=== RUN TestOdhOperator/DSCInitialization_and_DataScienceCluster_validation_E2E_Tests/Validate_DSCI_webhook_denies_invalid_PEM_on_update testing.go:1913: test executed panic(nil) or runtime.Goexit: subtest may have called FailNow on a parent test --- FAIL: TestOdhOperator/DSCInitialization_and_DataScienceCluster_validation_E2E_Tests/Validate_DSCI_webhook_denies_invalid_PEM_on_update (300.01s) === RUN TestOdhOperator/DSCInitialization_and_DataScienceCluster_validation_E2E_Tests 2026-07-09T02:03:59Z INFO Cluster config {"Operator Namespace": "redhat-ods-operator", "Application Namespace": "redhat-ods-applications", "Release": {"name":"OpenShift AI Self-Managed","version":"3.5.0-ea.2"}, "Cluster": {"type":"OpenShift","version":"4.20.12"}} test_context_test.go:1675: Timed out after 300.008s. Webhook should deny update with invalid PEM in customCABundle The function passed to Eventually failed at /workspace/tests/e2e/test_context_test.go:1664 with: Webhook should deny update with invalid PEM in customCABundle Expected an error to have occurred. Got: <nil>: nil --- FAIL: TestOdhOperator/DSCInitialization_and_DataScienceCluster_validation_E2E_Tests (300.17s) === RUN TestOdhOperator/components/group_2/kueue/Validate_autoCreateQueues_disabled_skips_queue_creation helper_test.go:156: Setting Kueue component (default-kueue) to Removed mode to start with a clean state. helper_test.go:156: Cleaning up any existing Kueue test resources. helper_test.go:156: Cleaning up Kueue cluster-scoped resources helper_test.go:156: Will attempt to delete 3 Kueue resources helper_test.go:156: Attempting to delete ClusterQueue /default helper_test.go:156: Successfully processed deletion of ClusterQueue /default helper_test.go:156: Attempting to delete ResourceFlavor /default-flavor helper_test.go:156: Successfully processed deletion of ResourceFlavor /default-flavor helper_test.go:156: Attempting to delete Kueue /cluster helper_test.go:156: Successfully processed deletion of Kueue /cluster helper_test.go:156: Ensuring LWS Operator is installed (namespace=openshift-lws-operator, name=leader-worker-set). helper_test.go:156: Ensuring LeaderWorkerSetOperator CR exists (namespace=openshift-lws-operator, name=cluster). helper_test.go:156: Ensuring OCP Kueue Operator is installed (namespace=openshift-kueue-operator, name=kueue-operator). helper_test.go:156: Creating test namespace (test-kueue-no-queues-d97g8qe8stnc7b9d043g) with Kueue management annotation. helper_test.go:156: Creating Kueue ConfigMap (kueue-manager-config) to verify default Kueue resource is created correctly. helper_test.go:156: Creating Kueue ConfigMap (kueue-manager-config) in namespace (redhat-ods-applications). helper_test.go:156: Updating DSC to set Kueue to Unmanaged with autoCreateQueues=false (default). 2026-07-09T02:16:19Z INFO unknown field "spec.components.kueue.autoCreateQueues" 2026-07-09T02:16:29Z INFO unknown field "spec.components.kueue.autoCreateQueues" helper_test.go:156: Verifying Kueue configuration (cluster) is still created. helper_test.go:156: Verifying no ClusterQueue, ResourceFlavor or LocalQueue is created (autoCreateQueues=false). testing.go:1913: test executed panic(nil) or runtime.Goexit: subtest may have called FailNow on a parent test --- FAIL: TestOdhOperator/components/group_2/kueue/Validate_autoCreateQueues_disabled_skips_queue_creation (320.77s) === RUN TestOdhOperator/components/group_2/kueue === PAUSE TestOdhOperator/components/group_2/kueue === CONT TestOdhOperator/components/group_2/kueue test_context_test.go:1106: cleanup: best-effort delete failed for /, Kind= redhat-ods-applications/kueue-manager-config: Object 'Kind' is missing in 'unstructured object has no kind' test_context_test.go:615: Timed out after 300.009s. The function passed to Eventually failed at /workspace/tests/e2e/test_context_test.go:1824 with: Expected resource list 'default' of kind 'ClusterQueue' to be empty, but it contains resources. Expected <[]unstructured.Unstructured | len:1, cap:1>: [ { Object: { "apiVersion": <string>"kueue.x-k8s.io/v1beta2", "kind": <string>"ClusterQueue", "metadata": <map[string]interface {} | len:9>{ "resourceVersion": <string>"207204332", "annotations": <map[string]interface {} | len:5>{ "platform.opendatahub.io/instance.uid": <string>"e9eb334c-e6ce-45cc-a9ed-502e56e35c13", "platform.opendatahub.io/type": <string>"OpenShift AI Self-Managed", "platform.opendatahub.io/version": <string>"3.5.0-ea.2", "platform.opendatahub.io/instance.generation": <string>"1", "platform.opendatahub.io/instance.name": <string>"default-kueue", }, "finalizers": <[]interface {} | len:1, cap:1>[ <string>"kueue.x-k8s.io/resource-in-use", ], "name": <string>"default", "uid": <string>"ffddd3c9-2432-414f-8fd8-0486c454362a", "creationTimestamp": <string>"2026-07-09T02:16:20Z", "generation": <int64>1, "labels": <map[string]interface {} | len:1>{ "platform.opendatahub.io/part-of": <string>"kueue", }, "managedFields": <[]interface {} | len:3, cap:4>[ <map[string]interface {} | len:6>{ "manager": <string>"manager", "operation": <string>"Update", "time": <string>"2026-07-09T02:16:20Z", "apiVersion": <string>"kueue.x-k8s.io/v1beta2", "fieldsType": <string>"FieldsV1", "fieldsV1": <map[string]interface {} | len:2>{ "f:metadata": <map[string]interface {} | len:2>{ "f:labels": <map[string]interface {} | len:2>{ ".": <map[string]interface {} | len:0>{}, "f:platform.opendatahub.io/part-of": <map[string]interface {} | len:0>{}, }, "f:annotations": <map[string]interface {} | len:6>{ ".": <map[string]interface {} | len:0>{}, "f:platform.opendatahub.io/instance.generation": <map[string]interface {} | len:0>{}, "f:platform.opendatahub.io/instance.name": <map[string]interface {} | len:0>{}, "f:platform.opendatahub.io/instance.uid": <map[string]interface {} | len:0>{}, "f:platform.opendatahub.io/type": <map[string]interface {} | len:0>{}, "f:platform.opendatahub.io/version": <map[string]interface {} | len:0>{}, }, }, "f:spec": <map[string]interface {} | len:7>{ "f:stopPolicy": <map[string]interface {} | len:0>{}, ".": <map[string]interface {} | len:0>{}, "f:flavorFungibility": <map[string]interface {} | len:3>{ ".": <map[string]interface {} | len:0>{}, "f:whenCanBorrow": <map[string]interface {} | len:0>{}, "f:whenCanPreempt": <map[string]interface {} | len:0>{}, }, "f:namespaceSelector": <map[string]interface {} | len:0>{}, "f:preemption": <map[string]interface {} | len:4>{ ".": <map[string]interface {} | len:0>{}, "f:borrowWithinCohort": <map[string]interface {} | len:2>{...: ..., ...: ...}, "f:reclaimWithinCohort": <map[string]interface {} | len:0>{}, "f:withinClusterQueue": <map[string]interface {} | len:0>{}, }, "f:queueingStrategy": <map[string]interface {} | len:0>{}, "f:resourceGroups": <map[string]interface {} | len:0>{}, }, }, }, <map[string]interface {} | len:6>{ "fieldsType": <string>"FieldsV1", "fieldsV1": <map[string]interface {} | len:1>{ "f:metadata": <map[string]interface {} | len:1>{ "f:finalizers": <map[string]interface {} | len:2>{ ".": <map[string]interface {} | len:0>{}, "v:\"kueue.x-k8s.io/resource-in-use\"": <map[string]interface {} | len:0>{}, }, }, }, "manager": <string>"kueue", "operation": <string>"Update", "time": <string>"2026-07-09T02:21:19Z", "apiVersion": <string>"kueue.x-k8s.io/v1beta2", }, <map[string]interface {} | len:7>{ "time": <string>"2026-07-09T02:21:19Z", "apiVersion": <string>"kueue.x-k8s.io/v1beta2", "fieldsType": <string>"FieldsV1", "fieldsV1": <map[string]interface {} | len:1>{ "f:status": <map[string]interface {} | len:7>{ "f:flavorsUsage": <map[string]interface {} | len:2>{ ".": <map[string]interface {} | len:0>{}, "k:{\"name\":\"default-flavor\"}": <map[string]interface {} | len:3>{...: ..., ...: ..., ...: ...}, }, "f:pendingWorkloads": <map[string]interface {} | len:0>{}, "f:reservingWorkloads": <map[string]interface {} | len:0>{}, ".": <map[string]interface {} | len:0>{}, "f:admittedWorkloads": <map[string]interface {} | len:0>{}, "f:conditions": <map[string]interface {} | len:2>{ ".": <map[string]interface {} | len:0>{}, "k:{\"type\":\"Active\"}": <map[string]interface {} | len:7>{...: ..., ...: ..., ...: ..., ...: ..., ...: ..., ...: ..., ...: ...}, }, "f:flavorsReservation": <map[string]interface {} | len:2>{ ".": <map[string]interface {} | len:0>{}, "k:{\"name\":\"default-flavor\"}": <map[string]interface {} | len:3>{...: ..., ...: ..., ...: ...}, }, }, }, "manager": <string>"kueue", "operation": <string>"Update", "subresource": <string>"status", }, ], }, "spec": <map[string]interface {} | len:6>{ "queueingStrategy": <string>"BestEffortFIFO", "resourceGroups": <[]interface {} | len:1, cap:1>[ <map[string]interface {} | len:2>{ "coveredResources": <[]interface {} | len:2, cap:2>[<string>"cpu", <string>"memory"], "flavors": <[]interface {} | len:1, cap:1>[ <map[string]interface {} | len:2>{ "name": <string>"default-flavor", "resources": <[]interface {} | len:2, cap:2>[ <map[string]interface {} | len:2>{...: ..., ...: ...}, <map[string]interface {} | len:2>{...: ..., ...: ...}, ], }, ], }, ], "stopPolicy": <string>"None", "flavorFungibility": <map[string]interface {} | len:2>{ "whenCanBorrow": <string>"MayStopSearch", "whenCanPreempt": <string>"TryNextFlavor", }, "namespaceSelector": <map[string]interface {} | len:1>{ "matchLabels": <map[string]interface {} | len:1>{ "kueue.openshift.io/managed": <string>"true", }, }, "preemption": <map[string]interface {} | len:3>{ "borrowWithinCohort": <map[string]interface {} | len:1>{ "policy": <string>"Never", }, "reclaimWithinCohort": <string>"Never", "withinClusterQueue": <string>"Never", }, }, "status": <map[string]interface {} | len:6>{ "pendingWorkloads": <int64>0, "reservingWorkloads": <int64>0, "admittedWorkloads": <int64>0, "conditions": <[]interface {} | len:1, cap:1>[ <map[string]interface {} | len:6>{ "status": <string>"True", "type": <string>"Active", "lastTransitionTime": <string>"2026-07-09T02:21:19Z", "message": <string>"Can admit new workloads", "observedGeneration": <int64>1, "reason": <string>"Ready", }, ], "flavorsReservation": <[]interface {} | len:1, cap:1>[ <map[string]interface {} | len:2>{ "name": <string>"default-flavor", "resources": <[]interface {} | len:2, cap:2>[ <map[string]interface {} | len:3>{ "borrowed": <string>"0", "name": <string>"cpu", "total": <string>"0", }, <map[string]interface {} | len:3>{ "borrowed": <string>"0", "name": <string>"memory", "total": <string>"0", }, ], }, ], "flavorsUsage": <[]interface {} | len:1, cap:1>[ <map[string]interface {} | len:2>{ "name": <string>"default-flavor", "resources": <[]interface {} | len:2, cap:2>[ <map[string]interface {} | len:3>{ "total": <string>"0", "borrowed": <string>"0", "name": <string>"cpu", }, <map[string]interface {} | len:3>{ "total": <string>"0", "borrowed": <string>"0", "name": <string>"memory", }, ], }, ], }, }, }, ] to be empty test_context_test.go:1106: cleanup: best-effort delete failed for /, Kind= redhat-ods-applications/kueue-manager-config: Object 'Kind' is missing in 'unstructured object has no kind' --- FAIL: TestOdhOperator/components/group_2/kueue (393.13s) === RUN TestOdhOperator/components/group_2 --- FAIL: TestOdhOperator/components/group_2 (0.00s) === RUN TestOdhOperator/components/group_4/modelsasservice/Validate_Tenant_deleted_on_disable helper_test.go:156: Verifying Tenant models-as-a-service/default-tenant is present before disable helper_test.go:156: Disabling MaaS subcomponent (setting to Removed) helper_test.go:156: Waiting for Tenant models-as-a-service/default-tenant to be deleted testing.go:1913: test executed panic(nil) or runtime.Goexit: subtest may have called FailNow on a parent test --- FAIL: TestOdhOperator/components/group_4/modelsasservice/Validate_Tenant_deleted_on_disable (430.21s) === RUN TestOdhOperator/components/group_4/modelsasservice === PAUSE TestOdhOperator/components/group_4/modelsasservice === CONT TestOdhOperator/components/group_4/modelsasservice 2026-07-09T02:25:39Z INFO Cluster config {"Operator Namespace": "redhat-ods-operator", "Application Namespace": "redhat-ods-applications", "Release": {"name":"OpenShift AI Self-Managed","version":"3.5.0-ea.2"}, "Cluster": {"type":"OpenShift","version":"4.20.12"}} controller_test.go:763: Creating MaaS PostgreSQL instance in namespace redhat-ods-applications controller_test.go:763: MaaS PostgreSQL instance and maas-db-config secret created in namespace redhat-ods-applications controller_test.go:763: Creating MaaS GatewayClass and Gateway: openshift-ingress/maas-default-gateway controller_test.go:763: Using hostname=maas.apps.rosa.rh-nightly-pm.nuth.p3.openshiftapps.com, certSecret=2o8clk8b6cj832lmkd2oj78crnf7qn6d-primary-cert-bundle-secret controller_test.go:763: MaaS Gateway openshift-ingress/maas-default-gateway created with HTTP+HTTPS listeners test_context_test.go:615: Timed out after 420.009s. The function passed to Eventually failed at /workspace/tests/e2e/test_context_test.go:1824 with: Expected resource list 'models-as-a-service/default-tenant' of kind 'Tenant' to be empty, but it contains resources. Expected <[]unstructured.Unstructured | len:1, cap:1>: [ { Object: { "apiVersion": <string>"maas.opendatahub.io/v1alpha1", "kind": <string>"Tenant", "metadata": <map[string]interface {} | len:8>{ "generation": <int64>1, "managedFields": <[]interface {} | len:2, cap:2>[ <map[string]interface {} | len:6>{ "fieldsV1": <map[string]interface {} | len:2>{ "f:metadata": <map[string]interface {} | len:1>{ "f:ownerReferences": <map[string]interface {} | len:2>{ ".": <map[string]interface {} | len:0>{}, "k:{\"uid\":\"3cef3d09-94ec-448a-999f-41167e77c92a\"}": <map[string]interface {} | len:0>{}, }, }, "f:spec": <map[string]interface {} | len:2>{ ".": <map[string]interface {} | len:0>{}, "f:gatewayRef": <map[string]interface {} | len:3>{ "f:name": <map[string]interface {} | len:0>{}, "f:namespace": <map[string]interface {} | len:0>{}, ".": <map[string]interface {} | len:0>{}, }, }, }, "manager": <string>"manager", "operation": <string>"Update", "time": <string>"2026-07-09T02:26:37Z", "apiVersion": <string>"maas.opendatahub.io/v1alpha1", "fieldsType": <string>"FieldsV1", }, <map[string]interface {} | len:7>{ "apiVersion": <string>"maas.opendatahub.io/v1alpha1", "fieldsType": <string>"FieldsV1", "fieldsV1": <map[string]interface {} | len:1>{ "f:status": <map[string]interface {} | len:3>{ ".": <map[string]interface {} | len:0>{}, "f:conditions": <map[string]interface {} | len:0>{}, "f:phase": <map[string]interface {} | len:0>{}, }, }, "manager": <string>"manager", "operation": <string>"Update", "subresource": <string>"status", "time": <string>"2026-07-09T02:27:04Z", }, ], "name": <string>"default-tenant", "namespace": <string>"models-as-a-service", "ownerReferences": <[]interface {} | len:1, cap:1>[ <map[string]interface {} | len:4>{ "apiVersion": <string>"maas.opendatahub.io/v1alpha1", "kind": <string>"Config", "name": <string>"default", "uid": <string>"3cef3d09-94ec-448a-999f-41167e77c92a", }, ], "resourceVersion": <string>"207211719", "uid": <string>"a83681a5-63d1-4538-80af-dc3a66c30617", "creationTimestamp": <string>"2026-07-09T02:26:37Z", }, "spec": <map[string]interface {} | len:1>{ "gatewayRef": <map[string]interface {} | len:2>{ "name": <string>"maas-default-gateway", "namespace": <string>"openshift-ingress", }, }, "status": <map[string]interface {} | len:2>{ "conditions": <[]interface {} | len:5, cap:8>[ <map[string]interface {} | len:6>{ "lastTransitionTime": <string>"2026-07-09T02:26:40Z", "message": <string>"AuthConfig CRD (Kuadrant) is available on the cluster", "observedGeneration": <int64>1, "reason": <string>"DependenciesMet", "status": <string>"True", "type": <string>"DependenciesAvailable", }, <map[string]interface {} | len:6>{ "lastTransitionTime": <string>"2026-07-09T02:26:40Z", "message": <string>"All prerequisites are satisfied", "observedGeneration": <int64>1, "reason": <string>"PrerequisitesMet", "status": <string>"True", "type": <string>"MaaSPrerequisitesAvailable", }, <map[string]interface {} | len:6>{ "lastTransitionTime": <string>"2026-07-09T02:26:40Z", "message": <string>"All prerequisites are satisfied", "observedGeneration": <int64>1, "reason": <string>"PrerequisitesMet", "status": <string>"False", "type": <string>"Degraded", }, <map[string]interface {} | len:6>{ "lastTransitionTime": <string>"2026-07-09T02:27:04Z", "message": <string>"maas-api deployment is available", "observedGeneration": <int64>1, "reason": <string>"DeploymentsReady", "status": <string>"True", "type": <string>"DeploymentsAvailable", }, <map[string]interface {} | len:6>{ "status": <string>"True", "type": <string>"Ready", "lastTransitionTime": <string>"2026-07-09T02:27:04Z", "message": <string>"MaaS platform manifests applied and maas-api deployment is available", "observedGeneration": <int64>1, "reason": <string>"Reconciled", }, ], "phase": <string>"Active", }, }, }, ] to be empty --- FAIL: TestOdhOperator/components/group_4/modelsasservice (521.70s) === RUN TestOdhOperator/components/group_4 --- FAIL: TestOdhOperator/components/group_4 (0.00s) === RUN TestOdhOperator/components 2026/07/09 02:21:29 TEST FAILURE DETECTED: group 2 2026/07/09 02:21:29 === RUNNING CLUSTER DIAGNOSTICS (triggered by test:group 2) === 2026/07/09 02:21:30 === CLUSTER STATE === 2026/07/09 02:21:30 Node: ip-10-0-1-132.us-east-2.compute.internal 2026/07/09 02:21:30 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/09 02:21:30 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/09 02:21:30 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/09 02:21:30 Condition Ready: True - kubelet is posting ready status 2026/07/09 02:21:30 Resources: 7500m CPU, 31236232Ki memory allocatable (of 8000m CPU, 32387208Ki memory capacity) 2026/07/09 02:21:30 Node: ip-10-0-1-39.us-east-2.compute.internal 2026/07/09 02:21:30 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/09 02:21:30 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/09 02:21:30 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/09 02:21:30 Condition Ready: True - kubelet is posting ready status 2026/07/09 02:21:30 Resources: 7500m CPU, 31236232Ki memory allocatable (of 8000m CPU, 32387208Ki memory capacity) 2026/07/09 02:21:30 Node: ip-10-0-1-7.us-east-2.compute.internal 2026/07/09 02:21:30 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/09 02:21:30 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/09 02:21:30 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/09 02:21:30 Condition Ready: True - kubelet is posting ready status 2026/07/09 02:21:30 Resources: 7500m CPU, 31236236Ki memory allocatable (of 8000m CPU, 32387212Ki memory capacity) 2026/07/09 02:21:30 === DEPLOYMENTS === 2026/07/09 02:21:30 Namespace: redhat-ods-applications 2026/07/09 02:21:30 Deployment mlflow-operator-controller-manager: 1/1 (READY) 2026/07/09 02:21:30 Deployment trustyai-service-operator-controller-manager: 1/1 (READY) 2026/07/09 02:21:30 Namespace: kube-system 2026/07/09 02:21:30 === PODS === 2026/07/09 02:21:30 Namespace redhat-ods-applications: no problematic pods found 2026/07/09 02:21:30 Namespace: kube-system 2026/07/09 02:21:30 Pod ecr-credential-refresh-initial-k6gr5: Succeeded 2026/07/09 02:21:30 Container refresh: ready=false, terminated: Completed (exit 0) 2026/07/09 02:21:30 === LOGS (CURRENT) for container refresh === 2026/07/09 02:21:30 2026-04-23 02:42:29 - Discovering ECR registries from cluster configuration... 2026/07/09 02:21:30 2026-04-23 02:42:31 - No IDMS mirrors found 2026/07/09 02:21:30 2026-04-23 02:42:31 - Skipping - no ECR IDMS mirrors found (not a zero-egress cluster) 2026/07/09 02:21:30 === END LOGS === 2026/07/09 02:21:30 === OPERATOR STATUS === 2026/07/09 02:21:30 Operator deployment: 3/3 ready 2026/07/09 02:21:30 === DSCI STATUS === 2026/07/09 02:21:30 Failed to collect DSCI data: default-dsci unhealthy conditions: MonitoringStackAvailable=False; TempoAvailable=False; OpenTelemetryCollectorAvailable=False; AlertingAvailable=False; ThanosQuerierAvailable=False; PersesAvailable=False; NodeMetricsEndpointAvailable=False 2026/07/09 02:21:30 === DSC STATUS === 2026/07/09 02:21:30 Failed to collect DSC data: default-dsc unhealthy conditions: ModelsAsServiceReady=False 2026/07/09 02:21:30 === RECENT EVENTS === 2026/07/09 02:21:30 02:18:42 INFO Pod/workload-variant-autoscaler-controller-manager-5bd688895b-jxtq2: Killing - Stopping container manager 2026/07/09 02:21:30 02:18:42 INFO Pod/model-serving-api-6688cd56bd-l2rqc: Killing - Stopping container server 2026/07/09 02:21:30 02:18:42 INFO Pod/llmisvc-controller-manager-5d65df97bb-9qsvz: Killing - Stopping container manager 2026/07/09 02:21:30 02:18:42 INFO Pod/maas-api-84449bdd5d-s5sn2: Killing - Stopping container maas-api 2026/07/09 02:21:30 02:18:42 INFO Pod/maas-controller-85bdcf9988-42z8f: Killing - Stopping container manager 2026/07/09 02:21:30 02:18:42 INFO Pod/model-registry-operator-controller-manager-66d8c86b58-7zhxb: Killing - Stopping container manager 2026/07/09 02:21:30 02:18:42 INFO Pod/odh-model-controller-867855946f-wr2rk: Killing - Stopping container manager 2026/07/09 02:21:30 02:18:41 INFO Pod/kserve-controller-manager-6c67dcb69c-ltfx6: Killing - Stopping container manager 2026/07/09 02:21:30 02:18:40 WARN ServiceMonitor/odh-model-controller-metrics-monitor: InvalidConfiguration - "redhat-ods-applications/odh-model-controller-metrics-monitor" was rejected due to invalid configuration: endpoints[0]: it accesses file system via bearer token [REDACTED] which Prometheus specification prohibits 2026/07/09 02:21:30 02:18:40 WARN ServiceMonitor/controller-manager-metrics-monitor: InvalidConfiguration - "redhat-ods-applications/controller-manager-metrics-monitor" was rejected due to invalid configuration: endpoints[0]: it accesses file system via bearer token [REDACTED] which Prometheus specification prohibits 2026/07/09 02:21:30 02:18:25 INFO Lease/odh-model-controller.opendatahub.io: LeaderElection - odh-model-controller-867855946f-wr2rk_fb4adfdb-9766-4aee-a3d5-efd1ac70197a became leader 2026/07/09 02:21:30 02:18:24 INFO Pod/workload-variant-autoscaler-controller-manager-5bd688895b-jxtq2: Started - Started container manager 2026/07/09 02:21:30 02:18:24 INFO Pod/workload-variant-autoscaler-controller-manager-5bd688895b-jxtq2: Created - Created container: manager 2026/07/09 02:21:30 02:18:24 INFO Lease/72dd1cf1.llm-d.ai: LeaderElection - workload-variant-autoscaler-controller-manager-5bd688895b-jxtq2_5d989d7c-42ac-45a4-8b43-702c80d46e8c became leader 2026/07/09 02:21:30 02:18:24 INFO Pod/workload-variant-autoscaler-controller-manager-5bd688895b-jxtq2: Pulled - Container image "quay.io/rhoai/odh-workload-variant-autoscaler-controller-rhel9@sha256:042a83d343bb9733c322eb22eeb445d8991365a2184ace45556acb7b110b6a83" already present on machine 2026/07/09 02:21:30 02:18:24 INFO Pod/workload-variant-autoscaler-controller-manager-5bd688895b-jxtq2: AddedInterface - Add eth0 [10.129.71.127/23] from ovn-kubernetes 2026/07/09 02:21:30 02:18:23 INFO Pod/workload-variant-autoscaler-controller-manager-5bd688895b-jxtq2: Scheduled - Successfully assigned redhat-ods-applications/workload-variant-autoscaler-controller-manager-5bd688895b-jxtq2 to ip-10-0-1-132.us-east-2.compute.internal 2026/07/09 02:21:30 02:18:23 INFO Deployment/workload-variant-autoscaler-controller-manager: ScalingReplicaSet - Scaled up replica set workload-variant-autoscaler-controller-manager-5bd688895b from 0 to 1 2026/07/09 02:21:30 02:18:23 INFO Pod/workload-variant-autoscaler-controller-manager-5bd688895b-54fls: Killing - Stopping container manager 2026/07/09 02:21:30 02:18:23 INFO Pod/workload-variant-autoscaler-controller-manager-5bd688895b-q6h56: Killing - Stopping container manager 2026/07/09 02:21:30 02:18:23 INFO ReplicaSet/workload-variant-autoscaler-controller-manager-5bd688895b: SuccessfulCreate - Created pod: workload-variant-autoscaler-controller-manager-5bd688895b-jxtq2 2026/07/09 02:21:30 02:18:09 INFO Pod/odh-model-controller-867855946f-wr2rk: Pulling - Pulling image "quay.io/rhoai/odh-model-controller-rhel9@sha256:b645d95a1d0ff3105935c0b8f980544d1b6003206262e4ceb77bac50fee78528" 2026/07/09 02:21:30 02:18:09 INFO Pod/odh-model-controller-867855946f-wr2rk: Started - Started container manager 2026/07/09 02:21:30 02:18:09 INFO Pod/odh-model-controller-867855946f-wr2rk: Created - Created container: manager 2026/07/09 02:21:30 02:18:09 INFO Pod/odh-model-controller-867855946f-wr2rk: Pulled - Successfully pulled image "quay.io/rhoai/odh-model-controller-rhel9@sha256:b645d95a1d0ff3105935c0b8f980544d1b6003206262e4ceb77bac50fee78528" in 563ms (563ms including waiting). Image size: 238959091 bytes. 2026/07/09 02:21:30 02:18:09 INFO Pod/odh-model-controller-867855946f-wr2rk: AddedInterface - Add eth0 [10.129.71.126/23] from ovn-kubernetes 2026/07/09 02:21:30 02:18:08 INFO Pod/odh-model-controller-867855946f-wr2rk: Scheduled - Successfully assigned redhat-ods-applications/odh-model-controller-867855946f-wr2rk to ip-10-0-1-132.us-east-2.compute.internal 2026/07/09 02:21:30 02:18:08 INFO Deployment/odh-model-controller: ScalingReplicaSet - Scaled up replica set odh-model-controller-867855946f from 0 to 1 2026/07/09 02:21:30 02:18:08 INFO Pod/odh-model-controller-867855946f-gnknj: Killing - Stopping container manager 2026/07/09 02:21:30 02:18:08 INFO ReplicaSet/odh-model-controller-867855946f: SuccessfulCreate - Created pod: odh-model-controller-867855946f-wr2rk 2026/07/09 02:21:30 02:18:08 INFO Pod/odh-model-controller-867855946f-7p8cz: Killing - Stopping container manager 2026/07/09 02:21:30 02:17:54 INFO Pod/model-serving-api-6688cd56bd-l2rqc: Started - Started container server 2026/07/09 02:21:30 02:17:54 INFO Pod/model-serving-api-6688cd56bd-l2rqc: AddedInterface - Add eth0 [10.129.71.125/23] from ovn-kubernetes 2026/07/09 02:21:30 02:17:54 INFO Pod/model-serving-api-6688cd56bd-l2rqc: Created - Created container: server 2026/07/09 02:21:30 02:17:54 INFO Pod/model-serving-api-6688cd56bd-l2rqc: Pulled - Container image "quay.io/rhoai/odh-model-serving-api-rhel9@sha256:2ed53d2b291a04804cf3c09e359c92b04ec0af9f3a842beba232efd42f7e47a0" already present on machine 2026/07/09 02:21:30 02:17:53 INFO Pod/model-serving-api-6688cd56bd-l2rqc: Scheduled - Successfully assigned redhat-ods-applications/model-serving-api-6688cd56bd-l2rqc to ip-10-0-1-132.us-east-2.compute.internal 2026/07/09 02:21:30 02:17:53 INFO Deployment/model-serving-api: ScalingReplicaSet - Scaled up replica set model-serving-api-6688cd56bd from 0 to 1 2026/07/09 02:21:30 02:17:53 INFO Pod/model-serving-api-6688cd56bd-fsvcs: Killing - Stopping container server 2026/07/09 02:21:30 02:17:53 INFO Pod/model-serving-api-6688cd56bd-974lf: Killing - Stopping container server 2026/07/09 02:21:30 02:17:53 INFO ReplicaSet/model-serving-api-6688cd56bd: SuccessfulCreate - Created pod: model-serving-api-6688cd56bd-l2rqc 2026/07/09 02:21:30 02:16:55 INFO Pod/workload-variant-autoscaler-controller-manager-5bd688895b-54fls: Created - Created container: manager 2026/07/09 02:21:30 02:16:55 INFO Pod/workload-variant-autoscaler-controller-manager-5bd688895b-54fls: Started - Started container manager 2026/07/09 02:21:30 02:16:54 INFO Pod/workload-variant-autoscaler-controller-manager-5bd688895b-54fls: Pulled - Successfully pulled image "quay.io/rhoai/odh-workload-variant-autoscaler-controller-rhel9@sha256:042a83d343bb9733c322eb22eeb445d8991365a2184ace45556acb7b110b6a83" in 1.595s (1.595s including waiting). Image size: 195240093 bytes. 2026/07/09 02:21:30 02:16:53 INFO Pod/workload-variant-autoscaler-controller-manager-5bd688895b-54fls: AddedInterface - Add eth0 [10.129.71.124/23] from ovn-kubernetes 2026/07/09 02:21:30 02:16:53 INFO Pod/workload-variant-autoscaler-controller-manager-5bd688895b-54fls: Pulling - Pulling image "quay.io/rhoai/odh-workload-variant-autoscaler-controller-rhel9@sha256:042a83d343bb9733c322eb22eeb445d8991365a2184ace45556acb7b110b6a83" 2026/07/09 02:21:30 02:16:52 INFO Pod/workload-variant-autoscaler-controller-manager-5bd688895b-54fls: Scheduled - Successfully assigned redhat-ods-applications/workload-variant-autoscaler-controller-manager-5bd688895b-54fls to ip-10-0-1-132.us-east-2.compute.internal 2026/07/09 02:21:30 02:16:52 INFO ReplicaSet/workload-variant-autoscaler-controller-manager-5bd688895b: SuccessfulCreate - Created pod: workload-variant-autoscaler-controller-manager-5bd688895b-54fls 2026/07/09 02:21:30 02:16:52 INFO Deployment/workload-variant-autoscaler-controller-manager: ScalingReplicaSet - Scaled up replica set workload-variant-autoscaler-controller-manager-5bd688895b from 1 to 2 2026/07/09 02:21:30 02:16:33 INFO Pod/odh-model-controller-867855946f-gnknj: AddedInterface - Add eth0 [10.130.10.242/23] from ovn-kubernetes 2026/07/09 02:21:30 02:16:33 INFO Pod/odh-model-controller-867855946f-gnknj: Pulling - Pulling image "quay.io/rhoai/odh-model-controller-rhel9@sha256:b645d95a1d0ff3105935c0b8f980544d1b6003206262e4ceb77bac50fee78528" 2026/07/09 02:21:30 02:16:33 INFO Pod/odh-model-controller-867855946f-gnknj: Pulled - Successfully pulled image "quay.io/rhoai/odh-model-controller-rhel9@sha256:b645d95a1d0ff3105935c0b8f980544d1b6003206262e4ceb77bac50fee78528" in 605ms (605ms including waiting). Image size: 238959091 bytes. 2026/07/09 02:21:30 02:16:33 INFO Pod/odh-model-controller-867855946f-gnknj: Created - Created container: manager 2026/07/09 02:21:30 02:16:33 INFO Pod/odh-model-controller-867855946f-gnknj: Started - Started container manager 2026/07/09 02:21:30 02:16:32 INFO Pod/odh-model-controller-867855946f-gnknj: Scheduled - Successfully assigned redhat-ods-applications/odh-model-controller-867855946f-gnknj to ip-10-0-1-39.us-east-2.compute.internal 2026/07/09 02:21:30 02:16:32 INFO ReplicaSet/odh-model-controller-867855946f: SuccessfulCreate - Created pod: odh-model-controller-867855946f-gnknj 2026/07/09 02:21:30 02:16:32 INFO Deployment/odh-model-controller: ScalingReplicaSet - Scaled up replica set odh-model-controller-867855946f from 1 to 2 2026/07/09 02:21:30 === RESOURCE QUOTAS === 2026/07/09 02:21:30 No resource quotas found in monitored namespaces 2026/07/09 02:21:30 Classification for group 2: infrastructure/dsci-unhealthy (code=1009, confidence=medium) 2026/07/09 02:21:30 Evidence: DSCI default-dsci unhealthy: default-dsci unhealthy conditions: MonitoringStackAvailable=False; TempoAvailable=False; OpenTelemetryCollectorAvailable=False; AlertingAvailable=False; ThanosQuerierAvailable=False; PersesAvailable=False; NodeMetricsEndpointAvailable=False FAILURE_CLASSIFICATION: {"category":"infrastructure","subcategory":"dsci-unhealthy","error_code":1009,"evidence":["DSCI default-dsci unhealthy: default-dsci unhealthy conditions: MonitoringStackAvailable=False; TempoAvailable=False; OpenTelemetryCollectorAvailable=False; AlertingAvailable=False; ThanosQuerierAvailable=False; PersesAvailable=False; NodeMetricsEndpointAvailable=False"],"confidence":"medium"} 2026/07/09 02:21:30 Diagnostics complete for failed test: group 2 controller_test.go:763: Stopping: group 2 test failed. 2026/07/09 02:21:30 Circuit breaker: failure classified as infrastructure/dsci-unhealthy (code=1009) 2026/07/09 02:21:30 Circuit breaker: infrastructure/unknown failure recorded (2/3) 2026/07/09 02:34:21 TEST FAILURE DETECTED: group 4 2026/07/09 02:34:21 === RUNNING CLUSTER DIAGNOSTICS (triggered by test:group 4) === 2026/07/09 02:34:21 === CLUSTER STATE === 2026/07/09 02:34:21 Node: ip-10-0-1-132.us-east-2.compute.internal 2026/07/09 02:34:21 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/09 02:34:21 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/09 02:34:21 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/09 02:34:21 Condition Ready: True - kubelet is posting ready status 2026/07/09 02:34:21 Resources: 7500m CPU, 31236232Ki memory allocatable (of 8000m CPU, 32387208Ki memory capacity) 2026/07/09 02:34:21 Node: ip-10-0-1-39.us-east-2.compute.internal 2026/07/09 02:34:21 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/09 02:34:21 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/09 02:34:21 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/09 02:34:21 Condition Ready: True - kubelet is posting ready status 2026/07/09 02:34:21 Resources: 7500m CPU, 31236232Ki memory allocatable (of 8000m CPU, 32387208Ki memory capacity) 2026/07/09 02:34:21 Node: ip-10-0-1-7.us-east-2.compute.internal 2026/07/09 02:34:21 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/09 02:34:21 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/09 02:34:21 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/09 02:34:21 Condition Ready: True - kubelet is posting ready status 2026/07/09 02:34:21 Resources: 7500m CPU, 31236236Ki memory allocatable (of 8000m CPU, 32387212Ki memory capacity) 2026/07/09 02:34:21 === DEPLOYMENTS === 2026/07/09 02:34:21 Failed to collect deployment data: deployments not ready: redhat-ods-applications/maas-controller (0/1) 2026/07/09 02:34:21 === PODS === 2026/07/09 02:34:21 Failed to collect pod data: redhat-ods-applications/maas-controller-85bdcf9988-2psds: container manager not ready 2026/07/09 02:34:21 === OPERATOR STATUS === 2026/07/09 02:34:21 Operator deployment: 3/3 ready 2026/07/09 02:34:21 === DSCI STATUS === 2026/07/09 02:34:21 Failed to collect DSCI data: default-dsci unhealthy conditions: MonitoringStackAvailable=False; TempoAvailable=False; OpenTelemetryCollectorAvailable=False; AlertingAvailable=False; ThanosQuerierAvailable=False; PersesAvailable=False; NodeMetricsEndpointAvailable=False 2026/07/09 02:34:21 === DSC STATUS === 2026/07/09 02:34:21 DSC default-dsc: 2026/07/09 02:34:21 Ready: True - 2026/07/09 02:34:21 ProvisioningSucceeded: True - 2026/07/09 02:34:21 ComponentsReady: True - 2026/07/09 02:34:21 AIPipelinesReady: False - Component ManagementState is set to Removed 2026/07/09 02:34:21 DashboardReady: False - Component ManagementState is set to Removed 2026/07/09 02:34:21 FeastOperatorReady: False - Component ManagementState is set to Removed 2026/07/09 02:34:21 KserveLLMInferenceServiceDependencies: True - 2026/07/09 02:34:21 KserveLLMInferenceServiceWideEPDependencies: True - 2026/07/09 02:34:21 KserveReady: True - 2026/07/09 02:34:21 KueueReady: True - 2026/07/09 02:34:21 LLM-D-WVADependencies: True - 2026/07/09 02:34:21 MLflowOperatorReady: False - Component ManagementState is set to Removed 2026/07/09 02:34:21 ModelControllerReady: True - 2026/07/09 02:34:21 ModelRegistryReady: False - Component ManagementState is set to Removed 2026/07/09 02:34:21 ModelsAsServiceReady: False - Component ManagementState is set to Removed 2026/07/09 02:34:21 OGXReady: False - Component ManagementState is set to Removed 2026/07/09 02:34:21 RayReady: False - Component ManagementState is set to Removed 2026/07/09 02:34:21 SparkOperatorReady: False - Component ManagementState is set to Removed 2026/07/09 02:34:21 TrainerReady: False - Component ManagementState is set to Removed 2026/07/09 02:34:21 TrainingOperatorReady: False - Component ManagementState is set to Removed 2026/07/09 02:34:21 TrustyAIReady: False - Component ManagementState is set to Removed 2026/07/09 02:34:21 WorkbenchesReady: False - Component ManagementState is set to Removed 2026/07/09 02:34:21 === RECENT EVENTS === 2026/07/09 02:34:21 02:33:03 INFO Pod/maas-controller-85bdcf9988-2psds: Pulled - Successfully pulled image "quay.io/rhoai/odh-maas-controller-rhel9@sha256:e291a29f5393e1114702511221154cf754b853bf1c227292acafe7777f583b07" in 516ms (516ms including waiting). Image size: 212866077 bytes. 