merge with main

giantswarm · Sep 19, 2023 · b67266c · b67266c
2 parents d7f5331 + 737a5e9
commit b67266c
Show file tree

Hide file tree

Showing 6 changed files with 12 additions and 2 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -10,6 +10,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Changed
 
 - Split `KubeStateMetricsDown` alert into 2 alerts : `KubeStateMetricsDown` and `KubeStateMetricsNotRetrievingMetrics`
+- Add missing prometheus-agent inhibition to `KubeStateMetricsDown` alert
+- Change time duration before `ManagementClusterDeploymentMissingAWS` pages because it is dependant on the `PrometheusAgentFailing` alert. 
 
 ## [2.132.0] - 2023-09-15
 
@@ -172,7 +174,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [2.115.0] - 2023-07-20
 
-
 ### Added
 
 - New alert `KubeStateMetricsSlow` that inhibits KSM related alerts.

diff --git a/helm/prometheus-rules/templates/alerting-rules/aws.management-cluster.rules.yml b/helm/prometheus-rules/templates/alerting-rules/aws.management-cluster.rules.yml
@@ -149,7 +149,7 @@ spec:
         description: '{{`Deployment {{ $labels.deployment }} is missing.`}}'
         opsrecipe: management-cluster-deployment-is-missing/
       expr: absent(kube_deployment_status_condition{namespace="giantswarm", condition="Available", deployment="aws-admission-controller"})
-      for: 5m
+      for: 15m
       labels:
         area: kaas
         cancel_if_prometheus_agent_down: "true"

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
@@ -32,6 +32,7 @@ spec:
         cancel_if_cluster_status_deleting: "true"
         cancel_if_cluster_has_no_workers: "true"
         inhibit_kube_state_metrics_down: "true"
+        cancel_if_prometheus_agent_down: "true"
         cancel_if_kubelet_down: "true"
         cancel_if_outside_working_hours: "false"
         severity: page

diff --git a/helm/prometheus-rules/templates/alerting-rules/up.all.rules.yml b/helm/prometheus-rules/templates/alerting-rules/up.all.rules.yml
@@ -25,6 +25,7 @@ spec:
         cancel_if_kubelet_down: "true"
         cancel_if_cluster_has_no_workers: "true"
         cancel_if_outside_working_hours: {{ include "workingHoursOnly" . }}
+        cancel_if_prometheus_agent_down: "true"
         severity: notify
         team: honeybadger
         topic: releng
@@ -41,6 +42,7 @@ spec:
         cancel_if_kubelet_down: "true"
         cancel_if_cluster_has_no_workers: "true"
         cancel_if_outside_working_hours: "true"
+        cancel_if_prometheus_agent_down: "true"
         severity: page
         team: atlas
         topic: observability
diff --git a/helm/prometheus-rules/templates/alerting-rules/vault.rules.yml b/helm/prometheus-rules/templates/alerting-rules/vault.rules.yml
@@ -57,6 +57,7 @@ spec:
       labels:
         area: kaas
         cancel_if_outside_working_hours: {{ include "workingHoursOnly" . }}
+        cancel_if_prometheus_agent_down: "true"
         severity: page
         team: {{ include "providerTeam" . }}
         topic: vault

diff --git a/test/tests/providers/global/up.all.rules.test.yml b/test/tests/providers/global/up.all.rules.test.yml
@@ -57,6 +57,7 @@ tests:
               cancel_if_kubelet_down: "true"
               cancel_if_outside_working_hours: "false"
               inhibit_kube_state_metrics_down: "true"
+              cancel_if_prometheus_agent_down: "true"
               severity: "page"
               team: "atlas"
               topic: "observability"
@@ -79,6 +80,7 @@ tests:
               cancel_if_kubelet_down: "true"
               cancel_if_outside_working_hours: "false"
               inhibit_kube_state_metrics_down: "true"
+              cancel_if_prometheus_agent_down: "true"
               severity: "page"
               team: "atlas"
               topic: "observability"
@@ -107,6 +109,7 @@ tests:
               cancel_if_kubelet_down: "true"
               cancel_if_outside_working_hours: "false"
               inhibit_kube_state_metrics_down: "true"
+              cancel_if_prometheus_agent_down: "true"
               severity: "page"
               team: "atlas"
               topic: "observability"
@@ -160,6 +163,7 @@ tests:
               cancel_if_kubelet_down: "true"
               cancel_if_outside_working_hours: "false"
               inhibit_kube_state_metrics_down: "true"
+              cancel_if_prometheus_agent_down: "true"
               severity: "page"
               team: "atlas"
               topic: "observability"
@@ -182,6 +186,7 @@ tests:
               cancel_if_kubelet_down: "true"
               cancel_if_outside_working_hours: "false"
               inhibit_kube_state_metrics_down: "true"
+              cancel_if_prometheus_agent_down: "true"
               severity: "page"
               team: "atlas"
               topic: "observability"