Temporary disable logging rebalance error before HELIX-631 is resolved. An issue is found that legacy code assumes all controllers' instance names start with "controller". However, this assumption is no longer valid now. This results in log to be written to a wrong path.
Before we resolve the problem cleanly, disable the error log. Project: http://git-wip-us.apache.org/repos/asf/helix/repo Commit: http://git-wip-us.apache.org/repos/asf/helix/commit/401ada63 Tree: http://git-wip-us.apache.org/repos/asf/helix/tree/401ada63 Diff: http://git-wip-us.apache.org/repos/asf/helix/diff/401ada63 Branch: refs/heads/master Commit: 401ada6391883f5cfcd7e04858dc94ee2b227ff7 Parents: d0a3c0d Author: Jiajun Wang <[email protected]> Authored: Tue Nov 7 16:12:42 2017 -0800 Committer: Junkai Xue <[email protected]> Committed: Wed Jan 24 18:30:33 2018 -0800 ---------------------------------------------------------------------- .../helix/controller/stages/BestPossibleStateCalcStage.java | 3 +++ .../helix/integration/TestAlertingRebalancerFailure.java | 6 +++--- .../TestPauseClusterWhenReachingOfflineInstancesLimit.java | 3 +++ 3 files changed, 9 insertions(+), 3 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/helix/blob/401ada63/helix-core/src/main/java/org/apache/helix/controller/stages/BestPossibleStateCalcStage.java ---------------------------------------------------------------------- diff --git a/helix-core/src/main/java/org/apache/helix/controller/stages/BestPossibleStateCalcStage.java b/helix-core/src/main/java/org/apache/helix/controller/stages/BestPossibleStateCalcStage.java index 20ebb8e..c43b96c 100644 --- a/helix-core/src/main/java/org/apache/helix/controller/stages/BestPossibleStateCalcStage.java +++ b/helix-core/src/main/java/org/apache/helix/controller/stages/BestPossibleStateCalcStage.java @@ -148,11 +148,14 @@ public class BestPossibleStateCalcStage extends AbstractBaseStage { @Override public Object call() { try { + // TODO re-enable logging error after ticket HELIX-631 is resolved + /* if (hasFailure && _statusUpdateUtil != null) { _statusUpdateUtil .logError(StatusUpdateUtil.ErrorType.RebalanceResourceFailure, this.getClass(), errorMessage, helixManager); } + */ if (clusterStatusMonitor != null) { clusterStatusMonitor.setRebalanceFailureGauge(hasFailure); } http://git-wip-us.apache.org/repos/asf/helix/blob/401ada63/helix-core/src/test/java/org/apache/helix/integration/TestAlertingRebalancerFailure.java ---------------------------------------------------------------------- diff --git a/helix-core/src/test/java/org/apache/helix/integration/TestAlertingRebalancerFailure.java b/helix-core/src/test/java/org/apache/helix/integration/TestAlertingRebalancerFailure.java index 0df817d..012760c 100644 --- a/helix-core/src/test/java/org/apache/helix/integration/TestAlertingRebalancerFailure.java +++ b/helix-core/src/test/java/org/apache/helix/integration/TestAlertingRebalancerFailure.java @@ -106,7 +106,7 @@ public class TestAlertingRebalancerFailure extends ZkStandAloneCMTestBase { accessor.removeProperty(errorNodeKey); } - @Test + @Test (enabled = false) public void testParticipantUnavailable() { _setupTool.addResourceToCluster(CLUSTER_NAME, testDb, 5, BuiltInStateModelDefinitions.MasterSlave.name(), RebalanceMode.FULL_AUTO.name()); @@ -145,7 +145,7 @@ public class TestAlertingRebalancerFailure extends ZkStandAloneCMTestBase { } } - @Test + @Test (enabled = false) public void testTagSetIncorrect() { _setupTool.addResourceToCluster(CLUSTER_NAME, testDb, 5, BuiltInStateModelDefinitions.MasterSlave.name(), RebalanceMode.FULL_AUTO.name()); @@ -164,7 +164,7 @@ public class TestAlertingRebalancerFailure extends ZkStandAloneCMTestBase { _setupTool.getClusterManagementTool().dropResource(CLUSTER_NAME, testDb); } - @Test + @Test (enabled = false) public void testWithDomainId() throws InterruptedException { int replicas = 2; ConfigAccessor configAccessor = new ConfigAccessor(_gZkClient); http://git-wip-us.apache.org/repos/asf/helix/blob/401ada63/helix-core/src/test/java/org/apache/helix/integration/rebalancer/TestPauseClusterWhenReachingOfflineInstancesLimit.java ---------------------------------------------------------------------- diff --git a/helix-core/src/test/java/org/apache/helix/integration/rebalancer/TestPauseClusterWhenReachingOfflineInstancesLimit.java b/helix-core/src/test/java/org/apache/helix/integration/rebalancer/TestPauseClusterWhenReachingOfflineInstancesLimit.java index 02668e0..9c2c434 100644 --- a/helix-core/src/test/java/org/apache/helix/integration/rebalancer/TestPauseClusterWhenReachingOfflineInstancesLimit.java +++ b/helix-core/src/test/java/org/apache/helix/integration/rebalancer/TestPauseClusterWhenReachingOfflineInstancesLimit.java @@ -167,6 +167,8 @@ public class TestPauseClusterWhenReachingOfflineInstancesLimit extends ZkIntegra Assert.assertNotNull(pauseSignal); Assert.assertNotNull(pauseSignal.getReason()); + // TODO re-enable the check after HELIX-631 is fixed + /* // Verify there is no rebalance error logged ZKHelixDataAccessor accessor = new ZKHelixDataAccessor(CLUSTER_NAME, _baseAccessor); PropertyKey errorNodeKey = @@ -177,6 +179,7 @@ public class TestPauseClusterWhenReachingOfflineInstancesLimit extends ZkIntegra (Long) _server.getAttribute(getMbeanName(CLUSTER_NAME), "RebalanceFailureGauge"); Assert.assertNotNull(value); Assert.assertTrue(value.longValue() > 0); + */ } @AfterClass
