Jason Dere created HIVE-11028:
---------------------------------
Summary: Tez: table self join and join with another table fails
with IndexOutOfBoundsException
Key: HIVE-11028
URL: https://issues.apache.org/jira/browse/HIVE-11028
Project: Hive
Issue Type: Bug
Components: Query Planning
Reporter: Jason Dere
Assignee: Jason Dere
{noformat}
create table tez_self_join1(id1 int, id2 string, id3 string);
insert into table tez_self_join1 values(1, 'aa','bb'), (2, 'ab','ab'),
(3,'ba','ba');
create table tez_self_join2(id1 int);
insert into table tez_self_join2 values(1),(2),(3);
explain
select s.id2, s.id3
from
(
select self1.id1, self1.id2, self1.id3
from tez_self_join1 self1 join tez_self_join1 self2
on self1.id2=self2.id3 ) s
join tez_self_join2
on s.id1=tez_self_join2.id1
where s.id2='ab';
{noformat}
fails with error:
{noformat}
2015-06-16 15:41:55,759 ERROR [main]: ql.Driver
(SessionState.java:printError(979)) - FAILED: Execution Error, return code 2
from org.apache.hadoop.hive.ql.exec.tez.TezTask. Vertex failed,
vertexName=Reducer 3, vertexId=vertex_1434494327112_0002_4_04,
diagnostics=[Task failed, taskId=task_1434494327112_0002_4_04_000000,
diagnostics=[TaskAttempt 0 failed, info=[Error: Failure while running
task:java.lang.RuntimeException: java.lang.IndexOutOfBoundsException: Index: 0,
Size: 0
at
org.apache.hadoop.hive.ql.exec.tez.TezProcessor.initializeAndRunProcessor(TezProcessor.java:171)
at
org.apache.hadoop.hive.ql.exec.tez.TezProcessor.run(TezProcessor.java:137)
at
org.apache.tez.runtime.LogicalIOProcessorRuntimeTask.run(LogicalIOProcessorRuntimeTask.java:324)
at
org.apache.tez.runtime.task.TezTaskRunner$TaskRunnerCallable$1.run(TezTaskRunner.java:176)
at
org.apache.tez.runtime.task.TezTaskRunner$TaskRunnerCallable$1.run(TezTaskRunner.java:168)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:415)
at
org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1628)
at
org.apache.tez.runtime.task.TezTaskRunner$TaskRunnerCallable.call(TezTaskRunner.java:168)
at
org.apache.tez.runtime.task.TezTaskRunner$TaskRunnerCallable.call(TezTaskRunner.java:163)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:744)
Caused by: java.lang.IndexOutOfBoundsException: Index: 0, Size: 0
at java.util.ArrayList.rangeCheck(ArrayList.java:635)
at java.util.ArrayList.get(ArrayList.java:411)
at
org.apache.hadoop.hive.serde2.objectinspector.StandardStructObjectInspector.init(StandardStructObjectInspector.java:118)
at
org.apache.hadoop.hive.serde2.objectinspector.StandardStructObjectInspector.<init>(StandardStructObjectInspector.java:109)
at
org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorFactory.getStandardStructObjectInspector(ObjectInspectorFactory.java:290)
at
org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorFactory.getStandardStructObjectInspector(ObjectInspectorFactory.java:275)
at
org.apache.hadoop.hive.ql.exec.CommonJoinOperator.getJoinOutputObjectInspector(CommonJoinOperator.java:175)
at
org.apache.hadoop.hive.ql.exec.CommonJoinOperator.initializeOp(CommonJoinOperator.java:313)
at
org.apache.hadoop.hive.ql.exec.AbstractMapJoinOperator.initializeOp(AbstractMapJoinOperator.java:71)
at
org.apache.hadoop.hive.ql.exec.CommonMergeJoinOperator.initializeOp(CommonMergeJoinOperator.java:99)
at org.apache.hadoop.hive.ql.exec.Operator.initialize(Operator.java:362)
at
org.apache.hadoop.hive.ql.exec.tez.ReduceRecordProcessor.init(ReduceRecordProcessor.java:146)
at
org.apache.hadoop.hive.ql.exec.tez.TezProcessor.initializeAndRunProcessor(TezProcessor.java:147)
... 13 more
{noformat}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
