<?xml version='1.0' encoding='utf-8'?>
<testsuites tests="26" failures="2" errors="0" skipped="4" time="1376.298"><testsuite name="Kubeflow Trainer E2E Suite" package="/workspace/source/src_code/test/e2e" tests="16" disabled="2" skipped="4" errors="0" failures="1" time="518.898" timestamp="2026-11-02T12:10:53">
          <properties>
              <property name="SuiteSucceeded" value="false" />
              <property name="SuiteHasProgrammaticFocus" value="false" />
              <property name="SpecialSuiteFailureReason" value="" />
              <property name="SuiteLabels" value="[]" />
              <property name="SuiteSemVerConstraints" value="[]" />
              <property name="SuiteComponentSemVerConstraints" value="[]" />
              <property name="RandomSeed" value="1793621302" />
              <property name="RandomizeAllSpecs" value="false" />
              <property name="LabelFilter" value="" />
              <property name="SemVerFilter" value="" />
              <property name="FocusStrings" value="" />
              <property name="SkipStrings" value="runtime status server instrumentation" />
              <property name="FocusFiles" value="" />
              <property name="SkipFiles" value="" />
              <property name="FailOnPending" value="false" />
              <property name="FailOnEmpty" value="false" />
              <property name="FailFast" value="false" />
              <property name="FlakeAttempts" value="0" />
              <property name="DryRun" value="false" />
              <property name="ParallelTotal" value="1" />
              <property name="OutputInterceptorMode" value="" />
          </properties>
          <testcase name="[BeforeSuite]" classname="Kubeflow Trainer E2E Suite" status="passed" time="0.001301043">
              <system-err>&gt; Enter [BeforeSuite] TOP-LEVEL - /workspace/source/src_code/test/e2e/suite_test.go:43 @ 11/02/26 12:10:53.387
&lt; Exit [BeforeSuite] TOP-LEVEL - /workspace/source/src_code/test/e2e/suite_test.go:43 @ 11/02/26 12:10:53.388 (1ms)
</system-err>
          </testcase>
          <testcase name="[It] OptimizationJob e2e when Creating OptimizationJob with random search algorithm should provision algorithm service, run trials to completion, record best result, and perform cleanup" classname="Kubeflow Trainer E2E Suite" status="pending" time="0">
              <skipped message="pending" />
          </testcase>
          <testcase name="[It] OptimizationJob e2e when Creating OptimizationJob with random search algorithm should fail if unsupported search algorithm is configured" classname="Kubeflow Trainer E2E Suite" status="pending" time="0">
              <skipped message="pending" />
          </testcase>
          <testcase name="[It] TrainJob e2e when Creating TrainJob to perform the PyTorch workload should create TrainJob with PyTorch runtime reference" classname="Kubeflow Trainer E2E Suite" status="passed" time="256.509790858">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 12:10:53.388
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 12:10:53.546 (157ms)
&gt; Enter [It] should create TrainJob with PyTorch runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:84 @ 11/02/26 12:10:53.546
STEP: Create a TrainJob with torch-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:93 @ 11/02/26 12:10:53.546
END STEP: Create a TrainJob with torch-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:93 @ 11/02/26 12:10:53.916 (371ms)
STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:98 @ 11/02/26 12:10:53.916
END STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:98 @ 11/02/26 12:10:55.264 (1.348s)
STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:116 @ 11/02/26 12:10:55.264
END STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:116 @ 11/02/26 12:15:09.881 (4m14.617s)
&lt; Exit [It] should create TrainJob with PyTorch runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:84 @ 11/02/26 12:15:09.881 (4m16.335s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 12:15:09.881
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 12:15:09.898 (17ms)
</system-err>
          </testcase>
          <testcase name="[It] TrainJob e2e when Creating TrainJob to perform DeepSpeed workload should create TrainJob with DeepSpeed runtime reference" classname="Kubeflow Trainer E2E Suite" status="skipped" time="0.054441578">
              <skipped message="skipped - MPI runtime image is not available" />
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 12:15:09.898
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 12:15:09.933 (35ms)
&gt; Enter [It] should create TrainJob with DeepSpeed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:145 @ 11/02/26 12:15:09.933
[SKIPPED] MPI runtime image is not available
In [It] at: /workspace/source/src_code/test/e2e/e2e_test.go:147 @ 11/02/26 12:15:09.933
&lt; Exit [It] should create TrainJob with DeepSpeed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:145 @ 11/02/26 12:15:09.933 (0s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 12:15:09.933
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 12:15:09.953 (19ms)
</system-err>
          </testcase>
          <testcase name="[It] TrainJob e2e when Creating TrainJob to perform OpenMPI 4.0 workload should create TrainJob with DeepSpeed runtime reference and OpenMPI 4.0 image" classname="Kubeflow Trainer E2E Suite" status="failed" time="0.400473801">
              <failure message="Expected success, but got an error:&#10;    &lt;*errors.StatusError | 0x301a52ee6000&gt;: &#10;    admission webhook &quot;validator.trainjob.trainer.kubeflow.org&quot; denied the request: spec.runtimeRef: Invalid value: {&quot;name&quot;:&quot;deepspeed-distributed&quot;,&quot;apiGroup&quot;:&quot;trainer.kubeflow.org&quot;,&quot;kind&quot;:&quot;ClusterTrainingRuntime&quot;}: ClusterTrainingRuntime.trainer.kubeflow.org &quot;deepspeed-distributed&quot; not found: specified clusterTrainingRuntime must be created before the TrainJob is created&#10;    {&#10;        ErrStatus: {&#10;            TypeMeta: {Kind: &quot;&quot;, APIVersion: &quot;&quot;},&#10;            ListMeta: {&#10;                SelfLink: &quot;&quot;,&#10;                ResourceVersion: &quot;&quot;,&#10;                Continue: &quot;&quot;,&#10;                RemainingItemCount: nil,&#10;                ShardInfo: nil,&#10;            },&#10;            Status: &quot;Failure&quot;,&#10;            Message: &quot;admission webhook \&quot;validator.trainjob.trainer.kubeflow.org\&quot; denied the request: spec.runtimeRef: Invalid value: {\&quot;name\&quot;:\&quot;deepspeed-distributed\&quot;,\&quot;apiGroup\&quot;:\&quot;trainer.kubeflow.org\&quot;,\&quot;kind\&quot;:\&quot;ClusterTrainingRuntime\&quot;}: ClusterTrainingRuntime.trainer.kubeflow.org \&quot;deepspeed-distributed\&quot; not found: specified clusterTrainingRuntime must be created before the TrainJob is created&quot;,&#10;            Reason: &quot;Forbidden&quot;,&#10;            Details: nil,&#10;            Code: 403,&#10;        },&#10;    }" type="failed">[FAILED] Expected success, but got an error:
    &lt;*errors.StatusError | 0x301a52ee6000&gt;: 
    admission webhook "validator.trainjob.trainer.kubeflow.org" denied the request: spec.runtimeRef: Invalid value: {"name":"deepspeed-distributed","apiGroup":"trainer.kubeflow.org","kind":"ClusterTrainingRuntime"}: ClusterTrainingRuntime.trainer.kubeflow.org "deepspeed-distributed" not found: specified clusterTrainingRuntime must be created before the TrainJob is created
    {
        ErrStatus: {
            TypeMeta: {Kind: "", APIVersion: ""},
            ListMeta: {
                SelfLink: "",
                ResourceVersion: "",
                Continue: "",
                RemainingItemCount: nil,
                ShardInfo: nil,
            },
            Status: "Failure",
            Message: "admission webhook \"validator.trainjob.trainer.kubeflow.org\" denied the request: spec.runtimeRef: Invalid value: {\"name\":\"deepspeed-distributed\",\"apiGroup\":\"trainer.kubeflow.org\",\"kind\":\"ClusterTrainingRuntime\"}: ClusterTrainingRuntime.trainer.kubeflow.org \"deepspeed-distributed\" not found: specified clusterTrainingRuntime must be created before the TrainJob is created",
            Reason: "Forbidden",
            Details: nil,
            Code: 403,
        },
    }
In [It] at: /workspace/source/src_code/test/e2e/e2e_test.go:216 @ 11/02/26 12:15:10.334
</failure>
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 12:15:09.953
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 12:15:09.988 (35ms)
&gt; Enter [It] should create TrainJob with DeepSpeed runtime reference and OpenMPI 4.0 image - /workspace/source/src_code/test/e2e/e2e_test.go:203 @ 11/02/26 12:15:09.988
STEP: Create a TrainJob with deepspeed-distributed runtime reference and the OpenMPI 4.0 image - /workspace/source/src_code/test/e2e/e2e_test.go:215 @ 11/02/26 12:15:09.988
END STEP: Create a TrainJob with deepspeed-distributed runtime reference and the OpenMPI 4.0 image - /workspace/source/src_code/test/e2e/e2e_test.go:215 @ 11/02/26 12:15:10.334 (346ms)
[FAILED] Expected success, but got an error:
    &lt;*errors.StatusError | 0x301a52ee6000&gt;: 
    admission webhook "validator.trainjob.trainer.kubeflow.org" denied the request: spec.runtimeRef: Invalid value: {"name":"deepspeed-distributed","apiGroup":"trainer.kubeflow.org","kind":"ClusterTrainingRuntime"}: ClusterTrainingRuntime.trainer.kubeflow.org "deepspeed-distributed" not found: specified clusterTrainingRuntime must be created before the TrainJob is created
    {
        ErrStatus: {
            TypeMeta: {Kind: "", APIVersion: ""},
            ListMeta: {
                SelfLink: "",
                ResourceVersion: "",
                Continue: "",
                RemainingItemCount: nil,
                ShardInfo: nil,
            },
            Status: "Failure",
            Message: "admission webhook \"validator.trainjob.trainer.kubeflow.org\" denied the request: spec.runtimeRef: Invalid value: {\"name\":\"deepspeed-distributed\",\"apiGroup\":\"trainer.kubeflow.org\",\"kind\":\"ClusterTrainingRuntime\"}: ClusterTrainingRuntime.trainer.kubeflow.org \"deepspeed-distributed\" not found: specified clusterTrainingRuntime must be created before the TrainJob is created",
            Reason: "Forbidden",
            Details: nil,
            Code: 403,
        },
    }
In [It] at: /workspace/source/src_code/test/e2e/e2e_test.go:216 @ 11/02/26 12:15:10.334
&lt; Exit [It] should create TrainJob with DeepSpeed runtime reference and OpenMPI 4.0 image - /workspace/source/src_code/test/e2e/e2e_test.go:203 @ 11/02/26 12:15:10.334 (347ms)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 12:15:10.334
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 12:15:10.354 (19ms)
</system-err>
          </testcase>
          <testcase name="[It] TrainJob e2e when Creating TrainJob to perform JAX workload should create TrainJob with JAX runtime reference" classname="Kubeflow Trainer E2E Suite" status="passed" time="132.327759517">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 12:15:10.354
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 12:15:10.387 (33ms)
&gt; Enter [It] should create TrainJob with JAX runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:259 @ 11/02/26 12:15:10.387
STEP: Create a TrainJob with jax-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:265 @ 11/02/26 12:15:10.387
END STEP: Create a TrainJob with jax-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:265 @ 11/02/26 12:15:10.508 (122ms)
STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:270 @ 11/02/26 12:15:10.508
END STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:270 @ 11/02/26 12:15:11.857 (1.349s)
STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:288 @ 11/02/26 12:15:11.857
END STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:288 @ 11/02/26 12:17:22.664 (2m10.807s)
&lt; Exit [It] should create TrainJob with JAX runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:259 @ 11/02/26 12:17:22.664 (2m12.277s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 12:17:22.664
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 12:17:22.681 (17ms)
</system-err>
          </testcase>
          <testcase name="[It] TrainJob e2e when Creating TrainJob to perform XGBoost workload should create TrainJob with XGBoost runtime reference" classname="Kubeflow Trainer E2E Suite" status="passed" time="67.298031242">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 12:17:22.682
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 12:17:22.715 (33ms)
