You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@geode.apache.org by "Kirk Lund (JIRA)" <ji...@apache.org> on 2019/02/28 22:02:00 UTC

[jira] [Updated] (GEODE-6471) Reconnect with UDP security throws NullPointerException from GMSEncrypt

     [ https://issues.apache.org/jira/browse/GEODE-6471?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Kirk Lund updated GEODE-6471:
-----------------------------
    Description: 
ReconnectWithUDPSecurityDUnitTest seems to fail inconsistently with the following NullPointerException thrown from GMSEncrypt. The field that is null is `GMSEncryptionCipherPool clusterEncryptor` which is set under synchronization but read without synchronization.

I tried changing the field to volatile but I can still get the test to fail intermittently with the same NPE.

Simply moving addIgnoredException statements around in the super class ReconnectDUnitTest seems to be enough to occasionally trigger a cluster of repeated failures with this NPE.

I can't tell if there's a GMS bug, a configuration bug, a test bug or something rotten the construction/usage of GMSEncrypt. JGroupsMessenger has a reference to GMSEncrypt and that reference doesn't appear to be thread-safe either.
{noformat}
[error 2019/02/28 13:53:20.935 PST <ReconnectThread> tid=70] Exception deserializing message payload: [dst: 10.118.33.197<v2>:41003, src: 10.118.33.197<v0>:41001 (2 headers), size=122 bytes, flags=OOB|DONT_BUNDLE|NO_FC|SKIP_BARRIER]
java.lang.Exception: Message id is -154
	at org.apache.geode.distributed.internal.membership.gms.messenger.JGroupsMessenger.readEncryptedMessage(JGroupsMessenger.java:1138)
	at org.apache.geode.distributed.internal.membership.gms.messenger.JGroupsMessenger.readJGMessage(JGroupsMessenger.java:1042)
	at org.apache.geode.distributed.internal.membership.gms.messenger.JGroupsMessenger$JGroupsReceiver.receive(JGroupsMessenger.java:1296)
	at org.apache.geode.distributed.internal.membership.gms.messenger.JGroupsMessenger$JGroupsReceiver.access$000(JGroupsMessenger.java:1261)
	at org.apache.geode.distributed.internal.membership.gms.messenger.JGroupsMessenger.started(JGroupsMessenger.java:419)
	at org.apache.geode.distributed.internal.membership.gms.Services.start(Services.java:164)
	at org.apache.geode.distributed.internal.membership.gms.GMSMemberFactory.newMembershipManager(GMSMemberFactory.java:106)
	at org.apache.geode.distributed.internal.membership.MemberFactory.newMembershipManager(MemberFactory.java:93)
	at org.apache.geode.distributed.internal.ClusterDistributionManager.<init>(ClusterDistributionManager.java:782)
	at org.apache.geode.distributed.internal.ClusterDistributionManager.<init>(ClusterDistributionManager.java:900)
	at org.apache.geode.distributed.internal.ClusterDistributionManager.create(ClusterDistributionManager.java:541)
	at org.apache.geode.distributed.internal.InternalDistributedSystem.initialize(InternalDistributedSystem.java:830)
	at org.apache.geode.distributed.internal.InternalDistributedSystem.newInstance(InternalDistributedSystem.java:442)
	at org.apache.geode.distributed.internal.InternalDistributedSystem.newInstance(InternalDistributedSystem.java:428)
	at org.apache.geode.distributed.internal.InternalDistributedSystem.connectInternal(InternalDistributedSystem.java:253)
	at org.apache.geode.distributed.DistributedSystem.connect(DistributedSystem.java:164)
	at org.apache.geode.distributed.internal.InternalDistributedSystem.reconnect(InternalDistributedSystem.java:2636)
	at org.apache.geode.distributed.internal.InternalDistributedSystem.tryReconnect(InternalDistributedSystem.java:2463)
	at org.apache.geode.distributed.internal.InternalDistributedSystem.disconnect(InternalDistributedSystem.java:1278)
	at org.apache.geode.distributed.internal.ClusterDistributionManager$DMListener.membershipFailure(ClusterDistributionManager.java:3424)
	at org.apache.geode.distributed.internal.membership.gms.mgr.GMSMembershipManager.uncleanShutdown(GMSMembershipManager.java:1554)
	at org.apache.geode.distributed.internal.membership.gms.mgr.GMSMembershipManager.lambda$forceDisconnect$3(GMSMembershipManager.java:2586)
	at java.lang.Thread.run(Thread.java:748)
Caused by: java.lang.NullPointerException
	at org.apache.geode.distributed.internal.membership.gms.messenger.GMSEncrypt.decryptData(GMSEncrypt.java:148)
	at org.apache.geode.distributed.internal.membership.gms.messenger.JGroupsMessenger.readEncryptedMessage(JGroupsMessenger.java:1117)
	... 22 more



