From b024bc5219539e566463d63349a592330da53bc1 Mon Sep 17 00:00:00 2001 From: Tom Hughes Date: Mon, 5 Aug 2024 14:53:06 +0100 Subject: [PATCH 1/1] Add load average alert --- .../prometheus/templates/default/alert_rules.yml.erb | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/cookbooks/prometheus/templates/default/alert_rules.yml.erb b/cookbooks/prometheus/templates/default/alert_rules.yml.erb index b78bbaddd..dfd885bb8 100644 --- a/cookbooks/prometheus/templates/default/alert_rules.yml.erb +++ b/cookbooks/prometheus/templates/default/alert_rules.yml.erb @@ -331,6 +331,15 @@ groups: alertgroup: "{{ $labels.site }}" annotations: power: "{{ $value }} dBm" + - name: load + rules: + - alert: load average + expr: sum(node_load5) by (instance) / count(node_cpu_frequency_max_hertz) by (instance) > 2 + for: 5m + labels: + alertgroup: "{{ $labels.instance }}" + annotations: + load: "{{ $value | humanizePercentage }}" - name: mail rules: - alert: exim down -- 2.39.5