=== RUN TestOdhOperator/DAG_Ordering_E2E_Tests 2026-07-02T12:00:36Z 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":"4.19.18"}} controller_test.go:763: Ensuring clean slate: setting all components to Removed 2026-07-02T12:00:36Z INFO unknown field "spec.components.aigateway" test_context_test.go:541: Timed out after 300.004s. The function passed to Eventually failed at /workspace/tests/e2e/test_context_test.go:1795 with: Expected resource 'default-kueue' of kind 'Kueue' to not exist, but it was found. Expected <*unstructured.Unstructured | 0x2fd06d990e0>: { Object: { "apiVersion": <string>"components.platform.opendatahub.io/v1alpha1", "kind": <string>"Kueue", "metadata": <map[string]interface {} | len:9>{ "annotations": <map[string]interface {} | len:6>{ "platform.opendatahub.io/type": <string>"OpenShift AI Self-Managed", "platform.opendatahub.io/version": <string>"3.5.0-ea.2", "component.opendatahub.io/management-state": <string>"Unmanaged", "platform.opendatahub.io/instance.generation": <string>"478", "platform.opendatahub.io/instance.name": <string>"default-dsc", "platform.opendatahub.io/instance.uid": <string>"191cdb15-01aa-4da4-9798-e6b508adbf9f", }, "creationTimestamp": <string>"2026-07-02T07:55:44Z", "labels": <map[string]interface {} | len:1>{ "platform.opendatahub.io/part-of": <string>"datasciencecluster", }, "managedFields": <[]interface {} | len:2, cap:2>[ <map[string]interface {} | len:6>{ "time": <string>"2026-07-02T12:00:36Z", "apiVersion": <string>"components.platform.opendatahub.io/v1alpha1", "fieldsType": <string>"FieldsV1", "fieldsV1": <map[string]interface {} | len:2>{ "f:spec": <map[string]interface {} | len:3>{ "f:defaultClusterQueueName": <map[string]interface {} | len:0>{}, "f:defaultLocalQueueName": <map[string]interface {} | len:0>{}, "f:managementState": <map[string]interface {} | len:0>{}, }, "f:metadata": <map[string]interface {} | len:3>{ "f:annotations": <map[string]interface {} | len:6>{ "f:platform.opendatahub.io/type": <map[string]interface {} | len:0>{}, "f:platform.opendatahub.io/version": <map[string]interface {} | len:0>{}, "f:component.opendatahub.io/management-state": <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:labels": <map[string]interface {} | len:1>{ "f:platform.opendatahub.io/part-of": <map[string]interface {} | len:0>{}, }, "f:ownerReferences": <map[string]interface {} | len:1>{ "k:{\"uid\":\"191cdb15-01aa-4da4-9798-e6b508adbf9f\"}": <map[string]interface {} | len:0>{}, }, }, }, "manager": <string>"datasciencecluster", "operation": <string>"Apply", }, <map[string]interface {} | len:7>{ "apiVersion": <string>"components.platform.opendatahub.io/v1alpha1", "fieldsType": <string>"FieldsV1", "fieldsV1": <map[string]interface {} | len:2>{ "f:metadata": <map[string]interface {} | len:3>{ "f:annotations": <map[string]interface {} | len:6>{ "f:component.opendatahub.io/management-state": <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:labels": <map[string]interface {} | len:1>{ "f:platform.opendatahub.io/part-of": <map[string]interface {} | len:0>{}, }, "f:ownerReferences": <map[string]interface {} | len:1>{ "k:{\"uid\":\"191cdb15-01aa-4da4-9798-e6b508adbf9f\"}": <map[string]interface {} | len:0>{}, }, }, "f:status": <map[string]interface {} | len:3>{ "f:conditions": <map[string]interface {} | len:0>{}, "f:observedGeneration": <map[string]interface {} | len:0>{}, "f:phase": <map[string]interface {} | len:0>{}, }, }, "manager": <string>"kueue", "operation": <string>"Apply", "subresource": <string>"status", "time": <string>"2026-07-02T12:00:38Z", }, ], "name": <string>"default-kueue", "uid": <string>"4105493d-dc8d-4535-8413-abc4c8ed3ae3", "generation": <int64>1, "ownerReferences": <[]interface {} | len:1, cap:1>[ <map[string]interface {} | len:6>{ "apiVersion": <string>"datasciencecluster.opendatahub.io/v2", "blockOwnerDeletion": <bool>true, "controller": <bool>true, "kind": <string>"DataScienceCluster", "name": <string>"default-dsc", "uid": <string>"191cdb15-01aa-4da4-9798-e6b508adbf9f", }, ], "resourceVersion": <string>"375237402", }, "spec": <map[string]interface {} | len:3>{ "defaultClusterQueueName": <string>"default", "defaultLocalQueueName": <string>"default", "managementState": <string>"Unmanaged", }, "status": <map[string]interface {} | len:3>{ "phase": <string>"Ready", "conditions": <[]interface {} | len:4, cap:4>[ <map[string]interface {} | len:3>{ "type": <string>"Ready", "lastTransitionTime": <string>"2026-07-02T12:00:38Z", "status": <string>"True", }, <map[string]interface {} | len:4>{ "observedGeneration": <int64>1, "status": <string>"True", "type": <string>"ProvisioningSucceeded", "lastTransitionTime": <string>"2026-07-02T07:55:46Z", }, <map[string]interface {} | len:4>{ "lastTransitionTime": <string>"2026-07-02T12:00:38Z", "severity": <string>"Info", "status": <string>"False", "type": <string>"DeploymentsAvailable", }, <map[string]interface {} | len:4>{ "lastTransitionTime": <string>"2026-07-02T07:58:11Z", "observedGeneration": <int64>1, "status": <string>"True", "type": <string>"DependenciesAvailable", }, ], "observedGeneration": <int64>1, }, }, } to be nil --- FAIL: TestOdhOperator/DAG_Ordering_E2E_Tests (310.50s) === RUN TestOdhOperator/components/group_1/aigateway/Validate_component_enabled 2026-07-02T12:05:47Z 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":"4.19.18"}} testing.go:1913: test executed panic(nil) or runtime.Goexit: subtest may have called FailNow on a parent test --- FAIL: TestOdhOperator/components/group_1/aigateway/Validate_component_enabled (300.00s) === RUN TestOdhOperator/components/group_1/aigateway === PAUSE TestOdhOperator/components/group_1/aigateway === CONT TestOdhOperator/components/group_1/aigateway resource_applier_test.go:202: Timed out after 300.002s. The function passed to Eventually failed at /workspace/tests/e2e/resource_applier_test.go:114 with: Expected resource 'default-dsc' of kind 'DataScienceCluster' to match condition {.spec.components.aigateway.managementState == "Removed" []}. Expected <string>: map[apiVersion:datasciencecluster.opendatahub.io/v2 kind:DataScienceCluster metadata:map[annotations:map[kubectl.kubernetes.io/last-applied-configuration:{"apiVersion":"datasciencecluster.opendatahub.io/v2","kind":"DataScienceCluster","metadata":{"annotations":{},"name":"default-dsc"},"spec":{"components":{"aipipelines":{"managementState":"Removed"},"codeflare":{"managementState":"Removed"},"dashboard":{"managementState":"Managed"},"kserve":{"defaultDeploymentMode":"RawDeployment","managementState":"Managed","serving":{"managementState":"Removed","name":"knative-serving"}},"kueue":{"managementState":"Removed"},"llamastackoperator":{"managementState":"Removed"},"mlflowoperator":{"managementState":"Removed"},"modelregistry":{"managementState":"Removed"},"ogx":{"managementState":"Removed"},"ray":{"managementState":"Removed"},"sparkoperator":{"managementState":"Removed"},"trainer":{"managementState":"Removed"},"trainingoperator":{"managementState":"Removed"},"trustyai":{"managementState":"Removed"},"workbenches":{"managementState":"Removed"}}}} ] creationTimestamp:2026-06-29T13:43:26Z generation:498 managedFields:[map[apiVersion:datasciencecluster.opendatahub.io/v2 fieldsType:FieldsV1 fieldsV1:map[f:metadata:map[f:annotations:map[f:kubectl.kubernetes.io/last-applied-configuration:map[]]] f:status:map[f:components:map[f:aipipelines:map[f:managementState:map[] f:releases:map[k:{"name":"Kubeflow Pipelines"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]]]] f:feastoperator:map[f:managementState:map[] f:releases:map[k:{"name":"Feast"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]]]] f:kserve:map[f:managementState:map[] f:releases:map[k:{"name":"KServe"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]] k:{"name":"llm-d-inference-scheduler"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]] k:{"name":"llm-d-workload-variant-autoscaler"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]] k:{"name":"vLLM"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]]]] f:kueue:map[f:managementState:map[]] f:llamastackoperator:map[] f:mlflowoperator:map[f:managementState:map[] f:releases:map[k:{"name":"MLflow"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]]]] f:modelregistry:map[f:managementState:map[] f:registriesNamespace:map[] f:releases:map[k:{"name":"Kubeflow Model Registry"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]] k:{"name":"Open Data Hub Model Registry Operator"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]]]] f:ogx:map[f:managementState:map[] f:releases:map[k:{"name":"OGX Operator"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]] k:{"name":"OGX"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]]]] f:ray:map[f:managementState:map[] f:releases:map[k:{"name":"KubeRay"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]]]] f:sparkoperator:map[f:managementState:map[] f:releases:map[k:{"name":"Spark Operator"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]] k:{"name":"Spark"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]]]] f:trainer:map[f:managementState:map[] f:releases:map[k:{"name":"Kubeflow Trainer"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]]]] f:trainingoperator:map[f:managementState:map[] f:releases:map[k:{"name":"Kubeflow Training Operator"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]]]] f:trustyai:map[f:managementState:map[] f:releases:map[k:{"name":"EvalHub"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]] k:{"name":"TrustyAI Guardrails orchestrator"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]] k:{"name":"TrustyAI LMEval driver"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]] k:{"name":"TrustyAI LMEval job"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]] k:{"name":"TrustyAI builtin detectors"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]] k:{"name":"TrustyAI operator"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]] k:{"name":"TrustyAI service"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]] k:{"name":"TrustyAI sidecar gateway"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]]]] f:workbenches:map[f:managementState:map[] f:releases:map[k:{"name":"Kubeflow Notebook Controller"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]]] f:workbenchNamespace:map[]]] f:observedGeneration:map[] f:release:map[f:name:map[] f:version:map[]]]] manager:modules operation:Apply subresource:status time:2026-07-02T12:10:26Z] map[apiVersion:datasciencecluster.opendatahub.io/v2 fieldsType:FieldsV1 fieldsV1:map[f:metadata:map[f:annotations:map[f:kubectl.kubernetes.io/last-applied-configuration:map[]]] f:status:map[f:components:map[f:aipipelines:map[f:managementState:map[]] f:dashboard:map[f:managementState:map[]] f:feastoperator:map[f:managementState:map[]] f:kserve:map[f:managementState:map[] f:releases:map[k:{"name":"KServe"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]] k:{"name":"llm-d-inference-scheduler"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]] k:{"name":"llm-d-workload-variant-autoscaler"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]] k:{"name":"vLLM"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]]]] f:kueue:map[f:managementState:map[]] f:llamastackoperator:map[] f:mlflowoperator:map[f:managementState:map[]] f:modelregistry:map[f:managementState:map[]] f:ogx:map[f:managementState:map[]] f:ray:map[f:managementState:map[]] f:sparkoperator:map[f:managementState:map[] f:releases:map[k:{"name":"Spark Operator"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]] k:{"name":"Spark"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]]]] f:trainer:map[f:managementState:map[]] f:trainingoperator:map[f:managementState:map[]] f:trustyai:map[f:managementState:map[]] f:workbenches:map[f:managementState:map[]]] f:conditions:map[] f:observedGeneration:map[] f:phase:map[] f:release:map[f:name:map[] f:version:map[]]]] manager:datasciencecluster operation:Apply subresource:status time:2026-07-02T12:10:29Z] map[apiVersion:datasciencecluster.opendatahub.io/v2 fieldsType:FieldsV1 fieldsV1:map[f:metadata:map[f:annotations:map[.:map[] f:kubectl.kubernetes.io/last-applied-configuration:map[]]] f:spec:map[.:map[] f:components:map[.:map[] f:aipipelines:map[] f:dashboard:map[] f:kserve:map[.:map[] f:rawDeploymentServiceConfig:map[]] f:kueue:map[.:map[] f:defaultClusterQueueName:map[] f:defaultLocalQueueName:map[]] f:llamastackoperator:map[] f:mlflowoperator:map[] f:modelregistry:map[.:map[] f:registriesNamespace:map[]] f:ogx:map[] f:ray:map[] f:sparkoperator:map[] f:trainer:map[] f:trainingoperator:map[] f:trustyai:map[.:map[] f:mcpGuardrailsMode:map[]] f:workbenches:map[.:map[] f:workbenchNamespace:map[]]]]] manager:kubectl-client-side-apply operation:Update time:2026-06-29T13:43:26Z] map[apiVersion:datasciencecluster.opendatahub.io/v2 fieldsType:FieldsV1 fieldsV1:map[f:spec:map[f:components:map[f:kserve:map[f:modelsAsService:map[.:map[] f:managementState:map[]]] f:llamastackoperator:map[f:managementState:map[]]]]] manager:kubectl-patch operation:Update time:2026-07-02T11:59:23Z] map[apiVersion:datasciencecluster.opendatahub.io/v2 fieldsType:FieldsV1 fieldsV1:map[f:spec:map[f:components:map[f:aipipelines:map[f:managementState:map[]] f:dashboard:map[f:managementState:map[]] f:feastoperator:map[.:map[] f:managementState:map[]] f:kserve:map[f:managementState:map[] f:wva:map[.:map[] f:managementState:map[]]] f:kueue:map[f:managementState:map[]] f:mlflowoperator:map[f:managementState:map[]] f:modelregistry:map[f:managementState:map[]] f:ogx:map[f:managementState:map[]] f:ray:map[f:managementState:map[]] f:sparkoperator:map[f:managementState:map[]] f:trainer:map[f:managementState:map[]] f:trainingoperator:map[f:managementState:map[]] f:trustyai:map[f:managementState:map[]] f:workbenches:map[f:managementState:map[]]]]] manager:e2e-tests operation:Update time:2026-07-02T12:10:26Z]] name:default-dsc resourceVersion:375248659 uid:191cdb15-01aa-4da4-9798-e6b508adbf9f] spec:map[components:map[aipipelines:map[managementState:Removed] dashboard:map[managementState:Removed] feastoperator:map[managementState:Removed] kserve:map[managementState:Managed modelsAsService:map[managementState:Managed] rawDeploymentServiceConfig:Headless wva:map[managementState:Removed]] kueue:map[defaultClusterQueueName:default defaultLocalQueueName:default managementState:Unmanaged] llamastackoperator:map[managementState:Removed] mlflowoperator:map[managementState:Removed] modelregistry:map[managementState:Removed registriesNamespace:rhoai-model-registries] ogx:map[managementState:Removed] ray:map[managementState:Removed] sparkoperator:map[managementState:Managed] trainer:map[managementState:Removed] trainingoperator:map[managementState:Removed] trustyai:map[managementState:Removed mcpGuardrailsMode:false] workbenches:map[managementState:Removed workbenchNamespace:rhods-notebooks]]] status:map[components:map[aipipelines:map[managementState:Removed releases:[map[name:Kubeflow Pipelines repoUrl:https://github.com/kubeflow/pipelines version:2.16.0]]] dashboard:map[managementState:Removed] feastoperator:map[managementState:Removed releases:[map[name:Feast repoUrl:https://github.com/feast-dev/feast version:0.63.0]]] kserve:map[managementState:Managed releases:[map[name:KServe repoUrl:https://github.com/kserve/kserve/ version:v0.17.0] map[name:vLLM repoUrl:https://github.com/vllm-project/vllm version:v0.18.0] map[name:llm-d-inference-scheduler repoUrl:https://github.com/llm-d/llm-d-inference-scheduler version:v0.7.1] map[name:llm-d-workload-variant-autoscaler repoUrl:https://github.com/llm-d/llm-d-workload-variant-autoscaler version:v0.6.0]]] kueue:map[managementState:Unmanaged] llamastackoperator:map[] mlflowoperator:map[managementState:Removed releases:[map[name:MLflow repoUrl:https://github.com/mlflow/mlflow version:v3.12.0]]] modelregistry:map[managementState:Removed registriesNamespace:rhoai-model-registries releases:[map[name:Kubeflow Model Registry repoUrl:https://github.com/kubeflow/model-registry version:latest] map[name:Open Data Hub Model Registry Operator repoUrl:https://github.com/opendatahub-io/model-registry-operator version:latest]]] ogx:map[managementState:Removed releases:[map[name:OGX repoUrl:https://github.com/opendatahub-io/ogx-distribution version:v1.0.2] map[name:OGX Operator repoUrl:https://github.com/opendatahub-io/ogx-k8s-operator version:v0.10.0]]] ray:map[managementState:Removed releases:[map[name:KubeRay repoUrl:https://github.com/ray-project/kuberay version:1.4.2]]] sparkoperator:map[managementState:Managed releases:[map[name:Spark Operator repoUrl:https://github.com/opendatahub-io/spark-operator version:v2.4.0] map[name:Spark repoUrl:https://github.com/apache/spark version:4.0.1]]] trainer:map[managementState:Removed releases:[map[name:Kubeflow Trainer repoUrl:https://github.com/kubeflow/trainer version:2.1.0]]] trainingoperator:map[managementState:Removed releases:[map[name:Kubeflow Training Operator repoUrl:https://github.com/kubeflow/trainer version:1.9.0]]] trustyai:map[managementState:Removed releases:[map[name:TrustyAI operator repoUrl:https://github.com/trustyai-explainability/trustyai-service-operator version:v1.37.0] map[name:TrustyAI service repoUrl:https://github.com/trustyai-explainability/trustyai-explainability version:v0.28.0] map[name:TrustyAI LMEval driver repoUrl:https://github.com/trustyai-explainability/trustyai-service-operator version:v1.37.0] map[name:TrustyAI LMEval job repoUrl:https://github.com/EleutherAI/lm-evaluation-harness version:v0.4.8] map[name:TrustyAI Guardrails orchestrator repoUrl:https://github.com/foundation-model-stack/fms-guardrails-orchestrator version:0.9.4] map[name:TrustyAI builtin detectors repoUrl:https://github.com/trustyai-explainability/guardrails-regex-detector version:v0.2.0] map[name:TrustyAI sidecar gateway repoUrl:https://github.com/trustyai-explainability/vllm-orchestrator-gateway version:v0.2.1] map[name:EvalHub repoUrl:https://github.com/eval-hub/eval-hub version:v0.3.0]]] workbenches:map[managementState:Removed releases:[map[name:Kubeflow Notebook Controller repoUrl:https://github.com/kubeflow/kubeflow version:1.10.0]] workbenchNamespace:rhods-notebooks]] conditions:[map[lastTransitionTime:2026-07-02T12:10:29Z status:True type:Ready] map[lastTransitionTime:2026-07-02T12:10:28Z observedGeneration:498 status:True type:ProvisioningSucceeded] map[lastTransitionTime:2026-07-02T12:10:29Z status:True type:ComponentsReady] map[lastTransitionTime:2026-07-02T12:10:29Z message:Component ManagementState is set to Removed reason:Removed severity:Info status:False type:AIPipelinesReady] map[lastTransitionTime:2026-07-02T12:10:29Z message:Component ManagementState is set to Removed reason:Removed severity:Info status:False type:DashboardReady] map[lastTransitionTime:2026-07-02T12:10:29Z message:Component ManagementState is set to Removed reason:Removed severity:Info status:False type:FeastOperatorReady] map[lastTransitionTime:2026-07-02T12:06:23Z status:True type:KserveLLMInferenceServiceDependencies] map[lastTransitionTime:2026-07-02T12:06:23Z status:True type:KserveLLMInferenceServiceWideEPDependencies] map[lastTransitionTime:2026-07-02T12:10:29Z status:True type:KserveReady] map[lastTransitionTime:2026-07-02T12:10:29Z status:True type:KueueReady] map[lastTransitionTime:2026-07-02T12:10:29Z message:Component ManagementState is set to Removed reason:Removed severity:Info status:False type:MLflowOperatorReady] map[lastTransitionTime:2026-07-02T12:05:48Z message:MaaS gateway annotations and Authorino TLS are correctly configured reason:MaaSPrerequisitesMet status:True type:MaaSPrerequisitesAvailable] map[lastTransitionTime:2026-07-02T12:10:29Z status:True type:ModelControllerReady] map[lastTransitionTime:2026-07-02T12:10:29Z message:Component ManagementState is set to Removed reason:Removed severity:Info status:False type:ModelRegistryReady] map[lastTransitionTime:2026-07-02T12:10:29Z message:MaaS platform manifests applied and maas-api deployment is available reason:Reconciled status:True type:ModelsAsServiceReady] map[lastTransitionTime:2026-07-02T12:10:29Z message:Component ManagementState is set to Removed reason:Removed severity:Info status:False type:OGXReady] map[lastTransitionTime:2026-07-02T12:10:29Z message:Component ManagementState is set to Removed reason:Removed severity:Info status:False type:RayReady] map[lastTransitionTime:2026-07-02T12:10:29Z status:True type:SparkOperatorReady] map[lastTransitionTime:2026-07-02T12:10:29Z message:Component ManagementState is set to Removed reason:Removed severity:Info status:False type:TrainerReady] map[lastTransitionTime:2026-07-02T12:10:29Z message:Component ManagementState is set to Removed reason:Removed severity:Info status:False type:TrainingOperatorReady] map[lastTransitionTime:2026-07-02T12:10:29Z message:Component ManagementState is set to Removed reason:Removed severity:Info status:False type:TrustyAIReady] map[lastTransitionTime:2026-07-02T12:10:29Z message:Component ManagementState is set to Removed reason:Removed severity:Info status:False type:WorkbenchesReady]] observedGeneration:498 phase:Ready release:map[name:OpenShift AI Self-Managed version:3.5.0-ea.2]]] to match expression <string>: .spec.components.aigateway.managementState == "Removed" --- FAIL: TestOdhOperator/components/group_1/aigateway (300.37s) === RUN TestOdhOperator/components/group_1/kserve/Validate_component_spec testing.go:1913: test executed panic(nil) or runtime.Goexit: subtest may have called FailNow on a parent test --- FAIL: TestOdhOperator/components/group_1/kserve/Validate_component_spec (600.03s) === RUN TestOdhOperator/components/group_1/kserve === PAUSE TestOdhOperator/components/group_1/kserve === CONT TestOdhOperator/components/group_1/kserve test_context_test.go:223: Timed out after 600.008s. The function passed to Eventually failed at /workspace/tests/e2e/resource_applier_test.go:114 with: Expected resource 'default-kserve' of kind 'Kserve' to match condition {.spec.nim.managementState == "" []}. Expected <string>: map[apiVersion:components.platform.opendatahub.io/v1alpha1 kind:Kserve metadata:map[annotations:map[component.opendatahub.io/management-state:Managed platform.opendatahub.io/instance.generation:499 platform.opendatahub.io/instance.name:default-dsc platform.opendatahub.io/instance.uid:191cdb15-01aa-4da4-9798-e6b508adbf9f platform.opendatahub.io/type:OpenShift AI Self-Managed platform.opendatahub.io/version:3.5.0-ea.2] creationTimestamp:2026-07-02T12:05:48Z finalizers:[platform.opendatahub.io/finalizer] generation:1 labels:map[platform.opendatahub.io/part-of:datasciencecluster] managedFields:[map[apiVersion:components.platform.opendatahub.io/v1alpha1 fieldsType:FieldsV1 fieldsV1:map[f:metadata:map[f:annotations:map[f:component.opendatahub.io/management-state:map[] f:platform.opendatahub.io/instance.generation:map[] f:platform.opendatahub.io/instance.name:map[] f:platform.opendatahub.io/instance.uid:map[] f:platform.opendatahub.io/type:map[] f:platform.opendatahub.io/version:map[]] f:finalizers:map[v:"platform.opendatahub.io/finalizer":map[]] f:labels:map[f:platform.opendatahub.io/part-of:map[]] f:ownerReferences:map[k:{"uid":"191cdb15-01aa-4da4-9798-e6b508adbf9f"}:map[]]] f:status:map[f:conditions:map[] f:observedGeneration:map[] f:phase:map[] f:releases:map[k:{"name":"KServe"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]] k:{"name":"llm-d-inference-scheduler"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]] k:{"name":"llm-d-workload-variant-autoscaler"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]] k:{"name":"vLLM"}:map[.:map[] f:name:map[] f:repoUrl:map[] f:version:map[]]]]] manager:kserve operation:Apply subresource:status time:2026-07-02T12:07:27Z] map[apiVersion:components.platform.opendatahub.io/v1alpha1 fieldsType:FieldsV1 fieldsV1:map[f:metadata:map[f:annotations:map[f:component.opendatahub.io/management-state:map[] f:platform.opendatahub.io/instance.generation:map[] f:platform.opendatahub.io/instance.name:map[] f:platform.opendatahub.io/instance.uid:map[] f:platform.opendatahub.io/type:map[] f:platform.opendatahub.io/version:map[]] f:labels:map[f:platform.opendatahub.io/part-of:map[]] f:ownerReferences:map[k:{"uid":"191cdb15-01aa-4da4-9798-e6b508adbf9f"}:map[]]] f:spec:map[f:modelsAsService:map[f:managementState:map[]] f:nim:map[] f:rawDeploymentServiceConfig:map[] f:wva:map[f:managementState:map[]]]] manager:datasciencecluster