From fca4e02c54c395d22f2fd8fbbd2d1f626d527d26 Mon Sep 17 00:00:00 2001
From: Viktor Barzin <viktorbarzin@meta.com>
Date: Sun, 15 Mar 2026 01:44:52 +0000
Subject: [PATCH] prometheus: increase memory to 4Gi and probe delays for TSDB
 compaction

Compaction of 5 years of TSDB blocks was OOM-killing at 3Gi (18 restarts
in 8h), causing sustained IO pressure on the PVE host spinning disk.
Increase liveness probe delay to 300s so WAL replay completes before
the probe kills the pod.
---
 .../platform/modules/monitoring/prometheus_chart_values.tpl | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/stacks/platform/modules/monitoring/prometheus_chart_values.tpl b/stacks/platform/modules/monitoring/prometheus_chart_values.tpl
index 253a4ddd..107a7199 100755
--- a/stacks/platform/modules/monitoring/prometheus_chart_values.tpl
+++ b/stacks/platform/modules/monitoring/prometheus_chart_values.tpl
@@ -153,9 +153,11 @@ server:
   resources:
     requests:
       cpu: 100m
-      memory: 3Gi
+      memory: 4Gi
     limits:
-      memory: 3Gi
+      memory: 4Gi
+  livenessProbeInitialDelay: 300
+  readinessProbeInitialDelay: 60
   strategy:
     type: Recreate
   baseURL: "https://prometheus.viktorbarzin.me"