[
https://issues.apache.org/jira/browse/HUDI-3593?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17504719#comment-17504719
]
shibei edited comment on HUDI-3593 at 3/11/22, 5:03 AM:
--------------------------------------------------------
Another failure
{code:java}
[ERROR] Tests run: 46, Failures: 0, Errors: 1, Skipped: 0, Time elapsed:
853.859 s <<< FAILURE! - in JUnit Vintage
[ERROR] String, String, String).[6] MERGE_ON_READ, linear,
null(testLayoutOptimizationFunctional Time elapsed: 6.185 s <<< ERROR!
org.apache.spark.SparkException: Writing job failed.
at
org.apache.spark.sql.execution.datasources.v2.WriteToDataSourceV2Exec.doExecute(WriteToDataSourceV2Exec.scala:87)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at
org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:80)
at
org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:80)
at
org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:676)
at
org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:676)
at
org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78)
at
org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73)
at
org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:676)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:260)
at
org.apache.hudi.HoodieSparkSqlWriter$.bulkInsertAsRow(HoodieSparkSqlWriter.scala:502)
at
org.apache.hudi.HoodieSparkSqlWriter$.write(HoodieSparkSqlWriter.scala:172)
at org.apache.hudi.DefaultSource.createRelation(DefaultSource.scala:162)
at
org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:45)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:86)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at
org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:80)
at
org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:80)
at
org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:676)
at
org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:676)
at
org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78)
at
org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73)
at
org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:676)
at
org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:285)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:271)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:229)
at
org.apache.hudi.functional.TestLayoutOptimization.testLayoutOptimizationFunctional(TestLayoutOptimization.scala:109)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at
org.junit.platform.commons.util.ReflectionUtils.invokeMethod(ReflectionUtils.java:688)
at
org.junit.jupiter.engine.execution.MethodInvocation.proceed(MethodInvocation.java:60)
at
org.junit.jupiter.engine.execution.InvocationInterceptorChain$ValidatingInvocation.proceed(InvocationInterceptorChain.java:131)
at
org.junit.jupiter.engine.extension.TimeoutExtension.intercept(TimeoutExtension.java:149)
at
org.junit.jupiter.engine.extension.TimeoutExtension.interceptTestableMethod(TimeoutExtension.java:140)
at
org.junit.jupiter.engine.extension.TimeoutExtension.interceptTestTemplateMethod(TimeoutExtension.java:92)
at
org.junit.jupiter.engine.execution.ExecutableInvoker$ReflectiveInterceptorCall.lambda$ofVoidMethod$0(ExecutableInvoker.java:115)
at
org.junit.jupiter.engine.execution.ExecutableInvoker.lambda$invoke$0(ExecutableInvoker.java:105)
at
org.junit.jupiter.engine.execution.InvocationInterceptorChain$InterceptedInvocation.proceed(InvocationInterceptorChain.java:106)
at
org.junit.jupiter.engine.execution.InvocationInterceptorChain.proceed(InvocationInterceptorChain.java:64)
at
org.junit.jupiter.engine.execution.InvocationInterceptorChain.chainAndInvoke(InvocationInterceptorChain.java:45)
at
org.junit.jupiter.engine.execution.InvocationInterceptorChain.invoke(InvocationInterceptorChain.java:37)
at
org.junit.jupiter.engine.execution.ExecutableInvoker.invoke(ExecutableInvoker.java:104)
