Improve API server alerts

kamu-data · Sep 19, 2024 · 186efd5 · 186efd5
1 parent 27a71fb
commit 186efd5
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 5 deletions.
diff --git a/charts/kamu-api-server/Chart.yaml b/charts/kamu-api-server/Chart.yaml
@@ -2,7 +2,7 @@ apiVersion: v2
 name: kamu-api-server
 description: API server component of the Kamu Compute Node
 type: application
-version: 0.38.1
+version: 0.38.2
 appVersion: "0.38.0"
 home: https://kamu.dev
 icon: https://www.kamu.dev/images/kamu_logo_icon_bg_square.png

diff --git a/charts/kamu-api-server/templates/prometheusrule.yaml b/charts/kamu-api-server/templates/prometheusrule.yaml
@@ -11,10 +11,12 @@ spec:
     rules:
       - alert: OutboxFailedConsumers
         expr: >
-          kamu_api_server_outbox_failed_consumers_total {
-            namespace="{{ .Release.Namespace }}",
-            service="{{ include "kamu-api-server.fullname" . }}",
-          } > 0
+          sum by (namespace,service) (
+            kamu_api_server_outbox_failed_consumers_total {
+              namespace="{{ .Release.Namespace }}",
+              service="{{ include "kamu-api-server.fullname" . }}",
+            }
+          ) > 0
         annotations:
           message: >
             API server {{ .Release.Namespace }}/{{ include "kamu-api-server.fullname" . }}