Add IRSAACMCertificateExpiringInLessThan60Days alert. (#1119)

* Add `IRSAACMCertificateExpiringInLessThan60Days` alert. * Update helm/prometheus-rules/templates/alerting-rules/aws.management-cluster.rules.yml Co-authored-by: Quentin Bisson <[email protected]> --------- Co-authored-by: Quentin Bisson <[email protected]>
giantswarm · Apr 10, 2024 · e66f966 · e66f966
1 parent 8b57a13
commit e66f966
Show file tree

Hide file tree

Showing 2 changed files with 18 additions and 0 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -7,6 +7,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Added
+
+- Add `IRSAACMCertificateExpiringInLessThan60Days` alert.
+
 ## [3.9.0] - 2024-04-10
 
 ### Added

diff --git a/helm/prometheus-rules/templates/alerting-rules/aws.management-cluster.rules.yml b/helm/prometheus-rules/templates/alerting-rules/aws.management-cluster.rules.yml
@@ -175,4 +175,18 @@ spec:
         severity: page
         team: phoenix
         topic: aws
+    - alert: IRSAACMCertificateExpiringInLessThan60Days
+      annotations:
+        description: '{{`IRSA ACM certificate for Cluster {{ $labels.cluster_id }} ({{ $labels.certificate_name }}) will expire in less than 2 months.`}}'
+        opsrecipe: irsa-acm-certificate-expiring/
+      expr: min(irsa_operator_acm_certificate_not_after) by (cluster_id, installation, pipeline, provider, certificate_name) - time() < 5184000
+      for: 10m
+      labels:
+        area: kaas
+        cancel_if_cluster_status_creating: "true"
+        cancel_if_cluster_status_deleting: "true"
+        cancel_if_outside_working_hours: "true"
+        severity: page
+        team: phoenix
+        topic: aws
 {{- end }}