From f7885fcf3e72649923ba011da1b8b8df6b933473 Mon Sep 17 00:00:00 2001
From: ale <ale@incal.net>
Date: Tue, 17 Dec 2024 15:43:08 +0000
Subject: [PATCH] Page for RAID failures
---
.../templates/rules/alerts_system_health.conf.yml | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/roles/float-infra-prometheus/templates/rules/alerts_system_health.conf.yml b/roles/float-infra-prometheus/templates/rules/alerts_system_health.conf.yml
index 209ec741..faa4cfe6 100644
--- a/roles/float-infra-prometheus/templates/rules/alerts_system_health.conf.yml
+++ b/roles/float-infra-prometheus/templates/rules/alerts_system_health.conf.yml
@@ -32,7 +32,7 @@ groups:
expr: node_md_degraded > 0
for: 15m
labels:
- severity: warn
+ severity: page
annotations:
summary: "RAID device {{ $labels.md_device }} on {{ $labels.host }} is unhealthy"
description: "The RAID device {{ $labels.md_device }} on {{ $labels.host }} is reporting a degraded state, which means that probably one or more of the disks in the array have failed."
--
GitLab