operation:Apply time:2026-07-02T12:11:36Z] map[apiVersion:components.platform.opendatahub.io/v1alpha1 fieldsType:FieldsV1 fieldsV1:map[f:metadata:map[f:finalizers:map[.:map[] v:"platform.opendatahub.io/finalizer":map[]]]] manager:manager operation:Update time:2026-07-02T12:05:48Z]] name:default-kserve ownerReferences:[map[apiVersion:datasciencecluster.opendatahub.io/v2 blockOwnerDeletion:true controller:true kind:DataScienceCluster name:default-dsc uid:191cdb15-01aa-4da4-9798-e6b508adbf9f]] resourceVersion:375249743 uid:6532d36e-216f-4cf5-aaa3-ab997c440617] spec:map[modelsAsService:map[managementState:Managed] nim:map[airGapped:false managementState:Managed] rawDeploymentServiceConfig:Headless wva:map[managementState:Removed]] status:map[conditions:[map[lastTransitionTime:2026-07-02T12:07:01Z status:True type:Ready] map[lastTransitionTime:2026-07-02T12:07:01Z observedGeneration:1 status:True type:ProvisioningSucceeded] map[lastTransitionTime:2026-07-02T12:07:05Z observedGeneration:1 status:True type:DeploymentsAvailable] map[lastTransitionTime:2026-07-02T12:06:23Z observedGeneration:1 status:True type:DependenciesAvailable] map[lastTransitionTime:2026-07-02T12:06:23Z observedGeneration:1 status:True type:KserveLLMInferenceServiceDependencies] map[lastTransitionTime:2026-07-02T12:06:23Z observedGeneration:1 status:True type:KserveLLMInferenceServiceWideEPDependencies]] observedGeneration:1 phase:Ready releases:[map[name:KServe repoUrl:https://github.com/kserve/kserve/ version:v0.17.0] map[name:vLLM repoUrl:https://github.com/vllm-project/vllm version:v0.18.0] map[name:llm-d-inference-scheduler repoUrl:https://github.com/llm-d/llm-d-inference-scheduler version:v0.7.1] map[name:llm-d-workload-variant-autoscaler repoUrl:https://github.com/llm-d/llm-d-workload-variant-autoscaler version:v0.6.0]]]] to match expression <string>: .spec.nim.managementState == "" --- FAIL: TestOdhOperator/components/group_1/kserve (681.30s) === RUN TestOdhOperator/components/group_1 --- FAIL: TestOdhOperator/components/group_1 (0.00s) === RUN TestOdhOperator/components/group_2/kueue/Validate_autoCreateQueues_disabled_skips_queue_creation helper_test.go:150: Setting Kueue component (default-kueue) to Removed mode to start with a clean state. helper_test.go:150: Cleaning up any existing Kueue test resources. helper_test.go:150: Cleaning up Kueue cluster-scoped resources helper_test.go:150: Will attempt to delete 3 Kueue resources helper_test.go:150: Attempting to delete ClusterQueue /default helper_test.go:150: Successfully processed deletion of ClusterQueue /default helper_test.go:150: Attempting to delete ResourceFlavor /default-flavor helper_test.go:150: Successfully processed deletion of ResourceFlavor /default-flavor helper_test.go:150: Attempting to delete Kueue /cluster helper_test.go:150: Successfully processed deletion of Kueue /cluster helper_test.go:150: Ensuring LWS Operator is installed (namespace=openshift-lws-operator, name=leader-worker-set). helper_test.go:150: Ensuring LeaderWorkerSetOperator CR exists (namespace=openshift-lws-operator, name=cluster). helper_test.go:150: Ensuring OCP Kueue Operator is installed (namespace=openshift-kueue-operator, name=kueue-operator). helper_test.go:150: Creating test namespace (test-kueue-no-queues-d935e3sn4eus7b2dci90) with Kueue management annotation. helper_test.go:150: Creating Kueue ConfigMap (kueue-manager-config) to verify default Kueue resource is created correctly. helper_test.go:150: Creating Kueue ConfigMap (kueue-manager-config) in namespace (redhat-ods-applications). helper_test.go:150: Updating DSC to set Kueue to Unmanaged with autoCreateQueues=false (default). 2026-07-02T12:18:34Z INFO unknown field "spec.components.kueue.autoCreateQueues" helper_test.go:150: Verifying Kueue configuration (cluster) is still created. helper_test.go:150: 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 (320.94s) === 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 300.006s. 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: { "spec": <map[string]interface {} | len:6>{ "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", }, "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", }, "apiVersion": <string>"kueue.x-k8s.io/v1beta2", "kind": <string>"ClusterQueue", "metadata": <map[string]interface {} | len:8>{ "creationTimestamp": <string>"2026-07-02T12:18:35Z", "generation": <int64>1, "labels": <map[string]interface {} | len:1>{ "platform.opendatahub.io/part-of": <string>"kueue", }, "managedFields": <[]interface {} | len:1, cap:1>[ <map[string]interface {} | len:6>{ "apiVersion": <string>"kueue.x-k8s.io/v1beta2", "fieldsType": <string>"FieldsV1", "fieldsV1": <map[string]interface {} | len:2>{ "f:metadata": <map[string]interface {} | len:2>{ "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:labels": <map[string]interface {} | len:2>{ ".": <map[string]interface {} | len:0>{}, "f:platform.opendatahub.io/part-of": <map[string]interface {} | len:0>{}, }, }, "f:spec": <map[string]interface {} | len:7>{ ".": <map[string]interface {} | len:0>{}, "f:flavorFungibility": <map[string]interface {} | len:3>{ "f:whenCanBorrow": <map[string]interface {} | len:0>{}, "f:whenCanPreempt": <map[string]interface {} | len:0>{}, ".": <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>{}, "f:stopPolicy": <map[string]interface {} | len:0>{}, }, }, "manager": <string>"manager", "operation": <string>"Update", "time": <string>"2026-07-02T12:18:35Z", }, ], "name": <string>"default", "resourceVersion": <string>"375256457", "uid": <string>"7559b617-1a34-41a5-bb9c-fa01214b0707", "annotations": <map[string]interface {} | len:5>{ "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", "platform.opendatahub.io/instance.uid": <string>"beff89bb-6cee-4cc4-9dc5-a7fffb1bbceb", }, }, }, }, ] 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 (395.23s) === RUN TestOdhOperator/components/group_2 --- FAIL: TestOdhOperator/components/group_2 (0.00s) === RUN TestOdhOperator/components 2026/07/02 12:17:08 TEST FAILURE DETECTED: group 1 2026/07/02 12:17:08 === RUNNING CLUSTER DIAGNOSTICS (triggered by test:group 1) === 2026/07/02 12:17:09 === CLUSTER STATE === 2026/07/02 12:17:09 Node: ods-qe-psi-07-b4mqp-master-0 2026/07/02 12:17:09 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:17:09 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:17:09 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:17:09 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:17:09 Resources: 11500m CPU, 23450728Ki memory allocatable (of 12000m CPU, 24601704Ki memory capacity) 2026/07/02 12:17:09 Node: ods-qe-psi-07-b4mqp-master-1 2026/07/02 12:17:09 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:17:09 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:17:09 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:17:09 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:17:09 Resources: 11500m CPU, 23452748Ki memory allocatable (of 12000m CPU, 24603724Ki memory capacity) 2026/07/02 12:17:09 Node: ods-qe-psi-07-b4mqp-master-2 2026/07/02 12:17:09 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:17:09 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:17:09 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:17:09 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:17:09 Resources: 11500m CPU, 23450732Ki memory allocatable (of 12000m CPU, 24601708Ki memory capacity) 2026/07/02 12:17:09 Node: ods-qe-psi-07-b4mqp-worker-0-gc6qk 2026/07/02 12:17:09 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:17:09 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:17:09 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:17:09 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:17:09 Resources: 11500m CPU, 23450728Ki memory allocatable (of 12000m CPU, 24601704Ki memory capacity) 2026/07/02 12:17:09 Node: ods-qe-psi-07-b4mqp-worker-0-jcdqk 2026/07/02 12:17:09 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:17:09 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:17:09 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:17:09 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:17:09 Resources: 11500m CPU, 23452748Ki memory allocatable (of 12000m CPU, 24603724Ki memory capacity) 2026/07/02 12:17:09 Node: ods-qe-psi-07-b4mqp-worker-0-jd4pm 2026/07/02 12:17:09 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:17:09 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:17:09 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:17:09 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:17:09 Resources: 11500m CPU, 23452736Ki memory allocatable (of 12000m CPU, 24603712Ki memory capacity) 2026/07/02 12:17:09 Node: ods-qe-psi-07-b4mqp-worker-0-tx6lc 2026/07/02 12:17:09 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:17:09 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:17:09 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:17:09 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:17:09 Resources: 11500m CPU, 23452744Ki memory allocatable (of 12000m CPU, 24603720Ki memory capacity) 2026/07/02 12:17:09 Node: ods-qe-psi-07-b4mqp-worker-0-wvlfv 2026/07/02 12:17:09 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:17:09 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:17:09 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:17:09 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:17:09 Resources: 11500m CPU, 23450720Ki memory allocatable (of 12000m CPU, 24601696Ki memory capacity) 2026/07/02 12:17:09 === DEPLOYMENTS === 2026/07/02 12:17:09 Namespace: redhat-ods-applications 2026/07/02 12:17:09 Deployment kserve-controller-manager: 1/1 (READY) 2026/07/02 12:17:09 Deployment llmisvc-controller-manager: 1/1 (READY) 2026/07/02 12:17:09 Deployment maas-api: 1/1 (READY) 2026/07/02 12:17:09 Deployment maas-controller: 1/1 (READY) 2026/07/02 12:17:09 Deployment maas-postgres: 1/1 (READY) 2026/07/02 12:17:09 Deployment model-serving-api: 1/1 (READY) 2026/07/02 12:17:09 Deployment odh-model-controller: 1/1 (READY) 2026/07/02 12:17:09 Deployment postgres: 1/1 (READY) 2026/07/02 12:17:09 Namespace: kube-system 2026/07/02 12:17:09 === PODS === 2026/07/02 12:17:09 Namespace: redhat-ods-applications 2026/07/02 12:17:09 Pod maas-api-key-cleanup-29716575-kvp86: Succeeded 2026/07/02 12:17:09 Container cleanup: ready=false, terminated: Completed (exit 0) 2026/07/02 12:17:09 Namespace kube-system: no problematic pods found 2026/07/02 12:17:09 === LOGS (CURRENT) for container cleanup === 2026/07/02 12:17:09 {"deletedCount":0,"message":"Successfully deleted 0 expired ephemeral key(s)"} 2026/07/02 12:17:09 === END LOGS === 2026/07/02 12:17:09 === OPERATOR STATUS === 2026/07/02 12:17:09 Operator deployment: 3/3 ready 2026/07/02 12:17:09 === DSCI STATUS === 2026/07/02 12:17:09 Failed to collect DSCI data: default-dsci unhealthy conditions: MonitoringStackAvailable=False; TempoAvailable=False; OpenTelemetryCollectorAvailable=False; AlertingAvailable=False; ThanosQuerierAvailable=False; PersesAvailable=False; NodeMetricsEndpointAvailable=False 2026/07/02 12:17:09 === DSC STATUS === 2026/07/02 12:17:09 DSC default-dsc: 2026/07/02 12:17:09 Ready: True - 2026/07/02 12:17:09 ProvisioningSucceeded: True - 2026/07/02 12:17:09 ComponentsReady: True - 2026/07/02 12:17:09 AIPipelinesReady: False - Component ManagementState is set to Removed 2026/07/02 12:17:09 DashboardReady: False - Component ManagementState is set to Removed 2026/07/02 12:17:09 FeastOperatorReady: False - Component ManagementState is set to Removed 2026/07/02 12:17:09 KserveLLMInferenceServiceDependencies: True - 2026/07/02 12:17:09 KserveLLMInferenceServiceWideEPDependencies: True - 2026/07/02 12:17:09 KserveReady: True - 2026/07/02 12:17:09 KueueReady: True - 2026/07/02 12:17:09 MLflowOperatorReady: False - Component ManagementState is set to Removed 2026/07/02 12:17:09 MaaSPrerequisitesAvailable: True - MaaS gateway annotations and Authorino TLS are correctly configured 2026/07/02 12:17:09 ModelControllerReady: True - 2026/07/02 12:17:09 ModelRegistryReady: False - Component ManagementState is set to Removed 2026/07/02 12:17:09 ModelsAsServiceReady: True - MaaS platform manifests applied and maas-api deployment is available 2026/07/02 12:17:09 OGXReady: False - Component ManagementState is set to Removed 2026/07/02 12:17:09 RayReady: False - Component ManagementState is set to Removed 2026/07/02 12:17:09 SparkOperatorReady: False - Component ManagementState is set to Removed 2026/07/02 12:17:09 TrainerReady: False - Component ManagementState is set to Removed 2026/07/02 12:17:09 TrainingOperatorReady: False - Component ManagementState is set to Removed 2026/07/02 12:17:09 TrustyAIReady: False - Component ManagementState is set to Removed 2026/07/02 12:17:09 WorkbenchesReady: False - Component ManagementState is set to Removed 2026/07/02 12:17:09 === RECENT EVENTS === 2026/07/02 12:17:09 12:15:04 INFO Job/maas-api-key-cleanup-29716575: Completed - Job completed 2026/07/02 12:17:09 12:15:04 INFO CronJob/maas-api-key-cleanup: SawCompletedJob - Saw completed job: maas-api-key-cleanup-29716575, condition: Complete 2026/07/02 12:17:09 12:15:01 INFO Pod/maas-api-key-cleanup-29716575-kvp86: Created - Created container: cleanup 2026/07/02 12:17:09 12:15:01 INFO Pod/maas-api-key-cleanup-29716575-kvp86: Started - Started container cleanup 2026/07/02 12:17:09 12:15:00 INFO Pod/maas-api-key-cleanup-29716575-kvp86: Scheduled - Successfully assigned redhat-ods-applications/maas-api-key-cleanup-29716575-kvp86 to ods-qe-psi-07-b4mqp-worker-0-tx6lc 2026/07/02 12:17:09 12:15:00 INFO Pod/maas-api-key-cleanup-29716575-kvp86: AddedInterface - Add eth0 [10.130.3.80/23] from ovn-kubernetes 2026/07/02 12:17:09 12:15:00 INFO Pod/maas-api-key-cleanup-29716575-kvp86: Pulled - Container image "registry.redhat.io/ubi9/ubi-minimal@sha256:907b68736aa798b2d38255b7aa070b2a70acb90803864a40f05d0ec47556ddd0" already present on machine 2026/07/02 12:17:09 12:15:00 INFO Job/maas-api-key-cleanup-29716575: SuccessfulCreate - Created pod: maas-api-key-cleanup-29716575-kvp86 2026/07/02 12:17:09 12:15:00 INFO CronJob/maas-api-key-cleanup: SuccessfulCreate - Created job maas-api-key-cleanup-29716575 2026/07/02 12:17:09 === RESOURCE QUOTAS === 2026/07/02 12:17:09 No resource quotas found in monitored namespaces 2026/07/02 12:17:09 Classification for group 1: infrastructure/dsci-unhealthy (code=1009, confidence=medium) 2026/07/02 12:17:09 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"} 2026/07/02 12:17:09 Diagnostics complete for failed test: group 1 controller_test.go:763: Stopping: group 1 test failed. 2026/07/02 12:17:09 Circuit breaker: failure classified as infrastructure/dsci-unhealthy (code=1009) 2026/07/02 12:17:09 Circuit breaker: infrastructure/unknown failure recorded (2/3 consecutive) 2026/07/02 12:23:44 TEST FAILURE DETECTED: group 2 2026/07/02 12:23:44 === RUNNING CLUSTER DIAGNOSTICS (triggered by test:group 2) === 2026/07/02 12:23:45 === CLUSTER STATE === 2026/07/02 12:23:45 Node: ods-qe-psi-07-b4mqp-master-0 2026/07/02 12:23:45 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:23:45 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:23:45 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:23:45 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:23:45 Resources: 11500m CPU, 23450728Ki memory allocatable (of 12000m CPU, 24601704Ki memory capacity) 2026/07/02 12:23:45 Node: ods-qe-psi-07-b4mqp-master-1 2026/07/02 12:23:45 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:23:45 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:23:45 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:23:45 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:23:45 Resources: 11500m CPU, 23452748Ki memory allocatable (of 12000m CPU, 24603724Ki memory capacity) 2026/07/02 12:23:45 Node: ods-qe-psi-07-b4mqp-master-2 2026/07/02 12:23:45 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:23:45 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:23:45 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:23:45 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:23:45 Resources: 11500m CPU, 23450732Ki memory allocatable (of 12000m CPU, 24601708Ki memory capacity) 2026/07/02 12:23:45 Node: ods-qe-psi-07-b4mqp-worker-0-gc6qk 2026/07/02 12:23:45 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:23:45 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:23:45 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:23:45 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:23:45 Resources: 11500m CPU, 23450728Ki memory allocatable (of 12000m CPU, 24601704Ki memory capacity) 2026/07/02 12:23:45 Node: ods-qe-psi-07-b4mqp-worker-0-jcdqk 2026/07/02 12:23:45 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:23:45 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:23:45 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:23:45 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:23:45 Resources: 11500m CPU, 23452748Ki memory allocatable (of 12000m CPU, 24603724Ki memory capacity) 2026/07/02 12:23:45 Node: ods-qe-psi-07-b4mqp-worker-0-jd4pm 2026/07/02 12:23:45 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:23:45 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:23:45 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:23:45 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:23:45 Resources: 11500m CPU, 23452736Ki memory allocatable (of 12000m CPU, 24603712Ki memory capacity) 2026/07/02 12:23:45 Node: ods-qe-psi-07-b4mqp-worker-0-tx6lc 2026/07/02 12:23:45 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:23:45 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:23:45 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:23:45 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:23:45 Resources: 11500m CPU, 23452744Ki memory allocatable (of 12000m CPU, 24603720Ki memory capacity) 2026/07/02 12:23:45 Node: ods-qe-psi-07-b4mqp-worker-0-wvlfv 2026/07/02 12:23:45 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:23:45 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:23:45 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:23:45 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:23:45 Resources: 11500m CPU, 23450720Ki memory allocatable (of 12000m CPU, 24601696Ki memory capacity) 2026/07/02 12:23:45 === DEPLOYMENTS === 2026/07/02 12:23:45 Namespace: redhat-ods-applications 2026/07/02 12:23:45 Deployment maas-postgres: 1/1 (READY) 2026/07/02 12:23:45 Deployment postgres: 1/1 (READY) 2026/07/02 12:23:45 Namespace: kube-system 2026/07/02 12:23:45 === PODS === 2026/07/02 12:23:45 Namespace redhat-ods-applications: no problematic pods found 2026/07/02 12:23:45 Namespace kube-system: no problematic pods found 2026/07/02 12:23:45 === OPERATOR STATUS === 2026/07/02 12:23:45 Operator deployment: 3/3 ready 2026/07/02 12:23:45 === DSCI STATUS === 2026/07/02 12:23:45 Failed to collect DSCI data: default-dsci unhealthy conditions: MonitoringStackAvailable=False; TempoAvailable=False; OpenTelemetryCollectorAvailable=False; AlertingAvailable=False; ThanosQuerierAvailable=False; PersesAvailable=False; NodeMetricsEndpointAvailable=False 2026/07/02 12:23:45 === DSC STATUS === 2026/07/02 12:23:45 Failed to collect DSC data: default-dsc unhealthy conditions: ModelsAsServiceReady=False 2026/07/02 12:23:45 === RECENT EVENTS === 2026/07/02 12:23:45 12:20:26 INFO Pod/maas-api-84c4b8dcb6-wrtkh: Killing - Stopping container maas-api 2026/07/02 12:23:45 12:20:26 INFO Pod/maas-controller-656b6867cb-h9pqk: Killing - Stopping container manager 2026/07/02 12:23:45 12:20:26 WARN Pod/odh-model-controller-6b647f87c-mwbdd: Unhealthy - Readiness probe failed: Get "http://10.130.3.84:8081/readyz": context deadline exceeded (Client.Timeout exceeded while awaiting headers) 2026/07/02 12:23:45 12:20:25 INFO Pod/workload-variant-autoscaler-controller-manager-56865c9848-8th6v: Killing - Stopping container manager 2026/07/02 12:23:45 12:20:25 INFO Pod/kserve-controller-manager-6c8cb86d7f-gkm6j: Killing - Stopping container manager 2026/07/02 12:23:45 12:20:25 INFO Pod/model-registry-operator-controller-manager-5f68f4fd76-wtm4q: Killing - Stopping container manager 2026/07/02 12:23:45 12:20:25 INFO Pod/odh-model-controller-6b647f87c-mwbdd: Killing - Stopping container manager 2026/07/02 12:23:45 12:20:25 INFO Pod/model-serving-api-78bbbb9bf8-nq7wm: Killing - Stopping container server 2026/07/02 12:23:45 12:20:24 INFO Pod/llmisvc-controller-manager-586c85c465-dwpqz: Killing - Stopping container manager 2026/07/02 12:23:45 12:20:10 INFO Lease/odh-model-controller.opendatahub.io: LeaderElection - odh-model-controller-6b647f87c-mwbdd_6b5b75b0-a02e-4006-84b1-5ce7564fdca0 became leader 2026/07/02 12:23:45 12:20:09 INFO Lease/72dd1cf1.llm-d.ai: LeaderElection - workload-variant-autoscaler-controller-manager-56865c9848-8th6v_949efa87-7068-4bb7-98ba-e7188dde8ccc became leader 2026/07/02 12:23:45 12:20:09 INFO Pod/workload-variant-autoscaler-controller-manager-56865c9848-8th6v: Pulled - Container image "registry.redhat.io/rhoai/odh-workload-variant-autoscaler-controller-rhel9@sha256:3d219851cf91eb92db3df70276a7e0615e56f41deeff9a7b83b5e93b686bb789" already present on machine 2026/07/02 12:23:45 12:20:09 INFO Pod/workload-variant-autoscaler-controller-manager-56865c9848-8th6v: AddedInterface - Add eth0 [10.130.3.85/23] from ovn-kubernetes 2026/07/02 12:23:45 12:20:09 INFO Pod/workload-variant-autoscaler-controller-manager-56865c9848-8th6v: Created - Created container: manager 2026/07/02 12:23:45 12:20:09 INFO Pod/workload-variant-autoscaler-controller-manager-56865c9848-8th6v: Started - Started container manager 2026/07/02 12:23:45 12:20:08 INFO Pod/workload-variant-autoscaler-controller-manager-56865c9848-8th6v: Scheduled - Successfully assigned redhat-ods-applications/workload-variant-autoscaler-controller-manager-56865c9848-8th6v to ods-qe-psi-07-b4mqp-worker-0-tx6lc 2026/07/02 12:23:45 12:20:08 INFO Deployment/workload-variant-autoscaler-controller-manager: ScalingReplicaSet - Scaled up replica set workload-variant-autoscaler-controller-manager-56865c9848 from 0 to 1 2026/07/02 12:23:45 12:20:08 INFO Pod/workload-variant-autoscaler-controller-manager-56865c9848-n8js9: Killing - Stopping container manager 2026/07/02 12:23:45 12:20:08 INFO ReplicaSet/workload-variant-autoscaler-controller-manager-56865c9848: SuccessfulCreate - Created pod: workload-variant-autoscaler-controller-manager-56865c9848-8th6v 2026/07/02 12:23:45 12:20:08 INFO Pod/workload-variant-autoscaler-controller-manager-56865c9848-6xhhg: Killing - Stopping container manager 2026/07/02 12:23:45 12:19:54 INFO Pod/odh-model-controller-6b647f87c-mwbdd: Started - Started container manager 2026/07/02 12:23:45 12:19:54 INFO Pod/odh-model-controller-6b647f87c-mwbdd: Created - Created container: manager 2026/07/02 12:23:45 12:19:54 INFO Pod/odh-model-controller-6b647f87c-mwbdd: Pulled - Successfully pulled image "registry.redhat.io/rhoai/odh-model-controller-rhel9@sha256:b423702816000ce0f075548e3a67de006f40ccf05c575a866cb62e2ac9711191" in 686ms (686ms including waiting). Image size: 238719956 bytes. 2026/07/02 12:23:45 12:19:53 INFO Pod/odh-model-controller-6b647f87c-mwbdd: Scheduled - Successfully assigned redhat-ods-applications/odh-model-controller-6b647f87c-mwbdd to ods-qe-psi-07-b4mqp-worker-0-tx6lc 2026/07/02 12:23:45 12:19:53 INFO Deployment/odh-model-controller: ScalingReplicaSet - Scaled up replica set odh-model-controller-6b647f87c from 0 to 1 2026/07/02 12:23:45 12:19:53 INFO Pod/odh-model-controller-6b647f87c-pk2t5: Killing - Stopping container manager 2026/07/02 12:23:45 12:19:53 INFO ReplicaSet/odh-model-controller-6b647f87c: SuccessfulCreate - Created pod: odh-model-controller-6b647f87c-mwbdd 2026/07/02 12:23:45 12:19:53 INFO Pod/odh-model-controller-6b647f87c-mwbdd: Pulling - Pulling image "registry.redhat.io/rhoai/odh-model-controller-rhel9@sha256:b423702816000ce0f075548e3a67de006f40ccf05c575a866cb62e2ac9711191" 2026/07/02 12:23:45 12:19:53 INFO Pod/odh-model-controller-6b647f87c-mwbdd: AddedInterface - Add eth0 [10.130.3.84/23] from ovn-kubernetes 2026/07/02 12:23:45 12:19:53 INFO Pod/odh-model-controller-6b647f87c-c5ph9: Killing - Stopping container manager 2026/07/02 12:23:45 12:19:38 INFO Pod/model-serving-api-78bbbb9bf8-nq7wm: Scheduled - Successfully assigned redhat-ods-applications/model-serving-api-78bbbb9bf8-nq7wm to ods-qe-psi-07-b4mqp-worker-0-jcdqk 2026/07/02 12:23:45 12:19:38 INFO ReplicaSet/model-serving-api-78bbbb9bf8: SuccessfulCreate - Created pod: model-serving-api-78bbbb9bf8-nq7wm 2026/07/02 12:23:45 12:19:38 INFO Pod/model-serving-api-78bbbb9bf8-xd5t7: Killing - Stopping container server 2026/07/02 12:23:45 12:19:38 INFO Pod/model-serving-api-78bbbb9bf8-nq7wm: Started - Started container server 2026/07/02 12:23:45 12:19:38 INFO Pod/model-serving-api-78bbbb9bf8-nq7wm: Created - Created container: server 2026/07/02 12:23:45 12:19:38 INFO Pod/model-serving-api-78bbbb9bf8-nq7wm: Pulled - Container image "registry.redhat.io/rhoai/odh-model-serving-api-rhel9@sha256:6dd699e678c3f4d6e51138eea62f096f26472b5f9c1ce2757cf9e9e2f80371a4" already present on machine 2026/07/02 12:23:45 12:19:38 INFO Pod/model-serving-api-78bbbb9bf8-nq7wm: AddedInterface - Add eth0 [10.129.3.158/23] from ovn-kubernetes 2026/07/02 12:23:45 12:19:38 INFO Deployment/model-serving-api: ScalingReplicaSet - Scaled up replica set model-serving-api-78bbbb9bf8 from 0 to 1 2026/07/02 12:23:45 12:19:38 INFO Pod/model-serving-api-78bbbb9bf8-5vrdv: Killing - Stopping container server 2026/07/02 12:23:45 === RESOURCE QUOTAS === 2026/07/02 12:23:45 No resource quotas found in monitored namespaces 2026/07/02 12:23:45 Classification for group 2: infrastructure/dsci-unhealthy (code=1009, confidence=medium) 2026/07/02 12:23:45 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"} 2026/07/02 12:23:45 Diagnostics complete for failed test: group 2 controller_test.go:763: Stopping: group 2 test failed. 2026/07/02 12:23:45 Circuit breaker: failure classified as infrastructure/dsci-unhealthy (code=1009) 2026/07/02 12:23:45 Circuit breaker: infrastructure/unknown failure recorded (3/3 consecutive) 2026/07/02 12:23:45 Circuit breaker: threshold reached (3 failures), running confirming health check... 2026/07/02 12:23:46 Circuit breaker: confirming health check passed — cluster appears healthy, resetting counter --- FAIL: TestOdhOperator/components (1514.57s) === RUN TestOdhOperator 2026/07/02 12:00:25 ARTIFACT_DIR not set, skipping periodic metrics collection 2026/07/02 12:05:46 TEST FAILURE DETECTED: DAG Ordering E2E Tests 2026/07/02 12:05:46 === RUNNING CLUSTER DIAGNOSTICS (triggered by test:DAG Ordering E2E Tests) === 2026/07/02 12:05:47 === CLUSTER STATE === 2026/07/02 12:05:47 Node: ods-qe-psi-07-b4mqp-master-0 2026/07/02 12:05:47 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:05:47 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:05:47 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:05:47 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:05:47 Resources: 11500m CPU, 23450728Ki memory allocatable (of 12000m CPU, 24601704Ki memory capacity) 2026/07/02 12:05:47 Node: ods-qe-psi-07-b4mqp-master-1 2026/07/02 12:05:47 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:05:47 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:05:47 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:05:47 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:05:47 Resources: 11500m CPU, 23452748Ki memory allocatable (of 12000m CPU, 24603724Ki memory capacity) 2026/07/02 12:05:47 Node: ods-qe-psi-07-b4mqp-master-2 2026/07/02 12:05:47 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:05:47 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:05:47 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:05:47 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:05:47 Resources: 11500m CPU, 23450732Ki memory allocatable (of 12000m CPU, 24601708Ki memory capacity) 2026/07/02 12:05:47 Node: ods-qe-psi-07-b4mqp-worker-0-gc6qk 2026/07/02 12:05:47 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:05:47 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:05:47 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:05:47 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:05:47 Resources: 11500m CPU, 23450728Ki memory allocatable (of 12000m CPU, 24601704Ki memory capacity) 2026/07/02 12:05:47 Node: ods-qe-psi-07-b4mqp-worker-0-jcdqk 2026/07/02 12:05:47 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:05:47 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:05:47 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:05:47 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:05:47 Resources: 11500m CPU, 23452748Ki memory allocatable (of 12000m CPU, 24603724Ki memory capacity) 2026/07/02 12:05:47 Node: ods-qe-psi-07-b4mqp-worker-0-jd4pm 2026/07/02 12:05:47 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:05:47 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:05:47 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:05:47 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:05:47 Resources: 11500m CPU, 23452736Ki memory allocatable (of 12000m CPU, 24603712Ki memory capacity) 2026/07/02 12:05:47 Node: ods-qe-psi-07-b4mqp-worker-0-tx6lc 2026/07/02 12:05:47 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:05:47 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:05:47 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:05:47 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:05:47 Resources: 11500m CPU, 23452744Ki memory allocatable (of 12000m CPU, 24603720Ki memory capacity) 2026/07/02 12:05:47 Node: ods-qe-psi-07-b4mqp-worker-0-wvlfv 2026/07/02 12:05:47 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:05:47 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:05:47 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:05:47 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:05:47 Resources: 11500m CPU, 23450720Ki memory allocatable (of 12000m CPU, 24601696Ki memory capacity) 2026/07/02 12:05:47 === DEPLOYMENTS === 2026/07/02 12:05:47 Namespace: redhat-ods-applications 2026/07/02 12:05:47 Deployment maas-postgres: 1/1 (READY) 2026/07/02 12:05:47 Deployment postgres: 1/1 (READY) 2026/07/02 12:05:47 Namespace: kube-system 2026/07/02 12:05:47 === PODS === 2026/07/02 12:05:47 Namespace redhat-ods-applications: no problematic pods found 2026/07/02 12:05:47 Namespace kube-system: no problematic pods found 2026/07/02 12:05:47 === OPERATOR STATUS === 2026/07/02 12:05:47 Operator deployment: 3/3 ready 2026/07/02 12:05:47 === DSCI STATUS === 2026/07/02 12:05:47 Failed to collect DSCI data: default-dsci unhealthy conditions: MonitoringStackAvailable=False; TempoAvailable=False; OpenTelemetryCollectorAvailable=False; AlertingAvailable=False; ThanosQuerierAvailable=False; PersesAvailable=False; NodeMetricsEndpointAvailable=False 2026/07/02 12:05:47 === DSC STATUS === 2026/07/02 12:05:47 Failed to collect DSC data: default-dsc unhealthy conditions: ModelsAsServiceReady=False 2026/07/02 12:05:47 === RECENT EVENTS === 2026/07/02 12:05:47 No recent events found in monitored namespaces 2026/07/02 12:05:47 === RESOURCE QUOTAS === 2026/07/02 12:05:47 No resource quotas found in monitored namespaces 2026/07/02 12:05:47 Classification for DAG Ordering E2E Tests: infrastructure/dsci-unhealthy (code=1009, confidence=medium) 2026/07/02 12:05:47 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"} 2026/07/02 12:05:47 Diagnostics complete for failed test: DAG Ordering E2E Tests controller_test.go:484: Stopping: DAG Ordering E2E Tests test failed. 2026/07/02 12:05:47 Circuit breaker: failure classified as infrastructure/dsci-unhealthy (code=1009) 2026/07/02 12:05:47 Circuit breaker: infrastructure/unknown failure recorded (1/3 consecutive) 2026/07/02 12:31:01 TEST FAILURE DETECTED: components 2026/07/02 12:31:01 === RUNNING CLUSTER DIAGNOSTICS (triggered by test:components) === 2026/07/02 12:31:02 === CLUSTER STATE === 2026/07/02 12:31:02 Node: ods-qe-psi-07-b4mqp-master-0 2026/07/02 12:31:02 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:31:02 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:31:02 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:31:02 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:31:02 Resources: 11500m CPU, 23450728Ki memory allocatable (of 12000m CPU, 24601704Ki memory capacity) 2026/07/02 12:31:02 Node: ods-qe-psi-07-b4mqp-master-1 2026/07/02 12:31:02 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:31:02 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:31:02 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:31:02 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:31:02 Resources: 11500m CPU, 23452748Ki memory allocatable (of 12000m CPU, 24603724Ki memory capacity) 2026/07/02 12:31:02 Node: ods-qe-psi-07-b4mqp-master-2 2026/07/02 12:31:02 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:31:02 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:31:02 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:31:02 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:31:02 Resources: 11500m CPU, 23450732Ki memory allocatable (of 12000m CPU, 24601708Ki memory capacity) 2026/07/02 12:31:02 Node: ods-qe-psi-07-b4mqp-worker-0-gc6qk 2026/07/02 12:31:02 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:31:02 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:31:02 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:31:02 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:31:02 Resources: 11500m CPU, 23450728Ki memory allocatable (of 12000m CPU, 24601704Ki memory capacity) 2026/07/02 12:31:02 Node: ods-qe-psi-07-b4mqp-worker-0-jcdqk 2026/07/02 12:31:02 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:31:02 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:31:02 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:31:02 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:31:02 Resources: 11500m CPU, 23452748Ki memory allocatable (of 12000m CPU, 24603724Ki memory capacity) 2026/07/02 12:31:02 Node: ods-qe-psi-07-b4mqp-worker-0-jd4pm 2026/07/02 12:31:02 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:31:02 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:31:02 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:31:02 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:31:02 Resources: 11500m CPU, 23452736Ki memory allocatable (of 12000m CPU, 24603712Ki memory capacity) 2026/07/02 12:31:02 Node: ods-qe-psi-07-b4mqp-worker-0-tx6lc 2026/07/02 12:31:02 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:31:02 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:31:02 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:31:02 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:31:02 Resources: 11500m CPU, 23452744Ki memory allocatable (of 12000m CPU, 24603720Ki memory capacity) 2026/07/02 12:31:02 Node: ods-qe-psi-07-b4mqp-worker-0-wvlfv 2026/07/02 12:31:02 Condition MemoryPressure: False - kubelet has sufficient memory available 2026/07/02 12:31:02 Condition DiskPressure: False - kubelet has no disk pressure 2026/07/02 12:31:02 Condition PIDPressure: False - kubelet has sufficient PID available 2026/07/02 12:31:02 Condition Ready: True - kubelet is posting ready status 2026/07/02 12:31:02 Resources: 11500m CPU, 23450720Ki memory allocatable (of 12000m CPU, 24601696Ki memory capacity) 2026/07/02 12:31:02 === DEPLOYMENTS === 2026/07/02 12:31:02 Namespace: kube-system 2026/07/02 12:31:02 Namespace: redhat-ods-applications 2026/07/02 12:31:02 Deployment kserve-controller-manager: 1/1 (READY) 2026/07/02 12:31:02 Deployment kubeflow-trainer-controller-manager: 1/1 (READY) 2026/07/02 12:31:02 Deployment llmisvc-controller-manager: 1/1 (READY) 2026/07/02 12:31:02 Deployment maas-postgres: 1/1 (READY) 2026/07/02 12:31:02 Deployment model-serving-api: 1/1 (READY) 2026/07/02 12:31:02 Deployment odh-model-controller: 1/1 (READY) 2026/07/02 12:31:02 Deployment postgres: 1/1 (READY) 2026/07/02 12:31:02 === PODS === 2026/07/02 12:31:02 Namespace redhat-ods-applications: no problematic pods found 2026/07/02 12:31:02 Namespace kube-system: no problematic pods found 2026/07/02 12:31:02 === OPERATOR STATUS === 2026/07/02 12:31:02 Operator deployment: 3/3 