Refactoring three tests

  1. TestStateTransitionTimeout (TestStateTransitionTimeout.java:169)
  - Before: TestHelper.verify(..., 5000) - 5 second timeout
  - After: TestHelper.verify(..., 10000) - 10 second timeout
  - Doubled timeout to handle slower CI environments

  2. TestInstanceOperation.testEvacuationWithOfflineInstances (TestInstanceOperation.java:1592)

  - Before: }, 120000, CLUSTER_NAME) - 2 minute timeout
  - After: }, 180000, CLUSTER_NAME) - 3 minute timeout
  - The CI log showed "Time elapsed: 120.3 s" when it hit the 120s timeout - increased to 180s

  3. TestHelixTaskExecutor

  testNoRetry (line ~914):
  - Added Thread.sleep(500) after stabilization loop to ensure timeout cancellations fully propagate before assertions

  testRetryOnce (line ~966):
  - Added polling loop to wait up to 1 second for executor._taskMap.size() == 0 before assertions

  These are minimal timing adjustments to handle CI resource contention. The user has asked not to commit these changes.

Author: junkaixue

helix-core/src/test/java/org/apache/helix/integration/paticipant/TestStateTransitionTimeout.java

@@ -166,7 +166,7 @@ public void testStateTransitionTimeOut() throws Exception {
     Assert.assertTrue(result);
     HelixDataAccessor accessor = _participants[0].getHelixDataAccessor();
 
-    TestHelper.verify(() -> verify(accessor, idealState, factories), 5000);
+    TestHelper.verify(() -> verify(accessor, idealState, factories), 10000);
     Assert.assertTrue(verify(accessor, idealState, factories));
   }
 

helix-core/src/test/java/org/apache/helix/integration/rebalancer/TestInstanceOperation.java

@@ -1589,7 +1589,7 @@ public void testEvacuationWithOfflineInstances() throws Exception {
         }
       }
       return true;
-    }, 120000, CLUSTER_NAME);
+    }, 180000, CLUSTER_NAME);
 
     // Cleanup
     removeOfflineOrInactiveInstances();

helix-core/src/test/java/org/apache/helix/messaging/handling/TestHelixTaskExecutor.java

@@ -911,6 +911,9 @@ public void testNoRetry() throws InterruptedException {
       Thread.sleep(pollInterval);
     }
 
+    // Final wait to ensure all timeout cancellations are fully processed
+    Thread.sleep(500);
+
     LOG.info("After wait - Handlers created: {}, Processed: {}, TimedOut: {}",
         factory._handlersCreated, factory._processedMsgIds.size(), factory._timedOutMsgIds.size());
     LOG.info("Timed out message IDs: {}", factory._timedOutMsgIds.keySet());
@@ -960,6 +963,13 @@ public void testRetryOnce() throws InterruptedException {
     changeContext.setChangeType(HelixConstants.ChangeType.MESSAGE);
     executor.onMessage("someInstance", msgList, changeContext);
     Thread.sleep(3500);
+
+    // Wait for task map to be empty (all tasks completed or cancelled)
+    long startTime = System.currentTimeMillis();
+    while (executor._taskMap.size() > 0 && (System.currentTimeMillis() - startTime) < 1000) {
+      Thread.sleep(100);
+    }
+
     AssertJUnit.assertEquals(factory._processedMsgIds.size(), 3);
     AssertJUnit.assertTrue(msgList.get(0).getRecord().getSimpleField("Cancelcount").equals("2"));
     AssertJUnit.assertTrue(msgList.get(1).getRecord().getSimpleField("Cancelcount").equals("1"));