&gt; Enter [It] should create TrainJob with XGBoost runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:317 @ 11/02/26 12:17:22.715
STEP: Create a TrainJob with xgboost-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:323 @ 11/02/26 12:17:22.715
END STEP: Create a TrainJob with xgboost-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:323 @ 11/02/26 12:17:23.063 (348ms)
STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:328 @ 11/02/26 12:17:23.063
END STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:328 @ 11/02/26 12:17:24.414 (1.35s)
STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:346 @ 11/02/26 12:17:24.414
END STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:346 @ 11/02/26 12:18:29.96 (1m5.547s)
&lt; Exit [It] should create TrainJob with XGBoost runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:317 @ 11/02/26 12:18:29.96 (1m7.245s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 12:18:29.96
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 12:18:29.98 (19ms)
</system-err>
          </testcase>
          <testcase name="[It] TrainJob e2e when Creating TrainJob to perform Flux workload should create TrainJob with Flux runtime reference" classname="Kubeflow Trainer E2E Suite" status="passed" time="29.259887884">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 12:18:29.98
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 12:18:30.012 (32ms)
&gt; Enter [It] should create TrainJob with Flux runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:374 @ 11/02/26 12:18:30.012
STEP: Create a TrainJob with flux-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:393 @ 11/02/26 12:18:30.012
END STEP: Create a TrainJob with flux-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:393 @ 11/02/26 12:18:30.135 (122ms)
STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:397 @ 11/02/26 12:18:30.135
END STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:397 @ 11/02/26 12:18:31.215 (1.08s)
STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:414 @ 11/02/26 12:18:31.215
END STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:414 @ 11/02/26 12:18:59.222 (28.008s)
&lt; Exit [It] should create TrainJob with Flux runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:374 @ 11/02/26 12:18:59.222 (29.21s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 12:18:59.222
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 12:18:59.24 (18ms)
</system-err>
          </testcase>
          <testcase name="[It] TrainJob e2e when Creating a TrainJob with RuntimePatches should preserve user-provided manager fields" classname="Kubeflow Trainer E2E Suite" status="passed" time="0.20218996">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 12:18:59.241
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 12:18:59.278 (37ms)
&gt; Enter [It] should preserve user-provided manager fields - /workspace/source/src_code/test/e2e/e2e_test.go:442 @ 11/02/26 12:18:59.278
STEP: Create a TrainJob with RuntimePatches - /workspace/source/src_code/test/e2e/e2e_test.go:494 @ 11/02/26 12:18:59.278
END STEP: Create a TrainJob with RuntimePatches - /workspace/source/src_code/test/e2e/e2e_test.go:494 @ 11/02/26 12:18:59.408 (131ms)
STEP: Verify user-provided Time is preserved for test.io/manager-one and Time is set for kueue.k8s.io/manager - /workspace/source/src_code/test/e2e/e2e_test.go:498 @ 11/02/26 12:18:59.408
END STEP: Verify user-provided Time is preserved for test.io/manager-one and Time is set for kueue.k8s.io/manager - /workspace/source/src_code/test/e2e/e2e_test.go:498 @ 11/02/26 12:18:59.424 (15ms)
&lt; Exit [It] should preserve user-provided manager fields - /workspace/source/src_code/test/e2e/e2e_test.go:442 @ 11/02/26 12:18:59.424 (146ms)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 12:18:59.424
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 12:18:59.443 (19ms)
</system-err>
          </testcase>
          <testcase name="[It] TrainJob e2e when Creating a TrainJob with RuntimePatches should update Time only for the changed patch on update" classname="Kubeflow Trainer E2E Suite" status="passed" time="1.357917474">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 12:18:59.443
