From 7b619f8bb0e08d81ee2e01ccbb37a03075d90b44 Mon Sep 17 00:00:00 2001
From: Keith Jackson <keithallenjackson@gmail.com>
Date: Mon, 24 Aug 2026 00:04:17 -0500
Subject: [PATCH] fix(monitoring): Prometheus memory limit 1Gi -> 2Gi
 (OOMKilled on compaction)

prometheus-...-0 was OOMKilled (exit 137) every ~4min during TSDB compaction/checkpoint
(261 restarts/37h). Raise limit to 2Gi + request to 512Mi; nodes have headroom.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---
 platform/monitoring/kube-prometheus-stack.yaml | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/platform/monitoring/kube-prometheus-stack.yaml b/platform/monitoring/kube-prometheus-stack.yaml
index 199dfc2..b42063f 100644
--- a/platform/monitoring/kube-prometheus-stack.yaml
+++ b/platform/monitoring/kube-prometheus-stack.yaml
@@ -56,9 +56,10 @@ spec:
         resources:
           requests:
             cpu: 100m
-            memory: 384Mi
+            memory: 512Mi
           limits:
-            memory: 1Gi
+            memory: 2Gi                        # 1Gi OOMKilled (exit 137) during TSDB compaction/checkpoint
+                                               # spikes; 2Gi holds. Nodes have headroom (~2Gi free each).
         storageSpec:
           volumeClaimTemplate:
             spec: