clusterconf/monitor: add rule for stalled lxcfs loadavg

HuyThanh2102 · Jul 1, 2023 · 936e0e3 · 936e0e3
1 parent f07fc16
commit 936e0e3
Showing 1 changed file with 20 additions and 0 deletions.
diff --git a/modules/clusterconf/monitor/rules/nodes.nix b/modules/clusterconf/monitor/rules/nodes.nix
@@ -861,6 +861,26 @@
           '';
         };
       }
+
+      {
+        alert = "LxcfsLoadavgStalled";
+        expr = ''sum by (instance) (osctl_container_load1{job="nodes",role="hypervisor"}) == sum by (instance) (osctl_container_load1{job="nodes",role="hypervisor"} offset 1m)'';
+        for = "5m";
+        labels = {
+          alertclass = "lxcfs_loadavg";
+          severity = "critical";
+          frequency = "15m";
+        };
+        annotations = {
+          summary = "LXCFS loadavg is not updating (instance {{ $labels.instance }})";
+          description = ''
+            LXCFS loadavg is not updating
+
+            VALUE = {{ $value }}
+            LABELS: {{ $labels }}
+          '';
+        };
+      }
     ];
   }