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 12:18:59.477 (33ms)
&gt; Enter [It] should update Time only for the changed patch on update - /workspace/source/src_code/test/e2e/e2e_test.go:512 @ 11/02/26 12:18:59.477
STEP: Create a suspended TrainJob with two RuntimePatches - /workspace/source/src_code/test/e2e/e2e_test.go:566 @ 11/02/26 12:18:59.477
END STEP: Create a suspended TrainJob with two RuntimePatches - /workspace/source/src_code/test/e2e/e2e_test.go:566 @ 11/02/26 12:18:59.605 (128ms)
STEP: Record the original Time values and verify user-provided Time is preserved - /workspace/source/src_code/test/e2e/e2e_test.go:571 @ 11/02/26 12:18:59.605
END STEP: Record the original Time values and verify user-provided Time is preserved - /workspace/source/src_code/test/e2e/e2e_test.go:571 @ 11/02/26 12:18:59.622 (17ms)
STEP: Update the second RuntimePatch and add two new patches - /workspace/source/src_code/test/e2e/e2e_test.go:588 @ 11/02/26 12:19:00.622
END STEP: Update the second RuntimePatch and add two new patches - /workspace/source/src_code/test/e2e/e2e_test.go:588 @ 11/02/26 12:19:00.765 (143ms)
STEP: Verify Time behaviour for all patches after update - /workspace/source/src_code/test/e2e/e2e_test.go:607 @ 11/02/26 12:19:00.765
END STEP: Verify Time behaviour for all patches after update - /workspace/source/src_code/test/e2e/e2e_test.go:607 @ 11/02/26 12:19:00.782 (16ms)
&lt; Exit [It] should update Time only for the changed patch on update - /workspace/source/src_code/test/e2e/e2e_test.go:512 @ 11/02/26 12:19:00.782 (1.305s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 12:19:00.782
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 12:19:00.801 (19ms)
</system-err>
          </testcase>
          <testcase name="[It] TrainJob e2e when Creating a TrainJob managed by an external controller should not be reconciled by the built-in controller" classname="Kubeflow Trainer E2E Suite" status="passed" time="15.180099325">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 12:19:00.801
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 12:19:00.837 (36ms)
&gt; Enter [It] should not be reconciled by the built-in controller - /workspace/source/src_code/test/e2e/e2e_test.go:629 @ 11/02/26 12:19:00.837
STEP: Create a TrainJob managed by MultiKueue - /workspace/source/src_code/test/e2e/e2e_test.go:636 @ 11/02/26 12:19:00.837
END STEP: Create a TrainJob managed by MultiKueue - /workspace/source/src_code/test/e2e/e2e_test.go:636 @ 11/02/26 12:19:00.96 (123ms)
STEP: Ensuring the built-in controller neither creates a JobSet nor sets any status - /workspace/source/src_code/test/e2e/e2e_test.go:640 @ 11/02/26 12:19:00.96
END STEP: Ensuring the built-in controller neither creates a JobSet nor sets any status - /workspace/source/src_code/test/e2e/e2e_test.go:640 @ 11/02/26 12:19:15.96 (15s)
&lt; Exit [It] should not be reconciled by the built-in controller - /workspace/source/src_code/test/e2e/e2e_test.go:629 @ 11/02/26 12:19:15.96 (15.123s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 12:19:15.96
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 12:19:15.981 (21ms)
</system-err>
          </testcase>
          <testcase name="[It] TrainJob e2e when Creating a TrainJob with Resource Timeouts should fail the TrainJob with DeadlineExceeded when active timeout expires" classname="Kubeflow Trainer E2E Suite" status="passed" time="10.356551027">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 12:19:15.982
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 12:19:16.021 (39ms)
&gt; Enter [It] should fail the TrainJob with DeadlineExceeded when active timeout expires - /workspace/source/src_code/test/e2e/e2e_test.go:652 @ 11/02/26 12:19:16.021
STEP: Waiting for TrainJob to fail due to deadline - /workspace/source/src_code/test/e2e/e2e_test.go:667 @ 11/02/26 12:19:16.148
STEP: Ensuring the underlying JobSet is deleted - /workspace/source/src_code/test/e2e/e2e_test.go:674 @ 11/02/26 12:19:26.305
&lt; Exit [It] should fail the TrainJob with DeadlineExceeded when active timeout expires - /workspace/source/src_code/test/e2e/e2e_test.go:652 @ 11/02/26 12:19:26.32 (10.299s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 12:19:26.32
