rename prometheus-agent inbitions to monitoring agent to be able to t…

…ake alloy into account
giantswarm · Oct 29, 2024 · 0e7f149 · 0e7f149
1 parent 78fa24f
commit 0e7f149
Show file tree

Hide file tree

Showing 32 changed files with 157 additions and 153 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
+
+- Rename all `prometheus-agent` related inhibitions to `monitoring-agent` inhibitions.
+
 ## [4.21.1] - 2024-10-25
 
 ### Fixed
@@ -1459,7 +1463,7 @@ Fix `PromtailRequestsErrors` alerts as promtail retries after some backoff so ac
 
 - Deprecate `role=master` in favor of `role=control-plane`.
 - Rename alerts containing `Master` with `ControlPlane`
-- Added "cancel_if_prometheus_agent_down" for phoenix alerts ManagementClusterCriticalPodMetricMissing, ManagementClusterDeploymentMissingAWS, WorkloadClusterNonCriticalDeploymentNotSatisfiedKaas
+- Added `cancel_if_prometheus_agent_down` for phoenix alerts ManagementClusterCriticalPodMetricMissing, ManagementClusterDeploymentMissingAWS, WorkloadClusterNonCriticalDeploymentNotSatisfiedKaas
 
 ## [2.94.0] - 2023-04-26
 

diff --git a/.../prometheus-rules/templates/kaas/phoenix/alerting-rules/capa.management-cluster.rules.yml b/.../prometheus-rules/templates/kaas/phoenix/alerting-rules/capa.management-cluster.rules.yml
@@ -24,7 +24,7 @@ spec:
       labels:
         area: kaas
         cancel_if_kube_state_metrics_down: "true"
-        cancel_if_prometheus_agent_down: "true"
+        cancel_if_monitoring_agent_down: "true"
         cancel_if_outside_working_hours: "true"
         severity: page
         team: phoenix
@@ -39,7 +39,7 @@ spec:
       labels:
         area: kaas
         cancel_if_kube_state_metrics_down: "true"
-        cancel_if_prometheus_agent_down: "true"
+        cancel_if_monitoring_agent_down: "true"
         cancel_if_outside_working_hours: "true"
         severity: page
         team: phoenix
@@ -58,7 +58,7 @@ spec:
       labels:
         area: kaas
         cancel_if_kube_state_metrics_down: "true"
-        cancel_if_prometheus_agent_down: "true"
+        cancel_if_monitoring_agent_down: "true"
         cancel_if_outside_working_hours: "true"
         severity: page
         team: phoenix

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
@@ -154,7 +154,7 @@ spec:
       for: 15m
       labels:
         area: kaas
-        cancel_if_prometheus_agent_down: "true"
+        cancel_if_monitoring_agent_down: "true"
         cancel_if_cluster_status_creating: "true"
         cancel_if_cluster_status_deleting: "true"
         cancel_if_cluster_status_updating: "true"

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
@@ -59,7 +59,7 @@ spec:
       labels:
         area: kaas
         cancel_if_outside_working_hours: {{ include "workingHoursOnly" . }}
-        cancel_if_prometheus_agent_down: "true"
+        cancel_if_monitoring_agent_down: "true"
         severity: page
         team: phoenix
         topic: vault

diff --git a/helm/prometheus-rules/templates/kaas/turtles/alerting-rules/capi-cluster.rules.yml b/helm/prometheus-rules/templates/kaas/turtles/alerting-rules/capi-cluster.rules.yml
@@ -14,7 +14,7 @@ spec:
           for: 1h
           labels:
             area: kaas
-            cancel_if_prometheus_agent_down: "true"
+            cancel_if_monitoring_agent_down: "true"
             cancel_if_outside_working_hours: "true"
             severity: page
             team: {{ include "providerTeam" . }}
@@ -29,7 +29,7 @@ spec:
           for: 1h
           labels:
             area: kaas
-            cancel_if_prometheus_agent_down: "true"
+            cancel_if_monitoring_agent_down: "true"
             cancel_if_outside_working_hours: "true"
             severity: notify
             team: {{ include "providerTeam" . }}
@@ -45,7 +45,7 @@ spec:
           for: 1h
           labels:
             area: kaas
-            cancel_if_prometheus_agent_down: "true"
+            cancel_if_monitoring_agent_down: "true"
             cancel_if_outside_working_hours: "true"
             severity: notify
             team: {{ include "providerTeam" . }}

diff --git a/...prometheus-rules/templates/kaas/turtles/alerting-rules/capi-kubeadmcontrolplane.rules.yml b/...prometheus-rules/templates/kaas/turtles/alerting-rules/capi-kubeadmcontrolplane.rules.yml
@@ -15,7 +15,7 @@ spec:
           for: 90m
           labels:
             area: kaas
-            cancel_if_prometheus_agent_down: "true"
+            cancel_if_monitoring_agent_down: "true"
             cancel_if_outside_working_hours: "true"
             severity: notify
             team: {{ include "providerTeam" . }}
@@ -30,7 +30,7 @@ spec:
           for: 1h
           labels:
             area: kaas
-            cancel_if_prometheus_agent_down: "true"
+            cancel_if_monitoring_agent_down: "true"
             cancel_if_outside_working_hours: "true"
             severity: notify
             team: {{ include "providerTeam" . }}

diff --git a/helm/prometheus-rules/templates/kaas/turtles/alerting-rules/capi-machine.rules.yml b/helm/prometheus-rules/templates/kaas/turtles/alerting-rules/capi-machine.rules.yml
@@ -19,7 +19,7 @@ spec:
           for: 30m
           labels:
             area: kaas
-            cancel_if_prometheus_agent_down: "true"
+            cancel_if_monitoring_agent_down: "true"
             cancel_if_outside_working_hours: "true"
             severity: page
             team: {{ include "providerTeam" . }}
@@ -29,7 +29,7 @@ spec:
           for: 1h
           labels:
             area: kaas
-            cancel_if_prometheus_agent_down: "true"
+            cancel_if_monitoring_agent_down: "true"
             cancel_if_outside_working_hours: "true"
             severity: notify
             team: {{ include "providerTeam" . }}

diff --git a/helm/prometheus-rules/templates/kaas/turtles/alerting-rules/capi-machinedeployment.rules.yml b/helm/prometheus-rules/templates/kaas/turtles/alerting-rules/capi-machinedeployment.rules.yml
@@ -14,7 +14,7 @@ spec:
           for: 15m
           labels:
             area: kaas
-            cancel_if_prometheus_agent_down: "true"
+            cancel_if_monitoring_agent_down: "true"
             cancel_if_outside_working_hours: "true"
             severity: notify
             team: {{ include "providerTeam" . }}
@@ -29,7 +29,7 @@ spec:
           for: 1h
           labels:
             area: kaas
-            cancel_if_prometheus_agent_down: "true"
+            cancel_if_monitoring_agent_down: "true"
             cancel_if_outside_working_hours: "true"
             severity: notify
             team: {{ include "providerTeam" . }}

diff --git a/helm/prometheus-rules/templates/kaas/turtles/alerting-rules/capi-machinepool.rules.yml b/helm/prometheus-rules/templates/kaas/turtles/alerting-rules/capi-machinepool.rules.yml
@@ -14,7 +14,7 @@ spec:
           for: 15m
           labels:
             area: kaas
-            cancel_if_prometheus_agent_down: "true"
+            cancel_if_monitoring_agent_down: "true"
             cancel_if_outside_working_hours: "true"
             severity: page
             team: {{ include "providerTeam" . }}
@@ -29,7 +29,7 @@ spec:
           for: 1h
           labels:
             area: kaas
-            cancel_if_prometheus_agent_down: "true"
+            cancel_if_monitoring_agent_down: "true"
             cancel_if_outside_working_hours: "true"
             severity: notify
             team: {{ include "providerTeam" . }}

