From 01d4c9c3e1b9a06d4d17a5ca1fae5284f209b9ee Mon Sep 17 00:00:00 2001
From: Viktor Barzin <vbarzin@gmail.com>
Date: Sat, 3 Jan 2026 23:30:28 +0000
Subject: [PATCH] update definition of high cpu usage to use pve metrics in
 stead for a longer period [ci skip]

---
 modules/kubernetes/monitoring/prometheus_chart_values.tpl | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/modules/kubernetes/monitoring/prometheus_chart_values.tpl b/modules/kubernetes/monitoring/prometheus_chart_values.tpl
index f5782d64..9dd9c020 100644
--- a/modules/kubernetes/monitoring/prometheus_chart_values.tpl
+++ b/modules/kubernetes/monitoring/prometheus_chart_values.tpl
@@ -303,8 +303,8 @@ serverFiles:
             annotations:
               summary: "Low registry cache hit rate"
           - alert: NodeHighCPUUsage
-            expr: node_load1{instance!="pve-node-r730"} > 2
-            for: 20m
+            expr: pve_cpu_usage_ratio > 0.3
+            for: 6h
             labels:
               severity: page
             annotations: