<?xml version='1.0' encoding='utf-8'?>
<testsuites tests="52" failures="0" errors="0" skipped="5" time="4078.149"><testsuite name="Kubeflow Trainer E2E Suite" package="/workspace/source/src_code/test/e2e" tests="16" disabled="2" skipped="5" errors="0" failures="0" time="654.038" timestamp="2026-11-02T22:02:04">
          <properties>
              <property name="SuiteSucceeded" value="true" />
              <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="1793656868" />
              <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="0.001697518">
              <system-err>&gt; Enter [BeforeSuite] TOP-LEVEL - /workspace/source/src_code/test/e2e/suite_test.go:43 @ 11/02/26 22:02:04.438
&lt; Exit [BeforeSuite] TOP-LEVEL - /workspace/source/src_code/test/e2e/suite_test.go:43 @ 11/02/26 22:02:04.44 (2ms)
</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="391.446852582">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:02:04.44
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:02:04.597 (156ms)
&gt; Enter [It] should create TrainJob with PyTorch runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:84 @ 11/02/26 22:02:04.597
STEP: Create a TrainJob with torch-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:93 @ 11/02/26 22:02:04.597
END STEP: Create a TrainJob with torch-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:93 @ 11/02/26 22:02:04.671 (74ms)
STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:98 @ 11/02/26 22:02:04.671
END STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:98 @ 11/02/26 22:02:04.955 (284ms)
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 22:02:04.955
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 22:08:35.868 (6m30.913s)
&lt; Exit [It] should create TrainJob with PyTorch runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:84 @ 11/02/26 22:08:35.868 (6m31.271s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:08:35.868
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:08:35.887 (19ms)
</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="0.068272476">
              <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 22:08:35.888
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:08:35.924 (36ms)
&gt; Enter [It] should create TrainJob with DeepSpeed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:145 @ 11/02/26 22:08:35.924
[SKIPPED] MPI runtime image is not available
In [It] at: /workspace/source/src_code/test/e2e/e2e_test.go:147 @ 11/02/26 22:08:35.924
&lt; Exit [It] should create TrainJob with DeepSpeed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:145 @ 11/02/26 22:08:35.924 (0s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:08:35.924
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:08:35.956 (32ms)
</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="skipped" time="0.069444986">
              <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 22:08:35.956
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:08:36.005 (49ms)
&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 22:08:36.005
[SKIPPED] MPI runtime image is not available
In [It] at: /workspace/source/src_code/test/e2e/e2e_test.go:205 @ 11/02/26 22:08:36.005
&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 22:08:36.005 (0s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:08:36.005
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:08:36.025 (21ms)
</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="153.654943426">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:08:36.026
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:08:36.061 (35ms)
&gt; Enter [It] should create TrainJob with JAX runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:262 @ 11/02/26 22:08:36.061
STEP: Create a TrainJob with jax-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:268 @ 11/02/26 22:08:36.061
END STEP: Create a TrainJob with jax-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:268 @ 11/02/26 22:08:36.132 (71ms)
STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:273 @ 11/02/26 22:08:36.132
END STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:273 @ 11/02/26 22:08:36.414 (283ms)
STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:291 @ 11/02/26 22:08:36.415
END STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:291 @ 11/02/26 22:11:09.646 (2m33.232s)
&lt; Exit [It] should create TrainJob with JAX runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:262 @ 11/02/26 22:11:09.646 (2m33.585s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:11:09.646
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:11:09.681 (34ms)
</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="49.269062399">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:11:09.681
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:11:09.727 (46ms)
&gt; Enter [It] should create TrainJob with XGBoost runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:320 @ 11/02/26 22:11:09.727
STEP: Create a TrainJob with xgboost-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:326 @ 11/02/26 22:11:09.727
END STEP: Create a TrainJob with xgboost-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:326 @ 11/02/26 22:11:09.804 (76ms)
STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:331 @ 11/02/26 22:11:09.804
END STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:331 @ 11/02/26 22:11:10.086 (282ms)
STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:349 @ 11/02/26 22:11:10.086
END STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:349 @ 11/02/26 22:11:58.93 (48.844s)
&lt; Exit [It] should create TrainJob with XGBoost runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:320 @ 11/02/26 22:11:58.93 (49.202s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:11:58.93
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:11:58.95 (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="30.839093729">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:11:58.951
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:11:58.99 (39ms)
&gt; Enter [It] should create TrainJob with Flux runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:377 @ 11/02/26 22:11:58.99
STEP: Create a TrainJob with flux-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:396 @ 11/02/26 22:11:58.99
END STEP: Create a TrainJob with flux-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:396 @ 11/02/26 22:11:59.025 (36ms)
STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:400 @ 11/02/26 22:11:59.025
END STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:400 @ 11/02/26 22:11:59.309 (284ms)
STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:417 @ 11/02/26 22:11:59.309
END STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:417 @ 11/02/26 22:12:29.772 (30.463s)
&lt; Exit [It] should create TrainJob with Flux runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:377 @ 11/02/26 22:12:29.772 (30.782s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:12:29.772
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:12:29.79 (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="0.105359041">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:12:29.79
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:12:29.826 (36ms)
&gt; Enter [It] should preserve user-provided manager fields - /workspace/source/src_code/test/e2e/e2e_test.go:445 @ 11/02/26 22:12:29.826
STEP: Create a TrainJob with RuntimePatches - /workspace/source/src_code/test/e2e/e2e_test.go:497 @ 11/02/26 22:12:29.826
END STEP: Create a TrainJob with RuntimePatches - /workspace/source/src_code/test/e2e/e2e_test.go:497 @ 11/02/26 22:12:29.857 (31ms)
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:501 @ 11/02/26 22:12:29.857
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:501 @ 11/02/26 22:12:29.875 (17ms)
&lt; Exit [It] should preserve user-provided manager fields - /workspace/source/src_code/test/e2e/e2e_test.go:445 @ 11/02/26 22:12:29.875 (49ms)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:12:29.875
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:12:29.896 (21ms)
</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="1.170396701">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:12:29.896
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:12:29.931 (35ms)
&gt; Enter [It] should update Time only for the changed patch on update - /workspace/source/src_code/test/e2e/e2e_test.go:515 @ 11/02/26 22:12:29.931
STEP: Create a suspended TrainJob with two RuntimePatches - /workspace/source/src_code/test/e2e/e2e_test.go:569 @ 11/02/26 22:12:29.931
END STEP: Create a suspended TrainJob with two RuntimePatches - /workspace/source/src_code/test/e2e/e2e_test.go:569 @ 11/02/26 22:12:29.962 (31ms)
STEP: Record the original Time values and verify user-provided Time is preserved - /workspace/source/src_code/test/e2e/e2e_test.go:574 @ 11/02/26 22:12:29.962
END STEP: Record the original Time values and verify user-provided Time is preserved - /workspace/source/src_code/test/e2e/e2e_test.go:574 @ 11/02/26 22:12:29.978 (16ms)
STEP: Update the second RuntimePatch and add two new patches - /workspace/source/src_code/test/e2e/e2e_test.go:591 @ 11/02/26 22:12:30.978
END STEP: Update the second RuntimePatch and add two new patches - /workspace/source/src_code/test/e2e/e2e_test.go:591 @ 11/02/26 22:12:31.03 (52ms)
STEP: Verify Time behaviour for all patches after update - /workspace/source/src_code/test/e2e/e2e_test.go:610 @ 11/02/26 22:12:31.03
END STEP: Verify Time behaviour for all patches after update - /workspace/source/src_code/test/e2e/e2e_test.go:610 @ 11/02/26 22:12:31.048 (18ms)
&lt; Exit [It] should update Time only for the changed patch on update - /workspace/source/src_code/test/e2e/e2e_test.go:515 @ 11/02/26 22:12:31.048 (1.117s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:12:31.048
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:12:31.066 (18ms)
</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="15.087429045">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:12:31.066
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:12:31.103 (37ms)
&gt; Enter [It] should not be reconciled by the built-in controller - /workspace/source/src_code/test/e2e/e2e_test.go:632 @ 11/02/26 22:12:31.103
STEP: Create a TrainJob managed by MultiKueue - /workspace/source/src_code/test/e2e/e2e_test.go:639 @ 11/02/26 22:12:31.103
END STEP: Create a TrainJob managed by MultiKueue - /workspace/source/src_code/test/e2e/e2e_test.go:639 @ 11/02/26 22:12:31.133 (30ms)
STEP: Ensuring the built-in controller neither creates a JobSet nor sets any status - /workspace/source/src_code/test/e2e/e2e_test.go:643 @ 11/02/26 22:12:31.133
END STEP: Ensuring the built-in controller neither creates a JobSet nor sets any status - /workspace/source/src_code/test/e2e/e2e_test.go:643 @ 11/02/26 22:12:46.133 (15.001s)
&lt; Exit [It] should not be reconciled by the built-in controller - /workspace/source/src_code/test/e2e/e2e_test.go:632 @ 11/02/26 22:12:46.134 (15.031s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:12:46.134
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:12:46.154 (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="9.986031719">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:12:46.154
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:12:46.191 (37ms)
&gt; Enter [It] should fail the TrainJob with DeadlineExceeded when active timeout expires - /workspace/source/src_code/test/e2e/e2e_test.go:655 @ 11/02/26 22:12:46.191
STEP: Waiting for TrainJob to fail due to deadline - /workspace/source/src_code/test/e2e/e2e_test.go:670 @ 11/02/26 22:12:46.218
STEP: Ensuring the underlying JobSet is deleted - /workspace/source/src_code/test/e2e/e2e_test.go:677 @ 11/02/26 22:12:56.104
&lt; Exit [It] should fail the TrainJob with DeadlineExceeded when active timeout expires - /workspace/source/src_code/test/e2e/e2e_test.go:655 @ 11/02/26 22:12:56.12 (9.929s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:12:56.12
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:12:56.14 (20ms)
</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="1.176389595">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:12:56.14
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:12:56.176 (36ms)
&gt; Enter [It] TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:908 @ 11/02/26 22:12:56.176
STEP: Creating a TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:800 @ 11/02/26 22:12:56.177
END STEP: Creating a TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:800 @ 11/02/26 22:12:56.223 (47ms)
STEP: Creating a TrainJob that references the TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:813 @ 11/02/26 22:12:56.223
END STEP: Creating a TrainJob that references the TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:813 @ 11/02/26 22:12:56.248 (25ms)
STEP: Waiting for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:817 @ 11/02/26 22:12:56.248
END STEP: Waiting for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:817 @ 11/02/26 22:12:56.53 (282ms)
STEP: Pausing the TrainJob - /workspace/source/src_code/test/e2e/e2e_test.go:828 @ 11/02/26 22:12:56.53
END STEP: Pausing the TrainJob - /workspace/source/src_code/test/e2e/e2e_test.go:828 @ 11/02/26 22:12:56.574 (43ms)
STEP: Waiting for TrainJob to be suspended - /workspace/source/src_code/test/e2e/e2e_test.go:837 @ 11/02/26 22:12:56.574
END STEP: Waiting for TrainJob to be suspended - /workspace/source/src_code/test/e2e/e2e_test.go:837 @ 11/02/26 22:12:56.856 (282ms)