	at org.junit.Assert.fail(Assert.java:88)
	at org.apache.geode.test.dunit.internal.DUnitLauncher.closeAndCheckForSuspects(DUnitLauncher.java:380)
	at org.apache.geode.test.dunit.internal.JUnit4DistributedTestCase.cleanupAllVms(JUnit4DistributedTestCase.java:553)
	at org.apache.geode.test.dunit.internal.JUnit4DistributedTestCase.doTearDownDistributedTestCase(JUnit4DistributedTestCase.java:500)
	at org.apache.geode.test.dunit.internal.JUnit4DistributedTestCase.tearDownDistributedTestCase(JUnit4DistributedTestCase.java:484)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:498)
	at org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:50)
	at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12)
	at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:47)
	at org.junit.internal.runners.statements.RunAfters.evaluate(RunAfters.java:33)
	at org.apache.geode.test.dunit.rules.AbstractDistributedRule$1.evaluate(AbstractDistributedRule.java:59)
	at org.junit.rules.ExternalResource$1.evaluate(ExternalResource.java:48)
	at org.junit.rules.TestWatcher$1.evaluate(TestWatcher.java:55)
	at org.junit.rules.RunRules.evaluate(RunRules.java:20)
	at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:325)
	at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:78)
	at junitparams.JUnitParamsRunner.runChild(JUnitParamsRunner.java:449)
	at junitparams.JUnitParamsRunner.runChild(JUnitParamsRunner.java:393)
	at org.junit.runners.ParentRunner$3.run(ParentRunner.java:290)
	at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:71)
	at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:288)
	at org.junit.runners.ParentRunner.access$000(ParentRunner.java:58)
	at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:268)
	at org.junit.internal.runners.statements.RunBefores.evaluate(RunBefores.java:26)
	at org.junit.runners.ParentRunner.run(ParentRunner.java:363)
	at org.junit.runner.JUnitCore.run(JUnitCore.java:137)
	at com.intellij.junit4.JUnit4IdeaTestRunner.startRunnerWithArgs(JUnit4IdeaTestRunner.java:68)
	at com.intellij.rt.execution.junit.IdeaTestRunner$Repeater.startRunnerWithArgs(IdeaTestRunner.java:47)
	at com.intellij.rt.execution.junit.JUnitStarter.prepareStreamsAndStart(JUnitStarter.java:242)
	at com.intellij.rt.execution.junit.JUnitStarter.main(JUnitStarter.java:70)
{noformat}

  was:
ReconnectWithUDPSecurityDUnitTest seems to fail inconsistently with the following NullPointerException thrown from GMSEncrypt. The field that is null is `GMSEncryptionCipherPool clusterEncryptor` which is set under synchronization but read without synchronization.

I tried changing the field to volatile but I can still get the test to fail intermittently with the same NPE.

Simply moving addIgnoredException statements around in the super class ReconnectDUnitTest seems to be enough to occasionally trigger a cluster of repeated failures with this NPE.

I can't tell if there's a GMS bug, a configuration bug, a test bug or something rotten the construction/usage of GMSEncrypt. JGroupsMessenger has a reference to GMSEncrypt and that reference doesn't appear to be thread-safe either.

