[
https://issues.apache.org/jira/browse/HIVE-8982?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14245173#comment-14245173
]
Xuefu Zhang commented on HIVE-8982:
-----------------------------------
join25.q failed because:
{code}
2014-12-12 19:14:50,084 ERROR [main]: ql.Driver
(SessionState.java:printError(838)) - FAILED: SemanticException Failed to get
spark memory/core info: java.util.concurrent.TimeoutException
org.apache.hadoop.hive.ql.parse.SemanticException: Failed to get spark
memory/core info: java.util.concurrent.TimeoutException
at
org.apache.hadoop.hive.ql.optimizer.spark.SetSparkReducerParallelism.process(SetSparkReducerParallelism.java:120)
at
org.apache.hadoop.hive.ql.lib.DefaultRuleDispatcher.dispatch(DefaultRuleDispatcher.java:90)
at
org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.dispatchAndReturn(DefaultGraphWalker.java:94)
at
org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.dispatch(DefaultGraphWalker.java:78)
at
org.apache.hadoop.hive.ql.lib.ForwardWalker.walk(ForwardWalker.java:79)
at
org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.startWalking(DefaultGraphWalker.java:109)
at
org.apache.hadoop.hive.ql.parse.spark.SparkCompiler.optimizeOperatorPlan(SparkCompiler.java:134)
at
org.apache.hadoop.hive.ql.parse.TaskCompiler.compile(TaskCompiler.java:99)
at
org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:10202)
at
org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:221)
at
org.apache.hadoop.hive.ql.parse.ExplainSemanticAnalyzer.analyzeInternal(ExplainSemanticAnalyzer.java:74)
at
org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:221)
at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:420)
at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:306)
at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:1108)
at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1170)
at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1045)
at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1035)
at
org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:199)
at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:151)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:362)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:297)
at org.apache.hadoop.hive.ql.QTestUtil.executeClient(QTestUtil.java:837)
at
org.apache.hadoop.hive.cli.TestSparkCliDriver.runTest(TestSparkCliDriver.java:234)
at
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_join25(TestSparkCliDriver.java:162)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at junit.framework.TestCase.runTest(TestCase.java:176)
at junit.framework.TestCase.runBare(TestCase.java:141)
at junit.framework.TestResult$1.protect(TestResult.java:122)
at junit.framework.TestResult.runProtected(TestResult.java:142)
at junit.framework.TestResult.run(TestResult.java:125)
at junit.framework.TestCase.run(TestCase.java:129)
at junit.framework.TestSuite.runTest(TestSuite.java:255)
at junit.framework.TestSuite.run(TestSuite.java:250)
at
org.junit.internal.runners.JUnit38ClassRunner.run(JUnit38ClassRunner.java:84)
at
org.apache.maven.surefire.junit4.JUnit4Provider.execute(JUnit4Provider.java:264)
at
org.apache.maven.surefire.junit4.JUnit4Provider.executeTestSet(JUnit4Provider.java:153)
at
org.apache.maven.surefire.junit4.JUnit4Provider.invoke(JUnit4Provider.java:124)
at
org.apache.maven.surefire.booter.ForkedBooter.invokeProviderInSameClassLoader(ForkedBooter.java:200)
at
org.apache.maven.surefire.booter.ForkedBooter.runSuitesInProcess(ForkedBooter.java:153)
at
org.apache.maven.surefire.booter.ForkedBooter.main(ForkedBooter.java:103)
Caused by: java.util.concurrent.TimeoutException
at io.netty.util.concurrent.AbstractFuture.get(AbstractFuture.java:49)
at org.apache.hive.spark.client.JobHandleImpl.get(JobHandleImpl.java:74)
at org.apache.hive.spark.client.JobHandleImpl.get(JobHandleImpl.java:35)
at
org.apache.hadoop.hive.ql.exec.spark.RemoteHiveSparkClient.getExecutorCount(RemoteHiveSparkClient.java:92)
at
org.apache.hadoop.hive.ql.exec.spark.session.SparkSessionImpl.getMemoryAndCores(SparkSessionImpl.java:77)
at
org.apache.hadoop.hive.ql.optimizer.spark.SetSparkReducerParallelism.process(SetSparkReducerParallelism.java:118)
... 43 more
{code}
Chengxiang has a patch to fix this. On the other hand, I'm not sure why
ppd_join4.q and smb_mapjoin_25.q failed.