2026/07/09 02:34:21 02:33:02 INFO Pod/maas-controller-85bdcf9988-2psds: Pulling - Pulling image "quay.io/rhoai/odh-maas-controller-rhel9@sha256:e291a29f5393e1114702511221154cf754b853bf1c227292acafe7777f583b07" 2026/07/09 02:34:21 02:32:24 WARN Pod/maas-controller-85bdcf9988-2psds: FailedToRetrieveImagePullSecret - Unable to retrieve some image pull secrets (maas-controller-dockercfg-vjnpp); attempting to pull the image may not succeed. 2026/07/09 02:34:21 02:30:13 INFO Pod/maas-controller-85bdcf9988-2psds: Pulled - Successfully pulled image "quay.io/rhoai/odh-maas-controller-rhel9@sha256:e291a29f5393e1114702511221154cf754b853bf1c227292acafe7777f583b07" in 476ms (476ms including waiting). Image size: 212866077 bytes. 2026/07/09 02:34:21 02:30:13 INFO Pod/maas-controller-85bdcf9988-2psds: Started - Started container manager 2026/07/09 02:34:21 02:30:13 INFO Pod/maas-controller-85bdcf9988-2psds: Created - Created container: manager 2026/07/09 02:34:21 02:30:04 INFO CronJob/maas-api-key-cleanup: SawCompletedJob - Saw completed job: maas-api-key-cleanup-29726070, condition: Complete 2026/07/09 02:34:21 02:30:04 INFO Job/maas-api-key-cleanup-29726070: Completed - Job completed 2026/07/09 02:34:21 02:30:00 INFO Pod/maas-api-key-cleanup-29726070-m2pb4: Scheduled - Successfully assigned redhat-ods-applications/maas-api-key-cleanup-29726070-m2pb4 to ip-10-0-1-7.us-east-2.compute.internal 2026/07/09 02:34:21 02:30:00 INFO CronJob/maas-api-key-cleanup: SuccessfulCreate - Created job maas-api-key-cleanup-29726070 2026/07/09 02:34:21 02:30:00 INFO Job/maas-api-key-cleanup-29726070: SuccessfulCreate - Created pod: maas-api-key-cleanup-29726070-m2pb4 2026/07/09 02:34:21 02:30:00 INFO Pod/maas-api-key-cleanup-29726070-m2pb4: Started - Started container cleanup 2026/07/09 02:34:21 02:30:00 INFO Pod/maas-api-key-cleanup-29726070-m2pb4: Created - Created container: cleanup 2026/07/09 02:34:21 02:30:00 INFO Pod/maas-api-key-cleanup-29726070-m2pb4: Pulled - Container image "registry.redhat.io/ubi9/ubi-minimal@sha256:907b68736aa798b2d38255b7aa070b2a70acb90803864a40f05d0ec47556ddd0" already present on machine 2026/07/09 02:34:21 02:30:00 INFO Pod/maas-api-key-cleanup-29726070-m2pb4: AddedInterface - Add eth0 [10.128.0.242/23] from ovn-kubernetes 2026/07/09 02:34:21 02:29:24 WARN ServiceMonitor/odh-model-controller-metrics-monitor: InvalidConfiguration - "redhat-ods-applications/odh-model-controller-metrics-monitor" was rejected due to invalid configuration: endpoints[0]: it accesses file system via bearer token [REDACTED] which Prometheus specification prohibits 2026/07/09 02:34:21 === RESOURCE QUOTAS === 2026/07/09 02:34:21 No resource quotas found in monitored namespaces 2026/07/09 02:34:21 Classification for group 4: infrastructure/pod-startup (code=1002, confidence=medium) 2026/07/09 02:34:21 Evidence: container maas-controller-85bdcf9988-2psds/manager waiting: CrashLoopBackOff back-off 5m0s restarting failed container=manager pod=maas-controller-85bdcf9988-2psds_redhat-ods-applications(fa0111e8-4691-48c4-b9cb-b16a37ee58d8) FAILURE_CLASSIFICATION: {"category":"infrastructure","subcategory":"pod-startup","error_code":1002,"evidence":["container maas-controller-85bdcf9988-2psds/manager waiting: CrashLoopBackOff back-off 5m0s restarting failed container=manager pod=maas-controller-85bdcf9988-2psds_redhat-ods-applications(fa0111e8-4691-48c4-b9cb-b16a37ee58d8)"],"confidence":"medium"} 2026/07/09 02:34:21 Diagnostics complete for failed test: group 4 controller_test.go:763: Stopping: group 4 test failed. 2026/07/09 02:34:21 Circuit breaker: failure classified as infrastructure/pod-startup (code=1002) 2026/07/09 02:34:21 Circuit breaker: infrastructure/unknown failure recorded (3/3) 2026/07/09 02:34:21 Circuit breaker: threshold reached (3 failures), running confirming health check... 2026/07/09 02:34:21 Circuit breaker: confirming health check passed — cluster appears healthy, resetting counter --- FAIL: TestOdhOperator/components (1653.21s) === RUN TestOdhOperator 2026/07/09 02:03:59 ARTIFACT_DIR not set, skipping periodic metrics collection 2026/07/09 02:09:10 TEST FAILURE DETECTED: DSCInitialization and DataScienceCluster validation E2E Tests 2026/07/09 02:09:10 === RUNNING CLUSTER DIAGNOSTICS (triggered by test:DSCInitialization and DataScienceCluster validation E2E Tests) === 2026/07/09 02:09:10 === CLUSTER STATE === 2026/07/09 02:09:10 Node: ip-10-0-1-132.us-east-2.compute.internal 2026/07/09 02:09:10 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/09 02:09:10 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/09 02:09:10 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/09 02:09:10 Condition Ready: True - kubelet is posting ready status 2026/07/09 02:09:10 Resources: 7500m CPU, 31236232Ki memory allocatable (of 8000m CPU, 32387208Ki memory capacity) 2026/07/09 02:09:10 Node: ip-10-0-1-39.us-east-2.compute.internal 2026/07/09 02:09:10 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/09 02:09:10 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/09 02:09:10 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/09 02:09:10 Condition Ready: True - kubelet is posting ready status 2026/07/09 02:09:10 Resources: 7500m CPU, 31236232Ki memory allocatable (of 8000m CPU, 32387208Ki memory capacity) 2026/07/09 02:09:10 Node: ip-10-0-1-7.us-east-2.compute.internal 2026/07/09 02:09:10 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/09 02:09:10 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/09 02:09:10 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/09 02:09:10 Condition Ready: True - kubelet is posting ready status 2026/07/09 02:09:10 Resources: 7500m CPU, 31236236Ki memory allocatable (of 8000m CPU, 32387212Ki memory capacity) 2026/07/09 02:09:10 === DEPLOYMENTS === 2026/07/09 02:09:10 Namespace: kube-system 2026/07/09 02:09:10 Namespace: redhat-ods-applications 2026/07/09 02:09:10 Deployment dashboard-redirect: 2/2 (READY) 2026/07/09 02:09:10 Deployment data-science-pipelines-operator-controller-manager: 1/1 (READY) 2026/07/09 02:09:10 Deployment feast-operator-controller-manager: 1/1 (READY) 2026/07/09 02:09:10 Deployment kserve-controller-manager: 1/1 (READY) 2026/07/09 02:09:10 Deployment kubeflow-trainer-controller-manager: 1/1 (READY) 2026/07/09 02:09:10 Deployment kubeflow-training-operator: 1/1 (READY) 2026/07/09 02:09:10 Deployment kuberay-operator: 1/1 (READY) 2026/07/09 02:09:10 Deployment llmisvc-controller-manager: 1/1 (READY) 2026/07/09 02:09:10 Deployment maas-api: 1/1 (READY) 2026/07/09 02:09:10 Deployment maas-controller: 1/1 (READY) 2026/07/09 02:09:10 Deployment mlflow-operator-controller-manager: 1/1 (READY) 2026/07/09 02:09:10 Deployment model-registry-operator-controller-manager: 1/1 (READY) 2026/07/09 02:09:10 Deployment model-serving-api: 1/1 (READY) 2026/07/09 02:09:10 Deployment notebook-controller-deployment: 1/1 (READY) 2026/07/09 02:09:10 Deployment odh-model-controller: 1/1 (READY) 2026/07/09 02:09:10 Deployment odh-notebook-controller-manager: 1/1 (READY) 2026/07/09 02:09:10 Deployment ogx-k8s-operator-controller-manager: 1/1 (READY) 2026/07/09 02:09:10 Deployment rhods-dashboard: 2/2 (READY) 2026/07/09 02:09:10 Deployment spark-operator-controller: 1/1 (READY) 2026/07/09 02:09:10 Deployment spark-operator-webhook: 1/1 (READY) 2026/07/09 02:09:10 Deployment trustyai-service-operator-controller-manager: 1/1 (READY) 2026/07/09 02:09:10 === PODS === 2026/07/09 02:09:10 Failed to collect pod data: redhat-ods-applications/feast-operator-controller-manager-5f8c4cc64d-f57ch: container manager restarts=1 2026/07/09 02:09:10 === OPERATOR STATUS === 2026/07/09 02:09:10 Operator deployment: 3/3 ready 2026/07/09 02:09:10 === DSCI STATUS === 2026/07/09 02:09:10 Failed to collect DSCI data: default-dsci