STEP: Updating the runtime with a new container image - /workspace/source/src_code/test/e2e/e2e_test.go:850 @ 11/02/26 22:12:56.856
END STEP: Updating the runtime with a new container image - /workspace/source/src_code/test/e2e/e2e_test.go:850 @ 11/02/26 22:12:56.896 (40ms)
STEP: Restarting the TrainJob by unpausing it - /workspace/source/src_code/test/e2e/e2e_test.go:871 @ 11/02/26 22:12:56.896
END STEP: Restarting the TrainJob by unpausing it - /workspace/source/src_code/test/e2e/e2e_test.go:871 @ 11/02/26 22:12:56.938 (42ms)
STEP: Verifying the TrainJob jobs become active after resuming - /workspace/source/src_code/test/e2e/e2e_test.go:882 @ 11/02/26 22:12:56.938
END STEP: Verifying the TrainJob jobs become active after resuming - /workspace/source/src_code/test/e2e/e2e_test.go:882 @ 11/02/26 22:12:57.221 (283ms)
STEP: Verifying the Runtime snapshot is garbage collected - /workspace/source/src_code/test/e2e/e2e_test.go:894 @ 11/02/26 22:12:57.221
END STEP: Verifying the Runtime snapshot is garbage collected - /workspace/source/src_code/test/e2e/e2e_test.go:894 @ 11/02/26 22:12:57.276 (56ms)
&lt; Exit [It] TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:908 @ 11/02/26 22:12:57.276 (1.1s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:12:57.276
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:12:57.296 (19ms)
&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:804 @ 11/02/26 22:12:57.296
&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:804 @ 11/02/26 22:12:57.317 (21ms)
</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="1.1634719470000001">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:12:57.317
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:12:57.353 (36ms)
&gt; Enter [It] ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:920 @ 11/02/26 22:12:57.353
STEP: Creating a ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:800 @ 11/02/26 22:12:57.353
END STEP: Creating a ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:800 @ 11/02/26 22:12:57.395 (42ms)
STEP: Creating a TrainJob that references the ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:813 @ 11/02/26 22:12:57.395
END STEP: Creating a TrainJob that references the ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:813 @ 11/02/26 22:12:57.419 (24ms)
STEP: Waiting for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:817 @ 11/02/26 22:12:57.419
END STEP: Waiting for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:817 @ 11/02/26 22:12:57.701 (282ms)
STEP: Pausing the TrainJob - /workspace/source/src_code/test/e2e/e2e_test.go:828 @ 11/02/26 22:12:57.701
END STEP: Pausing the TrainJob - /workspace/source/src_code/test/e2e/e2e_test.go:828 @ 11/02/26 22:12:57.742 (42ms)
STEP: Waiting for TrainJob to be suspended - /workspace/source/src_code/test/e2e/e2e_test.go:837 @ 11/02/26 22:12:57.742
END STEP: Waiting for TrainJob to be suspended - /workspace/source/src_code/test/e2e/e2e_test.go:837 @ 11/02/26 22:12:58.025 (282ms)
STEP: Updating the runtime with a new container image - /workspace/source/src_code/test/e2e/e2e_test.go:850 @ 11/02/26 22:12:58.025
END STEP: Updating the runtime with a new container image - /workspace/source/src_code/test/e2e/e2e_test.go:850 @ 11/02/26 22:12:58.064 (39ms)
STEP: Restarting the TrainJob by unpausing it - /workspace/source/src_code/test/e2e/e2e_test.go:871 @ 11/02/26 22:12:58.064
END STEP: Restarting the TrainJob by unpausing it - /workspace/source/src_code/test/e2e/e2e_test.go:871 @ 11/02/26 22:12:58.107 (44ms)
STEP: Verifying the TrainJob jobs become active after resuming - /workspace/source/src_code/test/e2e/e2e_test.go:882 @ 11/02/26 22:12:58.107
END STEP: Verifying the TrainJob jobs become active after resuming - /workspace/source/src_code/test/e2e/e2e_test.go:882 @ 11/02/26 22:12:58.39 (282ms)
STEP: Verifying the Runtime snapshot is garbage collected - /workspace/source/src_code/test/e2e/e2e_test.go:894 @ 11/02/26 22:12:58.39
END STEP: Verifying the Runtime snapshot is garbage collected - /workspace/source/src_code/test/e2e/e2e_test.go:894 @ 11/02/26 22:12:58.439 (49ms)
&lt; Exit [It] ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:920 @ 11/02/26 22:12:58.439 (1.086s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:12:58.439
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:12:58.462 (23ms)
&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:804 @ 11/02/26 22:12:58.462
&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:804 @ 11/02/26 22:12:58.48 (18ms)
</system-err>
          </testcase>
      </testsuite>
