]> git.openstreetmap.org Git - chef.git/commitdiff
Add alerts for rasdaemon events
authorTom Hughes <tom@compton.nu>
Sun, 28 Aug 2022 21:25:54 +0000 (22:25 +0100)
committerTom Hughes <tom@compton.nu>
Sun, 28 Aug 2022 21:25:54 +0000 (22:25 +0100)
cookbooks/prometheus/templates/default/alert_rules.yml.erb

index ab8cfe3ece3858a26d40772350c8ffe86d559066..2920d2b16b2dc3f3bfb0c6b99d3df1ab1bc8b5ac 100644 (file)
@@ -444,6 +444,22 @@ groups:
         for: 5m
         labels:
           alertgroup: "{{ $labels.instance }}"
+  - name: rasdaemon
+    rules:
+      - alert: memory controller errors
+        expr: increase(rasdaemon_mc_events_total) > 0
+        for: 0m
+        labels:
+          alertgroup: "{{ $labels.instance }}"
+        annotations:
+          new_errors: "{{ $value }}"
+      - alert: pcie aer errors
+        expr: increase(rasdaemon_aer_events_total) > 0
+        for: 0m
+        labels:
+          alertgroup: "{{ $labels.instance }}"
+        annotations:
+          new_errors: "{{ $value }}"
   - name: smart
     rules:
       - alert: smart failure