Elukey has submitted this change and it was merged. ( https://gerrit.wikimedia.org/r/401730 )
Change subject: role::icinga: add prometheus alerts profile ...................................................................... role::icinga: add prometheus alerts profile Change-Id: Ic955b3295f5d10472d47dcb11ffae082232dd694 --- A modules/profile/manifests/prometheus/alerts.pp M modules/role/manifests/icinga.pp 2 files changed, 22 insertions(+), 0 deletions(-) Approvals: Elukey: Looks good to me, approved jenkins-bot: Verified Volans: Looks good to me, but someone else must approve diff --git a/modules/profile/manifests/prometheus/alerts.pp b/modules/profile/manifests/prometheus/alerts.pp new file mode 100644 index 0000000..3621a2d --- /dev/null +++ b/modules/profile/manifests/prometheus/alerts.pp @@ -0,0 +1,21 @@ +# == Class: profile::prometheus::alerts +# +# Install icinga alerts based on Prometheus metrics. +# NOTE to be included only from one host, icinga will generate different alerts +# for all hosts that include this class. +# +class profile::prometheus::alerts { + + # Monitor Druid realtime ingestion event rate. + # Experimental, only alerting the Analytics alias. + monitoring::check_prometheus { 'druid_realtime_banner_activity': + description => 'Number of banner_activity realtime events received by Druid over a 30 minutes period', + query => 'sum_over_time(druid_realtime_ingest_events_processed_count{cluster="druid_analytics", instance=~"druid.*:8000", datasource=~"banner_activity_minutely"}[30m])', + prometheus_url => 'http://prometheus.svc.eqiad.wmnet/analytics', + method => 'le', + warning => 10, + critical => 0, + contact_group => 'analytics', + dashboard_links => ['https://grafana.wikimedia.org/dashboard/db/prometheus-druid?refresh=1m&panelId=41&fullscreen&orgId=1'] + } +} \ No newline at end of file diff --git a/modules/role/manifests/icinga.pp b/modules/role/manifests/icinga.pp index 9b0b87d..3d7498e 100644 --- a/modules/role/manifests/icinga.pp +++ b/modules/role/manifests/icinga.pp @@ -35,6 +35,7 @@ include icinga::monitor::reading_web include icinga::event_handlers::raid include ::profile::bird::anycast_monitoring + include ::profile::prometheus::alerts $monitoring_groups = hiera('monitoring::groups') create_resources(monitoring::group, $monitoring_groups) -- To view, visit https://gerrit.wikimedia.org/r/401730 To unsubscribe, visit https://gerrit.wikimedia.org/r/settings Gerrit-MessageType: merged Gerrit-Change-Id: Ic955b3295f5d10472d47dcb11ffae082232dd694 Gerrit-PatchSet: 6 Gerrit-Project: operations/puppet Gerrit-Branch: production Gerrit-Owner: Elukey <ltosc...@wikimedia.org> Gerrit-Reviewer: Alexandros Kosiaris <akosia...@wikimedia.org> Gerrit-Reviewer: Elukey <ltosc...@wikimedia.org> Gerrit-Reviewer: Filippo Giunchedi <fgiunch...@wikimedia.org> Gerrit-Reviewer: Giuseppe Lavagetto <glavage...@wikimedia.org> Gerrit-Reviewer: Joal <j...@wikimedia.org> Gerrit-Reviewer: Ottomata <ao...@wikimedia.org> Gerrit-Reviewer: Volans <rcocci...@wikimedia.org> Gerrit-Reviewer: jenkins-bot <> _______________________________________________ MediaWiki-commits mailing list MediaWiki-commits@lists.wikimedia.org https://lists.wikimedia.org/mailman/listinfo/mediawiki-commits