apiVersion: v1 items: - apiVersion: ray.io/v1 kind: RayCluster metadata: annotations: odh.ray.io/secure-trusted-network: "true" creationTimestamp: "2026-06-05T09:35:06Z" finalizers: - ray.io/authentication-resources generation: 1 name: raycluster namespace: test-ns-rfwvh resourceVersion: "16278" uid: c4625389-d462-4f96-9968-2d9c8dbc6f6b spec: headGroupSpec: enableIngress: false rayStartParams: dashboard-host: 0.0.0.0 template: metadata: {} spec: containers: - image: quay.io/modh/ray@sha256:42fbc5d898cb9c7d202ee89308ef328838d42985ec384f2476d8f3356acd01cb name: ray-head ports: - containerPort: 6379 name: gcs-server protocol: TCP - containerPort: 8000 name: serve protocol: TCP - containerPort: 8265 name: dashboard protocol: TCP - containerPort: 10001 name: client protocol: TCP resources: limits: cpu: "2" memory: 10G requests: cpu: 500m memory: 6G volumeMounts: - mountPath: /home/ray/jobs name: jobs volumes: - configMap: name: jobs name: jobs rayVersion: 2.46.0 workerGroupSpecs: - groupName: small-group maxReplicas: 1 minReplicas: 1 numOfHosts: 1 rayStartParams: num-cpus: "1" replicas: 1 scaleStrategy: {} template: metadata: {} spec: containers: - image: quay.io/modh/ray@sha256:42fbc5d898cb9c7d202ee89308ef328838d42985ec384f2476d8f3356acd01cb name: ray-worker resources: limits: cpu: "1" memory: 3G requests: cpu: 500m memory: 1G status: availableWorkerReplicas: 1 conditions: - lastTransitionTime: "2026-06-05T09:38:59Z" message: "" reason: HeadPodRunningAndReady status: "True" type: HeadPodReady - lastTransitionTime: "2026-06-05T09:39:01Z" message: All Ray Pods are ready for the first time reason: AllPodRunningAndReadyFirstTime status: "True" type: RayClusterProvisioned - lastTransitionTime: "2026-06-05T09:35:06Z" message: "" reason: RayClusterSuspended status: "False" type: RayClusterSuspended - lastTransitionTime: "2026-06-05T09:35:06Z" message: "" reason: RayClusterSuspending status: "False" type: RayClusterSuspending - lastTransitionTime: "2026-06-05T09:35:06Z" message: 'Authentication resources created successfully (mode: IntegratedOAuth)' observedGeneration: 1 reason: AuthenticationResourcesCreated status: "True" type: AuthenticationReady desiredCPU: "1" desiredGPU: "0" desiredMemory: 7G desiredTPU: "0" desiredWorkerReplicas: 1 endpoints: client: "10001" dashboard: "8265" gcs-server: "6379" metrics: "8080" serve: "8000" head: podIP: 10.134.0.20 podName: raycluster-head-vjd7d serviceIP: 10.134.0.20 serviceName: raycluster-head-svc lastUpdateTime: "2026-06-05T09:39:01Z" maxWorkerReplicas: 1 minWorkerReplicas: 1 observedGeneration: 1 readyWorkerReplicas: 1 state: ready stateTransitionTimes: ready: "2026-06-05T09:39:01Z" - apiVersion: ray.io/v1 kind: RayJob metadata: creationTimestamp: "2026-06-05T09:49:43Z" finalizers: - ray.io/rayjob-finalizer generation: 2 name: counter namespace: test-ns-rfwvh resourceVersion: "24077" uid: 2e57ebd9-e052-4278-a29c-536e7a60a22a spec: backoffLimit: 0 clusterSelector: ray.io/cluster: raycluster entrypoint: python /home/ray/jobs/counter.py runtimeEnvYAML: |2 env_vars: counter_name: test_counter submissionMode: K8sJobMode submitterPodTemplate: metadata: {} spec: containers: - image: quay.io/modh/ray@sha256:42fbc5d898cb9c7d202ee89308ef328838d42985ec384f2476d8f3356acd01cb name: ray-job-submitter resources: limits: cpu: 500m memory: 500Mi requests: cpu: 200m memory: 200Mi restartPolicy: Never ttlSecondsAfterFinished: 0 status: dashboardURL: raycluster-head-svc.test-ns-rfwvh.svc.cluster.local:8265 endTime: "2026-06-05T09:50:04Z" failed: 0 jobDeploymentStatus: Complete jobId: counter-65xg8 jobStatus: SUCCEEDED message: Job finished successfully. rayClusterName: raycluster rayClusterStatus: availableWorkerReplicas: 1 conditions: - lastTransitionTime: "2026-06-05T09:38:59Z" message: "" reason: HeadPodRunningAndReady status: "True" type: HeadPodReady - lastTransitionTime: "2026-06-05T09:39:01Z" message: All Ray Pods are ready for the first time reason: AllPodRunningAndReadyFirstTime status: "True" type: RayClusterProvisioned - lastTransitionTime: "2026-06-05T09:35:06Z" message: "" reason: RayClusterSuspended status: "False" type: RayClusterSuspended - lastTransitionTime: "2026-06-05T09:35:06Z" message: "" reason: RayClusterSuspending status: "False" type: RayClusterSuspending - lastTransitionTime: "2026-06-05T09:35:06Z" message: 'Authentication resources created successfully (mode: IntegratedOAuth)' observedGeneration: 1 reason: AuthenticationResourcesCreated status: "True" type: AuthenticationReady desiredCPU: "1" desiredGPU: "0" desiredMemory: 7G desiredTPU: "0" desiredWorkerReplicas: 1 endpoints: client: "10001" dashboard: "8265" gcs-server: "6379" metrics: "8080" serve: "8000" head: podIP: 10.134.0.20 podName: raycluster-head-vjd7d serviceIP: 10.134.0.20 serviceName: raycluster-head-svc lastUpdateTime: "2026-06-05T09:39:01Z" maxWorkerReplicas: 1 minWorkerReplicas: 1 observedGeneration: 1 readyWorkerReplicas: 1 state: ready stateTransitionTimes: ready: "2026-06-05T09:39:01Z" rayJobInfo: endTime: "2026-06-05T09:49:55Z" startTime: "2026-06-05T09:49:52Z" startTime: "2026-06-05T09:49:43Z" succeeded: 1 - apiVersion: ray.io/v1 kind: RayJob metadata: creationTimestamp: "2026-06-05T09:50:03Z" finalizers: - ray.io/rayjob-finalizer generation: 2 name: fail namespace: test-ns-rfwvh resourceVersion: "24114" uid: 1e08e96a-8ea6-407d-944d-388d1540c85b spec: backoffLimit: 0 clusterSelector: ray.io/cluster: raycluster entrypoint: python /home/ray/jobs/fail.py submissionMode: K8sJobMode submitterPodTemplate: metadata: {} spec: containers: - image: quay.io/modh/ray@sha256:42fbc5d898cb9c7d202ee89308ef328838d42985ec384f2476d8f3356acd01cb name: ray-job-submitter resources: limits: cpu: 500m memory: 500Mi requests: cpu: 200m memory: 200Mi restartPolicy: Never ttlSecondsAfterFinished: 0 status: dashboardURL: raycluster-head-svc.test-ns-rfwvh.svc.cluster.local:8265 failed: 0 jobDeploymentStatus: Running jobId: fail-vfl6r jobStatus: FAILED message: "Job entrypoint command failed with exit code 1, last available logs (truncated to 20,000 chars):\n2026-06-05 09:50:09,781\tINFO job_manager.py:587 -- Runtime env is setting up.\nRunning entrypoint for job fail-vfl6r: python /home/ray/jobs/fail.py\nSomething is seriously wrong.\n" rayClusterName: raycluster rayClusterStatus: availableWorkerReplicas: 1 conditions: - lastTransitionTime: "2026-06-05T09:38:59Z" message: "" reason: HeadPodRunningAndReady status: "True" type: HeadPodReady - lastTransitionTime: "2026-06-05T09:39:01Z" message: All Ray Pods are ready for the first time reason: AllPodRunningAndReadyFirstTime status: "True" type: RayClusterProvisioned - lastTransitionTime: "2026-06-05T09:35:06Z" message: "" reason: RayClusterSuspended status: "False" type: RayClusterSuspended - lastTransitionTime: "2026-06-05T09:35:06Z" message: "" reason: RayClusterSuspending status: "False" type: RayClusterSuspending - lastTransitionTime: "2026-06-05T09:35:06Z" message: 'Authentication resources created successfully (mode: IntegratedOAuth)' observedGeneration: 1 reason: AuthenticationResourcesCreated status: "True" type: AuthenticationReady desiredCPU: "1" desiredGPU: "0" desiredMemory: 7G desiredTPU: "0" desiredWorkerReplicas: 1 endpoints: client: "10001" dashboard: "8265" gcs-server: "6379" metrics: "8080" serve: "8000" head: podIP: 10.134.0.20 podName: raycluster-head-vjd7d serviceIP: 10.134.0.20 serviceName: raycluster-head-svc lastUpdateTime: "2026-06-05T09:39:01Z" maxWorkerReplicas: 1 minWorkerReplicas: 1 observedGeneration: 1 readyWorkerReplicas: 1 state: ready stateTransitionTimes: ready: "2026-06-05T09:39:01Z" rayJobInfo: endTime: "2026-06-05T09:50:11Z" startTime: "2026-06-05T09:50:09Z" startTime: "2026-06-05T09:50:03Z" succeeded: 0 - apiVersion: ray.io/v1 kind: RayJob metadata: creationTimestamp: "2026-06-05T09:49:40Z" generation: 1 name: managed-externally namespace: test-ns-rfwvh resourceVersion: "23361" uid: b141048b-5248-45ab-9fe8-3c1fbc205fa6 spec: backoffLimit: 0 clusterSelector: ray.io/cluster: raycluster entrypoint: python /home/ray/jobs/counter.py managedBy: kueue.x-k8s.io/multikueue runtimeEnvYAML: |2 env_vars: counter_name: test_counter submissionMode: K8sJobMode submitterPodTemplate: spec: containers: - image: quay.io/modh/ray@sha256:42fbc5d898cb9c7d202ee89308ef328838d42985ec384f2476d8f3356acd01cb name: ray-job-submitter resources: limits: cpu: 500m memory: 500Mi requests: cpu: 200m memory: 200Mi restartPolicy: Never ttlSecondsAfterFinished: 0 kind: List metadata: resourceVersion: ""