ready 2026/07/02 12:31:02 === DSCI STATUS === 2026/07/02 12:31:02 Failed to collect DSCI data: default-dsci unhealthy conditions: MonitoringStackAvailable=False; TempoAvailable=False; OpenTelemetryCollectorAvailable=False; AlertingAvailable=False; ThanosQuerierAvailable=False; PersesAvailable=False; NodeMetricsEndpointAvailable=False 2026/07/02 12:31:02 === DSC STATUS === 2026/07/02 12:31:02 DSC default-dsc: 2026/07/02 12:31:02 Ready: True - 2026/07/02 12:31:02 ProvisioningSucceeded: True - 2026/07/02 12:31:02 ComponentsReady: True - 2026/07/02 12:31:02 AIPipelinesReady: False - Component ManagementState is set to Removed 2026/07/02 12:31:02 DashboardReady: False - Component ManagementState is set to Removed 2026/07/02 12:31:02 FeastOperatorReady: False - Component ManagementState is set to Removed 2026/07/02 12:31:02 KserveLLMInferenceServiceDependencies: True - 2026/07/02 12:31:02 KserveLLMInferenceServiceWideEPDependencies: True - 2026/07/02 12:31:02 KserveReady: True - 2026/07/02 12:31:02 KueueReady: True - 2026/07/02 12:31:02 MLflowOperatorReady: False - Component ManagementState is set to Removed 2026/07/02 12:31:02 ModelControllerReady: True - 2026/07/02 12:31:02 ModelRegistryReady: False - Component ManagementState is set to Removed 2026/07/02 12:31:02 ModelsAsServiceReady: False - Component ManagementState is set to Removed 2026/07/02 12:31:02 OGXReady: False - Component ManagementState is set to Removed 2026/07/02 12:31:02 RayReady: False - Component ManagementState is set to Removed 2026/07/02 12:31:02 SparkOperatorReady: False - Component ManagementState is set to Removed 2026/07/02 12:31:02 TrainerReady: True - 2026/07/02 12:31:02 TrainingOperatorReady: False - Component ManagementState is set to Removed 2026/07/02 12:31:02 TrustyAIReady: False - Component ManagementState is set to Removed 2026/07/02 12:31:02 WorkbenchesReady: False - Component ManagementState is set to Removed 2026/07/02 12:31:02 === RECENT EVENTS === 2026/07/02 12:31:02 12:30:47 INFO Lease/llminferenceservice-kserve-controller-manager: LeaderElection - llmisvc-controller-manager-586c85c465-5s744_705fcbf6-1c0c-433c-bd6d-2ae1918fd7b2 became leader 2026/07/02 12:31:02 12:30:46 INFO Lease/kserve-controller-manager-leader-lock: LeaderElection - kserve-controller-manager-6c8cb86d7f-sr994_e01194d0-4f37-4f7b-ba4a-73bdc3ab5f2c became leader 2026/07/02 12:31:02 12:30:32 INFO Lease/odh-model-controller.opendatahub.io: LeaderElection - odh-model-controller-54bf759f64-8r4c2_e8bd2d6b-c06f-4dab-a6dc-8ca8862b20d6 became leader 2026/07/02 12:31:02 12:30:28 INFO Pod/kserve-controller-manager-6c8cb86d7f-sr994: Pulled - Successfully pulled image "registry.redhat.io/rhoai/odh-kserve-controller-rhel9@sha256:7f6f393635a7431d530256ef8ad48ebd35531166dbb361c6c0ff9fc37bd5dc2b" in 1.158s (1.158s including waiting). Image size: 237680379 bytes. 2026/07/02 12:31:02 12:30:28 INFO Pod/kserve-controller-manager-6c8cb86d7f-sr994: Created - Created container: manager 2026/07/02 12:31:02 12:30:28 INFO Pod/kserve-controller-manager-6c8cb86d7f-sr994: Started - Started container manager 2026/07/02 12:31:02 12:30:27 INFO Pod/kserve-controller-manager-6c8cb86d7f-sr994: Pulling - Pulling image "registry.redhat.io/rhoai/odh-kserve-controller-rhel9@sha256:7f6f393635a7431d530256ef8ad48ebd35531166dbb361c6c0ff9fc37bd5dc2b" 2026/07/02 12:31:02 12:30:27 INFO Pod/llmisvc-controller-manager-586c85c465-5s744: Started - Started container manager 2026/07/02 12:31:02 12:30:27 INFO Pod/llmisvc-controller-manager-586c85c465-5s744: Created - Created container: manager 2026/07/02 12:31:02 12:30:27 INFO Pod/llmisvc-controller-manager-586c85c465-5s744: Pulled - Successfully pulled image "registry.redhat.io/rhoai/odh-kserve-llmisvc-controller-rhel9@sha256:d3225eb3f0bfcb20a6d1dccd63403e58a810921680425ecae1b22d86a451417d" in 888ms (888ms including waiting). Image size: 235185383 bytes. 2026/07/02 12:31:02 12:30:27 INFO Pod/kserve-controller-manager-6c8cb86d7f-sr994: AddedInterface - Add eth0 [10.131.0.199/23] from ovn-kubernetes 2026/07/02 12:31:02 12:30:26 WARN Pod/kserve-controller-manager-6c8cb86d7f-sr994: FailedMount - MountVolume.SetUp failed for volume "cert" : secret "kserve-webhook-server-cert" not found 2026/07/02 12:31:02 12:30:26 INFO Pod/llmisvc-controller-manager-586c85c465-5s744: AddedInterface - Add eth0 [10.130.3.100/23] from ovn-kubernetes 2026/07/02 12:31:02 12:30:26 INFO Pod/llmisvc-controller-manager-586c85c465-5s744: Pulling - Pulling image "registry.redhat.io/rhoai/odh-kserve-llmisvc-controller-rhel9@sha256:d3225eb3f0bfcb20a6d1dccd63403e58a810921680425ecae1b22d86a451417d" 2026/07/02 12:31:02 12:30:25 INFO Pod/llmisvc-controller-manager-586c85c465-5s744: Scheduled - Successfully assigned redhat-ods-applications/llmisvc-controller-manager-586c85c465-5s744 to ods-qe-psi-07-b4mqp-worker-0-tx6lc 2026/07/02 12:31:02 12:30:25 INFO Pod/kserve-controller-manager-6c8cb86d7f-sr994: Scheduled - Successfully assigned redhat-ods-applications/kserve-controller-manager-6c8cb86d7f-sr994 to ods-qe-psi-07-b4mqp-worker-0-wvlfv 2026/07/02 12:31:02 12:30:25 INFO ReplicaSet/llmisvc-controller-manager-586c85c465: SuccessfulCreate - Created pod: llmisvc-controller-manager-586c85c465-5s744 2026/07/02 12:31:02 12:30:25 INFO ReplicaSet/kserve-controller-manager-6c8cb86d7f: SuccessfulCreate - Created pod: kserve-controller-manager-6c8cb86d7f-sr994 2026/07/02 12:31:02 12:30:25 INFO Deployment/kserve-controller-manager: ScalingReplicaSet - Scaled up replica set kserve-controller-manager-6c8cb86d7f from 0 to 1 2026/07/02 12:31:02 12:30:25 INFO Deployment/llmisvc-controller-manager: ScalingReplicaSet - Scaled up replica set llmisvc-controller-manager-586c85c465 from 0 to 1 2026/07/02 12:31:02 12:30:14 INFO Pod/odh-model-controller-54bf759f64-8r4c2: Started - Started container manager 2026/07/02 12:31:02 12:30:14 INFO Pod/model-serving-api-78bbbb9bf8-s5w9r: Pulled - Container image "registry.redhat.io/rhoai/odh-model-serving-api-rhel9@sha256:6dd699e678c3f4d6e51138eea62f096f26472b5f9c1ce2757cf9e9e2f80371a4" already present on machine 2026/07/02 12:31:02 12:30:14 INFO Pod/odh-model-controller-54bf759f64-8r4c2: Pulled - Successfully pulled image "registry.redhat.io/rhoai/odh-model-controller-rhel9@sha256:b423702816000ce0f075548e3a67de006f40ccf05c575a866cb62e2ac9711191" in 920ms (920ms including waiting). Image size: 238719956 bytes. 2026/07/02 12:31:02 12:30:14 INFO Pod/odh-model-controller-54bf759f64-8r4c2: Created - Created container: manager 2026/07/02 12:31:02 12:30:14 INFO Pod/model-serving-api-78bbbb9bf8-s5w9r: Started - Started container server 2026/07/02 12:31:02 12:30:14 INFO Pod/model-serving-api-78bbbb9bf8-s5w9r: Created - Created container: server 2026/07/02 12:31:02 12:30:14 INFO Pod/model-serving-api-78bbbb9bf8-s5w9r: AddedInterface - Add eth0 [10.130.3.99/23] from ovn-kubernetes 2026/07/02 12:31:02 12:30:14 WARN ServiceMonitor/odh-model-controller-metrics-monitor: InvalidConfiguration - ServiceMonitor odh-model-controller-metrics-monitor was rejected due to invalid configuration: it accesses file system via bearer token [REDACTED] which Prometheus specification prohibits 2026/07/02 12:31:02 12:30:13 INFO Pod/model-serving-api-78bbbb9bf8-s5w9r: Scheduled - Successfully assigned redhat-ods-applications/model-serving-api-78bbbb9bf8-s5w9r to ods-qe-psi-07-b4mqp-worker-0-tx6lc 2026/07/02 12:31:02 12:30:13 INFO Pod/odh-model-controller-54bf759f64-8r4c2: AddedInterface - Add eth0 [10.130.3.98/23] from ovn-kubernetes 2026/07/02 12:31:02 12:30:13 INFO ReplicaSet/model-serving-api-78bbbb9bf8: SuccessfulCreate - Created pod: model-serving-api-78bbbb9bf8-s5w9r 2026/07/02 12:31:02 12:30:13 INFO Pod/odh-model-controller-54bf759f64-8r4c2: Pulling - Pulling image "registry.redhat.io/rhoai/odh-model-controller-rhel9@sha256:b423702816000ce0f075548e3a67de006f40ccf05c575a866cb62e2ac9711191" 2026/07/02 12:31:02 12:30:13 INFO Deployment/model-serving-api: ScalingReplicaSet - Scaled up replica set model-serving-api-78bbbb9bf8 from 0 to 1 2026/07/02 12:31:02 12:30:13 WARN ReplicaSet/model-serving-api-78bbbb9bf8: FailedCreate - Error creating: pods "model-serving-api-78bbbb9bf8-" is forbidden: error looking up service account redhat-ods-applications/model-serving-api: serviceaccount "model-serving-api" not found 2026/07/02 12:31:02 12:30:12 INFO Pod/odh-model-controller-54bf759f64-8r4c2: Scheduled - Successfully assigned redhat-ods-applications/odh-model-controller-54bf759f64-8r4c2 to ods-qe-psi-07-b4mqp-worker-0-tx6lc 2026/07/02 12:31:02 12:30:12 INFO Deployment/odh-model-controller: ScalingReplicaSet - Scaled up replica set odh-model-controller-54bf759f64 from 0 to 1 2026/07/02 12:31:02 12:30:12 INFO ReplicaSet/odh-model-controller-54bf759f64: SuccessfulCreate - Created pod: odh-model-controller-54bf759f64-8r4c2 2026/07/02 12:31:02 12:30:12 WARN Pod/odh-model-controller-54bf759f64-8r4c2: FailedMount - MountVolume.SetUp failed for volume "cert" : secret "odh-model-controller-webhook-cert" not found 2026/07/02 12:31:02 12:30:02 INFO Pod/model-serving-api-78bbbb9bf8-b5wdg: Killing - Stopping container server 2026/07/02 12:31:02 12:30:02 INFO Pod/kserve-controller-manager-6c8cb86d7f-6rmd5: Killing - Stopping container manager 2026/07/02 12:31:02 12:30:02 INFO Pod/llmisvc-controller-manager-586c85c465-wqpng: Killing - Stopping container manager 2026/07/02 12:31:02 12:30:02 INFO Pod/odh-model-controller-54bf759f64-58gxw: Killing - Stopping container manager 2026/07/02 12:31:02 12:30:01 WARN ServiceMonitor/odh-model-controller-metrics-monitor: InvalidConfiguration - ServiceMonitor odh-model-controller-metrics-monitor was rejected due to invalid configuration: it accesses file system via bearer token [REDACTED] which Prometheus specification prohibits 2026/07/02 12:31:02 12:29:43 INFO Lease/llminferenceservice-kserve-controller-manager: LeaderElection - llmisvc-controller-manager-586c85c465-wqpng_3addd06b-7094-4278-8e16-e0c92605b11c became leader 2026/07/02 12:31:02 12:29:43 INFO Lease/kserve-controller-manager-leader-lock: LeaderElection - kserve-controller-manager-6c8cb86d7f-6rmd5_52e13deb-d756-4dd7-9e3a-1f00446eea88 became leader 2026/07/02 12:31:02 12:29:30 INFO Lease/odh-model-controller.opendatahub.io: LeaderElection - odh-model-controller-54bf759f64-58gxw_b7e46cdb-ed5f-42b3-84fd-4852ed45bd0a became leader 2026/07/02 12:31:02 12:29:27 INFO Pod/kserve-controller-manager-6c8cb86d7f-6rmd5: Pulled - Successfully pulled image "registry.redhat.io/rhoai/odh-kserve-controller-rhel9@sha256:7f6f393635a7431d530256ef8ad48ebd35531166dbb361c6c0ff9fc37bd5dc2b" in 571ms (571ms including waiting). Image size: 237680379 bytes. 2026/07/02 12:31:02 12:29:27 INFO Pod/kserve-controller-manager-6c8cb86d7f-6rmd5: Started - Started container manager 2026/07/02 12:31:02 12:29:27 INFO Pod/llmisvc-controller-manager-586c85c465-wqpng: Started - Started container manager 2026/07/02 12:31:02 12:29:27 INFO Pod/llmisvc-controller-manager-586c85c465-wqpng: Created - Created container: manager 2026/07/02 12:31:02 12:29:27 INFO Pod/kserve-controller-manager-6c8cb86d7f-6rmd5: Created - Created container: manager 2026/07/02 12:31:02 12:29:26 INFO Pod/llmisvc-controller-manager-586c85c465-wqpng: Pulling - Pulling image "registry.redhat.io/rhoai/odh-kserve-llmisvc-controller-rhel9@sha256:d3225eb3f0bfcb20a6d1dccd63403e58a810921680425ecae1b22d86a451417d" 2026/07/02 12:31:02 12:29:26 INFO Pod/kserve-controller-manager-6c8cb86d7f-6rmd5: AddedInterface - Add eth0 [10.131.0.198/23] from ovn-kubernetes 2026/07/02 12:31:02 12:29:26 INFO Pod/llmisvc-controller-manager-586c85c465-wqpng: AddedInterface - Add eth0 [10.130.3.97/23] from ovn-kubernetes 2026/07/02 12:31:02 12:29:26 INFO Pod/kserve-controller-manager-6c8cb86d7f-6rmd5: Pulling - Pulling image "registry.redhat.io/rhoai/odh-kserve-controller-rhel9@sha256:7f6f393635a7431d530256ef8ad48ebd35531166dbb361c6c0ff9fc37bd5dc2b" 2026/07/02 12:31:02 12:29:26 INFO Pod/llmisvc-controller-manager-586c85c465-wqpng: Pulled - Successfully pulled image "registry.redhat.io/rhoai/odh-kserve-llmisvc-controller-rhel9@sha256:d3225eb3f0bfcb20a6d1dccd63403e58a810921680425ecae1b22d86a451417d" in 756ms (756ms including waiting). Image size: 235185383 bytes. 