From ed8ba3beec3a1747633d83c8ef6ef4fdea7c8561 Mon Sep 17 00:00:00 2001
From: Kirill Ilin <stitch14@yandex.ru>
Date: Tue, 17 Mar 2026 13:21:28 +0500
Subject: [PATCH] fix(etcd): add protective limits to defrag CronJob

Without concurrencyPolicy and job limits, the defrag CronJob can
accumulate hundreds of running/failed pods during cluster upgrades
when etcd is temporarily unavailable. This was observed after
upgrading to v1.1.2 where defrag jobs piled up across tenants.

Assisted-By: Claude AI
Signed-off-by: Kirill Ilin <stitch14@yandex.ru>
---
 packages/extra/etcd/templates/etcd-defrag.yaml | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/packages/extra/etcd/templates/etcd-defrag.yaml b/packages/extra/etcd/templates/etcd-defrag.yaml
index 089df920..0478129f 100644
--- a/packages/extra/etcd/templates/etcd-defrag.yaml
+++ b/packages/extra/etcd/templates/etcd-defrag.yaml
@@ -4,9 +4,14 @@ metadata:
   name: {{ .Release.Name }}-defrag
 spec:
   schedule: "0 * * * *"
+  concurrencyPolicy: Forbid
+  startingDeadlineSeconds: 300
   successfulJobsHistoryLimit: 3
+  failedJobsHistoryLimit: 1
   jobTemplate:
     spec:
+      activeDeadlineSeconds: 1800
+      backoffLimit: 2
       template:
         spec:
           containers: