From ce36074de73cd3bf5bd750d6aade1b7ade0f6b9f Mon Sep 17 00:00:00 2001 From: Samuel Berthe Date: Mon, 27 Dec 2021 12:46:36 +0100 Subject: [PATCH] Update rules.yml --- _data/rules.yml | 46 ++++++++++++++++++---------------------------- 1 file changed, 18 insertions(+), 28 deletions(-) diff --git a/_data/rules.yml b/_data/rules.yml index 11e48d6..1f98cb6 100644 --- a/_data/rules.yml +++ b/_data/rules.yml @@ -2127,45 +2127,35 @@ groups: severity: critical for: 5m - - name: Jenkins Metrics (Plugin) + - name: Jenkins exporters: - - rules: - - name: JenkinsOffline + - 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 - summary: "Jenkins OFFLINE" - description: "Jenkins Offline: `{{$labels.instance}}` in realm {{$labels.realm}}/{{$labels.env}} ({{$labels.region}})" - jenkins_url: "https://{{$labels.instance}}/" - - name: JenkinsHealthCheck + - name: Jenkins healthcheck + description: "Jenkins healthcheck score: {{$value}}. Healthcheck failure for `{{$labels.instance}}` in realm {{$labels.realm}}/{{$labels.env}} ({{$labels.region}})" query: 'jenkins_health_check_score < 1' severity: critical - summary: "Jenkins Health Check Score: {{$value}}" - description: "Health Check Failure for `{{$labels.instance}}` in realm {{$labels.realm}}/{{$labels.env}} ({{$labels.region}})" - jenkins_url: "https://{{$labels.instance}}/" - - name: JenkinsBuildsHealthScore - query: 'default_jenkins_builds_health_score{} < 1' + - 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 - summary: "Jenkins Health Check Score: {{$value}}" - description: "Health Check Failure for `{{$labels.instance}}` in realm {{$labels.realm}}/{{$labels.env}} ({{$labels.region}})" - jenkins_url: "https://{{$labels.instance}}/search/?q={{$labels.jenkins_job}}" - - name: JenkinsRunFailureTotal - query: 'delta(jenkins_runs_failure_total{}[1h]) > 100' + - name: Jenkins run failure total + description: "Job run failures: ({{$value}}) {{$labels.jenkins_job}}. Healthcheck failure for `{{$labels.instance}}` in realm {{$labels.realm}}/{{$labels.env}} ({{$labels.region}})" + query: 'delta(jenkins_runs_failure_total[1h]) > 100' severity: warning - summary: "Job Run Failures: ({{$value}}) {{$labels.jenkins_job}}" - description: "Health Check Failure for `{{$labels.instance}}` in realm {{$labels.realm}}/{{$labels.env}} ({{$labels.region}})" - jenkins_url: "https://{{$labels.instance}}/search/?q={{$labels.jenkins_job}}" - name: JenkinsBuildTestsFailing + description: "Last build tests failed: {{$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 - summary: "Last Build Tests Failed: {{$labels.jenkins_job}}" - description: "FAILED Build Tests for Job `{{$labels.jenkins_job}}` on {{$labels.instance}}/{{$labels.env}} ({{$labels.region}})" - jenkins_url: "https://{{$labels.instance}}/search/?q={{$labels.jenkins_job}}" - - name: JenkinsLastBuildFailed - query: 'default_jenkins_builds_last_build_result_ordinal{} == 2' + - name: Jenkins last build failed + description: "Last build failed: {{$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 - summary: "Last Build Failed: {{$labels.jenkins_job}}" - description: "FAILED Build for Job `{{$labels.jenkins_job}}` on {{$labels.instance}}/{{$labels.env}} ({{$labels.region}})" - jenkins_url: "https://{{$labels.instance}}/search/?q={{$labels.jenkins_job}}" comments: | * RUNNING -1 true - The build had no errors. * SUCCESS 0 true - The build had no errors.