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 12:19:26.338 (18ms)
</system-err>
          </testcase>
          <testcase name="[It] TrainJob e2e when Creating TrainJob with runtime status server instrumentation should inject runtime configuration which allows the runtime status endpoint to be called" classname="Kubeflow Trainer E2E Suite" status="skipped" time="0">
              <skipped message="skipped" />
          </testcase>
          <testcase name="[It] TrainJob e2e when Updating a runtime a suspended TrainJob should use the original runtime configuration and not pick up the new configuration TrainingRuntime" classname="Kubeflow Trainer E2E Suite" status="passed" time="2.9734759">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 12:19:26.338
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 12:19:26.375 (37ms)
&gt; Enter [It] TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:905 @ 11/02/26 12:19:26.375
STEP: Creating a TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:797 @ 11/02/26 12:19:26.375
END STEP: Creating a TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:797 @ 11/02/26 12:19:26.55 (175ms)
STEP: Creating a TrainJob that references the TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:810 @ 11/02/26 12:19:26.55
END STEP: Creating a TrainJob that references the TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:810 @ 11/02/26 12:19:26.675 (125ms)
STEP: Waiting for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:814 @ 11/02/26 12:19:26.675
END STEP: Waiting for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:814 @ 11/02/26 12:19:27.489 (814ms)
STEP: Pausing the TrainJob - /workspace/source/src_code/test/e2e/e2e_test.go:825 @ 11/02/26 12:19:27.489
END STEP: Pausing the TrainJob - /workspace/source/src_code/test/e2e/e2e_test.go:825 @ 11/02/26 12:19:27.63 (140ms)
STEP: Waiting for TrainJob to be suspended - /workspace/source/src_code/test/e2e/e2e_test.go:834 @ 11/02/26 12:19:27.63
END STEP: Waiting for TrainJob to be suspended - /workspace/source/src_code/test/e2e/e2e_test.go:834 @ 11/02/26 12:19:28.179 (549ms)
STEP: Updating the runtime with a new container image - /workspace/source/src_code/test/e2e/e2e_test.go:847 @ 11/02/26 12:19:28.179
END STEP: Updating the runtime with a new container image - /workspace/source/src_code/test/e2e/e2e_test.go:847 @ 11/02/26 12:19:28.266 (88ms)
STEP: Restarting the TrainJob by unpausing it - /workspace/source/src_code/test/e2e/e2e_test.go:868 @ 11/02/26 12:19:28.266
END STEP: Restarting the TrainJob by unpausing it - /workspace/source/src_code/test/e2e/e2e_test.go:868 @ 11/02/26 12:19:28.409 (142ms)
STEP: Verifying the TrainJob jobs become active after resuming - /workspace/source/src_code/test/e2e/e2e_test.go:879 @ 11/02/26 12:19:28.409
END STEP: Verifying the TrainJob jobs become active after resuming - /workspace/source/src_code/test/e2e/e2e_test.go:879 @ 11/02/26 12:19:29.228 (819ms)
STEP: Verifying the Runtime snapshot is garbage collected - /workspace/source/src_code/test/e2e/e2e_test.go:891 @ 11/02/26 12:19:29.228
END STEP: Verifying the Runtime snapshot is garbage collected - /workspace/source/src_code/test/e2e/e2e_test.go:891 @ 11/02/26 12:19:29.276 (48ms)
&lt; Exit [It] TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:905 @ 11/02/26 12:19:29.276 (2.901s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 12:19:29.276
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 12:19:29.294 (18ms)
&gt; Enter [DeferCleanup (Each)] a suspended TrainJob should use the original runtime configuration and not pick up the new configuration - /workspace/source/src_code/test/e2e/e2e_test.go:801 @ 11/02/26 12:19:29.294
&lt; Exit [DeferCleanup (Each)] a suspended TrainJob should use the original runtime configuration and not pick up the new configuration - /workspace/source/src_code/test/e2e/e2e_test.go:801 @ 11/02/26 12:19:29.312 (17ms)
</system-err>
          </testcase>
          <testcase name="[It] TrainJob e2e when Updating a runtime a suspended TrainJob should use the original runtime configuration and not pick up the new configuration ClusterTrainingRuntime" classname="Kubeflow Trainer E2E Suite" status="passed" time="2.976093307">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 12:19:29.312
