<?xml version='1.0' encoding='utf-8'?>
<testsuites tests="41" failures="1" errors="0" skipped="4" time="3980.816"><testsuite name="Kubeflow Trainer E2E Suite" package="/workspace/source/src_code/test/e2e" tests="16" disabled="2" skipped="4" errors="0" failures="1" time="551.826" timestamp="2026-10-30T15:07:37">
          <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="1793372790" />
              <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="0.001170674">
              <system-err>&gt; Enter [BeforeSuite] TOP-LEVEL - /workspace/source/src_code/test/e2e/suite_test.go:43 @ 10/30/26 15:07:37.16
&lt; Exit [BeforeSuite] TOP-LEVEL - /workspace/source/src_code/test/e2e/suite_test.go:43 @ 10/30/26 15:07:37.161 (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="301.168625404">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 15:07:37.161
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 15:07:37.33 (169ms)
&gt; Enter [It] should create TrainJob with PyTorch runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:84 @ 10/30/26 15:07:37.33
STEP: Create a TrainJob with torch-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:93 @ 10/30/26 15:07:37.331
END STEP: Create a TrainJob with torch-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:93 @ 10/30/26 15:07:37.486 (156ms)
STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:98 @ 10/30/26 15:07:37.486
END STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:98 @ 10/30/26 15:07:38.134 (648ms)
STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:116 @ 10/30/26 15:07:38.134
END STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:116 @ 10/30/26 15:12:38.31 (5m0.176s)
&lt; Exit [It] should create TrainJob with PyTorch runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:84 @ 10/30/26 15:12:38.31 (5m0.979s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 15:12:38.31
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 15:12:38.33 (20ms)
</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="0.064587443">
              <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 @ 10/30/26 15:12:38.33
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 15:12:38.368 (38ms)
&gt; Enter [It] should create TrainJob with DeepSpeed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:145 @ 10/30/26 15:12:38.368
[SKIPPED] MPI runtime image is not available
In [It] at: /workspace/source/src_code/test/e2e/e2e_test.go:147 @ 10/30/26 15:12:38.368
&lt; Exit [It] should create TrainJob with DeepSpeed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:145 @ 10/30/26 15:12:38.368 (0s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 15:12:38.368
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 15:12:38.395 (27ms)
</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="0.195924287">
              <failure message="Expected success, but got an error:&#10;    &lt;*errors.StatusError | 0x2932818faaa0&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 | 0x2932818faaa0&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 @ 10/30/26 15:12:38.571
</failure>
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 15:12:38.395
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 15:12:38.431 (36ms)
&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 @ 10/30/26 15:12:38.431
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 @ 10/30/26 15:12:38.431
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 @ 10/30/26 15:12:38.571 (140ms)
[FAILED] Expected success, but got an error:
    &lt;*errors.StatusError | 0x2932818faaa0&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 @ 10/30/26 15:12:38.571
&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 @ 10/30/26 15:12:38.571 (140ms)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 15:12:38.572
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 15:12:38.591 (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="146.490418835">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 15:12:38.591
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 15:12:38.63 (39ms)
&gt; Enter [It] should create TrainJob with JAX runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:259 @ 10/30/26 15:12:38.63
STEP: Create a TrainJob with jax-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:265 @ 10/30/26 15:12:38.63
END STEP: Create a TrainJob with jax-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:265 @ 10/30/26 15:12:38.681 (51ms)
STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:270 @ 10/30/26 15:12:38.681
END STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:270 @ 10/30/26 15:12:39.235 (554ms)
STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:288 @ 10/30/26 15:12:39.235
END STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:288 @ 10/30/26 15:15:05.062 (2m25.827s)
&lt; Exit [It] should create TrainJob with JAX runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:259 @ 10/30/26 15:15:05.062 (2m26.432s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 15:15:05.062
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 15:15:05.081 (20ms)
</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="46.234376066">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 15:15:05.081
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 15:15:05.121 (40ms)
&gt; Enter [It] should create TrainJob with XGBoost runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:317 @ 10/30/26 15:15:05.121
STEP: Create a TrainJob with xgboost-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:323 @ 10/30/26 15:15:05.121
END STEP: Create a TrainJob with xgboost-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:323 @ 10/30/26 15:15:05.263 (141ms)
STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:328 @ 10/30/26 15:15:05.263
END STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:328 @ 10/30/26 15:15:05.818 (556ms)
STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:346 @ 10/30/26 15:15:05.819
END STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:346 @ 10/30/26 15:15:51.296 (45.477s)
&lt; Exit [It] should create TrainJob with XGBoost runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:317 @ 10/30/26 15:15:51.296 (46.175s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 15:15:51.296
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 15:15:51.316 (20ms)
</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="28.644166039">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 15:15:51.316
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 15:15:51.358 (42ms)
&gt; Enter [It] should create TrainJob with Flux runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:374 @ 10/30/26 15:15:51.358
STEP: Create a TrainJob with flux-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:393 @ 10/30/26 15:15:51.358
END STEP: Create a TrainJob with flux-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:393 @ 10/30/26 15:15:51.41 (53ms)
STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:397 @ 10/30/26 15:15:51.41
END STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:397 @ 10/30/26 15:15:51.984 (574ms)
STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:414 @ 10/30/26 15:15:51.984
END STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:414 @ 10/30/26 15:16:19.938 (27.954s)
&lt; Exit [It] should create TrainJob with Flux runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:374 @ 10/30/26 15:16:19.938 (28.58s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 15:16:19.938
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 15:16:19.96 (22ms)
</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="0.132107709">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 15:16:19.961
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 15:16:20.001 (41ms)
&gt; Enter [It] should preserve user-provided manager fields - /workspace/source/src_code/test/e2e/e2e_test.go:442 @ 10/30/26 15:16:20.001
STEP: Create a TrainJob with RuntimePatches - /workspace/source/src_code/test/e2e/e2e_test.go:494 @ 10/30/26 15:16:20.001
END STEP: Create a TrainJob with RuntimePatches - /workspace/source/src_code/test/e2e/e2e_test.go:494 @ 10/30/26 15:16:20.055 (54ms)
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 @ 10/30/26 15:16:20.055
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 @ 10/30/26 15:16:20.073 (18ms)
&lt; Exit [It] should preserve user-provided manager fields - /workspace/source/src_code/test/e2e/e2e_test.go:442 @ 10/30/26 15:16:20.073 (72ms)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 15:16:20.073
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 15:16:20.093 (20ms)
</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="1.2251387679999999">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 15:16:20.093
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 15:16:20.132 (39ms)
&gt; Enter [It] should update Time only for the changed patch on update - /workspace/source/src_code/test/e2e/e2e_test.go:512 @ 10/30/26 15:16:20.132
STEP: Create a suspended TrainJob with two RuntimePatches - /workspace/source/src_code/test/e2e/e2e_test.go:566 @ 10/30/26 15:16:20.132
END STEP: Create a suspended TrainJob with two RuntimePatches - /workspace/source/src_code/test/e2e/e2e_test.go:566 @ 10/30/26 15:16:20.184 (52ms)
STEP: Record the original Time values and verify user-provided Time is preserved - /workspace/source/src_code/test/e2e/e2e_test.go:571 @ 10/30/26 15:16:20.184
END STEP: Record the original Time values and verify user-provided Time is preserved - /workspace/source/src_code/test/e2e/e2e_test.go:571 @ 10/30/26 15:16:20.202 (17ms)
STEP: Update the second RuntimePatch and add two new patches - /workspace/source/src_code/test/e2e/e2e_test.go:588 @ 10/30/26 15:16:21.202
END STEP: Update the second RuntimePatch and add two new patches - /workspace/source/src_code/test/e2e/e2e_test.go:588 @ 10/30/26 15:16:21.278 (76ms)
STEP: Verify Time behaviour for all patches after update - /workspace/source/src_code/test/e2e/e2e_test.go:607 @ 10/30/26 15:16:21.278
END STEP: Verify Time behaviour for all patches after update - /workspace/source/src_code/test/e2e/e2e_test.go:607 @ 10/30/26 15:16:21.296 (18ms)
&lt; Exit [It] should update Time only for the changed patch on update - /workspace/source/src_code/test/e2e/e2e_test.go:512 @ 10/30/26 15:16:21.296 (1.164s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 15:16:21.296
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 15:16:21.318 (22ms)
</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="15.120688869">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 15:16:21.318
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 15:16:21.37 (52ms)
&gt; Enter [It] should not be reconciled by the built-in controller - /workspace/source/src_code/test/e2e/e2e_test.go:629 @ 10/30/26 15:16:21.37
STEP: Create a TrainJob managed by MultiKueue - /workspace/source/src_code/test/e2e/e2e_test.go:636 @ 10/30/26 15:16:21.37
END STEP: Create a TrainJob managed by MultiKueue - /workspace/source/src_code/test/e2e/e2e_test.go:636 @ 10/30/26 15:16:21.418 (48ms)
STEP: Ensuring the built-in controller neither creates a JobSet nor sets any status - /workspace/source/src_code/test/e2e/e2e_test.go:640 @ 10/30/26 15:16:21.418
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 @ 10/30/26 15:16:36.419 (15s)
&lt; Exit [It] should not be reconciled by the built-in controller - /workspace/source/src_code/test/e2e/e2e_test.go:629 @ 10/30/26 15:16:36.419 (15.049s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 15:16:36.419
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 15:16:36.439 (20ms)
</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="9.820896432">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 15:16:36.439
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 15:16:36.479 (40ms)
&gt; Enter [It] should fail the TrainJob with DeadlineExceeded when active timeout expires - /workspace/source/src_code/test/e2e/e2e_test.go:652 @ 10/30/26 15:16:36.479
STEP: Waiting for TrainJob to fail due to deadline - /workspace/source/src_code/test/e2e/e2e_test.go:667 @ 10/30/26 15:16:36.528
STEP: Ensuring the underlying JobSet is deleted - /workspace/source/src_code/test/e2e/e2e_test.go:674 @ 10/30/26 15:16:46.219
&lt; Exit [It] should fail the TrainJob with DeadlineExceeded when active timeout expires - /workspace/source/src_code/test/e2e/e2e_test.go:652 @ 10/30/26 15:16:46.238 (9.759s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 15:16:46.238
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 15:16:46.26 (22ms)
</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="1.345986659">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 15:16:46.26
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 15:16:46.301 (41ms)
&gt; Enter [It] TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:905 @ 10/30/26 15:16:46.301
STEP: Creating a TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:797 @ 10/30/26 15:16:46.301
END STEP: Creating a TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:797 @ 10/30/26 15:16:46.39 (89ms)
STEP: Creating a TrainJob that references the TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:810 @ 10/30/26 15:16:46.39
END STEP: Creating a TrainJob that references the TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:810 @ 10/30/26 15:16:46.444 (54ms)
STEP: Waiting for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:814 @ 10/30/26 15:16:46.444
END STEP: Waiting for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:814 @ 10/30/26 15:16:46.731 (286ms)
STEP: Pausing the TrainJob - /workspace/source/src_code/test/e2e/e2e_test.go:825 @ 10/30/26 15:16:46.731
END STEP: Pausing the TrainJob - /workspace/source/src_code/test/e2e/e2e_test.go:825 @ 10/30/26 15:16:46.806 (75ms)
STEP: Waiting for TrainJob to be suspended - /workspace/source/src_code/test/e2e/e2e_test.go:834 @ 10/30/26 15:16:46.806
END STEP: Waiting for TrainJob to be suspended - /workspace/source/src_code/test/e2e/e2e_test.go:834 @ 10/30/26 15:16:47.092 (286ms)
STEP: Updating the runtime with a new container image - /workspace/source/src_code/test/e2e/e2e_test.go:847 @ 10/30/26 15:16:47.092
END STEP: Updating the runtime with a new container image - /workspace/source/src_code/test/e2e/e2e_test.go:847 @ 10/30/26 15:16:47.147 (55ms)
STEP: Restarting the TrainJob by unpausing it - /workspace/source/src_code/test/e2e/e2e_test.go:868 @ 10/30/26 15:16:47.147
END STEP: Restarting the TrainJob by unpausing it - /workspace/source/src_code/test/e2e/e2e_test.go:868 @ 10/30/26 15:16:47.222 (75ms)
STEP: Verifying the TrainJob jobs become active after resuming - /workspace/source/src_code/test/e2e/e2e_test.go:879 @ 10/30/26 15:16:47.222
END STEP: Verifying the TrainJob jobs become active after resuming - /workspace/source/src_code/test/e2e/e2e_test.go:879 @ 10/30/26 15:16:47.51 (288ms)
STEP: Verifying the Runtime snapshot is garbage collected - /workspace/source/src_code/test/e2e/e2e_test.go:891 @ 10/30/26 15:16:47.51
END STEP: Verifying the Runtime snapshot is garbage collected - /workspace/source/src_code/test/e2e/e2e_test.go:891 @ 10/30/26 15:16:47.565 (55ms)
&lt; Exit [It] TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:905 @ 10/30/26 15:16:47.565 (1.264s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 15:16:47.565
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 15:16:47.586 (21ms)
&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 @ 10/30/26 15:16:47.586
&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 @ 10/30/26 15:16:47.606 (20ms)
</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="1.382065872">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 15:16:47.606
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 15:16:47.652 (47ms)
&gt; Enter [It] ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:917 @ 10/30/26 15:16:47.652
STEP: Creating a ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:797 @ 10/30/26 15:16:47.653
END STEP: Creating a ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:797 @ 10/30/26 15:16:47.746 (94ms)
STEP: Creating a TrainJob that references the ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:810 @ 10/30/26 15:16:47.747
END STEP: Creating a TrainJob that references the ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:810 @ 10/30/26 15:16:47.804 (57ms)
STEP: Waiting for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:814 @ 10/30/26 15:16:47.804
END STEP: Waiting for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:814 @ 10/30/26 15:16:48.091 (288ms)
STEP: Pausing the TrainJob - /workspace/source/src_code/test/e2e/e2e_test.go:825 @ 10/30/26 15:16:48.092
END STEP: Pausing the TrainJob - /workspace/source/src_code/test/e2e/e2e_test.go:825 @ 10/30/26 15:16:48.167 (75ms)
STEP: Waiting for TrainJob to be suspended - /workspace/source/src_code/test/e2e/e2e_test.go:834 @ 10/30/26 15:16:48.167
END STEP: Waiting for TrainJob to be suspended - /workspace/source/src_code/test/e2e/e2e_test.go:834 @ 10/30/26 15:16:48.453 (286ms)
STEP: Updating the runtime with a new container image - /workspace/source/src_code/test/e2e/e2e_test.go:847 @ 10/30/26 15:16:48.453
END STEP: Updating the runtime with a new container image - /workspace/source/src_code/test/e2e/e2e_test.go:847 @ 10/30/26 15:16:48.511 (58ms)