at
org.junit.jupiter.engine.execution.ExecutableInvoker.invoke(ExecutableInvoker.java:98)
at
org.junit.jupiter.engine.descriptor.TestMethodTestDescriptor.lambda$invokeTestMethod$6(TestMethodTestDescriptor.java:212)
at
org.junit.platform.engine.support.hierarchical.ThrowableCollector.execute(ThrowableCollector.java:73)
at
org.junit.jupiter.engine.descriptor.TestMethodTestDescriptor.invokeTestMethod(TestMethodTestDescriptor.java:208)
at
org.junit.jupiter.engine.descriptor.TestMethodTestDescriptor.execute(TestMethodTestDescriptor.java:137)
at
org.junit.jupiter.engine.descriptor.TestMethodTestDescriptor.execute(TestMethodTestDescriptor.java:71)
at
org.junit.platform.engine.support.hierarchical.NodeTestTask.lambda$executeRecursively$5(NodeTestTask.java:139)
at
org.junit.platform.engine.support.hierarchical.ThrowableCollector.execute(ThrowableCollector.java:73)
at
org.junit.platform.engine.support.hierarchical.NodeTestTask.lambda$executeRecursively$7(NodeTestTask.java:129)
at
org.junit.platform.engine.support.hierarchical.Node.around(Node.java:137)
at
org.junit.platform.engine.support.hierarchical.NodeTestTask.lambda$executeRecursively$8(NodeTestTask.java:127)
at
org.junit.platform.engine.support.hierarchical.ThrowableCollector.execute(ThrowableCollector.java:73)
at
org.junit.platform.engine.support.hierarchical.NodeTestTask.executeRecursively(NodeTestTask.java:126)
at
org.junit.platform.engine.support.hierarchical.NodeTestTask.execute(NodeTestTask.java:84)
at
org.junit.platform.engine.support.hierarchical.SameThreadHierarchicalTestExecutorService.submit(SameThreadHierarchicalTestExecutorService.java:32)
at
org.junit.platform.engine.support.hierarchical.NodeTestTask$DefaultDynamicTestExecutor.execute(NodeTestTask.java:212)
at
org.junit.platform.engine.support.hierarchical.NodeTestTask$DefaultDynamicTestExecutor.execute(NodeTestTask.java:192)
at
org.junit.jupiter.engine.descriptor.TestTemplateTestDescriptor.execute(TestTemplateTestDescriptor.java:139)
at
org.junit.jupiter.engine.descriptor.TestTemplateTestDescriptor.lambda$execute$2(TestTemplateTestDescriptor.java:107)
at java.util.stream.ForEachOps$ForEachOp$OfRef.accept(ForEachOps.java:183)
at
java.util.stream.ReferencePipeline$3$1.accept(ReferencePipeline.java:193)
at
java.util.stream.ReferencePipeline$2$1.accept(ReferencePipeline.java:175)
at
java.util.stream.ReferencePipeline$3$1.accept(ReferencePipeline.java:193)
at java.util.stream.ForEachOps$ForEachOp$OfRef.accept(ForEachOps.java:183)
at
java.util.stream.ReferencePipeline$11$1.accept(ReferencePipeline.java:440)
at
java.util.stream.ReferencePipeline$3$1.accept(ReferencePipeline.java:193)
at
java.util.stream.ReferencePipeline$3$1.accept(ReferencePipeline.java:193)
at
java.util.stream.ReferencePipeline$3$1.accept(ReferencePipeline.java:193)
at java.util.stream.ForEachOps$ForEachOp$OfRef.accept(ForEachOps.java:183)
at
java.util.stream.ReferencePipeline$3$1.accept(ReferencePipeline.java:193)
at
java.util.Spliterators$ArraySpliterator.forEachRemaining(Spliterators.java:948)
at
java.util.stream.ReferencePipeline$Head.forEach(ReferencePipeline.java:647)
at
java.util.stream.ReferencePipeline$7$1.accept(ReferencePipeline.java:272)
at
java.util.stream.ReferencePipeline$3$1.accept(ReferencePipeline.java:193)
at
java.util.stream.ReferencePipeline$3$1.accept(ReferencePipeline.java:193)
at
java.util.Spliterators$ArraySpliterator.forEachRemaining(Spliterators.java:948)
at java.util.stream.AbstractPipeline.copyInto(AbstractPipeline.java:482)
at
java.util.stream.AbstractPipeline.wrapAndCopyInto(AbstractPipeline.java:472)
at
java.util.stream.ForEachOps$ForEachOp.evaluateSequential(ForEachOps.java:150)
at
java.util.stream.ForEachOps$ForEachOp$OfRef.evaluateSequential(ForEachOps.java:173)
at java.util.stream.AbstractPipeline.evaluate(AbstractPipeline.java:234)