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 12:19:29.346 (34ms)
&gt; Enter [It] ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:917 @ 11/02/26 12:19:29.346
STEP: Creating a ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:797 @ 11/02/26 12:19:29.346
END STEP: Creating a ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:797 @ 11/02/26 12:19:29.532 (186ms)
STEP: Creating a TrainJob that references the ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:810 @ 11/02/26 12:19:29.532
END STEP: Creating a TrainJob that references the ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:810 @ 11/02/26 12:19:29.655 (123ms)
STEP: Waiting for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:814 @ 11/02/26 12:19:29.655
END STEP: Waiting for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:814 @ 11/02/26 12:19:30.472 (817ms)
STEP: Pausing the TrainJob - /workspace/source/src_code/test/e2e/e2e_test.go:825 @ 11/02/26 12:19:30.473
END STEP: Pausing the TrainJob - /workspace/source/src_code/test/e2e/e2e_test.go:825 @ 11/02/26 12:19:30.615 (142ms)
STEP: Waiting for TrainJob to be suspended - /workspace/source/src_code/test/e2e/e2e_test.go:834 @ 11/02/26 12:19:30.615
END STEP: Waiting for TrainJob to be suspended - /workspace/source/src_code/test/e2e/e2e_test.go:834 @ 11/02/26 12:19:31.163 (549ms)
STEP: Updating the runtime with a new container image - /workspace/source/src_code/test/e2e/e2e_test.go:847 @ 11/02/26 12:19:31.163
END STEP: Updating the runtime with a new container image - /workspace/source/src_code/test/e2e/e2e_test.go:847 @ 11/02/26 12:19:31.25 (87ms)
STEP: Restarting the TrainJob by unpausing it - /workspace/source/src_code/test/e2e/e2e_test.go:868 @ 11/02/26 12:19:31.25
END STEP: Restarting the TrainJob by unpausing it - /workspace/source/src_code/test/e2e/e2e_test.go:868 @ 11/02/26 12:19:31.389 (139ms)
STEP: Verifying the TrainJob jobs become active after resuming - /workspace/source/src_code/test/e2e/e2e_test.go:879 @ 11/02/26 12:19:31.389
END STEP: Verifying the TrainJob jobs become active after resuming - /workspace/source/src_code/test/e2e/e2e_test.go:879 @ 11/02/26 12:19:32.204 (815ms)
STEP: Verifying the Runtime snapshot is garbage collected - /workspace/source/src_code/test/e2e/e2e_test.go:891 @ 11/02/26 12:19:32.204
END STEP: Verifying the Runtime snapshot is garbage collected - /workspace/source/src_code/test/e2e/e2e_test.go:891 @ 11/02/26 12:19:32.253 (49ms)
&lt; Exit [It] ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:917 @ 11/02/26 12:19:32.253 (2.906s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 12:19:32.253
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 12:19:32.27 (18ms)
&gt; Enter [DeferCleanup (Each)] a suspended TrainJob should use the original runtime configuration and not pick up the new configuration - /workspace/source/src_code/test/e2e/e2e_test.go:801 @ 11/02/26 12:19:32.27
&lt; Exit [DeferCleanup (Each)] a suspended TrainJob should use the original runtime configuration and not pick up the new configuration - /workspace/source/src_code/test/e2e/e2e_test.go:801 @ 11/02/26 12:19:32.288 (18ms)
</system-err>
          </testcase>
      </testsuite>
      <testsuite name="" package="/workspace/source/src_code/test/e2e/rhai" tests="0" disabled="0" skipped="0" errors="0" failures="0" time="0" timestamp="0001-01-01T00:00:00">
          <properties>
              <property name="SuiteSucceeded" value="false" />
              <property name="SuiteHasProgrammaticFocus" value="false" />
              <property name="SpecialSuiteFailureReason" value="Suite did not run because prior suites failed and --keep-going is not set" />
              <property name="SuiteLabels" value="[]" />
              <property name="SuiteSemVerConstraints" value="[]" />
              <property name="SuiteComponentSemVerConstraints" value="[]" />
              <property name="RandomSeed" value="1793621302" />
              <property name="RandomizeAllSpecs" value="false" />
              <property name="LabelFilter" value="" />
              <property name="SemVerFilter" value="" />
              <property name="FocusStrings" value="" />
              <property name="SkipStrings" value="runtime status server instrumentation" />
