From: Tom Hughes Date: Mon, 29 Aug 2022 18:26:41 +0000 (+0100) Subject: Fix error in rasdaemon alerts X-Git-Url: https://git.openstreetmap.org/chef.git/commitdiff_plain/44b52281d387a2a26df9cd9ac5e228c0976089fd Fix error in rasdaemon alerts --- diff --git a/cookbooks/prometheus/templates/default/alert_rules.yml.erb b/cookbooks/prometheus/templates/default/alert_rules.yml.erb index 2920d2b16..23b94727c 100644 --- a/cookbooks/prometheus/templates/default/alert_rules.yml.erb +++ b/cookbooks/prometheus/templates/default/alert_rules.yml.erb @@ -447,19 +447,19 @@ groups: - name: rasdaemon rules: - alert: memory controller errors - expr: increase(rasdaemon_mc_events_total) > 0 + expr: increase(rasdaemon_mc_events_total[1m]) > 0 for: 0m labels: alertgroup: "{{ $labels.instance }}" annotations: new_errors: "{{ $value }}" - alert: pcie aer errors - expr: increase(rasdaemon_aer_events_total) > 0 + expr: increase(rasdaemon_aer_events_total[1m]) > 0 for: 0m labels: alertgroup: "{{ $labels.instance }}" annotations: - new_errors: "{{ $value }}" + new_ercrors: "{{ $value }}" - name: smart rules: - alert: smart failure