[error 2019/02/28 13:53:20.935 PST <ReconnectThread> tid=70] Exception deserializing message payload: [dst: 10.118.33.197<v2>:41003, src: 10.118.33.197<v0>:41001 (2 headers), size=122 bytes, flags=OOB|DONT_BUNDLE|NO_FC|SKIP_BARRIER]
java.lang.Exception: Message id is -154
	at org.apache.geode.distributed.internal.membership.gms.messenger.JGroupsMessenger.readEncryptedMessage(JGroupsMessenger.java:1138)
	at org.apache.geode.distributed.internal.membership.gms.messenger.JGroupsMessenger.readJGMessage(JGroupsMessenger.java:1042)
	at org.apache.geode.distributed.internal.membership.gms.messenger.JGroupsMessenger$JGroupsReceiver.receive(JGroupsMessenger.java:1296)
	at org.apache.geode.distributed.internal.membership.gms.messenger.JGroupsMessenger$JGroupsReceiver.access$000(JGroupsMessenger.java:1261)
	at org.apache.geode.distributed.internal.membership.gms.messenger.JGroupsMessenger.started(JGroupsMessenger.java:419)
	at org.apache.geode.distributed.internal.membership.gms.Services.start(Services.java:164)
	at org.apache.geode.distributed.internal.membership.gms.GMSMemberFactory.newMembershipManager(GMSMemberFactory.java:106)
	at org.apache.geode.distributed.internal.membership.MemberFactory.newMembershipManager(MemberFactory.java:93)
	at org.apache.geode.distributed.internal.ClusterDistributionManager.<init>(ClusterDistributionManager.java:782)
	at org.apache.geode.distributed.internal.ClusterDistributionManager.<init>(ClusterDistributionManager.java:900)
	at org.apache.geode.distributed.internal.ClusterDistributionManager.create(ClusterDistributionManager.java:541)
	at org.apache.geode.distributed.internal.InternalDistributedSystem.initialize(InternalDistributedSystem.java:830)
	at org.apache.geode.distributed.internal.InternalDistributedSystem.newInstance(InternalDistributedSystem.java:442)
	at org.apache.geode.distributed.internal.InternalDistributedSystem.newInstance(InternalDistributedSystem.java:428)
	at org.apache.geode.distributed.internal.InternalDistributedSystem.connectInternal(InternalDistributedSystem.java:253)
	at org.apache.geode.distributed.DistributedSystem.connect(DistributedSystem.java:164)
	at org.apache.geode.distributed.internal.InternalDistributedSystem.reconnect(InternalDistributedSystem.java:2636)
	at org.apache.geode.distributed.internal.InternalDistributedSystem.tryReconnect(InternalDistributedSystem.java:2463)
	at org.apache.geode.distributed.internal.InternalDistributedSystem.disconnect(InternalDistributedSystem.java:1278)
	at org.apache.geode.distributed.internal.ClusterDistributionManager$DMListener.membershipFailure(ClusterDistributionManager.java:3424)
	at org.apache.geode.distributed.internal.membership.gms.mgr.GMSMembershipManager.uncleanShutdown(GMSMembershipManager.java:1554)
	at org.apache.geode.distributed.internal.membership.gms.mgr.GMSMembershipManager.lambda$forceDisconnect$3(GMSMembershipManager.java:2586)
	at java.lang.Thread.run(Thread.java:748)
Caused by: java.lang.NullPointerException
	at org.apache.geode.distributed.internal.membership.gms.messenger.GMSEncrypt.decryptData(GMSEncrypt.java:148)
	at org.apache.geode.distributed.internal.membership.gms.messenger.JGroupsMessenger.readEncryptedMessage(JGroupsMessenger.java:1117)
	... 22 more



	at org.junit.Assert.fail(Assert.java:88)
	at org.apache.geode.test.dunit.internal.DUnitLauncher.closeAndCheckForSuspects(DUnitLauncher.java:380)
	at org.apache.geode.test.dunit.internal.JUnit4DistributedTestCase.cleanupAllVms(JUnit4DistributedTestCase.java:553)
	at org.apache.geode.test.dunit.internal.JUnit4DistributedTestCase.doTearDownDistributedTestCase(JUnit4DistributedTestCase.java:500)
	at org.apache.geode.test.dunit.internal.JUnit4DistributedTestCase.tearDownDistributedTestCase(JUnit4DistributedTestCase.java:484)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:498)
	at org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:50)
	at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12)
	at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:47)
	at org.junit.internal.runners.statements.RunAfters.evaluate(RunAfters.java:33)
	at org.apache.geode.test.dunit.rules.AbstractDistributedRule$1.evaluate(AbstractDistributedRule.java:59)
	at org.junit.rules.ExternalResource$1.evaluate(ExternalResource.java:48)
	at org.junit.rules.TestWatcher$1.evaluate(TestWatcher.java:55)
	at org.junit.rules.RunRules.evaluate(RunRules.java:20)
	at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:325)
	at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:78)
	at junitparams.JUnitParamsRunner.runChild(JUnitParamsRunner.java:449)
	at junitparams.JUnitParamsRunner.runChild(JUnitParamsRunner.java:393)
	at org.junit.runners.ParentRunner$3.run(ParentRunner.java:290)
	at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:71)
	at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:288)
	at org.junit.runners.ParentRunner.access$000(ParentRunner.java:58)
	at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:268)
	at org.junit.internal.runners.statements.RunBefores.evaluate(RunBefores.java:26)
	at org.junit.runners.ParentRunner.run(ParentRunner.java:363)
	at org.junit.runner.JUnitCore.run(JUnitCore.java:137)
	at com.intellij.junit4.JUnit4IdeaTestRunner.startRunnerWithArgs(JUnit4IdeaTestRunner.java:68)
	at com.intellij.rt.execution.junit.IdeaTestRunner$Repeater.startRunnerWithArgs(IdeaTestRunner.java:47)
	at com.intellij.rt.execution.junit.JUnitStarter.prepareStreamsAndStart(JUnitStarter.java:242)
	at com.intellij.rt.execution.junit.JUnitStarter.main(JUnitStarter.java:70)


> Reconnect with UDP security throws NullPointerException from GMSEncrypt
> -----------------------------------------------------------------------
>
>                 Key: GEODE-6471
>                 URL: https://issues.apache.org/jira/browse/GEODE-6471
>             Project: Geode
>          Issue Type: Bug
>          Components: membership, security
>            Reporter: Kirk Lund
>            Priority: Major
>
> ReconnectWithUDPSecurityDUnitTest seems to fail inconsistently with the following NullPointerException thrown from GMSEncrypt. The field that is null is `GMSEncryptionCipherPool clusterEncryptor` which is set under synchronization but read without synchronization.
> I tried changing the field to volatile but I can still get the test to fail intermittently with the same NPE.
> Simply moving addIgnoredException statements around in the super class ReconnectDUnitTest seems to be enough to occasionally trigger a cluster of repeated failures with this NPE.
> I can't tell if there's a GMS bug, a configuration bug, a test bug or something rotten the construction/usage of GMSEncrypt. JGroupsMessenger has a reference to GMSEncrypt and that reference doesn't appear to be thread-safe either.
> {noformat}
> [error 2019/02/28 13:53:20.935 PST <ReconnectThread> tid=70] Exception deserializing message payload: [dst: 10.118.33.197<v2>:41003, src: 10.118.33.197<v0>:41001 (2 headers), size=122 bytes, flags=OOB|DONT_BUNDLE|NO_FC|SKIP_BARRIER]
> java.lang.Exception: Message id is -154
> 	at org.apache.geode.distributed.internal.membership.gms.messenger.JGroupsMessenger.readEncryptedMessage(JGroupsMessenger.java:1138)
> 	at org.apache.geode.distributed.internal.membership.gms.messenger.JGroupsMessenger.readJGMessage(JGroupsMessenger.java:1042)
> 	at org.apache.geode.distributed.internal.membership.gms.messenger.JGroupsMessenger$JGroupsReceiver.receive(JGroupsMessenger.java:1296)
> 	at org.apache.geode.distributed.internal.membership.gms.messenger.JGroupsMessenger$JGroupsReceiver.access$000(JGroupsMessenger.java:1261)
> 	at org.apache.geode.distributed.internal.membership.gms.messenger.JGroupsMessenger.started(JGroupsMessenger.java:419)
> 	at org.apache.geode.distributed.internal.membership.gms.Services.start(Services.java:164)
> 	at org.apache.geode.distributed.internal.membership.gms.GMSMemberFactory.newMembershipManager(GMSMemberFactory.java:106)
> 	at org.apache.geode.distributed.internal.membership.MemberFactory.newMembershipManager(MemberFactory.java:93)
> 	at org.apache.geode.distributed.internal.ClusterDistributionManager.<init>(ClusterDistributionManager.java:782)
> 	at org.apache.geode.distributed.internal.ClusterDistributionManager.<init>(ClusterDistributionManager.java:900)
> 	at org.apache.geode.distributed.internal.ClusterDistributionManager.create(ClusterDistributionManager.java:541)
> 	at org.apache.geode.distributed.internal.InternalDistributedSystem.initialize(InternalDistributedSystem.java:830)
> 	at org.apache.geode.distributed.internal.InternalDistributedSystem.newInstance(InternalDistributedSystem.java:442)
> 	at org.apache.geode.distributed.internal.InternalDistributedSystem.newInstance(InternalDistributedSystem.java:428)
> 	at org.apache.geode.distributed.internal.InternalDistributedSystem.connectInternal(InternalDistributedSystem.java:253)
> 	at org.apache.geode.distributed.DistributedSystem.connect(DistributedSystem.java:164)
> 	at org.apache.geode.distributed.internal.InternalDistributedSystem.reconnect(InternalDistributedSystem.java:2636)