at java.util.stream.ReferencePipeline.forEach(ReferencePipeline.java:485)
at
java.util.stream.ReferencePipeline$7$1.accept(ReferencePipeline.java:272)
at
java.util.stream.ReferencePipeline$3$1.accept(ReferencePipeline.java:193)
at
java.util.stream.ReferencePipeline$3$1.accept(ReferencePipeline.java:193)
at
java.util.stream.ReferencePipeline$3$1.accept(ReferencePipeline.java:193)
at
java.util.ArrayList$ArrayListSpliterator.forEachRemaining(ArrayList.java:1384)
at java.util.stream.AbstractPipeline.copyInto(AbstractPipeline.java:482)
at
java.util.stream.AbstractPipeline.wrapAndCopyInto(AbstractPipeline.java:472)
at
java.util.stream.ForEachOps$ForEachOp.evaluateSequential(ForEachOps.java:150)
at
java.util.stream.ForEachOps$ForEachOp$OfRef.evaluateSequential(ForEachOps.java:173)
at java.util.stream.AbstractPipeline.evaluate(AbstractPipeline.java:234)
at java.util.stream.ReferencePipeline.forEach(ReferencePipeline.java:485)
at
java.util.stream.ReferencePipeline$7$1.accept(ReferencePipeline.java:272)
at
java.util.ArrayList$ArrayListSpliterator.forEachRemaining(ArrayList.java:1384)
at java.util.stream.AbstractPipeline.copyInto(AbstractPipeline.java:482)
at
java.util.stream.AbstractPipeline.wrapAndCopyInto(AbstractPipeline.java:472)
at
java.util.stream.ForEachOps$ForEachOp.evaluateSequential(ForEachOps.java:150)
at
java.util.stream.ForEachOps$ForEachOp$OfRef.evaluateSequential(ForEachOps.java:173)
at java.util.stream.AbstractPipeline.evaluate(AbstractPipeline.java:234)
at java.util.stream.ReferencePipeline.forEach(ReferencePipeline.java:485)
at
org.junit.jupiter.engine.descriptor.TestTemplateTestDescriptor.execute(TestTemplateTestDescriptor.java:107)
at
org.junit.jupiter.engine.descriptor.TestTemplateTestDescriptor.execute(TestTemplateTestDescriptor.java:42)
at
org.junit.platform.engine.support.hierarchical.NodeTestTask.lambda$executeRecursively$5(NodeTestTask.java:139)
at
org.junit.platform.engine.support.hierarchical.ThrowableCollector.execute(ThrowableCollector.java:73)
at
org.junit.platform.engine.support.hierarchical.NodeTestTask.lambda$executeRecursively$7(NodeTestTask.java:129)
at
org.junit.platform.engine.support.hierarchical.Node.around(Node.java:137)
at
org.junit.platform.engine.support.hierarchical.NodeTestTask.lambda$executeRecursively$8(NodeTestTask.java:127)
at
org.junit.platform.engine.support.hierarchical.ThrowableCollector.execute(ThrowableCollector.java:73)
at
org.junit.platform.engine.support.hierarchical.NodeTestTask.executeRecursively(NodeTestTask.java:126)
at
org.junit.platform.engine.support.hierarchical.NodeTestTask.execute(NodeTestTask.java:84)
at java.util.ArrayList.forEach(ArrayList.java:1259)
at
org.junit.platform.engine.support.hierarchical.SameThreadHierarchicalTestExecutorService.invokeAll(SameThreadHierarchicalTestExecutorService.java:38)
at
org.junit.platform.engine.support.hierarchical.NodeTestTask.lambda$executeRecursively$5(NodeTestTask.java:143)
at
org.junit.platform.engine.support.hierarchical.ThrowableCollector.execute(ThrowableCollector.java:73)
at
org.junit.platform.engine.support.hierarchical.NodeTestTask.lambda$executeRecursively$7(NodeTestTask.java:129)
at
org.junit.platform.engine.support.hierarchical.Node.around(Node.java:137)
at
org.junit.platform.engine.support.hierarchical.NodeTestTask.lambda$executeRecursively$8(NodeTestTask.java:127)
at
org.junit.platform.engine.support.hierarchical.ThrowableCollector.execute(ThrowableCollector.java:73)
at
org.junit.platform.engine.support.hierarchical.NodeTestTask.executeRecursively(NodeTestTask.java:126)
at
org.junit.platform.engine.support.hierarchical.NodeTestTask.execute(NodeTestTask.java:84)
at java.util.ArrayList.forEach(ArrayList.java:1259)
at
org.junit.platform.engine.support.hierarchical.SameThreadHierarchicalTestExecutorService.invokeAll(SameThreadHierarchicalTestExecutorService.java:38)
