@ spec:
severity: warning severity: warning
- alert: KubeJobFailed - alert: KubeJobFailed
annotations: annotations:
message: Job {{ $labels.namespaces }}/{{ $labels.job }} failed to complete. message: Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobfailed runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobfailed
expr: | expr: |
kube_job_status_failed{job="kube-state-metrics"} > 0 kube_job_status_failed{job="kube-state-metrics"} > 0
@@ -852,7 +852,7 @@ spec:
severity: warning severity: warning
- alert: KubeClientErrors - alert: KubeClientErrors
annotations: annotations:
message: Kubernetes API server client '{{ $labels.job }}/{{ $labels.instance message: Kubernetes API server client '{{ $labels.job_name }}/{{ $labels.instance
}}' is experiencing {{ printf "%0.0f" $value }}% errors.' }}' is experiencing {{ printf "%0.0f" $value }}% errors.'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclienterrors runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclienterrors
expr: | expr: |
@@ -865,7 +865,7 @@ spec:
severity: warning severity: warning
- alert: KubeClientErrors - alert: KubeClientErrors
annotations: annotations:
message: Kubernetes API server client '{{ $labels.job }}/{{ $labels.instance message: Kubernetes API server client '{{ $labels.job_name }}/{{ $labels.instance
}}' is experiencing {{ printf "%0.0f" $value }} errors / second. }}' is experiencing {{ printf "%0.0f" $value }} errors / second.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclienterrors runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclienterrors
expr: | expr: |
@@ -975,7 +975,7 @@ spec:
rules: rules:
- alert: TargetDown - alert: TargetDown
annotations: annotations:
message: '{{ $value }}% of the {{ $labels.job }} targets are down.' message: '{{ $value }}% of the {{ $labels.job_name }} targets are down.'
expr: 100 * (count(up == 0) BY (job) / count(up) BY (job)) > 10 expr: 100 * (count(up == 0) BY (job) / count(up) BY (job)) > 10
for: 10m for: 10m
labels: labels:
@@ -1060,7 +1060,7 @@ spec:
severity: warning severity: warning
- alert: PrometheusTSDBReloadsFailing - alert: PrometheusTSDBReloadsFailing
annotations: annotations:
description: '{{$labels.job}} at {{$labels.instance}} had {{$value | humanize}} description: '{{$labels.job_name}} at {{$labels.instance}} had {{$value | humanize}}
reload failures over the last four hours.' reload failures over the last four hours.'
summary: Prometheus has issues reloading data blocks from disk summary: Prometheus has issues reloading data blocks from disk
expr: | expr: |
@@ -1070,7 +1070,7 @@ spec:
severity: warning severity: warning
- alert: PrometheusTSDBCompactionsFailing - alert: PrometheusTSDBCompactionsFailing
annotations: annotations:
description: '{{$labels.job}} at {{$labels.instance}} had {{$value | humanize}} description: '{{$labels.job_name}} at {{$labels.instance}} had {{$value | humanize}}
compaction failures over the last four hours.' compaction failures over the last four hours.'
summary: Prometheus has issues compacting sample blocks summary: Prometheus has issues compacting sample blocks
expr: | expr: |
@@ -1080,7 +1080,7 @@ spec:
severity: warning severity: warning
- alert: PrometheusTSDBWALCorruptions - alert: PrometheusTSDBWALCorruptions
annotations: annotations:
description: '{{$labels.job}} at {{$labels.instance}} has a corrupted write-ahead description: '{{$labels.job_name}} at {{$labels.instance}} has a corrupted write-ahead
log (WAL).' log (WAL).'
summary: Prometheus write-ahead log is corrupted summary: Prometheus write-ahead log is corrupted
expr: | expr: |