From 58f843dbc6f34d137ae76e53c44e1195a19cadc9 Mon Sep 17 00:00:00 2001 From: Rob Brown Date: Thu, 12 Dec 2019 17:29:23 +0000 Subject: [PATCH] Added hardware temperature alerts --- _data/rules.yml | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/_data/rules.yml b/_data/rules.yml index a670106..65bff3c 100644 --- a/_data/rules.yml +++ b/_data/rules.yml @@ -77,6 +77,15 @@ services: description: 'SystemD service crashed' query: 'node_systemd_unit_state{state="failed"} == 1' severity: warning + - name: Physical component too hot + description: 'Physical hardware component too hot' + query: 'node_hwmon_temp_celsius > 75' + severity: warning + - name: Node overtemperature alarm + description: 'Physical node temperature alarm triggered' + query: 'node_hwmon_temp_alarm == 1' + severity: critical + - name: Docker containers exporters: