From 6179475625dca95aeb4c333bfc973806d0a1295d Mon Sep 17 00:00:00 2001
From: Per Lundberg <perlun@gmail.com>
Date: Fri, 30 Jan 2026 09:07:59 +0200
Subject: [PATCH] Adjust OOM kill detected rule

When a machine runs out of memory, it happens that the node
exporter stops responding for multiple minutes. I've adjusted
the rule now to take this into account: even if it takes 15-20
minutes before the machine becomes responsive again, the
alert should still fire.
---
 _data/rules.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/_data/rules.yml b/_data/rules.yml
index 715f181..1bb6ece 100644
--- a/_data/rules.yml
+++ b/_data/rules.yml
@@ -271,7 +271,7 @@ groups:
                 severity: info
               - name: Host OOM kill detected
                 description: OOM kill detected
-                query: "(increase(node_vmstat_oom_kill[1m]) > 0)"
+                query: "(increase(node_vmstat_oom_kill[30m]) > 0)"
                 severity: warning
               - name: Host EDAC Correctable Errors detected
                 description: 'Host {{ $labels.instance }} has had {{ printf "%.0f" $value }} correctable memory errors reported by EDAC in the last 5 minutes.'