      <testsuite name="RHAI Progression Tracking E2E Suite" package="/workspace/source/src_code/test/e2e/rhai" tests="11" disabled="0" skipped="0" errors="0" failures="0" time="309.671" timestamp="2026-11-02T22:12:58">
          <properties>
              <property name="SuiteSucceeded" value="true" />
              <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="1793656868" />
              <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="RHAI Progression Tracking E2E Suite" status="passed" time="0.132309886">
              <system-err>&gt; Enter [BeforeSuite] TOP-LEVEL - /workspace/source/src_code/test/e2e/rhai/suite_test.go:45 @ 11/02/26 22:12:58.5
Created shared test namespace: rhai-e2e-progression-s9sfm
&lt; Exit [BeforeSuite] TOP-LEVEL - /workspace/source/src_code/test/e2e/rhai/suite_test.go:45 @ 11/02/26 22:12:58.632 (132ms)
</system-err>
          </testcase>
          <testcase name="[It] RHAI Progression Tracking E2E Tests When progression tracking is enabled should poll metrics and update trainerStatus annotation during training" classname="RHAI Progression Tracking E2E Suite" status="passed" time="161.511432088">
              <system-err>&gt; Enter [BeforeEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:130 @ 11/02/26 22:12:58.632
&lt; Exit [BeforeEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:130 @ 11/02/26 22:12:58.675 (43ms)
&gt; Enter [It] should poll metrics and update trainerStatus annotation during training - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:150 @ 11/02/26 22:12:58.675
STEP: Creating TrainJob with progression tracking enabled - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:172 @ 11/02/26 22:12:58.675
STEP: Waiting for TrainJob pod to be running with IP - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:175 @ 11/02/26 22:12:58.702
STEP: Waiting for trainerStatus annotation to be populated - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:195 @ 11/02/26 22:15:15.877
STEP: Verifying trainerStatus is continuously updated during training - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:222 @ 11/02/26 22:15:15.892
STEP: Waiting for TrainJob to complete and verify final status - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:241 @ 11/02/26 22:15:15.908
&lt; Exit [It] should poll metrics and update trainerStatus annotation during training - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:150 @ 11/02/26 22:15:40.126 (2m41.451s)
&gt; Enter [AfterEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:142 @ 11/02/26 22:15:40.126
&lt; Exit [AfterEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:142 @ 11/02/26 22:15:40.144 (18ms)
</system-err>
          </testcase>
          <testcase name="[It] RHAI Progression Tracking E2E Tests When progression tracking is NOT enabled should NOT create trainerStatus annotation" classname="RHAI Progression Tracking E2E Suite" status="passed" time="35.122079049">
              <system-err>&gt; Enter [BeforeEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:130 @ 11/02/26 22:15:40.144
&lt; Exit [BeforeEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:130 @ 11/02/26 22:15:40.203 (59ms)
&gt; Enter [It] should NOT create trainerStatus annotation - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:274 @ 11/02/26 22:15:40.203
STEP: Creating TrainJob without progression tracking annotation - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:289 @ 11/02/26 22:15:40.203
STEP: Verifying trainerStatus annotation is NOT created (checking over time) - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:292 @ 11/02/26 22:15:40.233
&lt; Exit [It] should NOT create trainerStatus annotation - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:274 @ 11/02/26 22:16:15.245 (35.042s)
&gt; Enter [AfterEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:142 @ 11/02/26 22:16:15.245
&lt; Exit [AfterEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:142 @ 11/02/26 22:16:15.266 (21ms)
</system-err>
          </testcase>
          <testcase name="[It] RHAI Progression Tracking E2E Tests When progression tracking annotation has invalid value should NOT enable progression tracking for non-'true' values" classname="RHAI Progression Tracking E2E Suite" status="passed" time="15.088688706">
              <system-err>&gt; Enter [BeforeEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:130 @ 11/02/26 22:16:15.266
&lt; Exit [BeforeEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:130 @ 11/02/26 22:16:15.303 (37ms)
