[
https://issues.apache.org/jira/browse/HIVE-20990?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Yi Zhang updated HIVE-20990:
----------------------------
Summary: ORC case when/if with coalesce wrong results or case:
java.lang.AssertionError: Output column number expected to be 0 when
isRepeating (was: ORC, group by, case: java.lang.AssertionError: Output column
number expected to be 0 when isRepeating)
> ORC case when/if with coalesce wrong results or case:
> java.lang.AssertionError: Output column number expected to be 0 when
> isRepeating
> --------------------------------------------------------------------------------------------------------------------------------------
>
> Key: HIVE-20990
> URL: https://issues.apache.org/jira/browse/HIVE-20990
> Project: Hive
> Issue Type: Bug
> Components: Vectorization
> Affects Versions: 3.0.0, 3.1.3
> Environment: * Hive 3.0.0 from hdp 3.0.1.
> * centos 7
> * 5 datanodes, 2 masters
>
> Reporter: Guillaume
> Priority: Major
> Labels: duplicate
>
> Run this to replicate:
> {code:sql}
> drop table if exists ds;
> create table ds stored as orc as select
> inline(array(
> struct('gmail.com'), -- when branch of the case statement
> struct('apache.org') -- else branch of the case statement
> )) as (domain)
> ;
> select
> case
> when domain='gmail.com' then 'gmail'
> else coalesce(domain, 'other')
> end as domaingroup
> from ds
> group by 1 -- useless (datawise) for this example, but triggers the bug.
> ;
> {code}
> Exceptions out with:
> {noformat}
> java.lang.RuntimeException: java.lang.AssertionError: Output column number
> expected to be 0 when isRepeating
> {noformat}
>
> Full exception is shown below.
> Of interest:
> * if the case is removed (eg. replaced only by the else clause), the query
> works,
> * if only the else clause from the case matches, the query works,
> * replacing the case by a bunch of nested if does not change anything,
> * removing the group by and the query works,
> * replacing the table (ds) by a CTE and the query works.
> Workaround, at the cost of performance:
> {code:java}
> set hive.vectorized.execution.enabled = false;
> {code}
>
> Full exception:
> {noformat}
> ERROR : FAILED: Execution Error, return code 2 from
> org.apache.hadoop.hive.ql.exec.tez.TezTask. Vertex failed, vertexName=Map 1,
> vertexId=vertex_1543326624484_8258_45_00, diagnostics=[Task failed,
> taskId=task_1543326624484_8258_45_00_000000, diagnostics=[TaskAttempt 0
> failed, info=[Error: Error while running task ( failure ) :
> java.lang.RuntimeException: java.lang.AssertionError: Output column number
> expected to be 0 when isRepeating
> at
> org.apache.hadoop.hive.ql.exec.tez.MapRecordSource.processRow(MapRecordSource.java:101)
> at
> org.apache.hadoop.hive.ql.exec.tez.MapRecordSource.pushRecord(MapRecordSource.java:76)
> at
> org.apache.hadoop.hive.ql.exec.tez.MapRecordProcessor.run(MapRecordProcessor.java:419)
> at
> org.apache.hadoop.hive.ql.exec.tez.TezProcessor.initializeAndRunProcessor(TezProcessor.java:267)
> at
> org.apache.hadoop.hive.ql.exec.tez.TezProcessor.run(TezProcessor.java:250)
> at
> org.apache.tez.runtime.LogicalIOProcessorRuntimeTask.run(LogicalIOProcessorRuntimeTask.java:374)
> at
> org.apache.tez.runtime.task.TaskRunner2Callable$1.run(TaskRunner2Callable.java:73)
> at
> org.apache.tez.runtime.task.TaskRunner2Callable$1.run(TaskRunner2Callable.java:61)
> at java.security.AccessController.doPrivileged(Native Method)
> at javax.security.auth.Subject.doAs(Subject.java:422)
> at
> org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1730)
> at
> org.apache.tez.runtime.task.TaskRunner2Callable.callInternal(TaskRunner2Callable.java:61)
> at
> org.apache.tez.runtime.task.TaskRunner2Callable.callInternal(TaskRunner2Callable.java:37)
> at org.apache.tez.common.CallableWithNdc.call(CallableWithNdc.java:36)
> at