diff --git a/helm/prometheus-rules/templates/kaas/turtles/alerting-rules/capi-machineset.rules.yml b/helm/prometheus-rules/templates/kaas/turtles/alerting-rules/capi-machineset.rules.yml
@@ -14,7 +14,7 @@ spec:
           for: 1h
           labels:
             area: kaas
-            cancel_if_prometheus_agent_down: "true"
+            cancel_if_monitoring_agent_down: "true"
             cancel_if_outside_working_hours: "true"
             severity: notify
             team: {{ include "providerTeam" . }}

diff --git a/.../prometheus-rules/templates/kaas/turtles/alerting-rules/capi.management-cluster.rules.yml b/.../prometheus-rules/templates/kaas/turtles/alerting-rules/capi.management-cluster.rules.yml
@@ -22,7 +22,7 @@ spec:
       labels:
         area: kaas
         cancel_if_kube_state_metrics_down: "true"
-        cancel_if_prometheus_agent_down: "true"
+        cancel_if_monitoring_agent_down: "true"
         cancel_if_outside_working_hours: "true"
         severity: page
         team: {{ include "providerTeam" . }}
@@ -37,7 +37,7 @@ spec:
       labels:
         area: kaas
         cancel_if_kube_state_metrics_down: "true"
-        cancel_if_prometheus_agent_down: "true"
+        cancel_if_monitoring_agent_down: "true"
         cancel_if_outside_working_hours: "true"
         severity: page
         team: {{ include "providerTeam" . }}
@@ -54,7 +54,7 @@ spec:
       labels:
         area: kaas
         cancel_if_kube_state_metrics_down: "true"
-        cancel_if_prometheus_agent_down: "true"
+        cancel_if_monitoring_agent_down: "true"
         cancel_if_outside_working_hours: "true"
         severity: page
         team: {{ include "providerTeam" . }}

diff --git a/helm/prometheus-rules/templates/kaas/turtles/alerting-rules/kubelet.rules.yml b/helm/prometheus-rules/templates/kaas/turtles/alerting-rules/kubelet.rules.yml
@@ -23,7 +23,7 @@ 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"
+          cancel_if_monitoring_agent_down: "true"
           severity: page
           team: turtles
           topic: kubernetes

diff --git a/helm/prometheus-rules/templates/kaas/turtles/alerting-rules/management-cluster.rules.yml b/helm/prometheus-rules/templates/kaas/turtles/alerting-rules/management-cluster.rules.yml
@@ -97,7 +97,7 @@ spec:
       for: 25m
       labels:
         area: kaas
-        cancel_if_prometheus_agent_down: "true"
+        cancel_if_monitoring_agent_down: "true"
         cancel_if_kube_state_metrics_down: "true"
         cancel_if_outside_working_hours: {{ include "workingHoursOnly" . }}
         severity: page

diff --git a/...theus-rules/templates/platform/atlas/alerting-rules/deployment.workload-cluster.rules.yml b/...theus-rules/templates/platform/atlas/alerting-rules/deployment.workload-cluster.rules.yml
@@ -46,7 +46,7 @@ spec:
       for: 30m
       labels:
         area: kaas
-        cancel_if_prometheus_agent_down: "true"
+        cancel_if_monitoring_agent_down: "true"
         cancel_if_outside_working_hours: "true"
         severity: page
         team: {{ include "providerTeam" . }}

diff --git a/...-rules/inhibit.prometheus-agent.rules.yml → ...-rules/inhibit.monitoring-agent.rules.yml b/...-rules/inhibit.prometheus-agent.rules.yml → ...-rules/inhibit.monitoring-agent.rules.yml
@@ -5,11 +5,11 @@ metadata:
   creationTimestamp: null
   labels:
     {{- include "labels.common" . | nindent 4 }}
-  name: inhibit.prometheus-agent.rules
+  name: inhibit.monitoring-agent.rules
   namespace: {{ .Values.namespace  }}
 spec:
   groups:
-  - name: inhibit.prometheus-agent
+  - name: inhibit.monitoring-agent
     rules:
     # this inhibition fires when a cluster is not running prometheus-agent.
     # we retrieve the list of existing cluster IDs from `kube_namespace_created`
@@ -38,7 +38,7 @@ spec:
           )
         ) by (cluster_id)
       labels:
-        cluster_is_not_running_prometheus_agent: "true"
+        cluster_is_not_running_monitoring_agent: "true"
         area: platform
         team: atlas
         topic: monitoring