&gt; Enter [It] should NOT enable progression tracking for non-'true' values - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:307 @ 11/02/26 22:16:15.303
STEP: Creating TrainJob with invalid annotation value - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:324 @ 11/02/26 22:16:15.304
STEP: Verifying progression tracking is NOT enabled (checking over time) - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:327 @ 11/02/26 22:16:15.331
&lt; Exit [It] should NOT enable progression tracking for non-'true' values - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:307 @ 11/02/26 22:16:30.337 (15.033s)
&gt; Enter [AfterEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:142 @ 11/02/26 22:16:30.337
&lt; Exit [AfterEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:142 @ 11/02/26 22:16:30.355 (18ms)
</system-err>
          </testcase>
          <testcase name="[It] RHAI Progression Tracking E2E Tests When metrics polling configuration is customized should honor custom metrics port and poll interval" classname="RHAI Progression Tracking E2E Suite" status="passed" time="4.147496574">
              <system-err>&gt; Enter [BeforeEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:130 @ 11/02/26 22:16:30.355
&lt; Exit [BeforeEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:130 @ 11/02/26 22:16:30.393 (38ms)
&gt; Enter [It] should honor custom metrics port and poll interval - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:342 @ 11/02/26 22:16:30.393
STEP: Creating TrainJob with custom metrics configuration - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:360 @ 11/02/26 22:16:30.393
STEP: Verifying custom configuration is applied - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:363 @ 11/02/26 22:16:30.421
STEP: Verifying metrics are polled on the custom port - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:370 @ 11/02/26 22:16:30.436
&lt; Exit [It] should honor custom metrics port and poll interval - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:342 @ 11/02/26 22:16:34.484 (4.092s)
&gt; Enter [AfterEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:142 @ 11/02/26 22:16:34.484
&lt; Exit [AfterEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:142 @ 11/02/26 22:16:34.502 (18ms)
</system-err>
          </testcase>
          <testcase name="[It] RHAI Progression Tracking E2E Tests When metrics polling configuration is customized should handle minimum SDK-recommended poll interval (5s)" classname="RHAI Progression Tracking E2E Suite" status="passed" time="0.098812236">
              <system-err>&gt; Enter [BeforeEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:130 @ 11/02/26 22:16:34.503
&lt; Exit [BeforeEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:130 @ 11/02/26 22:16:34.541 (38ms)
&gt; Enter [It] should handle minimum SDK-recommended poll interval (5s) - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:385 @ 11/02/26 22:16:34.541
STEP: Creating TrainJob with minimum poll interval - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:403 @ 11/02/26 22:16:34.541
STEP: Verifying minimum interval is respected - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:406 @ 11/02/26 22:16:34.568
&lt; Exit [It] should handle minimum SDK-recommended poll interval (5s) - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:385 @ 11/02/26 22:16:34.584 (43ms)
&gt; Enter [AfterEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:142 @ 11/02/26 22:16:34.584
&lt; Exit [AfterEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:142 @ 11/02/26 22:16:34.601 (18ms)
</system-err>
          </testcase>
          <testcase name="[It] RHAI Progression Tracking E2E Tests When metrics polling configuration is customized should handle maximum SDK-recommended poll interval (300s)" classname="RHAI Progression Tracking E2E Suite" status="passed" time="0.102782277">
              <system-err>&gt; Enter [BeforeEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:130 @ 11/02/26 22:16:34.601
&lt; Exit [BeforeEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:130 @ 11/02/26 22:16:34.638 (37ms)
&gt; Enter [It] should handle maximum SDK-recommended poll interval (300s) - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:412 @ 11/02/26 22:16:34.638
STEP: Creating TrainJob with maximum poll interval - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:430 @ 11/02/26 22:16:34.638
STEP: Verifying maximum interval is respected - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:433 @ 11/02/26 22:16:34.668
