moved KSMDown alert to the adequate file

giantswarm · Sep 19, 2023 · d7f5331 · d7f5331
1 parent 68a3ac8
commit d7f5331
Show file tree

Hide file tree

Showing 3 changed files with 28 additions and 29 deletions.
diff --git a/helm/prometheus-rules/templates/alerting-rules/kube-state-metrics.rules.yml b/helm/prometheus-rules/templates/alerting-rules/kube-state-metrics.rules.yml
@@ -10,6 +10,33 @@ spec:
   groups:
   - name: kube-state-metrics
     rules:
+    - alert: KubeStateMetricsDown
+      annotations:
+        description: '{{`KubeStateMetrics ({{ $labels.instance }}) is down.`}}'
+        opsrecipe: kube-state-metrics-down/
+      expr: |-
+        (
+          # modern clusters
+          label_replace(up{app="kube-state-metrics",instance=~".*:8080"}, "ip", "$1.$2.$3.$4", "node", "ip-(\\d+)-(\\d+)-(\\d+)-(\\d+).*") == 0 or absent(up{app="kube-state-metrics",instance=~".*:8080"} == 1)
+        )
+        and
+        (
+          # vintage clusters without servicemonitor
+          label_replace(up{app="kube-state-metrics",container=""}, "ip", "$1.$2.$3.$4", "node", "ip-(\\d+)-(\\d+)-(\\d+)-(\\d+).*") == 0 or absent(up{app="kube-state-metrics",container=""} == 1)
+        )
+      for: 15m
+      labels:
+        area: kaas
+        cancel_if_apiserver_down: "true"
+        cancel_if_cluster_status_creating: "true"
+        cancel_if_cluster_status_deleting: "true"
+        cancel_if_cluster_has_no_workers: "true"
+        inhibit_kube_state_metrics_down: "true"
+        cancel_if_kubelet_down: "true"
+        cancel_if_outside_working_hours: "false"
+        severity: page
+        team: atlas
+        topic: observability
     - alert: KubeStateMetricsSlow
       annotations:
         description: '{{`KubeStateMetrics ({{ $labels.instance }}) is too slow.`}}'

diff --git a/helm/prometheus-rules/templates/alerting-rules/up.all.rules.yml b/helm/prometheus-rules/templates/alerting-rules/up.all.rules.yml
@@ -44,31 +44,3 @@ spec:
         severity: page
         team: atlas
         topic: observability
-    - alert: KubeStateMetricsDown
-      annotations:
-        description: '{{`KubeStateMetrics ({{ $labels.instance }}) is down.`}}'
-        opsrecipe: kube-state-metrics-down/
-      expr: |-
-        (
-          # modern clusters
-          label_replace(up{app="kube-state-metrics",instance=~".*:8080"}, "ip", "$1.$2.$3.$4", "node", "ip-(\\d+)-(\\d+)-(\\d+)-(\\d+).*") == 0 or absent(up{app="kube-state-metrics",instance=~".*:8080"} == 1)
-        )
-        and
-        (
-          # vintage clusters without servicemonitor
-          label_replace(up{app="kube-state-metrics",container=""}, "ip", "$1.$2.$3.$4", "node", "ip-(\\d+)-(\\d+)-(\\d+)-(\\d+).*") == 0 or absent(up{app="kube-state-metrics",container=""} == 1)
-        )
-      for: 15m
-      labels:
-        area: kaas
-        cancel_if_apiserver_down: "true"
-        cancel_if_cluster_status_creating: "true"
-        cancel_if_cluster_status_deleting: "true"
-        cancel_if_cluster_has_no_workers: "true"
-        inhibit_kube_state_metrics_down: "true"
-        cancel_if_kubelet_down: "true"
-        cancel_if_outside_working_hours: "false"
-        severity: page
-        team: atlas
-        topic: observability
-
diff --git a/test/tests/providers/global/up.all.rules.test.yml b/test/tests/providers/global/up.all.rules.test.yml
@@ -1,6 +1,6 @@
 ---
 rule_files:
-- up.all.rules.yml
+- kube-state-metrics.rules.yml
 
 tests:
   # KubeStateMetricsDown tests