at
org.junit.platform.engine.support.hierarchical.NodeTestTask.lambda$executeRecursively$5(NodeTestTask.java:143)
at
org.junit.platform.engine.support.hierarchical.ThrowableCollector.execute(ThrowableCollector.java:73)
at
org.junit.platform.engine.support.hierarchical.NodeTestTask.lambda$executeRecursively$7(NodeTestTask.java:129)
at
org.junit.platform.engine.support.hierarchical.Node.around(Node.java:137)
at
org.junit.platform.engine.support.hierarchical.NodeTestTask.lambda$executeRecursively$8(NodeTestTask.java:127)
at
org.junit.platform.engine.support.hierarchical.ThrowableCollector.execute(ThrowableCollector.java:73)
at
org.junit.platform.engine.support.hierarchical.NodeTestTask.executeRecursively(NodeTestTask.java:126)
at
org.junit.platform.engine.support.hierarchical.NodeTestTask.execute(NodeTestTask.java:84)
at
org.junit.platform.engine.support.hierarchical.SameThreadHierarchicalTestExecutorService.submit(SameThreadHierarchicalTestExecutorService.java:32)
at
org.junit.platform.engine.support.hierarchical.HierarchicalTestExecutor.execute(HierarchicalTestExecutor.java:57)
at
org.junit.platform.engine.support.hierarchical.HierarchicalTestEngine.execute(HierarchicalTestEngine.java:51)
at
org.junit.platform.launcher.core.EngineExecutionOrchestrator.execute(EngineExecutionOrchestrator.java:107)
at
org.junit.platform.launcher.core.EngineExecutionOrchestrator.execute(EngineExecutionOrchestrator.java:87)
at
org.junit.platform.launcher.core.EngineExecutionOrchestrator.lambda$execute$0(EngineExecutionOrchestrator.java:53)
at
org.junit.platform.launcher.core.EngineExecutionOrchestrator.withInterceptedStreams(EngineExecutionOrchestrator.java:66)
at
org.junit.platform.launcher.core.EngineExecutionOrchestrator.execute(EngineExecutionOrchestrator.java:51)
at
org.junit.platform.launcher.core.DefaultLauncher.execute(DefaultLauncher.java:87)
at
org.junit.platform.launcher.core.DefaultLauncher.execute(DefaultLauncher.java:75)
at org.junit.platform.runner.JUnitPlatform.run(JUnitPlatform.java:139)
at org.junit.runners.Suite.runChild(Suite.java:128)
at org.junit.runners.Suite.runChild(Suite.java:27)
at org.junit.runners.ParentRunner$4.run(ParentRunner.java:331)
at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:79)
at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:329)
at org.junit.runners.ParentRunner.access$100(ParentRunner.java:66)
at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:293)
at org.junit.runners.ParentRunner$3.evaluate(ParentRunner.java:306)
at org.junit.runners.ParentRunner.run(ParentRunner.java:413)
at org.apache.maven.surefire.junitcore.JUnitCore.run(JUnitCore.java:55)
at
org.apache.maven.surefire.junitcore.JUnitCoreWrapper.createRequestAndRun(JUnitCoreWrapper.java:137)
at
org.apache.maven.surefire.junitcore.JUnitCoreWrapper.executeEager(JUnitCoreWrapper.java:107)
at
org.apache.maven.surefire.junitcore.JUnitCoreWrapper.execute(JUnitCoreWrapper.java:83)
at
org.apache.maven.surefire.junitcore.JUnitCoreWrapper.execute(JUnitCoreWrapper.java:75)
at
org.apache.maven.surefire.junitcore.JUnitCoreProvider.invoke(JUnitCoreProvider.java:158)
at
org.apache.maven.surefire.booter.ForkedBooter.runSuitesInProcess(ForkedBooter.java:377)
at
org.apache.maven.surefire.booter.ForkedBooter.execute(ForkedBooter.java:138)
at org.apache.maven.surefire.booter.ForkedBooter.run(ForkedBooter.java:465)
at
org.apache.maven.surefire.booter.ForkedBooter.main(ForkedBooter.java:451)
Caused by: org.apache.hudi.exception.HoodieException:
org.apache.spark.SparkException: Task not serializable
at
org.apache.hudi.internal.DataSourceInternalWriterHelper.commit(DataSourceInternalWriterHelper.java:86)
at
org.apache.hudi.internal.HoodieDataSourceInternalWriter.commit(HoodieDataSourceInternalWriter.java:94)
at
org.apache.spark.sql.execution.datasources.v2.WriteToDataSourceV2Exec.doExecute(WriteToDataSourceV2Exec.scala:76)
... 178 more
Suppressed: org.apache.hudi.exception.HoodieRollbackException: Failed to
rollback /tmp/junit33047877808134846/dataset commits 20220311022937642
at
org.apache.hudi.client.BaseHoodieWriteClient.rollback(BaseHoodieWriteClient.java:695)
at
org.apache.hudi.client.BaseHoodieWriteClient.rollback(BaseHoodieWriteClient.java:651)
at
org.apache.hudi.internal.DataSourceInternalWriterHelper.abort(DataSourceInternalWriterHelper.java:94)
at
org.apache.hudi.internal.HoodieDataSourceInternalWriter.abort(HoodieDataSourceInternalWriter.java:99)
at
org.apache.spark.sql.execution.datasources.v2.WriteToDataSourceV2Exec.doExecute(WriteToDataSourceV2Exec.scala:82)
... 178 more
Caused by: java.lang.IllegalArgumentException: Cannot use marker based
rollback strategy on completed
instant:[20220311022937642__deltacommit__COMPLETED]
at
org.apache.hudi.common.util.ValidationUtils.checkArgument(ValidationUtils.java:40)
at
org.apache.hudi.table.action.rollback.BaseRollbackActionExecutor.<init>(BaseRollbackActionExecutor.java:90)
at
org.apache.hudi.table.action.rollback.BaseRollbackActionExecutor.<init>(BaseRollbackActionExecutor.java:71)
at
org.apache.hudi.table.action.rollback.MergeOnReadRollbackActionExecutor.<init>(MergeOnReadRollbackActionExecutor.java:48)
at
org.apache.hudi.table.HoodieSparkMergeOnReadTable.rollback(HoodieSparkMergeOnReadTable.java:172)
at
org.apache.hudi.client.BaseHoodieWriteClient.rollback(BaseHoodieWriteClient.java:680)
... 182 more
Caused by: java.util.concurrent.CompletionException:
org.apache.spark.SparkException: Task not serializable
at
java.util.concurrent.CompletableFuture.encodeThrowable(CompletableFuture.java:273)
at
java.util.concurrent.CompletableFuture.completeThrowable(CompletableFuture.java:280)
at
java.util.concurrent.CompletableFuture$AsyncSupply.run(CompletableFuture.java:1606)
at java.lang.Thread.run(Thread.java:750)
Caused by: org.apache.spark.SparkException: Task not serializable
at
org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:403)
at
org.apache.spark.util.ClosureCleaner$.org$apache$spark$util$ClosureCleaner$$clean(ClosureCleaner.scala:393)
at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:162)
at org.apache.spark.SparkContext.clean(SparkContext.scala:2326)
at org.apache.spark.rdd.RDD$$anonfun$map$1.apply(RDD.scala:371)
at org.apache.spark.rdd.RDD$$anonfun$map$1.apply(RDD.scala:370)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:363)
at org.apache.spark.rdd.RDD.map(RDD.scala:370)
at org.apache.spark.api.java.JavaRDDLike$class.map(JavaRDDLike.scala:93)
at org.apache.spark.api.java.AbstractJavaRDDLike.map(JavaRDDLike.scala:45)
at
org.apache.hudi.client.clustering.run.strategy.MultipleSparkJobExecutionStrategy.readRecordsForGroupBaseFiles(MultipleSparkJobExecutionStrategy.java:269)
at
org.apache.hudi.client.clustering.run.strategy.MultipleSparkJobExecutionStrategy.readRecordsForGroup(MultipleSparkJobExecutionStrategy.java:191)
at
org.apache.hudi.client.clustering.run.strategy.MultipleSparkJobExecutionStrategy.lambda$runClusteringForGroupAsync$4(MultipleSparkJobExecutionStrategy.java:171)
at
java.util.concurrent.CompletableFuture$AsyncSupply.run(CompletableFuture.java:1604)
... 1 more
Caused by: java.util.ConcurrentModificationException
at
java.util.LinkedHashMap$LinkedHashIterator.nextNode(LinkedHashMap.java:719)
at java.util.LinkedHashMap$LinkedKeyIterator.next(LinkedHashMap.java:742)
at java.util.HashSet.writeObject(HashSet.java:287)
at sun.reflect.GeneratedMethodAccessor19.invoke(Unknown Source)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at java.io.ObjectStreamClass.invokeWriteObject(ObjectStreamClass.java:1154)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1496)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.writeArray(ObjectOutputStream.java:1378)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1174)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:348)