unhealthy conditions: MonitoringStackAvailable=False; TempoAvailable=False; OpenTelemetryCollectorAvailable=False; AlertingAvailable=False; ThanosQuerierAvailable=False; PersesAvailable=False; NodeMetricsEndpointAvailable=False 2026/07/09 02:09:10 === DSC STATUS === 2026/07/09 02:09:10 DSC default-dsc: 2026/07/09 02:09:10 Ready: True - 2026/07/09 02:09:10 ProvisioningSucceeded: True - 2026/07/09 02:09:10 ModulesReady: True - All registered modules have ManagementState Removed or are not configured 2026/07/09 02:09:10 AIPipelinesReady: True - 2026/07/09 02:09:10 ComponentsReady: True - 2026/07/09 02:09:10 DashboardReady: True - 2026/07/09 02:09:10 FeastOperatorReady: True - 2026/07/09 02:09:10 KserveLLMInferenceServiceDependencies: True - 2026/07/09 02:09:10 KserveLLMInferenceServiceWideEPDependencies: True - 2026/07/09 02:09:10 KserveReady: True - 2026/07/09 02:09:10 KueueReady: True - 2026/07/09 02:09:10 LLM-D-WVADependencies: True - 2026/07/09 02:09:10 MLflowOperatorReady: True - 2026/07/09 02:09:10 MaaSPrerequisitesAvailable: True - MaaS gateway annotations and Authorino TLS are correctly configured 2026/07/09 02:09:10 ModelControllerReady: True - 2026/07/09 02:09:10 ModelRegistryReady: True - 2026/07/09 02:09:10 ModelsAsServiceReady: True - MaaS platform manifests applied and maas-api deployment is available 2026/07/09 02:09:10 OGXReady: True - 2026/07/09 02:09:10 RayReady: True - 2026/07/09 02:09:10 SparkOperatorReady: True - 2026/07/09 02:09:10 TrainerReady: True - 2026/07/09 02:09:10 TrainingOperatorReady: True - 2026/07/09 02:09:10 TrustyAIReady: True - 2026/07/09 02:09:10 WorkbenchesReady: True - 2026/07/09 02:09:10 === RECENT EVENTS === 2026/07/09 02:09:10 No recent events found in monitored namespaces 2026/07/09 02:09:10 === RESOURCE QUOTAS === 2026/07/09 02:09:10 No resource quotas found in monitored namespaces 2026/07/09 02:09:10 Classification for DSCInitialization and DataScienceCluster validation E2E Tests: infrastructure/dsci-unhealthy (code=1009, confidence=medium) 2026/07/09 02:09:10 Evidence: DSCI default-dsci unhealthy: default-dsci unhealthy conditions: MonitoringStackAvailable=False; TempoAvailable=False; OpenTelemetryCollectorAvailable=False; AlertingAvailable=False; ThanosQuerierAvailable=False; PersesAvailable=False; NodeMetricsEndpointAvailable=False FAILURE_CLASSIFICATION: {"category":"infrastructure","subcategory":"dsci-unhealthy","error_code":1009,"evidence":["DSCI default-dsci unhealthy: default-dsci unhealthy conditions: MonitoringStackAvailable=False; TempoAvailable=False; OpenTelemetryCollectorAvailable=False; AlertingAvailable=False; ThanosQuerierAvailable=False; PersesAvailable=False; NodeMetricsEndpointAvailable=False"],"confidence":"medium"} 2026/07/09 02:09:10 Diagnostics complete for failed test: DSCInitialization and DataScienceCluster validation E2E Tests controller_test.go:478: Stopping: DSCInitialization and DataScienceCluster validation E2E Tests test failed. 2026/07/09 02:09:10 Circuit breaker: failure classified as infrastructure/dsci-unhealthy (code=1009) 2026/07/09 02:09:10 Circuit breaker: infrastructure/unknown failure recorded (1/3) 2026/07/09 02:36:43 TEST FAILURE DETECTED: components 2026/07/09 02:36:43 === RUNNING CLUSTER DIAGNOSTICS (triggered by test:components) === 2026/07/09 02:36:44 === CLUSTER STATE === 2026/07/09 02:36:44 Node: ip-10-0-1-132.us-east-2.compute.internal 2026/07/09 02:36:44 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/09 02:36:44 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/09 02:36:44 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/09 02:36:44 Condition Ready: True - kubelet is posting ready status 2026/07/09 02:36:44 Resources: 7500m CPU, 31236232Ki memory allocatable (of 8000m CPU, 32387208Ki memory capacity) 2026/07/09 02:36:44 Node: ip-10-0-1-39.us-east-2.compute.internal 2026/07/09 02:36:44 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/09 02:36:44 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/09 02:36:44 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/09 02:36:44 Condition Ready: True - kubelet is posting ready status 2026/07/09 02:36:44 Resources: 7500m CPU, 31236232Ki memory allocatable (of 8000m CPU, 32387208Ki memory capacity) 2026/07/09 02:36:44 Node: ip-10-0-1-7.us-east-2.compute.internal 2026/07/09 02:36:44 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/09 02:36:44 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/09 02:36:44 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/09 02:36:44 Condition Ready: True - kubelet is posting ready status 2026/07/09 02:36:44 Resources: 7500m CPU, 31236236Ki memory allocatable (of 8000m CPU, 32387212Ki memory capacity) 2026/07/09 02:36:44 === DEPLOYMENTS === 2026/07/09 02:36:44 Failed to collect deployment data: deployments not ready: redhat-ods-applications/maas-controller (0/1) 2026/07/09 02:36:44 === PODS === 2026/07/09 02:36:44 Failed to collect pod data: redhat-ods-applications/maas-controller-85bdcf9988-2psds: container manager not ready 2026/07/09 02:36:44 === OPERATOR STATUS === 2026/07/09 02:36:44 Operator deployment: 3/3 ready 2026/07/09 02:36:44 === DSCI STATUS === 2026/07/09 02:36:44 Failed to collect DSCI data: default-dsci unhealthy conditions: MonitoringStackAvailable=False; TempoAvailable=False; OpenTelemetryCollectorAvailable=False; AlertingAvailable=False; ThanosQuerierAvailable=False; PersesAvailable=False; NodeMetricsEndpointAvailable=False 2026/07/09 02:36:44 === DSC STATUS === 2026/07/09 02:36:44 DSC default-dsc: 2026/07/09 02:36:44 Ready: True - 2026/07/09 02:36:44 ProvisioningSucceeded: True - 2026/07/09 02:36:44 ComponentsReady: True - 2026/07/09 02:36:44 AIPipelinesReady: False - Component ManagementState is set to Removed 2026/07/09 02:36:44 DashboardReady: False - Component ManagementState is set to Removed 2026/07/09 02:36:44 FeastOperatorReady: False - Component ManagementState is set to Removed 2026/07/09 02:36:44 KserveLLMInferenceServiceDependencies: True - 2026/07/09 02:36:44 KserveLLMInferenceServiceWideEPDependencies: True - 2026/07/09 02:36:44 KserveReady: True - 2026/07/09 02:36:44 KueueReady: True - 2026/07/09 02:36:44 LLM-D-WVADependencies: True - 2026/07/09 02:36:44 MLflowOperatorReady: False - Component ManagementState is set to Removed 2026/07/09 02:36:44 ModelControllerReady: True - 2026/07/09 02:36:44 ModelRegistryReady: False - Component ManagementState is set to Removed 2026/07/09 02:36:44 ModelsAsServiceReady: False - Component ManagementState is set to Removed 2026/07/09 02:36:44 OGXReady: False - Component ManagementState is set to Removed 2026/07/09 02:36:44 RayReady: False - Component ManagementState is set to Removed 2026/07/09 02:36:44 SparkOperatorReady: False - Component ManagementState is set to Removed 2026/07/09 02:36:44 TrainerReady: True - 2026/07/09 02:36:44 TrainingOperatorReady: False - Component ManagementState is set to Removed 2026/07/09 02:36:44 TrustyAIReady: False - Component ManagementState is set to Removed 2026/07/09 02:36:44 WorkbenchesReady: False - Component ManagementState is set to Removed 2026/07/09 02:36:44 === RECENT EVENTS === 2026/07/09 02:36:44 02:36:19 INFO Lease/kserve-controller-manager-leader-lock: LeaderElection - kserve-controller-manager-6c67dcb69c-7j485_4e4a9ac0-06ed-479d-96b5-f41e85015570 became leader 2026/07/09 02:36:44 02:36:17 INFO Lease/llminferenceservice-kserve-controller-manager: LeaderElection - llmisvc-controller-manager-5d65df97bb-wgkm6_ee22c8f8-6a42-4719-9c68-e0c3001c518f became leader 2026/07/09 02:36:44 02:36:04 INFO Lease/odh-model-controller.opendatahub.io: LeaderElection - odh-model-controller-6849fc49d8-dt78w_ed211767-1321-4e8c-a624-007240b31fda became leader 2026/07/09 02:36:44 02:36:00 INFO Pod/llmisvc-controller-manager-5d65df97bb-wgkm6: Started - Started container manager 2026/07/09 02:36:44 02:36:00 INFO Pod/llmisvc-controller-manager-5d65df97bb-wgkm6: Created - Created container: manager 2026/07/09 02:36:44 02:36:00 INFO Pod/kserve-controller-manager-6c67dcb69c-7j485: Pulled - Successfully pulled image "quay.io/rhoai/odh-kserve-controller-rhel9@sha256:272e4a1ff2ad34d0c660ea1e6d0e48691106380580d5067ac06f2a132781606c" in 633ms (633ms including waiting). Image size: 238435613 bytes. 2026/07/09 02:36:44 02:36:00 INFO Pod/kserve-controller-manager-6c67dcb69c-7j485: Created - Created container: manager 2026/07/09 02:36:44 02:36:00 INFO Pod/kserve-controller-manager-6c67dcb69c-7j485: Started - Started container manager 2026/07/09 02:36:44 02:36:00 INFO Pod/llmisvc-controller-manager-5d65df97bb-wgkm6: Pulled - Successfully pulled image "quay.io/rhoai/odh-kserve-llmisvc-controller-rhel9@sha256:3963f882e12e82b3725c7b940109b995b1a690929039b601b1eb8b24318bc960" in 555ms (555ms including waiting). Image size: 236366599 bytes. 