Remove app label in phoenix rules (#1272)

* Remove app label in phoenix rules * Apply suggestions from code review Co-authored-by: Marie Roque <[email protected]> --------- Co-authored-by: Marie Roque <[email protected]>
giantswarm · Jul 3, 2024 · 0e658d1 · 0e658d1
1 parent 15ee37d
commit 0e658d1
Show file tree

Hide file tree

Showing 3 changed files with 11 additions and 7 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -7,6 +7,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Changed
+
+- Get rid of the `app`, `role` and `node` external labels in Phoenix rules.
+
 ## [4.4.2] - 2024-07-02
 
 ### Added

diff --git a/...heus-rules/templates/kaas/phoenix/alerting-rules/vintage.aws.management-cluster.rules.yml b/...heus-rules/templates/kaas/phoenix/alerting-rules/vintage.aws.management-cluster.rules.yml
@@ -18,7 +18,7 @@ spec:
       annotations:
         description: '{{`Cluster {{ $labels.cluster_id }} creation is taking longer than expected.`}}'
         opsrecipe: cluster-creation-failed/
-      expr: (statusresource_cluster_status{app=~"aws-operator.*", status="Creating"} == 1 or cluster_operator_cluster_status{app=~"cluster-operator.*", status="Creating", provider="aws"} == 1)
+      expr: (statusresource_cluster_status{pod=~"aws-operator.*", status="Creating"} == 1 or cluster_operator_cluster_status{pod=~"cluster-operator.*", status="Creating", provider="aws"} == 1)
       for: 30m
       labels:
         area: kaas
@@ -31,7 +31,7 @@ spec:
       annotations:
         description: '{{`Cluster {{ $labels.cluster_id }} update is taking longer than expected.`}}'
         opsrecipe: cluster-update-failed/
-      expr: (statusresource_cluster_status{app=~"aws-operator.*", status="Updating"} == 1 or cluster_operator_cluster_status{app=~"cluster-operator.*", status="Updating", provider="aws"} == 1)
+      expr: (statusresource_cluster_status{pod=~"aws-operator.*", status="Updating"} == 1 or cluster_operator_cluster_status{pod=~"cluster-operator.*", status="Updating", provider="aws"} == 1)
       for: 3h
       labels:
         area: kaas
@@ -44,7 +44,7 @@ spec:
       annotations:
         description: '{{`Cluster {{ $labels.cluster_id }} deletion is taking longer than expected.`}}'
         opsrecipe: cluster-deletion-failed/
-      expr: (statusresource_cluster_status{app=~"aws-operator.*", status="Deleting"} == 1 or cluster_operator_cluster_status{app=~"cluster-operator.*", status="Deleting", provider="aws"} == 1)
+      expr: (statusresource_cluster_status{pod=~"aws-operator.*", status="Deleting"} == 1 or cluster_operator_cluster_status{pod=~"cluster-operator.*", status="Deleting", provider="aws"} == 1)
       for: 1h
       labels:
         area: kaas

diff --git a/helm/prometheus-rules/templates/kaas/phoenix/alerting-rules/vintage.vault.rules.yml b/helm/prometheus-rules/templates/kaas/phoenix/alerting-rules/vintage.vault.rules.yml
@@ -40,9 +40,9 @@ spec:
         topic: vault
     - alert: ClusterServiceVaultTokenAlmostExpired
       annotations:
-        description: '{{`Vault token for {{ $labels.app }} ({{ $labels.instance }}) is about to expire.`}}'
+        description: '{{`Vault token for {{ $labels.job }} ({{ $labels.instance }}) is about to expire.`}}'
         opsrecipe: recreate-vault-tokens/
-      expr: sum((cluster_service_vault_token_expire_time - time()) < (60 * 60 * 24 * 7)) BY (app, instance)
+      expr: sum((cluster_service_vault_token_expire_time - time()) < (60 * 60 * 24 * 7)) BY (job, instance)
       for: 5m
       labels:
         area: kaas
@@ -65,9 +65,9 @@ spec:
         topic: vault
     - alert: CertOperatorVaultTokenAlmostExpired
       annotations:
-        description: '{{`Vault token for {{ $labels.app }} ({{ $labels.instance }}) is about to expire.`}}'
+        description: '{{`Vault token for {{ $labels.container }} ({{ $labels.instance }}) is about to expire.`}}'
         opsrecipe: cert-operator-vault-token-expired/
-      expr: sum((cert_operator_vault_token_expire_time_seconds - time()) < (60 * 60 * 24 * 7)) BY (app, instance)
+      expr: sum((cert_operator_vault_token_expire_time_seconds - time()) < (60 * 60 * 24 * 7)) BY (container, instance)
       for: 5m
       labels:
         area: kaas