at
org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:43)
at
org.apache.spark.serializer.JavaSerializerInstance.serialize(JavaSerializer.scala:100)
at
org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:400)
... 16 more {code}
was (Author: JIRAUSER279853):
{code:java}
at
org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:403)
at
org.apache.spark.util.ClosureCleaner$.org$apache$spark$util$ClosureCleaner$$clean(ClosureCleaner.scala:393)
at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:162)
at org.apache.spark.SparkContext.clean(SparkContext.scala:2326)
at org.apache.spark.rdd.RDD$$anonfun$map$1.apply(RDD.scala:371)
at org.apache.spark.rdd.RDD$$anonfun$map$1.apply(RDD.scala:370)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:363)
at org.apache.spark.rdd.RDD.map(RDD.scala:370)
at org.apache.spark.api.java.JavaRDDLike$class.map(JavaRDDLike.scala:93)
at
org.apache.spark.api.java.AbstractJavaRDDLike.map(JavaRDDLike.scala:45)
at
org.apache.hudi.client.clustering.run.strategy.MultipleSparkJobExecutionStrategy.readRecordsForGroupBaseFiles(MultipleSparkJobExecutionStrategy.java:269)
at
org.apache.hudi.client.clustering.run.strategy.MultipleSparkJobExecutionStrategy.readRecordsForGroup(MultipleSparkJobExecutionStrategy.java:191)
at
org.apache.hudi.client.clustering.run.strategy.MultipleSparkJobExecutionStrategy.lambda$runClusteringForGroupAsync$4(MultipleSparkJobExecutionStrategy.java:171)
at
java.util.concurrent.CompletableFuture$AsyncSupply.run(CompletableFuture.java:1604)
... 1 more
Caused by: java.util.ConcurrentModificationException
at
java.util.LinkedHashMap$LinkedHashIterator.nextNode(LinkedHashMap.java:719)
at
java.util.LinkedHashMap$LinkedKeyIterator.next(LinkedHashMap.java:742)
at java.util.HashSet.writeObject(HashSet.java:287)
at sun.reflect.GeneratedMethodAccessor19.invoke(Unknown Source)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at
java.io.ObjectStreamClass.invokeWriteObject(ObjectStreamClass.java:1154)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1496)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.writeArray(ObjectOutputStream.java:1378)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1174)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:348)
at
org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:43)
at
org.apache.spark.serializer.JavaSerializerInstance.serialize(JavaSerializer.scala:100)
at
org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:400)
... 16 more
{code}
> AsyncClustering failed because of ConcurrentModificationException
> -----------------------------------------------------------------
>
> Key: HUDI-3593
> URL: https://issues.apache.org/jira/browse/HUDI-3593
> Project: Apache Hudi
> Issue Type: Bug
> Reporter: Hui An
> Assignee: Hui An
> Priority: Major
> Labels: pull-request-available
> Attachments: Screen Shot 2022-03-10 at 9.53.13 AM.png
>
>
> Following is the stacktrace I met,
> {code:java}
> ERROR AsyncClusteringService: Clustering executor failed
> java.util.concurrent.CompletionException: org.apache.spark.SparkException:
> Task not serializable
> at
> java.util.concurrent.CompletableFuture.encodeThrowable(CompletableFuture.java:273)
>
> at
> java.util.concurrent.CompletableFuture.completeThrowable(CompletableFuture.java:280)
>
> at
> java.util.concurrent.CompletableFuture$AsyncSupply.run(CompletableFuture.java:1606)
>
> at
> java.util.concurrent.CompletableFuture$AsyncSupply.exec(CompletableFuture.java:1596)
>
> at java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:289)
> at
> java.util.concurrent.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1056)
> at java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1692)
> at
> java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:157)