STEP: Restarting the TrainJob by unpausing it - /workspace/source/src_code/test/e2e/e2e_test.go:868 @ 10/30/26 15:16:48.511
END STEP: Restarting the TrainJob by unpausing it - /workspace/source/src_code/test/e2e/e2e_test.go:868 @ 10/30/26 15:16:48.581 (70ms)
STEP: Verifying the TrainJob jobs become active after resuming - /workspace/source/src_code/test/e2e/e2e_test.go:879 @ 10/30/26 15:16:48.581
END STEP: Verifying the TrainJob jobs become active after resuming - /workspace/source/src_code/test/e2e/e2e_test.go:879 @ 10/30/26 15:16:48.878 (297ms)
STEP: Verifying the Runtime snapshot is garbage collected - /workspace/source/src_code/test/e2e/e2e_test.go:891 @ 10/30/26 15:16:48.878
END STEP: Verifying the Runtime snapshot is garbage collected - /workspace/source/src_code/test/e2e/e2e_test.go:891 @ 10/30/26 15:16:48.937 (59ms)
&lt; Exit [It] ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:917 @ 10/30/26 15:16:48.937 (1.285s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 15:16:48.937
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 15:16:48.965 (28ms)
&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 @ 10/30/26 15:16:48.965
&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 @ 10/30/26 15:16:48.988 (23ms)
</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="1793372790" />
              <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="1.49" name="trainer" timestamp="2026-10-30T15:18:18Z" 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="0.040000" />
		<testcase classname="tests/trainer" name="TestDefaultTrainingHubRuntimesMatchDefaultClusterRuntimes" time="0.030000" />
		<testcase classname="tests/trainer" name="TestDraFieldsOnTrainJobReachPods" time="1.420000" />
	</testsuite>
<testsuite tests="7" failures="0" time="820.53" name="trainer" timestamp="2026-10-30T15:18:24Z" 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="TestRunTrainJobWithDefaultClusterTrainingRuntimes" time="468.800000" />
		<testcase classname="tests/trainer" name="TestJobSetWorkflow" time="102.040000" />
		<testcase classname="tests/trainer" name="TestKubeflowSdk" time="53.150000" />
		<testcase classname="tests/trainer" name="TestKubeflowSdkKueueIntegration" time="52.490000" />
		<testcase classname="tests/trainer" name="TestKueueWorkloadPreemptionSuspendsTrainJob" time="3.580000" />
		<testcase classname="tests/trainer" name="TestKueueSchedulingReachesTrainJobPods" time="1.470000" />
		<testcase classname="tests/trainer" name="TestMultiNodeOpenMPICpuTrainJob" time="139.000000" />
	</testsuite>
<testsuite tests="15" failures="0" time="2606.97" name="trainer" timestamp="2026-10-30T15:32:18Z" 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="TestFailedJobSetWorkflow" time="13.670000" />
		<testcase classname="tests/trainer" name="TestRhaiTrainingProgressionCPU" time="535.600000" />
		<testcase classname="tests/trainer" name="TestRhaiJitCheckpointingCPU" time="619.010000" />
		<testcase classname="tests/trainer" name="TestRhaiFeaturesCPU" time="625.030000" />
		<testcase classname="tests/trainer" name="TestRhaiS3CheckpointingCPU" time="620.550000" />
		<testcase classname="tests/trainer" name="TestPyTorchDDPMultiNodeMultiCPUWithTorchCuda28" time="134.150000" />
		<testcase classname="tests/trainer" name="TestKueueWorkloadInadmissibleWithNonExistentLocalQueue" time="1.390000" />
		<testcase classname="tests/trainer" name="TestTrainerSecureServing" time="0.700000" />
		<testcase classname="tests/trainer" name="TestTrainerPrometheusScrape" time="0.380000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherNamespacesToMetrics" time="10.400000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherNamespacesToHealth" time="8.380000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherNamespacesToStatusServer" time="6.350000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherNamespacesToUnpublishedPort" time="8.310000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherNamespacesToWorkloadPort" time="11.590000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherWorkloadsToWorkloadPort" time="11.460000" />
	</testsuite>
<testsuite tests="0" failures="0" time="0" name="trainer" timestamp="2026-10-30T16:15:48Z" errors="0" skipped="0">
		<properties>
			<property name="go.version" value="go1.26.7 (Red Hat 1.26.7-1.el9_8) linux/amd64" />
		</properties>
	</testsuite>
</testsuites>