diff --git a/helm/prometheus-rules/templates/platform/atlas/alerting-rules/kube-state-metrics.rules.yml b/helm/prometheus-rules/templates/platform/atlas/alerting-rules/kube-state-metrics.rules.yml
@@ -40,7 +40,7 @@ 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_monitoring_agent_down: "true"
         cancel_if_kubelet_down: "true"
         cancel_if_outside_working_hours: {{ include "workingHoursOnly" . }}
         severity: page

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
@@ -47,8 +47,8 @@ spec:
         severity: page
         team: atlas
         topic: observability
-        inhibit_prometheus_agent_down: "true"
-        cancel_if_cluster_is_not_running_prometheus_agent: "true"
+        inhibit_monitoring_agent_down: "true"
+        cancel_if_cluster_is_not_running_monitoring_agent: "true"
         cancel_if_cluster_status_creating: "true"
         cancel_if_cluster_status_deleting: "true"
         cancel_if_cluster_has_no_workers: "true"
@@ -89,8 +89,8 @@ spec:
         severity: none
         team: atlas
         topic: observability
-        inhibit_prometheus_agent_down: "true"
-        cancel_if_cluster_is_not_running_prometheus_agent: "true"
+        inhibit_monitoring_agent_down: "true"
+        cancel_if_cluster_is_not_running_monitoring_agent: "true"
         cancel_if_cluster_status_creating: "true"
         cancel_if_cluster_status_deleting: "true"
     ## Page Atlas if prometheus agent is missing shards to send samples to MC prometheus.
@@ -119,8 +119,8 @@ spec:
         severity: page
         team: atlas
         topic: observability
-        inhibit_prometheus_agent_down: "true"
-        cancel_if_cluster_is_not_running_prometheus_agent: "true"
+        inhibit_monitoring_agent_down: "true"
+        cancel_if_cluster_is_not_running_monitoring_agent: "true"
         cancel_if_cluster_status_creating: "true"
         cancel_if_cluster_status_deleting: "true"
         cancel_if_outside_working_hours: "true"
@@ -150,8 +150,8 @@ spec:
         severity: none
         team: atlas
         topic: observability
-        inhibit_prometheus_agent_down: "true"
-        cancel_if_cluster_is_not_running_prometheus_agent: "true"
+        inhibit_monitoring_agent_down: "true"
+        cancel_if_cluster_is_not_running_monitoring_agent: "true"
         cancel_if_cluster_status_creating: "true"
         cancel_if_cluster_status_deleting: "true"
         cancel_if_outside_working_hours: "true"
diff --git a/helm/prometheus-rules/templates/platform/atlas/alerting-rules/prometheus.rules.yml b/helm/prometheus-rules/templates/platform/atlas/alerting-rules/prometheus.rules.yml
@@ -112,6 +112,6 @@ spec:
         team: atlas
         topic: observability
         cancel_if_outside_working_hours: "true"
-        cancel_if_cluster_is_not_running_prometheus_agent: "true"
+        cancel_if_cluster_is_not_running_monitoring_agent: "true"
         cancel_if_cluster_status_creating: "true"
         cancel_if_cluster_status_deleting: "true"
diff --git a/helm/prometheus-rules/templates/platform/honeybadger/alerting-rules/chart.rules.yml b/helm/prometheus-rules/templates/platform/honeybadger/alerting-rules/chart.rules.yml
@@ -26,7 +26,7 @@ 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"
+        cancel_if_monitoring_agent_down: "true"
         severity: notify
         team: honeybadger
         topic: releng