mirror of
https://github.com/samber/awesome-prometheus-alerts.git
synced 2026-06-25 02:46:59 +08:00
added jenkins alert rules for jenkins metrics plugin (#268)
* added jenkins alert rules * Update rules.yml Co-authored-by: Samuel Berthe <dev@samuel-berthe.fr>
This commit is contained in:
parent
fd0f2805c0
commit
78a7e61050
1 changed files with 38 additions and 0 deletions
|
|
@ -2126,3 +2126,41 @@ groups:
|
||||||
query: sum by (job) (cortex_query_frontend_queue_length) > 0
|
query: sum by (job) (cortex_query_frontend_queue_length) > 0
|
||||||
severity: critical
|
severity: critical
|
||||||
for: 5m
|
for: 5m
|
||||||
|
|
||||||
|
- name: Jenkins
|
||||||
|
exporters:
|
||||||
|
- name: Metric plugin
|
||||||
|
doc_url: https://plugins.jenkins.io/prometheus/
|
||||||
|
rules:
|
||||||
|
- name: Jenkins offline
|
||||||
|
description: "Jenkins offline: `{{$labels.instance}}` in realm {{$labels.realm}}/{{$labels.env}} ({{$labels.region}})"
|
||||||
|
query: 'jenkins_node_offline_value > 1'
|
||||||
|
severity: critical
|
||||||
|
- name: Jenkins healthcheck
|
||||||
|
description: "Jenkins healthcheck score: {{$value}}. Healthcheck failure for `{{$labels.instance}}` in realm {{$labels.realm}}/{{$labels.env}} ({{$labels.region}})"
|
||||||
|
query: 'jenkins_health_check_score < 1'
|
||||||
|
severity: critical
|
||||||
|
- name: Jenkins builds health score
|
||||||
|
description: "Healthcheck failure for `{{$labels.instance}}` in realm {{$labels.realm}}/{{$labels.env}} ({{$labels.region}})"
|
||||||
|
query: 'default_jenkins_builds_health_score < 1'
|
||||||
|
severity: critical
|
||||||
|
- name: Jenkins run failure total
|
||||||
|
description: "Job run failures: ({{$value}}) {{$labels.jenkins_job}}. Healthcheck failure for `{{$labels.instance}}` in realm {{$labels.realm}}/{{$labels.env}} ({{$labels.region}})"
|
||||||
|
query: 'delta(jenkins_runs_failure_total[1h]) > 100'
|
||||||
|
severity: warning
|
||||||
|
- name: JenkinsBuildTestsFailing
|
||||||
|
description: "Last build tests failed: {{$labels.jenkins_job}}. Failed build Tests for job `{{$labels.jenkins_job}}` on {{$labels.instance}}/{{$labels.env}} ({{$labels.region}})"
|
||||||
|
query: 'default_jenkins_builds_last_build_tests_failing > 0'
|
||||||
|
severity: warning
|
||||||
|
- name: Jenkins last build failed
|
||||||
|
description: "Last build failed: {{$labels.jenkins_job}}. Failed build for job `{{$labels.jenkins_job}}` on {{$labels.instance}}/{{$labels.env}} ({{$labels.region}})"
|
||||||
|
query: 'default_jenkins_builds_last_build_result_ordinal == 2'
|
||||||
|
severity: warning
|
||||||
|
comments: |
|
||||||
|
* RUNNING -1 true - The build had no errors.
|
||||||
|
* SUCCESS 0 true - The build had no errors.
|
||||||
|
* UNSTABLE 1 true - The build had some errors but they were not fatal. For example, some tests failed.
|
||||||
|
* FAILURE 2 false - The build had a fatal error.
|
||||||
|
* NOT_BUILT 3 false - The module was not built.
|
||||||
|
* ABORTED 4 false - The build was manually aborted.
|
||||||
|
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue