From 21939764410f980084536205599f5b98113e3141 Mon Sep 17 00:00:00 2001
From: Vladimir Videlov <vladimir.videlov@sap.com>
Date: Wed, 17 Sep 2025 10:36:13 +0200
Subject: [PATCH] Add alert for when Argora pod not ready for 5 minutes

---
 .../alerts/controlplane-remote.yaml                | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/charts/controlplane-operations/alerts/controlplane-remote.yaml b/charts/controlplane-operations/alerts/controlplane-remote.yaml
index 12dca6d..1242541 100644
--- a/charts/controlplane-operations/alerts/controlplane-remote.yaml
+++ b/charts/controlplane-operations/alerts/controlplane-remote.yaml
@@ -15,3 +15,17 @@ groups:
       description: "Argora Update CR status is in Error state for more than 1 minute."
       summary: "Update CR in Error state."
 {{- end }}
+
+{{- if not (.Values.prometheusRules.disabled.ArgoraPodNotReadyError | default false) }}
+  - alert: ArgoraPodNotReadyError
+    expr: >
+      kube_pod_status_ready{namespace="shoot-control-plane",pod=~"argora-controller-manager-.+",condition="true"} == 0
+    for: {{ dig "ArgoraPodNotReadyError" "for" "5m" .Values.prometheusRules }}
+    labels:
+      severity: {{ dig "ArgoraPodNotReadyError" "severity" "warning" .Values.prometheusRules }}
+      playbook: https://github.com/cobaltcore-dev/controlplane-operations/playbooks/ArgoraPodNotReadyError.md
+      {{ include "controlplane-operations.additionalRuleLabels" . }}
+    annotations:
+      description: "Argora Pod is not ready for more than 5 minutes."
+      summary: "Pod not ready."
+{{- end }}