[HIVE-8982] IndexOutOfBounds exception in mapjoin [Spark Branch]

• Type: Sub-task
• Status: Resolved
• Priority: Major
• Resolution: Fixed
• Affects Version/s: spark-branch
• Fix Version/s: 1.1.0
• Component/s: Spark
• Assignee: Chao Sun
• Reporter: Szehon Ho
• Created: 27/Nov/14 02:11
• Updated: 29/May/15 02:32
• Resolved: 13/Dec/14 15:32

Description

There are sometimes random failures in spark mapjoin during unit tests like:

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)

Issue Links

• is related to: HIVE-9094 TimeoutException when trying get executor count from RSC [Spark Branch]