[
https://issues.apache.org/jira/browse/HIVE-8942?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14221735#comment-14221735
]
Szehon Ho commented on HIVE-8942:
---------------------------------
Committed to spark. Thanks Chao for contribution!
> Investigate test failure on skewjoin.q [Spark Branch]
> -----------------------------------------------------
>
> Key: HIVE-8942
> URL: https://issues.apache.org/jira/browse/HIVE-8942
> Project: Hive
> Issue Type: Sub-task
> Components: Spark
> Affects Versions: spark-branch
> Reporter: Chao
> Assignee: Chao
> Fix For: spark-branch
>
> Attachments: HIVE-8942.1-spark.patch
>
>
> This test is failing with exceptions.
> The query:
> {noformat}
> FROM T1 a JOIN src c ON c.key+1=a.key SELECT /*+ STREAMTABLE(a) */
> sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key));
> {noformat}
> throws following exception:
> {noformat}
> java.lang.RuntimeException: cannot find field val from [0:key, 1:value]
> at
> org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorUtils.getStandardStructFieldRef(ObjectInspectorUtils.java:410)
> at
> org.apache.hadoop.hive.serde2.BaseStructObjectInspector.getStructFieldRef(BaseStructObjectInspector.java:133)
> at
> org.apache.hadoop.hive.ql.exec.ExprNodeColumnEvaluator.initialize(ExprNodeColumnEvaluator.java:55)
> at
> org.apache.hadoop.hive.ql.exec.JoinUtil.getObjectInspectorsFromEvaluators(JoinUtil.java:68)
> at
> org.apache.hadoop.hive.ql.exec.CommonJoinOperator.initializeOp(CommonJoinOperator.java:221)
> at
> org.apache.hadoop.hive.ql.exec.AbstractMapJoinOperator.initializeOp(AbstractMapJoinOperator.java:72)
> at
> org.apache.hadoop.hive.ql.exec.MapJoinOperator.initializeOp(MapJoinOperator.java:96)
> at org.apache.hadoop.hive.ql.exec.Operator.initialize(Operator.java:385)
> at org.apache.hadoop.hive.ql.exec.Operator.initialize(Operator.java:469)
> at
> org.apache.hadoop.hive.ql.exec.Operator.initializeChildren(Operator.java:425)
> at
> org.apache.hadoop.hive.ql.exec.HashTableDummyOperator.initializeOp(HashTableDummyOperator.java:40)
> at org.apache.hadoop.hive.ql.exec.Operator.initialize(Operator.java:385)
> at
> org.apache.hadoop.hive.ql.exec.spark.SparkMapRecordHandler.init(SparkMapRecordHandler.java:127)
> at
> org.apache.hadoop.hive.ql.exec.spark.HiveMapFunction.call(HiveMapFunction.java:54)
> at
> org.apache.hadoop.hive.ql.exec.spark.HiveMapFunction.call(HiveMapFunction.java:29)
> at
> org.apache.spark.api.java.JavaRDDLike$$anonfun$fn$7$1.apply(JavaRDDLike.scala:167)
> at
> org.apache.spark.api.java.JavaRDDLike$$anonfun$fn$7$1.apply(JavaRDDLike.scala:167)
> at org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:601)
> at org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:601)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:263)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:230)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
> at org.apache.spark.scheduler.Task.run(Task.scala:56)
> at org.apache.spark.executor.Executor$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:745)
> {noformat}
> and the query:
> {noformat}
> FROM T1 a RIGHT OUTER JOIN T2 c ON c.key+1=a.key SELECT /*+ STREAMTABLE(a) */
> sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key));
> {noformat}
> throws following exception:
> {noformat}
> 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.AbstractMapJoinOperator.getValueObjectInspectors(AbstractMapJoinOperator.java:101)
> at
> org.apache.hadoop.hive.ql.exec.MapJoinOperator.getValueObjectInspectors(MapJoinOperator.java:128)
> at
> org.apache.hadoop.hive.ql.exec.CommonJoinOperator.getJoinOutputObjectInspector(CommonJoinOperator.java:167)
> at
> org.apache.hadoop.hive.ql.exec.CommonJoinOperator.initializeOp(CommonJoinOperator.java:310)
> at
> org.apache.hadoop.hive.ql.exec.AbstractMapJoinOperator.initializeOp(AbstractMapJoinOperator.java:72)
> at
> org.apache.hadoop.hive.ql.exec.MapJoinOperator.initializeOp(MapJoinOperator.java:96)
> at org.apache.hadoop.hive.ql.exec.Operator.initialize(Operator.java:385)
> at org.apache.hadoop.hive.ql.exec.Operator.initialize(Operator.java:469)
> at
> org.apache.hadoop.hive.ql.exec.Operator.initializeChildren(Operator.java:425)
> at
> org.apache.hadoop.hive.ql.exec.HashTableDummyOperator.initializeOp(HashTableDummyOperator.java:40)
> at org.apache.hadoop.hive.ql.exec.Operator.initialize(Operator.java:385)
> at
> org.apache.hadoop.hive.ql.exec.spark.SparkMapRecordHandler.init(SparkMapRecordHandler.java:127)
> at
> org.apache.hadoop.hive.ql.exec.spark.HiveMapFunction.call(HiveMapFunction.java:54)
> at
> org.apache.hadoop.hive.ql.exec.spark.HiveMapFunction.call(HiveMapFunction.java:29)
> at
> org.apache.spark.api.java.JavaRDDLike$$anonfun$fn$7$1.apply(JavaRDDLike.scala:167)
> at
> org.apache.spark.api.java.JavaRDDLike$$anonfun$fn$7$1.apply(JavaRDDLike.scala:167)
> at org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:601)
> at org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:601)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:263)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:230)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
> at org.apache.spark.scheduler.Task.run(Task.scala:56)
> at org.apache.spark.executor.Executor$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:745)
> {noformat}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