2026/07/02 12:31:02 12:29:25 INFO Pod/llmisvc-controller-manager-586c85c465-wqpng: Scheduled - Successfully assigned redhat-ods-applications/llmisvc-controller-manager-586c85c465-wqpng to ods-qe-psi-07-b4mqp-worker-0-tx6lc 2026/07/02 12:31:02 12:29:25 INFO Pod/kserve-controller-manager-6c8cb86d7f-6rmd5: Scheduled - Successfully assigned redhat-ods-applications/kserve-controller-manager-6c8cb86d7f-6rmd5 to ods-qe-psi-07-b4mqp-worker-0-wvlfv 2026/07/02 12:31:02 12:29:25 WARN Pod/kserve-controller-manager-6c8cb86d7f-6rmd5: FailedMount - MountVolume.SetUp failed for volume "cert" : secret "kserve-webhook-server-cert" not found 2026/07/02 12:31:02 12:29:25 INFO ReplicaSet/llmisvc-controller-manager-586c85c465: SuccessfulCreate - Created pod: llmisvc-controller-manager-586c85c465-wqpng 2026/07/02 12:31:02 12:29:25 INFO Deployment/llmisvc-controller-manager: ScalingReplicaSet - Scaled up replica set llmisvc-controller-manager-586c85c465 from 0 to 1 2026/07/02 12:31:02 12:29:25 INFO ReplicaSet/kserve-controller-manager-6c8cb86d7f: SuccessfulCreate - Created pod: kserve-controller-manager-6c8cb86d7f-6rmd5 2026/07/02 12:31:02 12:29:25 INFO Deployment/kserve-controller-manager: ScalingReplicaSet - Scaled up replica set kserve-controller-manager-6c8cb86d7f from 0 to 1 2026/07/02 12:31:02 12:29:23 INFO Lease/trainer.kubeflow.org: LeaderElection - kubeflow-trainer-controller-manager-776d978f97-bnfjn_d5426647-aefd-487b-83e7-5748b9b189a2 became leader 2026/07/02 12:31:02 12:29:13 INFO Pod/odh-model-controller-54bf759f64-58gxw: Created - Created container: manager 2026/07/02 12:31:02 12:29:13 INFO Pod/model-serving-api-78bbbb9bf8-b5wdg: Created - Created container: server 2026/07/02 12:31:02 12:29:13 INFO Pod/odh-model-controller-54bf759f64-58gxw: Started - Started container manager 2026/07/02 12:31:02 12:29:13 INFO Pod/model-serving-api-78bbbb9bf8-b5wdg: AddedInterface - Add eth0 [10.130.3.96/23] from ovn-kubernetes 2026/07/02 12:31:02 12:29:13 INFO Pod/model-serving-api-78bbbb9bf8-b5wdg: Pulled - Container image "registry.redhat.io/rhoai/odh-model-serving-api-rhel9@sha256:6dd699e678c3f4d6e51138eea62f096f26472b5f9c1ce2757cf9e9e2f80371a4" already present on machine 2026/07/02 12:31:02 12:29:13 INFO Pod/odh-model-controller-54bf759f64-58gxw: Pulled - Successfully pulled image "registry.redhat.io/rhoai/odh-model-controller-rhel9@sha256:b423702816000ce0f075548e3a67de006f40ccf05c575a866cb62e2ac9711191" in 1.049s (1.049s including waiting). Image size: 238719956 bytes. 2026/07/02 12:31:02 12:29:13 INFO Pod/model-serving-api-78bbbb9bf8-b5wdg: Started - Started container server 2026/07/02 12:31:02 12:29:12 INFO Pod/model-serving-api-78bbbb9bf8-b5wdg: Scheduled - Successfully assigned redhat-ods-applications/model-serving-api-78bbbb9bf8-b5wdg to ods-qe-psi-07-b4mqp-worker-0-tx6lc 2026/07/02 12:31:02 12:29:12 WARN ReplicaSet/model-serving-api-78bbbb9bf8: FailedCreate - Error creating: pods "model-serving-api-78bbbb9bf8-" is forbidden: error looking up service account redhat-ods-applications/model-serving-api: serviceaccount "model-serving-api" not found 2026/07/02 12:31:02 12:29:12 INFO Pod/odh-model-controller-54bf759f64-58gxw: AddedInterface - Add eth0 [10.130.3.95/23] from ovn-kubernetes 2026/07/02 12:31:02 12:29:12 INFO Pod/odh-model-controller-54bf759f64-58gxw: Pulling - Pulling image "registry.redhat.io/rhoai/odh-model-controller-rhel9@sha256:b423702816000ce0f075548e3a67de006f40ccf05c575a866cb62e2ac9711191" 2026/07/02 12:31:02 12:29:12 INFO ReplicaSet/model-serving-api-78bbbb9bf8: SuccessfulCreate - Created pod: model-serving-api-78bbbb9bf8-b5wdg 2026/07/02 12:31:02 12:29:12 INFO Deployment/model-serving-api: ScalingReplicaSet - Scaled up replica set model-serving-api-78bbbb9bf8 from 0 to 1 2026/07/02 12:31:02 12:29:11 INFO Pod/odh-model-controller-54bf759f64-58gxw: Scheduled - Successfully assigned redhat-ods-applications/odh-model-controller-54bf759f64-58gxw to ods-qe-psi-07-b4mqp-worker-0-tx6lc 2026/07/02 12:31:02 12:29:11 INFO ReplicaSet/odh-model-controller-54bf759f64: SuccessfulCreate - Created pod: odh-model-controller-54bf759f64-58gxw 2026/07/02 12:31:02 12:29:11 INFO Deployment/odh-model-controller: ScalingReplicaSet - Scaled up replica set odh-model-controller-54bf759f64 from 0 to 1 2026/07/02 12:31:02 12:29:08 INFO Pod/kserve-controller-manager-6c8cb86d7f-2jslp: Created - Created container: manager 2026/07/02 12:31:02 12:29:08 INFO Pod/kserve-controller-manager-6c8cb86d7f-2jslp: Started - Started container manager 2026/07/02 12:31:02 12:29:08 INFO Pod/llmisvc-controller-manager-586c85c465-kdjp7: Started - Started container manager 2026/07/02 12:31:02 12:29:08 INFO Pod/llmisvc-controller-manager-586c85c465-kdjp7: Pulled - Successfully pulled image "registry.redhat.io/rhoai/odh-kserve-llmisvc-controller-rhel9@sha256:d3225eb3f0bfcb20a6d1dccd63403e58a810921680425ecae1b22d86a451417d" in 786ms (786ms including waiting). Image size: 235185383 bytes. 2026/07/02 12:31:02 12:29:08 INFO Pod/llmisvc-controller-manager-586c85c465-kdjp7: Created - Created container: manager 2026/07/02 12:31:02 12:29:07 INFO Pod/kserve-controller-manager-6c8cb86d7f-2jslp: Pulled - Successfully pulled image "registry.redhat.io/rhoai/odh-kserve-controller-rhel9@sha256:7f6f393635a7431d530256ef8ad48ebd35531166dbb361c6c0ff9fc37bd5dc2b" in 820ms (820ms including waiting). Image size: 237680379 bytes. 2026/07/02 12:31:02 12:29:07 INFO Pod/kserve-controller-manager-6c8cb86d7f-2jslp: Pulling - Pulling image "registry.redhat.io/rhoai/odh-kserve-controller-rhel9@sha256:7f6f393635a7431d530256ef8ad48ebd35531166dbb361c6c0ff9fc37bd5dc2b" 2026/07/02 12:31:02 12:29:07 INFO Pod/kserve-controller-manager-6c8cb86d7f-2jslp: AddedInterface - Add eth0 [10.130.3.94/23] from ovn-kubernetes 2026/07/02 12:31:02 12:29:07 INFO Pod/llmisvc-controller-manager-586c85c465-kdjp7: AddedInterface - Add eth0 [10.131.0.197/23] from ovn-kubernetes 2026/07/02 12:31:02 12:29:07 INFO Pod/llmisvc-controller-manager-586c85c465-kdjp7: Pulling - Pulling image "registry.redhat.io/rhoai/odh-kserve-llmisvc-controller-rhel9@sha256:d3225eb3f0bfcb20a6d1dccd63403e58a810921680425ecae1b22d86a451417d" 2026/07/02 12:31:02 12:29:06 INFO Pod/llmisvc-controller-manager-586c85c465-kdjp7: Scheduled - Successfully assigned redhat-ods-applications/llmisvc-controller-manager-586c85c465-kdjp7 to ods-qe-psi-07-b4mqp-worker-0-wvlfv 2026/07/02 12:31:02 12:29:06 INFO Pod/kserve-controller-manager-6c8cb86d7f-2jslp: Scheduled - Successfully assigned redhat-ods-applications/kserve-controller-manager-6c8cb86d7f-2jslp to ods-qe-psi-07-b4mqp-worker-0-tx6lc 2026/07/02 12:31:02 12:29:06 INFO Pod/kubeflow-trainer-controller-manager-776d978f97-bnfjn: Created - Created container: manager 2026/07/02 12:31:02 12:29:06 INFO ReplicaSet/kserve-controller-manager-6c8cb86d7f: SuccessfulCreate - Created pod: kserve-controller-manager-6c8cb86d7f-2jslp 2026/07/02 12:31:02 12:29:06 INFO Deployment/llmisvc-controller-manager: ScalingReplicaSet - Scaled up replica set llmisvc-controller-manager-586c85c465 from 0 to 1 2026/07/02 12:31:02 12:29:06 INFO Deployment/kserve-controller-manager: ScalingReplicaSet - Scaled up replica set kserve-controller-manager-6c8cb86d7f from 0 to 1 2026/07/02 12:31:02 12:29:06 INFO Pod/kubeflow-trainer-controller-manager-776d978f97-bnfjn: AddedInterface - Add eth0 [10.131.0.196/23] from ovn-kubernetes 2026/07/02 12:31:02 12:29:06 INFO ReplicaSet/llmisvc-controller-manager-586c85c465: SuccessfulCreate - Created pod: llmisvc-controller-manager-586c85c465-kdjp7 2026/07/02 12:31:02 12:29:06 INFO Pod/kubeflow-trainer-controller-manager-776d978f97-bnfjn: Started - Started container manager 2026/07/02 12:31:02 12:29:06 INFO Pod/kubeflow-trainer-controller-manager-776d978f97-bnfjn: Pulled - Container image "registry.redhat.io/rhoai/odh-trainer-rhel9@sha256:904dd86da976fced2d3618cbe932baadaf94934280aab3a68f6cc9f04ee2efbd" already present on machine 2026/07/02 12:31:02 12:29:05 INFO Pod/kubeflow-trainer-controller-manager-776d978f97-bnfjn: Scheduled - Successfully assigned redhat-ods-applications/kubeflow-trainer-controller-manager-776d978f97-bnfjn to ods-qe-psi-07-b4mqp-worker-0-wvlfv 2026/07/02 12:31:02 12:29:05 INFO ReplicaSet/kubeflow-trainer-controller-manager-776d978f97: SuccessfulCreate - Created pod: kubeflow-trainer-controller-manager-776d978f97-bnfjn 2026/07/02 12:31:02 12:29:05 INFO Deployment/kubeflow-trainer-controller-manager: ScalingReplicaSet - Scaled up replica set kubeflow-trainer-controller-manager-776d978f97 from 0 to 1 2026/07/02 12:31:02 12:29:01 INFO Pod/model-serving-api-78bbbb9bf8-q7h2l: Killing - Stopping container server 2026/07/02 12:31:02 12:29:01 INFO Pod/odh-model-controller-54bf759f64-bwnsc: Killing - Stopping container manager 2026/07/02 12:31:02 12:29:00 INFO Pod/llmisvc-controller-manager-586c85c465-mvrg2: Killing - Stopping container manager 2026/07/02 12:31:02 12:29:00 WARN Service/kserve-controller-manager-metrics-service: FailedToUpdateEndpointSlices - Error updating Endpoint Slices for Service redhat-ods-applications/kserve-controller-manager-metrics-service: failed to update kserve-controller-manager-metrics-service-pfcfj EndpointSlice for Service redhat-ods-applications/kserve-controller-manager-metrics-service: endpointslices.discovery.k8s.io "kserve-controller-manager-metrics-service-pfcfj" not found 2026/07/02 12:31:02 12:29:00 WARN Endpoints/kserve-webhook-server-service: FailedToUpdateEndpoint - Failed to update endpoint redhat-ods-applications/kserve-webhook-server-service: Operation cannot be fulfilled on endpoints "kserve-webhook-server-service": StorageError: invalid object, Code: 4, Key: /kubernetes.io/services/endpoints/redhat-ods-applications/kserve-webhook-server-service, ResourceVersion: 0, AdditionalErrorMsg: Precondition failed: UID in precondition: 574b3511-8e50-4f33-b880-9cda4365ce07, UID in object meta: 2026/07/02 12:31:02 12:29:00 INFO Pod/kserve-controller-manager-6c8cb86d7f-szj5n: Killing - Stopping container manager 2026/07/02 12:31:02 12:28:50 WARN ServiceMonitor/odh-model-controller-metrics-monitor: InvalidConfiguration - ServiceMonitor odh-model-controller-metrics-monitor was rejected due to invalid configuration: it accesses file system via bearer token [REDACTED] which Prometheus specification prohibits 2026/07/02 12:31:02 12:28:50 INFO Pod/maas-api-84c4b8dcb6-dnsqv: Killing - Stopping container maas-api 2026/07/02 12:31:02 12:28:49 INFO Pod/maas-controller-656b6867cb-2b2tq: Killing - Stopping container manager 2026/07/02 12:31:02 12:28:20 INFO Pod/maas-api-84c4b8dcb6-dnsqv: AddedInterface - Add eth0 [10.131.0.194/23] from ovn-kubernetes 2026/07/02 12:31:02 12:28:20 INFO Pod/maas-api-84c4b8dcb6-dnsqv: Pulling - Pulling image "registry.redhat.io/rhoai/odh-maas-api-rhel9@sha256:f1cc3f00d35421d0b60782cdb4e0331d94e922b483bc1f0e837ceabe63570328" 2026/07/02 12:31:02 12:28:20 INFO Pod/maas-api-84c4b8dcb6-dnsqv: Created - Created container: maas-api 2026/07/02 12:31:02 12:28:20 INFO Pod/maas-api-84c4b8dcb6-dnsqv: Pulled - Successfully pulled image "registry.redhat.io/rhoai/odh-maas-api-rhel9@sha256:f1cc3f00d35421d0b60782cdb4e0331d94e922b483bc1f0e837ceabe63570328" in 776ms (776ms including waiting). Image size: 174987716 bytes. 