Move KSM alerts from Atlas to Turtles

CHANGELOG.md

@@ -15,6 +15,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Changed
 
+- Change ownership from Atlas to Turtles/Phoenix for all vertical pod autoscaler and kube state metrics related alerts.
 - Loki alerts only during working hours
 - `PrometheusAgentFailing` does not rely on KSM metrics anymore
 - Prometheus-agent inhibition rework, run on the MC

helm/prometheus-rules/templates/alerting-rules/kube-state-metrics.rules.yml

@@ -26,7 +26,7 @@ spec:
         cancel_if_kubelet_down: "true"
         cancel_if_outside_working_hours: "true"
         severity: page
-        team: atlas
+        team: phoenix
         topic: observability
     - alert: KubeConfigMapCreatedMetricMissing
       annotations:
@@ -39,7 +39,7 @@ spec:
         cancel_if_outside_working_hours: "true"
         cancel_if_kube_state_metrics_down: "true"
         severity: page
-        team: atlas
+        team: phoenix
         topic: kubernetes
     - alert: KubeDaemonSetCreatedMetricMissing
       annotations:
@@ -52,7 +52,7 @@ spec:
         cancel_if_outside_working_hours: "true"
         cancel_if_kube_state_metrics_down: "true"
         severity: page
-        team: atlas
+        team: phoenix
         topic: kubernetes
     - alert: KubeDeploymentCreatedMetricMissing
       annotations:
@@ -65,7 +65,7 @@ spec:
         cancel_if_outside_working_hours: "true"
         cancel_if_kube_state_metrics_down: "true"
         severity: page
-        team: atlas
+        team: phoenix
         topic: kubernetes
     - alert: KubeEndpointCreatedMetricMissing
       annotations:
@@ -78,7 +78,7 @@ spec:
         cancel_if_outside_working_hours: "true"
         cancel_if_kube_state_metrics_down: "true"
         severity: page
-        team: atlas
+        team: phoenix
         topic: kubernetes
     - alert: KubeNamespaceCreatedMetricMissing
       annotations:
@@ -91,7 +91,7 @@ spec:
         cancel_if_outside_working_hours: "true"
         cancel_if_kube_state_metrics_down: "true"
         severity: page
-        team: atlas
+        team: phoenix
         topic: kubernetes
     - alert: KubeNodeCreatedMetricMissing
       annotations:
@@ -104,7 +104,7 @@ spec:
         cancel_if_outside_working_hours: "true"
         cancel_if_kube_state_metrics_down: "true"
         severity: page
-        team: atlas
+        team: phoenix
         topic: kubernetes
     - alert: KubePodCreatedMetricMissing
       annotations:
@@ -117,7 +117,7 @@ spec:
         cancel_if_outside_working_hours: "true"
         cancel_if_kube_state_metrics_down: "true"
         severity: page
-        team: atlas
+        team: phoenix
         topic: kubernetes
     - alert: KubeReplicaSetCreatedMetricMissing
       annotations:
@@ -130,7 +130,7 @@ spec:
         cancel_if_outside_working_hours: "true"
         cancel_if_kube_state_metrics_down: "true"
         severity: page
-        team: atlas
+        team: phoenix
         topic: kubernetes
     - alert: KubeSecretCreatedMetricMissing
       annotations:
@@ -143,7 +143,7 @@ spec:
         cancel_if_outside_working_hours: "true"
         cancel_if_kube_state_metrics_down: "true"
         severity: page
-        team: atlas
+        team: phoenix
         topic: kubernetes
     - alert: KubeServiceCreatedMetricMissing
       annotations:
@@ -156,5 +156,5 @@ spec:
         cancel_if_outside_working_hours: "true"
         cancel_if_kube_state_metrics_down: "true"
         severity: page
-        team: atlas
+        team: phoenix
         topic: kubernetes

helm/prometheus-rules/templates/alerting-rules/up.all.rules.yml

@@ -74,5 +74,5 @@ spec:
         cancel_if_kubelet_down: "true"
         cancel_if_outside_working_hours: "false"
         severity: page
-        team: atlas
+        team: phoenix
         topic: observability

helm/prometheus-rules/templates/alerting-rules/vpa.all.rules.yml

@@ -27,5 +27,5 @@ spec:
         cancel_if_scrape_timeout: "true"
         cancel_if_outside_working_hours: "true"
         severity: page
-        team: atlas
+        team: phoenix
         topic: observability

helm/prometheus-rules/templates/recording-rules/service-level.rules.yml

@@ -331,7 +331,7 @@ spec:
 
     # -- VPA
     # Amount of requests for VPA
-    - expr: label_replace(count(up{app=~'vertical-pod-autoscaler.*'}) by (cluster_type,cluster_id), "label_application_giantswarm_io_team", "atlas", "", "")
+    - expr: label_replace(count(up{app=~'vertical-pod-autoscaler.*'}) by (cluster_type,cluster_id), "label_application_giantswarm_io_team", "phoenix", "", "")
       labels:
         class: MEDIUM
         area: platform
@@ -344,7 +344,7 @@ spec:
     # and summed with 1 so the final result is 0 : no error recorded.
     # If up was unsuccessful, there is an error. Up returns 0, multiplied by -1 and summed
     # with 1 so the final result is 1 : 1 error is recorded .
-    - expr: label_replace(sum((up{app=~'vertical-pod-autoscaler.*'} * -1) + 1) by (cluster_id, cluster_type), "label_application_giantswarm_io_team", "atlas", "", "")
+    - expr: label_replace(sum((up{app=~'vertical-pod-autoscaler.*'} * -1) + 1) by (cluster_id, cluster_type), "label_application_giantswarm_io_team", "phoenix", "", "")
       labels:
         class: MEDIUM
         area: platform

test/tests/providers/global/up.all.rules.test.yml

@@ -58,7 +58,7 @@ tests:
               cancel_if_outside_working_hours: "false"
               inhibit_kube_state_metrics_down: "true"
               severity: "page"
-              team: "atlas"
+              team: "phoenix"
               topic: "observability"
             exp_annotations:
               description: "KubeStateMetrics () is down."
@@ -80,7 +80,7 @@ tests:
               cancel_if_outside_working_hours: "false"
               inhibit_kube_state_metrics_down: "true"
               severity: "page"
-              team: "atlas"
+              team: "phoenix"
               topic: "observability"
             exp_annotations:
               description: "KubeStateMetrics () is down."
@@ -108,7 +108,7 @@ tests:
               cancel_if_outside_working_hours: "false"
               inhibit_kube_state_metrics_down: "true"
               severity: "page"
-              team: "atlas"
+              team: "phoenix"
               topic: "observability"
             exp_annotations:
               description: "KubeStateMetrics () is down."
@@ -161,7 +161,7 @@ tests:
               cancel_if_outside_working_hours: "false"
               inhibit_kube_state_metrics_down: "true"
               severity: "page"
-              team: "atlas"
+              team: "phoenix"
               topic: "observability"
             exp_annotations:
               description: "KubeStateMetrics () is down."
@@ -183,7 +183,7 @@ tests:
               cancel_if_outside_working_hours: "false"
               inhibit_kube_state_metrics_down: "true"
               severity: "page"
-              team: "atlas"
+              team: "phoenix"
               topic: "observability"
             exp_annotations:
               description: "KubeStateMetrics () is down."