From 1c8ce967ae52d8639d472c42270e60be2f04d155 Mon Sep 17 00:00:00 2001 From: Ryan Yin Date: Sat, 17 Oct 2026 19:19:20 +0800 Subject: [PATCH] fix(monitoring): ignore floating nct6775 temperature inputs CPUTIN and AUXTIN* read 101 C or saturate at -128/127 C with no sensor wired, so the alert fired while the CPU package stayed near 53 C. Assisted-by: DeepSeek Harness (deepseek-flash) --- .../homelab-services/monitoring/alert_rules/node-exporter.yml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/hosts/12kingdoms-youko/homelab-services/monitoring/alert_rules/node-exporter.yml b/hosts/12kingdoms-youko/homelab-services/monitoring/alert_rules/node-exporter.yml index 5f91ae88..51a4e11f 100644 --- a/hosts/12kingdoms-youko/homelab-services/monitoring/alert_rules/node-exporter.yml +++ b/hosts/12kingdoms-youko/homelab-services/monitoring/alert_rules/node-exporter.yml @@ -309,8 +309,8 @@ groups: - alert: HostPhysicalComponentTooHot expr: '((node_hwmon_temp_celsius * ignoring(label) group_left(instance, job, node, sensor) - node_hwmon_sensor_label{label!~"(?i)^(tctl|tccd|tdie)$"} > 75)) * on(instance) group_left - (nodename) node_uname_info{nodename=~".+"}' + node_hwmon_sensor_label{label!~"(?i)^(tctl|tccd|tdie|auxtin[0-9]*|cputin)$"} > 75)) * + on(instance) group_left (nodename) node_uname_info{nodename=~".+"}' for: 5m labels: severity: warning