              <property name="FocusFiles" value="" />
              <property name="SkipFiles" value="" />
              <property name="FailOnPending" value="false" />
              <property name="FailOnEmpty" value="false" />
              <property name="FailFast" value="false" />
              <property name="FlakeAttempts" value="0" />
              <property name="DryRun" value="false" />
              <property name="ParallelTotal" value="1" />
              <property name="OutputInterceptorMode" value="" />
          </properties>
      </testsuite>
  <testsuite tests="3" failures="0" time="1.35" name="trainer" timestamp="2026-11-02T12:20:31Z" errors="0" skipped="0">
		<properties>
			<property name="go.version" value="go1.26.7 (Red Hat 1.26.7-1.el9_8) linux/amd64" />
		</properties>
		<testcase classname="tests/trainer" name="TestOpenMPICudaClusterTrainingRuntime" time="0.030000" />
		<testcase classname="tests/trainer" name="TestDefaultTrainingHubRuntimesMatchDefaultClusterRuntimes" time="0.030000" />
		<testcase classname="tests/trainer" name="TestDraFieldsOnTrainJobReachPods" time="1.290000" />
	</testsuite>
<testsuite tests="7" failures="1" time="856.05" name="trainer" timestamp="2026-11-02T12:20:36Z" errors="0" skipped="0">
		<properties>
			<property name="go.version" value="go1.26.7 (Red Hat 1.26.7-1.el9_8) linux/amd64" />
		</properties>
		<testcase classname="tests/trainer" name="TestKueueSchedulingReachesTrainJobPods" time="2.060000">
			<failure message="Failed" type="">=== RUN   TestKueueSchedulingReachesTrainJobPods
    kueue_operator.go:105: SetupKueue: no DataScienceCluster found; using standalone RHBoK
    kueue_operator.go:227: Kueue CR 'cluster' exists
    kueue_operator.go:229: Waiting for Kueue CR to be ready...
    kueue_operator.go:236: Kueue CR is ready
    kueue_operator.go:239: Verifying TrainJob framework is present in Kueue CR...
    kueue_operator.go:243: TrainJob framework is present in Kueue CR
    trainer_kueue_integration_test.go:251: Created Kueue-managed namespace: test-ns-sddzb
    trainer_kueue_integration_test.go:259: Created Kueue ResourceFlavor rf-q65ff successfully
    trainer_kueue_integration_test.go:274: Created Kueue ClusterQueue cq-v85gt successfully
    trainer_kueue_integration_test.go:298: Created Kueue LocalQueue test-ns-sddzb/lq-hbfq8 successfully
    trainer_kueue_integration_test.go:332: Created TrainJob: test-runtimepatches-trainjob-8qzvh
    trainer_kueue_integration_test.go:340: Workload admitted
    trainer_kueue_integration_test.go:351: 
        replicated job "node" should carry the ResourceFlavor's node label
        Expected
            &lt;map[string]string | len:0&gt;: nil
        to have {key: value}
            &lt;map[interface {}]interface {} | len:1&gt;: {
                &lt;string&gt;"kueue-test-flavor": &lt;string&gt;"on",
            }
    test.go:145: Creating output directory in parent directory: /workspace/artifacts-dir
    test.go:160: Output directory has been created at: /workspace/artifacts-dir/TestKueueSchedulingReachesTrainJobPods2749126739
    kueue_operator.go:100: Collecting Kueue diagnostics...
    kueue_operator.go:100: Stored Kueue CR state
    kueue_operator.go:100: DataScienceCluster is not installed; skipping DSC diagnostics
    kueue_operator.go:100: Stored Kueue operator logs for kueue-controller-manager-6df7755674-h2qkk/manager
    kueue_operator.go:100: Stored Kueue operator logs for kueue-controller-manager-6df7755674-ppwhs/manager
--- FAIL: TestKueueSchedulingReachesTrainJobPods (2.06s)
</failure>
		</testcase>
		<testcase classname="tests/trainer" name="TestRunTrainJobWithDefaultClusterTrainingRuntimes" time="432.470000" />
		<testcase classname="tests/trainer" name="TestJobSetWorkflow" time="103.650000" />
		<testcase classname="tests/trainer" name="TestKubeflowSdk" time="171.880000" />
		<testcase classname="tests/trainer" name="TestKubeflowSdkKueueIntegration" time="56.610000" />
		<testcase classname="tests/trainer" name="TestKueueWorkloadPreemptionSuspendsTrainJob" time="5.800000" />
		<testcase classname="tests/trainer" name="TestMultiNodeOpenMPICpuTrainJob" time="83.580000" />
	</testsuite>
</testsuites>