KFLUXINFRA-2067: Push Kueue metrics to RHOBS

Those metrics will be used for creating SLO alerts.

Signed-off-by: Gal Ben Haim <[email protected]>

Author: gbenhaim

components/monitoring/prometheus/production/base/monitoringstack/endpoints-params.yaml

@@ -52,6 +52,15 @@
     - '{__name__="kube_deployment_status_replicas_ready", namespace="gitops-service-argocd"}'
     - '{__name__="kube_deployment_spec_replicas", namespace=~"gitops-service-argocd"}'
 
+    # Kueue
+    - '{__name__="tekton_kueue_cel_evaluations_total"}'
+    - '{__name__="kube_pod_container_status_restarts_total", namespace=~"tekton-kueue|kueue-external-admission|openshift-kueue-operator"}'
+    - '{__name__="kube_pod_container_status_ready", namespace=~"tekton-kueue|kueue-external-admission|openshift-kueue-operator"}'
+    - '{__name__="kueue_cluster_queue_status"}'
+    - '{__name__="kueue_admission_wait_time_seconds_bucket"}'
+    - '{__name__="apiserver_admission_webhook_request_total", name="pipelinerun-kueue-defaulter.tekton-kueue.io"}'
+    - '{__name__="up", job=~".*kueue.*"}'
+
     # Namespace (expression):  "build-service"
     - '{__name__="kube_deployment_status_replicas_ready", namespace="build-service"}'
     - '{__name__="kube_deployment_status_replicas_available", namespace="build-service"}'

components/monitoring/prometheus/production/base/monitoringstack/writeRelabelConfigs.yaml

@@ -15,4 +15,5 @@
       verb|request_kind|tested_cluster|resource_type|exported_job|http_method|\
       http_route|http_status_code|gin_errors|rule_result|rule_execution_cause|\
       policy_name|policy_background_mode|rule_type|policy_type|policy_validation_mode|\
-      resource_request_operation|resource_kind|policy_change_type|event_type"
+      resource_request_operation|resource_kind|policy_change_type|event_type|\
+      name|cluster_queue"

components/monitoring/prometheus/staging/base/monitoringstack/endpoints-params.yaml

@@ -52,6 +52,15 @@
     - '{__name__="kube_deployment_status_replicas_ready", namespace="gitops-service-argocd"}'
     - '{__name__="kube_deployment_spec_replicas", namespace=~"gitops-service-argocd"}'
 
+    # Kueue
+    - '{__name__="tekton_kueue_cel_evaluations_total"}'
+    - '{__name__="kube_pod_container_status_restarts_total", namespace=~"tekton-kueue|kueue-external-admission|openshift-kueue-operator"}'
+    - '{__name__="kube_pod_container_status_ready", namespace=~"tekton-kueue|kueue-external-admission|openshift-kueue-operator"}'
+    - '{__name__="kueue_cluster_queue_status"}'
+    - '{__name__="kueue_admission_wait_time_seconds_bucket"}'
+    - '{__name__="apiserver_admission_webhook_request_total", name="pipelinerun-kueue-defaulter.tekton-kueue.io"}'
+    - '{__name__="up", job=~".*kueue.*"}'
+
     # Namespace (expression):  "build-service"
     - '{__name__="kube_deployment_status_replicas_ready", namespace="build-service"}'
     - '{__name__="kube_deployment_status_replicas_available", namespace="build-service"}'

components/monitoring/prometheus/staging/base/monitoringstack/writeRelabelConfigs.yaml

@@ -15,4 +15,5 @@
       verb|request_kind|tested_cluster|resource_type|exported_job|http_method|\
       http_route|http_status_code|gin_errors|rule_result|rule_execution_cause|\
       policy_name|policy_background_mode|rule_type|policy_type|policy_validation_mode|\
-      resource_request_operation|resource_kind|policy_change_type|event_type"
+      resource_request_operation|resource_kind|policy_change_type|event_type|\
+      name|cluster_queue"