&lt; Exit [It] should handle maximum SDK-recommended poll interval (300s) - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:412 @ 11/02/26 22:16:34.684 (46ms)
&gt; Enter [AfterEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:142 @ 11/02/26 22:16:34.684
&lt; Exit [AfterEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:142 @ 11/02/26 22:16:34.704 (20ms)
</system-err>
          </testcase>
          <testcase name="[It] RHAI Progression Tracking E2E Tests When metrics polling configuration is customized should use default interval when annotation is missing" classname="RHAI Progression Tracking E2E Suite" status="passed" time="0.099337536">
              <system-err>&gt; Enter [BeforeEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:130 @ 11/02/26 22:16:34.704
&lt; Exit [BeforeEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:130 @ 11/02/26 22:16:34.743 (39ms)
&gt; Enter [It] should use default interval when annotation is missing - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:439 @ 11/02/26 22:16:34.743
STEP: Creating TrainJob without poll interval annotation - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:457 @ 11/02/26 22:16:34.743
STEP: Verifying default interval (30s) is used - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:460 @ 11/02/26 22:16:34.771
&lt; Exit [It] should use default interval when annotation is missing - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:439 @ 11/02/26 22:16:34.786 (43ms)
&gt; Enter [AfterEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:142 @ 11/02/26 22:16:34.786
&lt; Exit [AfterEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:142 @ 11/02/26 22:16:34.804 (18ms)
</system-err>
          </testcase>
          <testcase name="[It] RHAI Progression Tracking E2E Tests When TrainJob fails during training should capture final status even when job fails" classname="RHAI Progression Tracking E2E Suite" status="passed" time="82.881452673">
              <system-err>&gt; Enter [BeforeEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:130 @ 11/02/26 22:16:34.804
&lt; Exit [BeforeEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:130 @ 11/02/26 22:16:34.844 (40ms)
&gt; Enter [BeforeEach] When TrainJob fails during training - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:470 @ 11/02/26 22:16:34.844
&lt; Exit [BeforeEach] When TrainJob fails during training - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:470 @ 11/02/26 22:16:34.881 (37ms)
&gt; Enter [It] should capture final status even when job fails - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:487 @ 11/02/26 22:16:34.881
STEP: Creating TrainJob that will fail mid-training - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:505 @ 11/02/26 22:16:34.881
STEP: Waiting for trainerStatus annotation to be populated during training - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:508 @ 11/02/26 22:16:34.908
STEP: Waiting for TrainJob to fail - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:516 @ 11/02/26 22:17:47.533
STEP: Verifying final status is captured with progress=100% even on failure - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:530 @ 11/02/26 22:17:57.633
&lt; Exit [It] should capture final status even when job fails - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:487 @ 11/02/26 22:17:57.649 (1m22.768s)
&gt; Enter [AfterEach] When TrainJob fails during training - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:481 @ 11/02/26 22:17:57.649
&lt; Exit [AfterEach] When TrainJob fails during training - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:481 @ 11/02/26 22:17:57.668 (18ms)
&gt; Enter [AfterEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:142 @ 11/02/26 22:17:57.668
&lt; Exit [AfterEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:142 @ 11/02/26 22:17:57.685 (18ms)
</system-err>
          </testcase>
          <testcase name="[It] RHAI Progression Tracking E2E Tests When metrics endpoint is unreachable should handle connection errors gracefully without crashing" classname="RHAI Progression Tracking E2E Suite" status="passed" time="10.469622858">
              <system-err>&gt; Enter [BeforeEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:130 @ 11/02/26 22:17:57.686
&lt; Exit [BeforeEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:130 @ 11/02/26 22:17:57.725 (39ms)
&gt; Enter [BeforeEach] When metrics endpoint is unreachable - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:550 @ 11/02/26 22:17:57.725