2026/07/02 12:31:02 12:28:20 INFO Pod/maas-api-84c4b8dcb6-dnsqv: Started - Started container maas-api 2026/07/02 12:31:02 12:28:19 INFO Pod/maas-api-84c4b8dcb6-dnsqv: Scheduled - Successfully assigned redhat-ods-applications/maas-api-84c4b8dcb6-dnsqv to ods-qe-psi-07-b4mqp-worker-0-wvlfv 2026/07/02 12:31:02 12:28:19 INFO Deployment/maas-api: ScalingReplicaSet - Scaled up replica set maas-api-84c4b8dcb6 from 0 to 1 2026/07/02 12:31:02 12:28:19 WARN ReplicaSet/maas-api-84c4b8dcb6: FailedCreate - Error creating: pods "maas-api-84c4b8dcb6-" is forbidden: error looking up service account redhat-ods-applications/maas-api: serviceaccount "maas-api" not found 2026/07/02 12:31:02 12:28:19 INFO ReplicaSet/maas-api-84c4b8dcb6: SuccessfulCreate - Created pod: maas-api-84c4b8dcb6-dnsqv 2026/07/02 12:31:02 12:28:05 INFO Lease/llminferenceservice-kserve-controller-manager: LeaderElection - llmisvc-controller-manager-586c85c465-mvrg2_25ff1440-8cfc-4bde-bae8-8d75126a1741 became leader 2026/07/02 12:31:02 12:28:03 INFO Lease/kserve-controller-manager-leader-lock: LeaderElection - kserve-controller-manager-6c8cb86d7f-szj5n_823b5a0f-a9bc-41d3-a038-2ab1a3ea1e2c became leader 2026/07/02 12:31:02 12:27:48 INFO Pod/kserve-controller-manager-6c8cb86d7f-szj5n: Created - Created container: manager 2026/07/02 12:31:02 12:27:48 INFO Lease/odh-model-controller.opendatahub.io: LeaderElection - odh-model-controller-54bf759f64-bwnsc_1a54a143-4825-4307-bc19-6f4f5459af77 became leader 2026/07/02 12:31:02 12:27:48 INFO Pod/llmisvc-controller-manager-586c85c465-mvrg2: Started - Started container manager 2026/07/02 12:31:02 12:27:48 INFO Pod/kserve-controller-manager-6c8cb86d7f-szj5n: Started - Started container manager 2026/07/02 12:31:02 12:27:48 INFO Pod/llmisvc-controller-manager-586c85c465-mvrg2: Created - Created container: manager 2026/07/02 12:31:02 12:27:48 INFO Pod/llmisvc-controller-manager-586c85c465-mvrg2: Pulled - Successfully pulled image "registry.redhat.io/rhoai/odh-kserve-llmisvc-controller-rhel9@sha256:d3225eb3f0bfcb20a6d1dccd63403e58a810921680425ecae1b22d86a451417d" in 1.413s (1.413s including waiting). Image size: 235185383 bytes. 2026/07/02 12:31:02 12:27:47 INFO Pod/kserve-controller-manager-6c8cb86d7f-szj5n: Pulling - Pulling image "registry.redhat.io/rhoai/odh-kserve-controller-rhel9@sha256:7f6f393635a7431d530256ef8ad48ebd35531166dbb361c6c0ff9fc37bd5dc2b" 2026/07/02 12:31:02 12:27:47 INFO Pod/kserve-controller-manager-6c8cb86d7f-szj5n: AddedInterface - Add eth0 [10.131.0.193/23] from ovn-kubernetes 2026/07/02 12:31:02 12:27:47 INFO Pod/kserve-controller-manager-6c8cb86d7f-szj5n: Pulled - Successfully pulled image "registry.redhat.io/rhoai/odh-kserve-controller-rhel9@sha256:7f6f393635a7431d530256ef8ad48ebd35531166dbb361c6c0ff9fc37bd5dc2b" in 875ms (875ms including waiting). Image size: 237680379 bytes. 2026/07/02 12:31:02 12:27:47 INFO Lease/maas-controller.models-as-a-service.opendatahub.io: LeaderElection - maas-controller-656b6867cb-2b2tq_c9e5d03d-e2c0-498c-a06a-109b31652743 became leader 2026/07/02 12:31:02 12:27:46 INFO Pod/llmisvc-controller-manager-586c85c465-mvrg2: Scheduled - Successfully assigned redhat-ods-applications/llmisvc-controller-manager-586c85c465-mvrg2 to ods-qe-psi-07-b4mqp-worker-0-tx6lc 2026/07/02 12:31:02 12:27:46 INFO Pod/kserve-controller-manager-6c8cb86d7f-szj5n: Scheduled - Successfully assigned redhat-ods-applications/kserve-controller-manager-6c8cb86d7f-szj5n to ods-qe-psi-07-b4mqp-worker-0-wvlfv 2026/07/02 12:31:02 12:27:46 INFO ReplicaSet/kserve-controller-manager-6c8cb86d7f: SuccessfulCreate - Created pod: kserve-controller-manager-6c8cb86d7f-szj5n 2026/07/02 12:31:02 12:27:46 INFO Deployment/kserve-controller-manager: ScalingReplicaSet - Scaled up replica set kserve-controller-manager-6c8cb86d7f from 0 to 1 2026/07/02 12:31:02 12:27:46 INFO Pod/llmisvc-controller-manager-586c85c465-mvrg2: AddedInterface - Add eth0 [10.130.3.93/23] from ovn-kubernetes 2026/07/02 12:31:02 12:27:46 INFO Pod/llmisvc-controller-manager-586c85c465-mvrg2: Pulling - Pulling image "registry.redhat.io/rhoai/odh-kserve-llmisvc-controller-rhel9@sha256:d3225eb3f0bfcb20a6d1dccd63403e58a810921680425ecae1b22d86a451417d" 2026/07/02 12:31:02 12:27:46 INFO ReplicaSet/llmisvc-controller-manager-586c85c465: SuccessfulCreate - Created pod: llmisvc-controller-manager-586c85c465-mvrg2 2026/07/02 12:31:02 12:27:46 INFO Deployment/llmisvc-controller-manager: ScalingReplicaSet - Scaled up replica set llmisvc-controller-manager-586c85c465 from 0 to 1 2026/07/02 12:31:02 12:27:32 INFO Pod/model-serving-api-78bbbb9bf8-q7h2l: AddedInterface - Add eth0 [10.130.3.92/23] from ovn-kubernetes 2026/07/02 12:31:02 12:27:32 INFO Pod/model-serving-api-78bbbb9bf8-q7h2l: Started - Started container server 2026/07/02 12:31:02 12:27:32 INFO Pod/model-serving-api-78bbbb9bf8-q7h2l: Created - Created container: server 2026/07/02 12:31:02 12:27:32 INFO Pod/model-serving-api-78bbbb9bf8-q7h2l: Pulled - Container image "registry.redhat.io/rhoai/odh-model-serving-api-rhel9@sha256:6dd699e678c3f4d6e51138eea62f096f26472b5f9c1ce2757cf9e9e2f80371a4" already present on machine 2026/07/02 12:31:02 12:27:31 INFO Pod/odh-model-controller-54bf759f64-bwnsc: Started - Started container manager 2026/07/02 12:31:02 12:27:31 INFO Pod/odh-model-controller-54bf759f64-bwnsc: Created - Created container: manager 2026/07/02 12:31:02 12:27:30 INFO Pod/model-serving-api-78bbbb9bf8-q7h2l: Scheduled - Successfully assigned redhat-ods-applications/model-serving-api-78bbbb9bf8-q7h2l to ods-qe-psi-07-b4mqp-worker-0-tx6lc 2026/07/02 12:31:02 12:27:30 INFO Pod/maas-controller-656b6867cb-2b2tq: AddedInterface - Add eth0 [10.131.0.192/23] from ovn-kubernetes 2026/07/02 12:31:02 12:27:30 INFO Pod/maas-controller-656b6867cb-2b2tq: Started - Started container manager 2026/07/02 12:31:02 12:27:30 WARN Pod/model-serving-api-78bbbb9bf8-q7h2l: FailedMount - MountVolume.SetUp failed for volume "tls-certs" : secret "model-serving-api-tls" not found 2026/07/02 12:31:02 12:27:30 WARN ReplicaSet/model-serving-api-78bbbb9bf8: FailedCreate - Error creating: pods "model-serving-api-78bbbb9bf8-" is forbidden: error looking up service account redhat-ods-applications/model-serving-api: serviceaccount "model-serving-api" not found 2026/07/02 12:31:02 12:27:30 INFO Pod/maas-controller-656b6867cb-2b2tq: Pulling - Pulling image "registry.redhat.io/rhoai/odh-maas-controller-rhel9@sha256:b8cca0d56d9ca5ab366cdc4042f13a908326e57b1b711c59e6ff101507058fb4" 2026/07/02 12:31:02 12:27:30 INFO Pod/maas-controller-656b6867cb-2b2tq: Pulled - Successfully pulled image "registry.redhat.io/rhoai/odh-maas-controller-rhel9@sha256:b8cca0d56d9ca5ab366cdc4042f13a908326e57b1b711c59e6ff101507058fb4" in 714ms (714ms including waiting). Image size: 212345923 bytes. 2026/07/02 12:31:02 12:27:30 INFO Pod/odh-model-controller-54bf759f64-bwnsc: AddedInterface - Add eth0 [10.131.0.191/23] from ovn-kubernetes 2026/07/02 12:31:02 12:27:30 INFO Pod/odh-model-controller-54bf759f64-bwnsc: Pulling - Pulling image "registry.redhat.io/rhoai/odh-model-controller-rhel9@sha256:b423702816000ce0f075548e3a67de006f40ccf05c575a866cb62e2ac9711191" 2026/07/02 12:31:02 12:27:30 INFO Pod/odh-model-controller-54bf759f64-bwnsc: Pulled - Successfully pulled image "registry.redhat.io/rhoai/odh-model-controller-rhel9@sha256:b423702816000ce0f075548e3a67de006f40ccf05c575a866cb62e2ac9711191" in 832ms (832ms including waiting). Image size: 238719956 bytes. 2026/07/02 12:31:02 12:27:30 INFO ReplicaSet/model-serving-api-78bbbb9bf8: SuccessfulCreate - Created pod: model-serving-api-78bbbb9bf8-q7h2l 2026/07/02 12:31:02 12:27:30 INFO Deployment/model-serving-api: ScalingReplicaSet - Scaled up replica set model-serving-api-78bbbb9bf8 from 0 to 1 2026/07/02 12:31:02 12:27:30 INFO Pod/maas-controller-656b6867cb-2b2tq: Created - Created container: manager 2026/07/02 12:31:02 12:27:29 INFO Pod/maas-controller-656b6867cb-2b2tq: Scheduled - Successfully assigned redhat-ods-applications/maas-controller-656b6867cb-2b2tq to ods-qe-psi-07-b4mqp-worker-0-wvlfv 2026/07/02 12:31:02 12:27:29 INFO Deployment/maas-controller: ScalingReplicaSet - Scaled up replica set maas-controller-656b6867cb from 0 to 1 2026/07/02 12:31:02 12:27:29 INFO ReplicaSet/maas-controller-656b6867cb: SuccessfulCreate - Created pod: maas-controller-656b6867cb-2b2tq 2026/07/02 12:31:02 12:27:29 WARN Pod/odh-model-controller-54bf759f64-bwnsc: FailedMount - MountVolume.SetUp failed for volume "cert" : secret "odh-model-controller-webhook-cert" not found 2026/07/02 12:31:02 12:27:28 INFO Pod/odh-model-controller-54bf759f64-bwnsc: Scheduled - Successfully assigned redhat-ods-applications/odh-model-controller-54bf759f64-bwnsc to ods-qe-psi-07-b4mqp-worker-0-wvlfv 2026/07/02 12:31:02 12:27:28 INFO Deployment/odh-model-controller: ScalingReplicaSet - Scaled up replica set odh-model-controller-54bf759f64 from 0 to 1 2026/07/02 12:31:02 12:27:28 INFO ReplicaSet/odh-model-controller-54bf759f64: SuccessfulCreate - Created pod: odh-model-controller-54bf759f64-bwnsc 2026/07/02 12:31:02 12:27:16 INFO Pod/trustyai-service-operator-controller-manager-6f7f88c874-ck7qf: Killing - Stopping container manager 2026/07/02 12:31:02 12:27:07 INFO Pod/model-serving-api-78bbbb9bf8-hcqmv: Killing - Stopping container server 2026/07/02 12:31:02 12:27:07 INFO Pod/odh-model-controller-54bf759f64-wlrsf: Killing - Stopping container manager 2026/07/02 12:31:02 12:27:07 INFO Pod/maas-controller-656b6867cb-4k88d: Killing - Stopping container manager 2026/07/02 12:31:02 12:27:07 INFO Lease/b7e9931f.trustyai.opendatahub.io: LeaderElection - trustyai-service-operator-controller-manager-6f7f88c874-ck7qf_07ed48c6-1796-41f2-ba77-d6d1c82cacdd became leader 2026/07/02 12:31:02 12:27:07 INFO Pod/maas-api-84c4b8dcb6-58pwl: Killing - Stopping container maas-api 2026/07/02 12:31:02 12:27:06 INFO Pod/llmisvc-controller-manager-586c85c465-dd2bp: Killing - Stopping container manager 2026/07/02 12:31:02 12:27:06 INFO Pod/kserve-controller-manager-6c8cb86d7f-d8zd5: Killing - Stopping container manager 2026/07/02 12:31:02 12:26:51 INFO Pod/trustyai-service-operator-controller-manager-6f7f88c874-ck7qf: Pulled - Container image "registry.redhat.io/rhoai/odh-trustyai-service-operator-rhel9@sha256:b9d442a66d0ac181c430fd5f27b6de0dac8b4f815ca9668c436da246676f0980" already present on machine 2026/07/02 12:31:02 12:26:51 INFO Pod/trustyai-service-operator-controller-manager-6f7f88c874-ck7qf: AddedInterface - Add eth0 [10.131.0.190/23] from ovn-kubernetes 2026/07/02 12:31:02 12:26:51 INFO Pod/trustyai-service-operator-controller-manager-6f7f88c874-ck7qf: Created - Created container: manager 2026/07/02 12:31:02 12:26:51 INFO Pod/trustyai-service-operator-controller-manager-6f7f88c874-ck7qf: Started - Started container manager 2026/07/02 12:31:02 12:26:51 WARN Pod/trustyai-service-operator-controller-manager-6f7f88c874-g69lk: Unhealthy - Readiness probe failed: Get "http://10.131.0.188:8081/readyz": context deadline exceeded (Client.Timeout exceeded while awaiting headers) 2026/07/02 12:31:02 12:26:50 INFO Pod/trustyai-service-operator-controller-manager-6f7f88c874-ck7qf: Scheduled - Successfully assigned redhat-ods-applications/trustyai-service-operator-controller-manager-6f7f88c874-ck7qf to ods-qe-psi-07-b4mqp-worker-0-wvlfv 2026/07/02 12:31:02 12:26:50 INFO Pod/trustyai-service-operator-controller-manager-6f7f88c874-g69lk: Killing - Stopping container manager 2026/07/02 12:31:02 12:26:50 INFO Pod/trustyai-service-operator-controller-manager-6f7f88c874-zwtwp: Killing - Stopping container manager 2026/07/02 12:31:02 12:26:50 INFO ReplicaSet/trustyai-service-operator-controller-manager-6f7f88c874: SuccessfulCreate - Created pod: trustyai-service-operator-controller-manager-6f7f88c874-ck7qf 2026/07/02 12:31:02 12:26:50 INFO Deployment/trustyai-service-operator-controller-manager: ScalingReplicaSet - Scaled up replica set trustyai-service-operator-controller-manager-6f7f88c874 from 0 to 1 2026/07/02 12:31:02 === RESOURCE QUOTAS === 2026/07/02 12:31:02 No resource quotas found in monitored namespaces 2026/07/02 12:31:02 Classification for components: infrastructure/storage (code=1006, confidence=medium) 2026/07/02 12:31:02 Evidence: event Pod/kserve-controller-manager-6c8cb86d7f-sr994: FailedMount - MountVolume.SetUp failed for volume "cert" : secret "kserve-webhook-server-cert" not found FAILURE_CLASSIFICATION: {"category":"infrastructure","subcategory":"storage","error_code":1006,"evidence":["event Pod/kserve-controller-manager-6c8cb86d7f-sr994: FailedMount - MountVolume.SetUp failed for volume \"cert\" : secret \"kserve-webhook-server-cert\" not found"],"confidence":"medium"} 2026/07/02 12:31:02 Diagnostics complete for failed test: components controller_test.go:491: Stopping: components test failed. 2026/07/02 12:31:02 Circuit breaker: failure classified as infrastructure/storage (code=1006) 2026/07/02 12:31:02 Circuit breaker: infrastructure/unknown failure recorded (1/3 consecutive) Deletion Policy: Never. Skipping deletion tests. 2026/07/02 12:31:04 Circuit breaker: no trips during this run (threshold=3) --- FAIL: TestOdhOperator (1838.47s)