> IndexOutOfBounds exception in mapjoin [Spark Branch]
> ----------------------------------------------------
>
> Key: HIVE-8982
> URL: https://issues.apache.org/jira/browse/HIVE-8982
> Project: Hive
> Issue Type: Sub-task
> Components: Spark
> Affects Versions: spark-branch
> Reporter: Szehon Ho
> Assignee: Chao
> Attachments: HIVE-8982.1-spark.patch
>
>
> There are sometimes random failures in spark mapjoin during unit tests like:
> {noformat}
> org.apache.hadoop.hive.ql.metadata.HiveException:
> java.lang.IndexOutOfBoundsException: Index: 1, Size: 1
> at
> org.apache.hadoop.hive.ql.exec.SparkHashTableSinkOperator.closeOp(SparkHashTableSinkOperator.java:83)
> at org.apache.hadoop.hive.ql.exec.Operator.close(Operator.java:598)
> at org.apache.hadoop.hive.ql.exec.Operator.close(Operator.java:610)
> at org.apache.hadoop.hive.ql.exec.Operator.close(Operator.java:610)
> at org.apache.hadoop.hive.ql.exec.Operator.close(Operator.java:610)
> at
> org.apache.hadoop.hive.ql.exec.spark.SparkMapRecordHandler.close(SparkMapRecordHandler.java:185)
> at
> org.apache.hadoop.hive.ql.exec.spark.HiveMapFunctionResultList.closeRecordProcessor(HiveMapFunctionResultList.java:57)
> at
> org.apache.hadoop.hive.ql.exec.spark.HiveBaseFunctionResultList$ResultIterator.hasNext(HiveBaseFunctionResultList.java:108)
> at
> scala.collection.convert.Wrappers$JIteratorWrapper.hasNext(Wrappers.scala:41)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at
> org.apache.spark.rdd.AsyncRDDActions$$anonfun$foreachAsync$2.apply(AsyncRDDActions.scala:115)
> at
> org.apache.spark.rdd.AsyncRDDActions$$anonfun$foreachAsync$2.apply(AsyncRDDActions.scala:115)
> at
> org.apache.spark.SparkContext$$anonfun$30.apply(SparkContext.scala:1365)
> at
> org.apache.spark.SparkContext$$anonfun$30.apply(SparkContext.scala:1365)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
> at org.apache.spark.scheduler.Task.run(Task.scala:56)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:744)
> Caused by: java.lang.IndexOutOfBoundsException: Index: 1, Size: 1
> at java.util.ArrayList.rangeCheck(ArrayList.java:635)
> at java.util.ArrayList.get(ArrayList.java:411)
> at
> org.apache.hadoop.hive.ql.exec.persistence.MapJoinEagerRowContainer.first(MapJoinEagerRowContainer.java:70)
> at
> org.apache.hadoop.hive.ql.exec.persistence.MapJoinEagerRowContainer.write(MapJoinEagerRowContainer.java:150)
> at
> org.apache.hadoop.hive.ql.exec.persistence.MapJoinTableContainerSerDe.persist(MapJoinTableContainerSerDe.java:167)
> at
> org.apache.hadoop.hive.ql.exec.SparkHashTableSinkOperator.flushToFile(SparkHashTableSinkOperator.java:128)
> at
> org.apache.hadoop.hive.ql.exec.SparkHashTableSinkOperator.closeOp(SparkHashTableSinkOperator.java:77)
> ... 20 more
> org.apache.hadoop.hive.ql.metadata.HiveException:
> java.lang.IndexOutOfBoundsException: Index: 1, Size: 1
> at
> org.apache.hadoop.hive.ql.exec.SparkHashTableSinkOperator.closeOp(SparkHashTableSinkOperator.java:83)
> at org.apache.hadoop.hive.ql.exec.Operator.close(Operator.java:598)
> at org.apache.hadoop.hive.ql.exec.Operator.close(Operator.java:610)
> at org.apache.hadoop.hive.ql.exec.Operator.close(Operator.java:610)
> at org.apache.hadoop.hive.ql.exec.Operator.close(Operator.java:610)
> at
> org.apache.hadoop.hive.ql.exec.spark.SparkMapRecordHandler.close(SparkMapRecordHandler.java:185)
> at
> org.apache.hadoop.hive.ql.exec.spark.HiveMapFunctionResultList.closeRecordProcessor(HiveMapFunctionResultList.java:57)
> at
> org.apache.hadoop.hive.ql.exec.spark.HiveBaseFunctionResultList$ResultIterator.hasNext(HiveBaseFunctionResultList.java:108)
> at
> scala.collection.convert.Wrappers$JIteratorWrapper.hasNext(Wrappers.scala:41)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at
