From 46ed8eb9e4f6ae04e30e9dad0e0c677e1f458715 Mon Sep 17 00:00:00 2001 From: Tom Hughes Date: Thu, 26 Feb 2026 16:30:58 +0000 Subject: [PATCH] Update alerts to check cinc-client instead of chef-client --- cookbooks/prometheus/templates/default/alert_rules.yml.erb | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/cookbooks/prometheus/templates/default/alert_rules.yml.erb b/cookbooks/prometheus/templates/default/alert_rules.yml.erb index b6b4cc307..506b3e3ca 100644 --- a/cookbooks/prometheus/templates/default/alert_rules.yml.erb +++ b/cookbooks/prometheus/templates/default/alert_rules.yml.erb @@ -78,7 +78,7 @@ groups: - name: chef rules: - alert: chef client not running - expr: time() - node_systemd_timer_last_trigger_seconds{name="chef-client.timer"} > 3600 + expr: time() - node_systemd_timer_last_trigger_seconds{name="cinc-client.timer"} > 3600 for: 12h keep_firing_for: 10m labels: @@ -833,13 +833,13 @@ groups: - name: systemd rules: - alert: systemd failed service - expr: node_systemd_unit_state{state="failed",name!="chef-client.service"} == 1 + expr: node_systemd_unit_state{state="failed",name!="cinc-client.service"} == 1 for: 5m keep_firing_for: 150s labels: alertgroup: "{{ $labels.instance }}" - alert: systemd failed chef client service - expr: sum_over_time(node_systemd_unit_state{state="inactive",name="chef-client.service"}[6h]) == 0 + expr: sum_over_time(node_systemd_unit_state{state="inactive",name="cinc-client.service"}[6h]) == 0 for: 0m labels: alertgroup: "{{ $labels.instance }}" -- 2.39.5