&lt; Exit [BeforeEach] When metrics endpoint is unreachable - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:550 @ 11/02/26 22:17:57.764 (39ms)
&gt; Enter [It] should handle connection errors gracefully without crashing - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:567 @ 11/02/26 22:17:57.764
STEP: Creating TrainJob without metrics endpoint - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:585 @ 11/02/26 22:17:57.764
STEP: Waiting for TrainJob pod to be running - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:588 @ 11/02/26 22:17:57.791
STEP: Check controller still reconciles the TrainJob by ensuring it gets marked complete - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:598 @ 11/02/26 22:18:00.036
&lt; Exit [It] should handle connection errors gracefully without crashing - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:567 @ 11/02/26 22:18:08.119 (10.355s)
&gt; Enter [AfterEach] When metrics endpoint is unreachable - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:561 @ 11/02/26 22:18:08.119
&lt; Exit [AfterEach] When metrics endpoint is unreachable - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:561 @ 11/02/26 22:18:08.137 (18ms)
&gt; Enter [AfterEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:142 @ 11/02/26 22:18:08.137
&lt; Exit [AfterEach] RHAI Progression Tracking E2E Tests - /workspace/source/src_code/test/e2e/rhai/progression_e2e_test.go:142 @ 11/02/26 22:18:08.155 (18ms)
</system-err>
          </testcase>
          <testcase name="[AfterSuite]" classname="RHAI Progression Tracking E2E Suite" status="passed" time="0.017365465">
              <system-err>&gt; Enter [AfterSuite] TOP-LEVEL - /workspace/source/src_code/test/e2e/rhai/suite_test.go:71 @ 11/02/26 22:18:08.156
Cleaning up test namespace: rhai-e2e-progression-s9sfm
&lt; Exit [AfterSuite] TOP-LEVEL - /workspace/source/src_code/test/e2e/rhai/suite_test.go:71 @ 11/02/26 22:18:08.173 (17ms)
</system-err>
          </testcase>
      </testsuite>
  <testsuite tests="3" failures="0" time="1.28" name="trainer" timestamp="2026-11-02T22:18:55Z" 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="1.210000" />
	</testsuite>
<testsuite tests="7" failures="0" time="930.96" name="trainer" timestamp="2026-11-02T22:18:59Z" 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="499.960000" />
		<testcase classname="tests/trainer" name="TestJobSetWorkflow" time="186.700000" />
		<testcase classname="tests/trainer" name="TestKubeflowSdk" time="161.710000" />
		<testcase classname="tests/trainer" name="TestKubeflowSdkKueueIntegration" time="52.000000" />
		<testcase classname="tests/trainer" name="TestKueueWorkloadPreemptionSuspendsTrainJob" time="3.490000" />
		<testcase classname="tests/trainer" name="TestKueueSchedulingReachesTrainJobPods" time="1.310000" />
		<testcase classname="tests/trainer" name="TestMultiNodeOpenMPICpuTrainJob" time="25.790000" />
	</testsuite>
<testsuite tests="15" failures="0" time="2182.2" name="trainer" timestamp="2026-11-02T22:34:34Z" 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="10.450000" />
		<testcase classname="tests/trainer" name="TestRhaiTrainingProgressionCPU" time="444.040000" />
		<testcase classname="tests/trainer" name="TestRhaiJitCheckpointingCPU" time="527.850000" />
		<testcase classname="tests/trainer" name="TestRhaiFeaturesCPU" time="531.950000" />
		<testcase classname="tests/trainer" name="TestRhaiS3CheckpointingCPU" time="538.740000" />
		<testcase classname="tests/trainer" name="TestPyTorchDDPMultiNodeMultiCPUWithTorchCuda28" time="70.890000" />
		<testcase classname="tests/trainer" name="TestKueueWorkloadInadmissibleWithNonExistentLocalQueue" time="1.200000" />
		<testcase classname="tests/trainer" name="TestTrainerSecureServing" time="0.460000" />
		<testcase classname="tests/trainer" name="TestTrainerPrometheusScrape" time="0.410000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherNamespacesToMetrics" time="12.390000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherNamespacesToHealth" time="6.350000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherNamespacesToStatusServer" time="8.350000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherNamespacesToUnpublishedPort" time="8.280000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherNamespacesToWorkloadPort" time="9.480000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherWorkloadsToWorkloadPort" time="11.360000" />
	</testsuite>
<testsuite tests="0" failures="0" time="0" name="trainer" timestamp="2026-11-02T23:10:58Z" 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>