> Caused by: org.apache.spark.SparkException: Task not serializable
> at
> org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:416)
>
> at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:406)
> at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:162)
> at org.apache.spark.SparkContext.clean(SparkContext.scala:2467)
> at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsWithIndex$1(RDD.scala:912)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
>
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
>
> at org.apache.spark.rdd.RDD.withScope(RDD.scala:414)
> at org.apache.spark.rdd.RDD.mapPartitionsWithIndex(RDD.scala:911)
> at
> org.apache.spark.api.java.JavaRDDLike.mapPartitionsWithIndex(JavaRDDLike.scala:103)
>
> at
> org.apache.spark.api.java.JavaRDDLike.mapPartitionsWithIndex$(JavaRDDLike.scala:99)
>
> at
> org.apache.spark.api.java.AbstractJavaRDDLike.mapPartitionsWithIndex(JavaRDDLike.scala:45)
>
> at
> org.apache.hudi.table.action.commit.SparkBulkInsertHelper.bulkInsert(SparkBulkInsertHelper.java:115)
>
> at
> org.apache.hudi.client.clustering.run.strategy.SparkSortAndSizeExecutionStrategy.performClusteringWithRecordsRDD(SparkSortAndSizeExecutionStrategy.java:68)
>
> at
> org.apache.hudi.client.clustering.run.strategy.MultipleSparkJobExecutionStrategy.lambda$runClusteringForGroupAsync$4(MultipleSparkJobExecutionStrategy.java:175)
>
> at
> java.util.concurrent.CompletableFuture$AsyncSupply.run(CompletableFuture.java:1604)
> ... 5 more
> Caused by: java.util.ConcurrentModificationException
> at
> java.util.LinkedHashMap$LinkedHashIterator.nextNode(LinkedHashMap.java:719)
> at java.util.LinkedHashMap$LinkedKeyIterator.next(LinkedHashMap.java:742)
> at java.util.HashSet.writeObject(HashSet.java:287)
> at sun.reflect.GeneratedMethodAccessor54.invoke(Unknown Source)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
>
> at java.lang.reflect.Method.invoke(Method.java:498)
> at java.io.ObjectStreamClass.invokeWriteObject(ObjectStreamClass.java:1140)
> at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1496)
> at
> java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
> at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
> at
> java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
> at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
> at
> java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
> at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
> at
> java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
> at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
> at
> java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
> at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
> at
> java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
> at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
> at
> java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
> at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
> at
> java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
> at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
> at
> java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
> at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
> at java.io.ObjectOutputStream.writeArray(ObjectOutputStream.java:1378)
> at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1174)
> at
> java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
> at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
> at
> java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
> at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
> at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:348)
> at
> org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:44)
>
> at org.apache.spark.serializer.JavaSerializerInstance
> {code}
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