2026/07/09 02:36:44 02:35:59 INFO Pod/llmisvc-controller-manager-5d65df97bb-wgkm6: Scheduled - Successfully assigned redhat-ods-applications/llmisvc-controller-manager-5d65df97bb-wgkm6 to ip-10-0-1-132.us-east-2.compute.internal 2026/07/09 02:36:44 02:35:59 INFO Pod/kserve-controller-manager-6c67dcb69c-7j485: Scheduled - Successfully assigned redhat-ods-applications/kserve-controller-manager-6c67dcb69c-7j485 to ip-10-0-1-132.us-east-2.compute.internal 2026/07/09 02:36:44 02:35:59 INFO Pod/llmisvc-controller-manager-5d65df97bb-wgkm6: AddedInterface - Add eth0 [10.129.71.147/23] from ovn-kubernetes 2026/07/09 02:36:44 02:35:59 INFO Deployment/kserve-controller-manager: ScalingReplicaSet - Scaled up replica set kserve-controller-manager-6c67dcb69c from 0 to 1 2026/07/09 02:36:44 02:35:59 INFO Deployment/llmisvc-controller-manager: ScalingReplicaSet - Scaled up replica set llmisvc-controller-manager-5d65df97bb from 0 to 1 2026/07/09 02:36:44 02:35:59 INFO ReplicaSet/llmisvc-controller-manager-5d65df97bb: SuccessfulCreate - Created pod: llmisvc-controller-manager-5d65df97bb-wgkm6 2026/07/09 02:36:44 02:35:59 INFO ReplicaSet/kserve-controller-manager-6c67dcb69c: SuccessfulCreate - Created pod: kserve-controller-manager-6c67dcb69c-7j485 2026/07/09 02:36:44 02:35:59 INFO Pod/kserve-controller-manager-6c67dcb69c-7j485: AddedInterface - Add eth0 [10.129.71.146/23] from ovn-kubernetes 2026/07/09 02:36:44 02:35:59 INFO Pod/kserve-controller-manager-6c67dcb69c-7j485: Pulling - Pulling image "quay.io/rhoai/odh-kserve-controller-rhel9@sha256:272e4a1ff2ad34d0c660ea1e6d0e48691106380580d5067ac06f2a132781606c" 2026/07/09 02:36:44 02:35:59 INFO Pod/llmisvc-controller-manager-5d65df97bb-wgkm6: Pulling - Pulling image "quay.io/rhoai/odh-kserve-llmisvc-controller-rhel9@sha256:3963f882e12e82b3725c7b940109b995b1a690929039b601b1eb8b24318bc960" 2026/07/09 02:36:44 02:35:48 INFO Pod/model-serving-api-6688cd56bd-ps9wg: Created - Created container: server 2026/07/09 02:36:44 02:35:48 INFO Pod/model-serving-api-6688cd56bd-ps9wg: AddedInterface - Add eth0 [10.129.71.145/23] from ovn-kubernetes 2026/07/09 02:36:44 02:35:48 INFO Pod/model-serving-api-6688cd56bd-ps9wg: Pulled - Container image "quay.io/rhoai/odh-model-serving-api-rhel9@sha256:2ed53d2b291a04804cf3c09e359c92b04ec0af9f3a842beba232efd42f7e47a0" already present on machine 2026/07/09 02:36:44 02:35:48 INFO Pod/model-serving-api-6688cd56bd-ps9wg: Started - Started container server 2026/07/09 02:36:44 02:35:47 WARN Pod/model-serving-api-6688cd56bd-ps9wg: FailedMount - MountVolume.SetUp failed for volume "tls-certs" : secret "model-serving-api-tls" not found 2026/07/09 02:36:44 02:35:47 WARN ServiceMonitor/odh-model-controller-metrics-monitor: InvalidConfiguration - "redhat-ods-applications/odh-model-controller-metrics-monitor" was rejected due to invalid configuration: endpoints[0]: it accesses file system via bearer token [REDACTED] which Prometheus specification prohibits 2026/07/09 02:36:44 02:35:46 INFO Pod/model-serving-api-6688cd56bd-ps9wg: Scheduled - Successfully assigned redhat-ods-applications/model-serving-api-6688cd56bd-ps9wg to ip-10-0-1-132.us-east-2.compute.internal 2026/07/09 02:36:44 02:35:46 INFO ReplicaSet/model-serving-api-6688cd56bd: SuccessfulCreate - Created pod: model-serving-api-6688cd56bd-ps9wg 2026/07/09 02:36:44 02:35:46 INFO Pod/odh-model-controller-6849fc49d8-dt78w: Pulling - Pulling image "quay.io/rhoai/odh-model-controller-rhel9@sha256:b645d95a1d0ff3105935c0b8f980544d1b6003206262e4ceb77bac50fee78528" 2026/07/09 02:36:44 02:35:46 INFO Deployment/model-serving-api: ScalingReplicaSet - Scaled up replica set model-serving-api-6688cd56bd from 0 to 1 2026/07/09 02:36:44 02:35:46 WARN ReplicaSet/model-serving-api-6688cd56bd: FailedCreate - Error creating: pods "model-serving-api-6688cd56bd-" is forbidden: error looking up service account redhat-ods-applications/model-serving-api: serviceaccount "model-serving-api" not found 2026/07/09 02:36:44 02:35:46 INFO Pod/odh-model-controller-6849fc49d8-dt78w: Started - Started container manager 2026/07/09 02:36:44 02:35:46 INFO Pod/odh-model-controller-6849fc49d8-dt78w: AddedInterface - Add eth0 [10.129.71.144/23] from ovn-kubernetes 2026/07/09 02:36:44 02:35:46 INFO Pod/odh-model-controller-6849fc49d8-dt78w: Created - Created container: manager 2026/07/09 02:36:44 02:35:46 INFO Pod/odh-model-controller-6849fc49d8-dt78w: Pulled - Successfully pulled image "quay.io/rhoai/odh-model-controller-rhel9@sha256:b645d95a1d0ff3105935c0b8f980544d1b6003206262e4ceb77bac50fee78528" in 582ms (582ms including waiting). Image size: 238959091 bytes. 2026/07/09 02:36:44 02:35:45 WARN Pod/odh-model-controller-6849fc49d8-dt78w: FailedMount - MountVolume.SetUp failed for volume "cert" : secret "odh-model-controller-webhook-cert" not found 2026/07/09 02:36:44 02:35:44 INFO Pod/odh-model-controller-6849fc49d8-dt78w: Scheduled - Successfully assigned redhat-ods-applications/odh-model-controller-6849fc49d8-dt78w to ip-10-0-1-132.us-east-2.compute.internal 2026/07/09 02:36:44 02:35:44 INFO ReplicaSet/odh-model-controller-6849fc49d8: SuccessfulCreate - Created pod: odh-model-controller-6849fc49d8-dt78w 2026/07/09 02:36:44 02:35:44 INFO Deployment/odh-model-controller: ScalingReplicaSet - Scaled up replica set odh-model-controller-6849fc49d8 from 0 to 1 2026/07/09 02:36:44 02:35:34 INFO Pod/kserve-controller-manager-6c67dcb69c-nnrgr: Killing - Stopping container manager 2026/07/09 02:36:44 02:35:34 INFO Pod/llmisvc-controller-manager-5d65df97bb-cnqlh: Killing - Stopping container manager 2026/07/09 02:36:44 02:35:34 INFO Pod/odh-model-controller-6849fc49d8-7p2gt: Killing - Stopping container manager 2026/07/09 02:36:44 02:35:34 INFO Pod/model-serving-api-6688cd56bd-p9jmf: Killing - Stopping container server 2026/07/09 02:36:44 02:35:14 INFO Lease/llminferenceservice-kserve-controller-manager: LeaderElection - llmisvc-controller-manager-5d65df97bb-cnqlh_aa1460fc-070b-45ab-a75b-5d47b264bb1f became leader 2026/07/09 02:36:44 02:35:12 INFO Lease/kserve-controller-manager-leader-lock: LeaderElection - kserve-controller-manager-6c67dcb69c-nnrgr_18365b14-4b9b-481a-ae1f-6b90fb64282b became leader 2026/07/09 02:36:44 02:34:56 INFO Pod/llmisvc-controller-manager-5d65df97bb-cnqlh: Started - Started container manager 2026/07/09 02:36:44 02:34:56 INFO Pod/llmisvc-controller-manager-5d65df97bb-cnqlh: Pulled - Successfully pulled image "quay.io/rhoai/odh-kserve-llmisvc-controller-rhel9@sha256:3963f882e12e82b3725c7b940109b995b1a690929039b601b1eb8b24318bc960" in 452ms (452ms including waiting). Image size: 236366599 bytes. 2026/07/09 02:36:44 02:34:56 INFO Pod/llmisvc-controller-manager-5d65df97bb-cnqlh: Created - Created container: manager 2026/07/09 02:36:44 02:34:55 INFO Pod/kserve-controller-manager-6c67dcb69c-nnrgr: Pulled - Successfully pulled image "quay.io/rhoai/odh-kserve-controller-rhel9@sha256:272e4a1ff2ad34d0c660ea1e6d0e48691106380580d5067ac06f2a132781606c" in 531ms (531ms including waiting). Image size: 238435613 bytes. 2026/07/09 02:36:44 02:34:55 INFO Pod/llmisvc-controller-manager-5d65df97bb-cnqlh: AddedInterface - Add eth0 [10.129.71.142/23] from ovn-kubernetes 2026/07/09 02:36:44 02:34:55 INFO Pod/llmisvc-controller-manager-5d65df97bb-cnqlh: Pulling - Pulling image "quay.io/rhoai/odh-kserve-llmisvc-controller-rhel9@sha256:3963f882e12e82b3725c7b940109b995b1a690929039b601b1eb8b24318bc960" 2026/07/09 02:36:44 02:34:55 INFO Pod/kserve-controller-manager-6c67dcb69c-nnrgr: Created - Created container: manager 2026/07/09 02:36:44 02:34:55 INFO Pod/kserve-controller-manager-6c67dcb69c-nnrgr: Started - Started container manager 2026/07/09 02:36:44 02:34:55 INFO Pod/kserve-controller-manager-6c67dcb69c-nnrgr: Pulling - Pulling image "quay.io/rhoai/odh-kserve-controller-rhel9@sha256:272e4a1ff2ad34d0c660ea1e6d0e48691106380580d5067ac06f2a132781606c" 2026/07/09 02:36:44 02:34:55 INFO Pod/kserve-controller-manager-6c67dcb69c-nnrgr: AddedInterface - Add eth0 [10.129.71.141/23] from ovn-kubernetes 2026/07/09 02:36:44 02:34:54 INFO Pod/llmisvc-controller-manager-5d65df97bb-cnqlh: Scheduled - Successfully assigned redhat-ods-applications/llmisvc-controller-manager-5d65df97bb-cnqlh to ip-10-0-1-132.us-east-2.compute.internal 2026/07/09 02:36:44 02:34:54 INFO Pod/kserve-controller-manager-6c67dcb69c-nnrgr: Scheduled - Successfully assigned redhat-ods-applications/kserve-controller-manager-6c67dcb69c-nnrgr to ip-10-0-1-132.us-east-2.compute.internal 2026/07/09 02:36:44 02:34:54 INFO ReplicaSet/llmisvc-controller-manager-5d65df97bb: SuccessfulCreate - Created pod: llmisvc-controller-manager-5d65df97bb-cnqlh 2026/07/09 02:36:44 02:34:54 WARN Pod/llmisvc-controller-manager-5d65df97bb-cnqlh: FailedMount - MountVolume.SetUp failed for volume "cert" : secret "llmisvc-webhook-server-cert" not found 2026/07/09 02:36:44 02:34:54 INFO ReplicaSet/kserve-controller-manager-6c67dcb69c: SuccessfulCreate - Created pod: kserve-controller-manager-6c67dcb69c-nnrgr 2026/07/09 02:36:44 02:34:54 INFO Deployment/kserve-controller-manager: ScalingReplicaSet - Scaled up replica set kserve-controller-manager-6c67dcb69c from 0 to 1 2026/07/09 02:36:44 02:34:54 INFO Deployment/llmisvc-controller-manager: ScalingReplicaSet - Scaled up replica set llmisvc-controller-manager-5d65df97bb from 0 to 1 2026/07/09 02:36:44 02:34:51 INFO Lease/odh-model-controller.opendatahub.io: LeaderElection - odh-model-controller-6849fc49d8-7p2gt_32057bca-4409-43c3-8548-900d576d57d0 became leader 2026/07/09 02:36:44 02:34:43 INFO Lease/trainer.kubeflow.org: LeaderElection - kubeflow-trainer-controller-manager-7ccfdd66-z2cwq_634418db-a847-4d1a-953a-132873087852 became leader 2026/07/09 02:36:44 02:34:36 INFO Pod/model-serving-api-6688cd56bd-p9jmf: Created - Created container: server 2026/07/09 02:36:44 02:34:36 INFO Pod/model-serving-api-6688cd56bd-p9jmf: Pulled - Container image "quay.io/rhoai/odh-model-serving-api-rhel9@sha256:2ed53d2b291a04804cf3c09e359c92b04ec0af9f3a842beba232efd42f7e47a0" already present on machine 2026/07/09 02:36:44 02:34:36 INFO Pod/model-serving-api-6688cd56bd-p9jmf: Started - Started container server 2026/07/09 02:36:44 02:34:36 INFO Pod/model-serving-api-6688cd56bd-p9jmf: AddedInterface - Add eth0 [10.129.71.140/23] from ovn-kubernetes 2026/07/09 02:36:44 02:34:34 INFO Pod/model-serving-api-6688cd56bd-p9jmf: Scheduled - Successfully assigned redhat-ods-applications/model-serving-api-6688cd56bd-p9jmf to ip-10-0-1-132.us-east-2.compute.internal 2026/07/09 02:36:44 02:34:34 INFO Pod/odh-model-controller-6849fc49d8-7p2gt: Created - Created container: manager 2026/07/09 02:36:44 02:34:34 WARN ServiceMonitor/odh-model-controller-metrics-monitor: InvalidConfiguration - "redhat-ods-applications/odh-model-controller-metrics-monitor" was rejected due to invalid configuration: endpoints[0]: it accesses file system via bearer token [REDACTED] which Prometheus specification prohibits 2026/07/09 02:36:44 02:34:34 WARN Pod/model-serving-api-6688cd56bd-p9jmf: FailedMount - MountVolume.SetUp failed for volume "tls-certs" : secret "model-serving-api-tls" not found 2026/07/09 02:36:44 02:34:34 WARN ReplicaSet/model-serving-api-6688cd56bd: FailedCreate - Error creating: pods "model-serving-api-6688cd56bd-" is forbidden: error looking up service account redhat-ods-applications/model-serving-api: serviceaccount "model-serving-api" not found 2026/07/09 02:36:44 02:34:34 INFO Pod/odh-model-controller-6849fc49d8-7p2gt: Started - Started container manager 2026/07/09 02:36:44 02:34:34 INFO Pod/odh-model-controller-6849fc49d8-7p2gt: AddedInterface - Add eth0 [10.129.71.139/23] from ovn-kubernetes 2026/07/09 02:36:44 02:34:34 INFO Pod/odh-model-controller-6849fc49d8-7p2gt: Pulling - Pulling image "quay.io/rhoai/odh-model-controller-rhel9@sha256:b645d95a1d0ff3105935c0b8f980544d1b6003206262e4ceb77bac50fee78528" 2026/07/09 02:36:44 02:34:34 INFO Pod/odh-model-controller-6849fc49d8-7p2gt: Pulled - Successfully pulled image "quay.io/rhoai/odh-model-controller-rhel9@sha256:b645d95a1d0ff3105935c0b8f980544d1b6003206262e4ceb77bac50fee78528" in 521ms (521ms including waiting). Image size: 238959091 bytes. 2026/07/09 02:36:44 02:34:34 INFO ReplicaSet/model-serving-api-6688cd56bd: SuccessfulCreate - Created pod: model-serving-api-6688cd56bd-p9jmf 2026/07/09 02:36:44 02:34:33 WARN Pod/odh-model-controller-6849fc49d8-7p2gt: FailedMount - MountVolume.SetUp failed for volume "cert" : secret "odh-model-controller-webhook-cert" not found 2026/07/09 02:36:44 02:34:33 INFO Deployment/model-serving-api: ScalingReplicaSet - Scaled up replica set model-serving-api-6688cd56bd from 0 to 1 2026/07/09 02:36:44 02:34:32 INFO Pod/odh-model-controller-6849fc49d8-7p2gt: Scheduled - Successfully assigned redhat-ods-applications/odh-model-controller-6849fc49d8-7p2gt to ip-10-0-1-132.us-east-2.compute.internal 2026/07/09 02:36:44 02:34:32 INFO Deployment/odh-model-controller: ScalingReplicaSet - Scaled up replica set odh-model-controller-6849fc49d8 from 0 to 1 2026/07/09 02:36:44 02:34:32 INFO ReplicaSet/odh-model-controller-6849fc49d8: SuccessfulCreate - Created pod: odh-model-controller-6849fc49d8-7p2gt 2026/07/09 02:36:44 02:34:27 INFO Pod/kubeflow-trainer-controller-manager-7ccfdd66-z2cwq: Started - Started container manager 2026/07/09 02:36:44 02:34:27 INFO Pod/kubeflow-trainer-controller-manager-7ccfdd66-z2cwq: AddedInterface - Add eth0 [10.128.0.244/23] from ovn-kubernetes 2026/07/09 02:36:44 02:34:27 INFO Pod/kubeflow-trainer-controller-manager-7ccfdd66-z2cwq: Pulled - Container image "quay.io/rhoai/odh-trainer-rhel9@sha256:59ea523e2df9c1e705c755308ac11420682081cc63d54890e2b15fbd7d8ba570" already present on machine 2026/07/09 02:36:44 02:34:27 INFO Pod/kubeflow-trainer-controller-manager-7ccfdd66-z2cwq: Created - Created container: manager 2026/07/09 02:36:44 02:34:26 INFO Pod/kubeflow-trainer-controller-manager-7ccfdd66-z2cwq: Scheduled - Successfully assigned redhat-ods-applications/kubeflow-trainer-controller-manager-7ccfdd66-z2cwq to ip-10-0-1-7.us-east-2.compute.internal 2026/07/09 02:36:44 02:34:26 INFO Deployment/kubeflow-trainer-controller-manager: ScalingReplicaSet - Scaled up replica set kubeflow-trainer-controller-manager-7ccfdd66 from 0 to 1 2026/07/09 02:36:44 02:34:26 INFO ReplicaSet/kubeflow-trainer-controller-manager-7ccfdd66: SuccessfulCreate - Created pod: kubeflow-trainer-controller-manager-7ccfdd66-z2cwq 2026/07/09 02:36:44 02:34:23 INFO Pod/odh-model-controller-6849fc49d8-v77hx: Killing - Stopping container manager 2026/07/09 02:36:44 02:34:23 INFO Pod/llmisvc-controller-manager-5d65df97bb-nklpc: Killing - Stopping container manager 2026/07/09 02:36:44 02:34:23 INFO Pod/model-serving-api-6688cd56bd-lgjnh: Killing - Stopping container server 2026/07/09 02:36:44 02:34:23 INFO Pod/kserve-controller-manager-6c67dcb69c-bs5g6: Killing - Stopping container manager 2026/07/09 02:36:44 02:34:22 WARN ServiceMonitor/odh-model-controller-metrics-monitor: InvalidConfiguration - "redhat-ods-applications/odh-model-controller-metrics-monitor" was rejected due to invalid configuration: endpoints[0]: it accesses file system via bearer token [REDACTED] which Prometheus specification prohibits 2026/07/09 02:36:44 02:33:03 INFO Pod/maas-controller-85bdcf9988-2psds: Pulled - Successfully pulled image "quay.io/rhoai/odh-maas-controller-rhel9@sha256:e291a29f5393e1114702511221154cf754b853bf1c227292acafe7777f583b07" in 516ms (516ms including waiting). Image size: 212866077 bytes. 2026/07/09 02:36:44 02:33:02 INFO Pod/maas-controller-85bdcf9988-2psds: Pulling - Pulling image "quay.io/rhoai/odh-maas-controller-rhel9@sha256:e291a29f5393e1114702511221154cf754b853bf1c227292acafe7777f583b07" 2026/07/09 02:36:44 02:32:24 WARN Pod/maas-controller-85bdcf9988-2psds: FailedToRetrieveImagePullSecret - Unable to retrieve some image pull secrets (maas-controller-dockercfg-vjnpp); attempting to pull the image may not succeed. 2026/07/09 02:36:44 === RESOURCE QUOTAS === 2026/07/09 02:36:44 No resource quotas found in monitored namespaces 2026/07/09 02:36:44 Classification for components: infrastructure/pod-startup (code=1002, confidence=medium) 2026/07/09 02:36:44 Evidence: container maas-controller-85bdcf9988-2psds/manager waiting: CrashLoopBackOff back-off 5m0s restarting failed container=manager pod=maas-controller-85bdcf9988-2psds_redhat-ods-applications(fa0111e8-4691-48c4-b9cb-b16a37ee58d8) FAILURE_CLASSIFICATION: {"category":"infrastructure","subcategory":"pod-startup","error_code":1002,"evidence":["container maas-controller-85bdcf9988-2psds/manager waiting: CrashLoopBackOff back-off 5m0s restarting failed container=manager pod=maas-controller-85bdcf9988-2psds_redhat-ods-applications(fa0111e8-4691-48c4-b9cb-b16a37ee58d8)"],"confidence":"medium"} 2026/07/09 02:36:44 Diagnostics complete for failed test: components controller_test.go:491: Stopping: components test failed. 2026/07/09 02:36:44 Circuit breaker: failure classified as infrastructure/pod-startup (code=1002) 2026/07/09 02:36:44 Circuit breaker: infrastructure/unknown failure recorded (1/3) Deletion Policy: Never. Skipping deletion tests. 2026/07/09 02:36:45 Circuit breaker: no trips during this run (threshold=3) --- FAIL: TestOdhOperator (1966.29s)