From 4d622f184d507d5756daff40af7788ba4ad42ad5 Mon Sep 17 00:00:00 2001 From: Your Name Date: Sun, 24 May 2026 13:59:39 +0800 Subject: [PATCH] fix(k8s): stop retaining failed cronjob noise --- k8s/awoooi-prod/12-cronjob-drift-scanner.yaml | 5 ++++- k8s/awoooi-prod/15-cronjob-km-vectorize.yaml | 5 ++++- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/k8s/awoooi-prod/12-cronjob-drift-scanner.yaml b/k8s/awoooi-prod/12-cronjob-drift-scanner.yaml index e8191f13..81093bb3 100644 --- a/k8s/awoooi-prod/12-cronjob-drift-scanner.yaml +++ b/k8s/awoooi-prod/12-cronjob-drift-scanner.yaml @@ -27,7 +27,10 @@ spec: schedule: "0 * * * *" concurrencyPolicy: Forbid # 禁止並發:上次未完成則跳過 successfulJobsHistoryLimit: 3 - failedJobsHistoryLimit: 5 + # 2026-05-24 Codex: failed Job objects make ArgoCD Application health stay + # Degraded long after the next scans have recovered. Failure evidence must + # live in AwoooP/alert logs, not as retained Kubernetes Job noise. + failedJobsHistoryLimit: 0 startingDeadlineSeconds: 60 # 錯過時間窗口超過 60s 則跳過 jobTemplate: spec: diff --git a/k8s/awoooi-prod/15-cronjob-km-vectorize.yaml b/k8s/awoooi-prod/15-cronjob-km-vectorize.yaml index 2c2e5e7c..c14a04c9 100644 --- a/k8s/awoooi-prod/15-cronjob-km-vectorize.yaml +++ b/k8s/awoooi-prod/15-cronjob-km-vectorize.yaml @@ -22,7 +22,10 @@ spec: timeZone: "Asia/Taipei" concurrencyPolicy: Forbid successfulJobsHistoryLimit: 3 - failedJobsHistoryLimit: 3 + # 2026-05-24 Codex: do not retain Failed Jobs in the ArgoCD app tree; stale + # failure evidence belongs in AwoooP/KM governance, while retained Job + # objects keep the whole Application Degraded after recovery. + failedJobsHistoryLimit: 0 startingDeadlineSeconds: 300 jobTemplate: spec: