diff --git a/manifests/kube-prometheus-prometheusRule.yaml b/manifests/kube-prometheus-prometheusRule.yaml index 530dc0cd170f2a91a4fe2012cd6b4dcb74a59878..e3ee47faec50fb673badaa40cd1afd830fe3104e 100644 --- a/manifests/kube-prometheus-prometheusRule.yaml +++ b/manifests/kube-prometheus-prometheusRule.yaml @@ -15,21 +15,23 @@ spec: rules: - alert: TargetDown annotations: - message: '{{ printf "%.4g" $value }}% of the {{ $labels.job }}/{{ $labels.service }} targets in {{ $labels.namespace }} namespace are down.' + description: '{{ printf "%.4g" $value }}% of the {{ $labels.job }}/{{ $labels.service }} targets in {{ $labels.namespace }} namespace are down.' runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/targetdown + summary: One or more targets are unreachable. expr: 100 * (count(up == 0) BY (job, namespace, service) / count(up) BY (job, namespace, service)) > 10 for: 10m labels: severity: warning - alert: Watchdog annotations: - message: | + description: | This is an alert meant to ensure that the entire alerting pipeline is functional. This alert is always firing, therefore it should always be firing in Alertmanager and always fire against a receiver. There are integrations with various notification mechanisms that send a notification when this alert is not firing. For example the "DeadMansSnitch" integration in PagerDuty. runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/watchdog + summary: An alert that should always be firing to certify that Alertmanager is working properly. expr: vector(1) labels: severity: none