> org.apache.spark.rdd.AsyncRDDActions$$anonfun$foreachAsync$2.apply(AsyncRDDActions.scala:115)
> at
> org.apache.spark.rdd.AsyncRDDActions$$anonfun$foreachAsync$2.apply(AsyncRDDActions.scala:115)
> at
> org.apache.spark.SparkContext$$anonfun$30.apply(SparkContext.scala:1365)
> at
> org.apache.spark.SparkContext$$anonfun$30.apply(SparkContext.scala:1365)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
> at org.apache.spark.scheduler.Task.run(Task.scala:56)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:744)
> Caused by: java.lang.IndexOutOfBoundsException: Index: 1, Size: 1
> at java.util.ArrayList.rangeCheck(ArrayList.java:635)
> at java.util.ArrayList.get(ArrayList.java:411)
> at
> org.apache.hadoop.hive.ql.exec.persistence.MapJoinEagerRowContainer.first(MapJoinEagerRowContainer.java:70)
> at
> org.apache.hadoop.hive.ql.exec.persistence.MapJoinEagerRowContainer.write(MapJoinEagerRowContainer.java:150)
> at
> org.apache.hadoop.hive.ql.exec.persistence.MapJoinTableContainerSerDe.persist(MapJoinTableContainerSerDe.java:167)
> at
> org.apache.hadoop.hive.ql.exec.SparkHashTableSinkOperator.flushToFile(SparkHashTableSinkOperator.java:128)
> at
> org.apache.hadoop.hive.ql.exec.SparkHashTableSinkOperator.closeOp(SparkHashTableSinkOperator.java:77)
> ... 20 more
> org.apache.hadoop.hive.ql.metadata.HiveException:
> java.lang.IndexOutOfBoundsException: Index: 1, Size: 1
> at
> org.apache.hadoop.hive.ql.exec.SparkHashTableSinkOperator.closeOp(SparkHashTableSinkOperator.java:83)
> at org.apache.hadoop.hive.ql.exec.Operator.close(Operator.java:598)
> at org.apache.hadoop.hive.ql.exec.Operator.close(Operator.java:610)
> at org.apache.hadoop.hive.ql.exec.Operator.close(Operator.java:610)
> at org.apache.hadoop.hive.ql.exec.Operator.close(Operator.java:610)
> at
> org.apache.hadoop.hive.ql.exec.spark.SparkMapRecordHandler.close(SparkMapRecordHandler.java:185)
> at
> org.apache.hadoop.hive.ql.exec.spark.HiveMapFunctionResultList.closeRecordProcessor(HiveMapFunctionResultList.java:57)
> at
> org.apache.hadoop.hive.ql.exec.spark.HiveBaseFunctionResultList$ResultIterator.hasNext(HiveBaseFunctionResultList.java:108)
> at
> scala.collection.convert.Wrappers$JIteratorWrapper.hasNext(Wrappers.scala:41)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at
> org.apache.spark.rdd.AsyncRDDActions$$anonfun$foreachAsync$2.apply(AsyncRDDActions.scala:115)
> at
> org.apache.spark.rdd.AsyncRDDActions$$anonfun$foreachAsync$2.apply(AsyncRDDActions.scala:115)
> at
> org.apache.spark.SparkContext$$anonfun$30.apply(SparkContext.scala:1365)
> at
> org.apache.spark.SparkContext$$anonfun$30.apply(SparkContext.scala:1365)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
> at org.apache.spark.scheduler.Task.run(Task.scala:56)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:744)
> Caused by: java.lang.IndexOutOfBoundsException: Index: 1, Size: 1
> at java.util.ArrayList.rangeCheck(ArrayList.java:635)
> at java.util.ArrayList.get(ArrayList.java:411)
> at
> org.apache.hadoop.hive.ql.exec.persistence.MapJoinEagerRowContainer.first(MapJoinEagerRowContainer.java:70)
> at
> org.apache.hadoop.hive.ql.exec.persistence.MapJoinEagerRowContainer.write(MapJoinEagerRowContainer.java:150)
> at
> org.apache.hadoop.hive.ql.exec.persistence.MapJoinTableContainerSerDe.persist(MapJoinTableContainerSerDe.java:167)
> at
> org.apache.hadoop.hive.ql.exec.SparkHashTableSinkOperator.flushToFile(SparkHashTableSinkOperator.java:128)
> at
> org.apache.hadoop.hive.ql.exec.SparkHashTableSinkOperator.closeOp(SparkHashTableSinkOperator.java:77)
> {noformat}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
