Inhibit prometheus-agent alerts when a cluster has no worker nodes (#…

…1395) * Inhibit prometheas-agent alerts when a cluster has no worker nodes --------- Co-authored-by: Herve Nicol <12008875+hervenicol@users.noreply.github.com>
giantswarm · Oct 19, 2024 · ebd1682 · ebd1682
1 parent 948e174
commit ebd1682
Show file tree

Hide file tree

Showing 6 changed files with 10 additions and 0 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -10,6 +10,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Changed
 
 - Modify `KyvernoWebhookHasNoAvailableReplicas` to check specifically for Kyverno resource webhook.
+- Inhibit prometheas-agent alerts when a cluster has no worker nodes (AWS vintage only for now)
 
 ## [4.19.0] - 2024-10-15
 

diff --git a/helm/prometheus-rules/templates/platform/atlas/alerting-rules/prometheus-agent.rules.yml b/helm/prometheus-rules/templates/platform/atlas/alerting-rules/prometheus-agent.rules.yml
@@ -51,6 +51,7 @@ spec:
         cancel_if_cluster_is_not_running_prometheus_agent: "true"
         cancel_if_cluster_status_creating: "true"
         cancel_if_cluster_status_deleting: "true"
+        cancel_if_cluster_has_no_workers: "true"
     ## Same as PrometheusAgentFailing, but triggers inhibition earlier and does not page.
     - alert: PrometheusAgentFailingInhibition
       annotations:

diff --git a/...s/providers/capi/capa-mimir/platform/atlas/alerting-rules/prometheus-agent.rules.test.yml b/...s/providers/capi/capa-mimir/platform/atlas/alerting-rules/prometheus-agent.rules.test.yml
@@ -21,6 +21,7 @@ tests:
               team: atlas
               topic: observability
               inhibit_prometheus_agent_down: "true"
+              cancel_if_cluster_has_no_workers: "true"
               cancel_if_cluster_is_not_running_prometheus_agent: "true"
               cancel_if_cluster_status_creating: "true"
               cancel_if_cluster_status_deleting: "true"
@@ -78,6 +79,7 @@ tests:
               topic: observability
               inhibit_prometheus_agent_down: "true"
               installation: myinstall
+              cancel_if_cluster_has_no_workers: "true"
               cancel_if_cluster_is_not_running_prometheus_agent: "true"
               cancel_if_cluster_status_creating: "true"
               cancel_if_cluster_status_deleting: "true"

diff --git a/test/tests/providers/capi/capa/platform/atlas/alerting-rules/prometheus-agent.rules.test.yml b/test/tests/providers/capi/capa/platform/atlas/alerting-rules/prometheus-agent.rules.test.yml
@@ -22,6 +22,7 @@ tests:
               topic: observability
               inhibit_prometheus_agent_down: "true"
               instance: prometheus-agent
+              cancel_if_cluster_has_no_workers: "true"
               cancel_if_cluster_is_not_running_prometheus_agent: "true"
               cancel_if_cluster_status_creating: "true"
               cancel_if_cluster_status_deleting: "true"
@@ -61,6 +62,7 @@ tests:
               inhibit_prometheus_agent_down: "true"
               installation: myinstall
               instance: prometheus-agent
+              cancel_if_cluster_has_no_workers: "true"
               cancel_if_cluster_is_not_running_prometheus_agent: "true"
               cancel_if_cluster_status_creating: "true"
               cancel_if_cluster_status_deleting: "true"

diff --git a/test/tests/providers/capi/capz/platform/atlas/alerting-rules/prometheus-agent.rules.test.yml b/test/tests/providers/capi/capz/platform/atlas/alerting-rules/prometheus-agent.rules.test.yml
@@ -22,6 +22,7 @@ tests:
               topic: observability
               inhibit_prometheus_agent_down: "true"
               instance: prometheus-agent
+              cancel_if_cluster_has_no_workers: "true"
               cancel_if_cluster_is_not_running_prometheus_agent: "true"
               cancel_if_cluster_status_creating: "true"
               cancel_if_cluster_status_deleting: "true"
@@ -61,6 +62,7 @@ tests:
               inhibit_prometheus_agent_down: "true"
               installation: myinstall
               instance: prometheus-agent
+              cancel_if_cluster_has_no_workers: "true"
               cancel_if_cluster_is_not_running_prometheus_agent: "true"
               cancel_if_cluster_status_creating: "true"
               cancel_if_cluster_status_deleting: "true"

diff --git a/...tests/providers/vintage/aws/platform/atlas/alerting-rules/prometheus-agent.rules.test.yml b/...tests/providers/vintage/aws/platform/atlas/alerting-rules/prometheus-agent.rules.test.yml
@@ -22,6 +22,7 @@ tests:
               topic: observability
               inhibit_prometheus_agent_down: "true"
               instance: prometheus-agent
+              cancel_if_cluster_has_no_workers: "true"
               cancel_if_cluster_is_not_running_prometheus_agent: "true"
               cancel_if_cluster_status_creating: "true"
               cancel_if_cluster_status_deleting: "true"
@@ -61,6 +62,7 @@ tests:
               inhibit_prometheus_agent_down: "true"
               installation: myinstall
               instance: prometheus-agent
+              cancel_if_cluster_has_no_workers: "true"
               cancel_if_cluster_is_not_running_prometheus_agent: "true"
               cancel_if_cluster_status_creating: "true"
               cancel_if_cluster_status_deleting: "true"