> 	at org.apache.geode.distributed.internal.InternalDistributedSystem.tryReconnect(InternalDistributedSystem.java:2463)
> 	at org.apache.geode.distributed.internal.InternalDistributedSystem.disconnect(InternalDistributedSystem.java:1278)
> 	at org.apache.geode.distributed.internal.ClusterDistributionManager$DMListener.membershipFailure(ClusterDistributionManager.java:3424)
> 	at org.apache.geode.distributed.internal.membership.gms.mgr.GMSMembershipManager.uncleanShutdown(GMSMembershipManager.java:1554)
> 	at org.apache.geode.distributed.internal.membership.gms.mgr.GMSMembershipManager.lambda$forceDisconnect$3(GMSMembershipManager.java:2586)
> 	at java.lang.Thread.run(Thread.java:748)
> Caused by: java.lang.NullPointerException
> 	at org.apache.geode.distributed.internal.membership.gms.messenger.GMSEncrypt.decryptData(GMSEncrypt.java:148)
> 	at org.apache.geode.distributed.internal.membership.gms.messenger.JGroupsMessenger.readEncryptedMessage(JGroupsMessenger.java:1117)
> 	... 22 more
> 	at org.junit.Assert.fail(Assert.java:88)
> 	at org.apache.geode.test.dunit.internal.DUnitLauncher.closeAndCheckForSuspects(DUnitLauncher.java:380)
> 	at org.apache.geode.test.dunit.internal.JUnit4DistributedTestCase.cleanupAllVms(JUnit4DistributedTestCase.java:553)
> 	at org.apache.geode.test.dunit.internal.JUnit4DistributedTestCase.doTearDownDistributedTestCase(JUnit4DistributedTestCase.java:500)
> 	at org.apache.geode.test.dunit.internal.JUnit4DistributedTestCase.tearDownDistributedTestCase(JUnit4DistributedTestCase.java:484)
> 	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> 	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
> 	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> 	at java.lang.reflect.Method.invoke(Method.java:498)
> 	at org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:50)
> 	at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12)
> 	at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:47)
> 	at org.junit.internal.runners.statements.RunAfters.evaluate(RunAfters.java:33)
> 	at org.apache.geode.test.dunit.rules.AbstractDistributedRule$1.evaluate(AbstractDistributedRule.java:59)
> 	at org.junit.rules.ExternalResource$1.evaluate(ExternalResource.java:48)
> 	at org.junit.rules.TestWatcher$1.evaluate(TestWatcher.java:55)
> 	at org.junit.rules.RunRules.evaluate(RunRules.java:20)
> 	at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:325)
> 	at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:78)
> 	at junitparams.JUnitParamsRunner.runChild(JUnitParamsRunner.java:449)
> 	at junitparams.JUnitParamsRunner.runChild(JUnitParamsRunner.java:393)
> 	at org.junit.runners.ParentRunner$3.run(ParentRunner.java:290)
> 	at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:71)
> 	at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:288)
> 	at org.junit.runners.ParentRunner.access$000(ParentRunner.java:58)
> 	at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:268)
> 	at org.junit.internal.runners.statements.RunBefores.evaluate(RunBefores.java:26)
> 	at org.junit.runners.ParentRunner.run(ParentRunner.java:363)
> 	at org.junit.runner.JUnitCore.run(JUnitCore.java:137)
> 	at com.intellij.junit4.JUnit4IdeaTestRunner.startRunnerWithArgs(JUnit4IdeaTestRunner.java:68)
> 	at com.intellij.rt.execution.junit.IdeaTestRunner$Repeater.startRunnerWithArgs(IdeaTestRunner.java:47)
> 	at com.intellij.rt.execution.junit.JUnitStarter.prepareStreamsAndStart(JUnitStarter.java:242)
> 	at com.intellij.rt.execution.junit.JUnitStarter.main(JUnitStarter.java:70)
> {noformat}



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)