> com.google.common.util.concurrent.TrustedListenableFutureTask$TrustedFutureInterruptibleTask.runInterruptibly(TrustedListenableFutureTask.java:108)
> at
> com.google.common.util.concurrent.InterruptibleTask.run(InterruptibleTask.java:41)
> at
> com.google.common.util.concurrent.TrustedListenableFutureTask.run(TrustedListenableFutureTask.java:77)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> Caused by: java.lang.AssertionError: Output column number expected to be 0
> when isRepeating
> at
> org.apache.hadoop.hive.ql.exec.vector.BytesColumnVector.setElement(BytesColumnVector.java:492)
> at
> org.apache.hadoop.hive.ql.exec.vector.expressions.IfExprColumnCondExpr.evaluate(IfExprColumnCondExpr.java:117)
> at
> org.apache.hadoop.hive.ql.exec.vector.VectorSelectOperator.process(VectorSelectOperator.java:146)
> at
> org.apache.hadoop.hive.ql.exec.Operator.vectorForward(Operator.java:965)
> at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:938)
> at
> org.apache.hadoop.hive.ql.exec.TableScanOperator.process(TableScanOperator.java:125)
> at
> org.apache.hadoop.hive.ql.exec.vector.VectorMapOperator.deliverVectorizedRowBatch(VectorMapOperator.java:812)
> at
> org.apache.hadoop.hive.ql.exec.vector.VectorMapOperator.process(VectorMapOperator.java:845)
> at
> org.apache.hadoop.hive.ql.exec.tez.MapRecordSource.processRow(MapRecordSource.java:92)
> ... 19 more
> , errorMessage=Cannot recover from this error:java.lang.RuntimeException:
> java.lang.AssertionError: Output column number expected to be 0 when
> isRepeating
> at
> org.apache.hadoop.hive.ql.exec.tez.MapRecordSource.processRow(MapRecordSource.java:101)
> at
> org.apache.hadoop.hive.ql.exec.tez.MapRecordSource.pushRecord(MapRecordSource.java:76)
> at
> org.apache.hadoop.hive.ql.exec.tez.MapRecordProcessor.run(MapRecordProcessor.java:419)
> at
> org.apache.hadoop.hive.ql.exec.tez.TezProcessor.initializeAndRunProcessor(TezProcessor.java:267)
> at
> org.apache.hadoop.hive.ql.exec.tez.TezProcessor.run(TezProcessor.java:250)
> at
> org.apache.tez.runtime.LogicalIOProcessorRuntimeTask.run(LogicalIOProcessorRuntimeTask.java:374)
> at
> org.apache.tez.runtime.task.TaskRunner2Callable$1.run(TaskRunner2Callable.java:73)
> at
> org.apache.tez.runtime.task.TaskRunner2Callable$1.run(TaskRunner2Callable.java:61)
> at java.security.AccessController.doPrivileged(Native Method)
> at javax.security.auth.Subject.doAs(Subject.java:422)
> at
> org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1730)
> at
> org.apache.tez.runtime.task.TaskRunner2Callable.callInternal(TaskRunner2Callable.java:61)
> at
> org.apache.tez.runtime.task.TaskRunner2Callable.callInternal(TaskRunner2Callable.java:37)
> at org.apache.tez.common.CallableWithNdc.call(CallableWithNdc.java:36)
> at
> com.google.common.util.concurrent.TrustedListenableFutureTask$TrustedFutureInterruptibleTask.runInterruptibly(TrustedListenableFutureTask.java:108)
> at
> com.google.common.util.concurrent.InterruptibleTask.run(InterruptibleTask.java:41)
> at
> com.google.common.util.concurrent.TrustedListenableFutureTask.run(TrustedListenableFutureTask.java:77)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> Caused by: java.lang.AssertionError: Output column number expected to be 0
> when isRepeating
> at
> org.apache.hadoop.hive.ql.exec.vector.BytesColumnVector.setElement(BytesColumnVector.java:492)
> at
> org.apache.hadoop.hive.ql.exec.vector.expressions.IfExprColumnCondExpr.evaluate(IfExprColumnCondExpr.java:117)
> at
> org.apache.hadoop.hive.ql.exec.vector.VectorSelectOperator.process(VectorSelectOperator.java:146)
> at
> org.apache.hadoop.hive.ql.exec.Operator.vectorForward(Operator.java:965)
> at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:938)
> at
> org.apache.hadoop.hive.ql.exec.TableScanOperator.process(TableScanOperator.java:125)
> at
> org.apache.hadoop.hive.ql.exec.vector.VectorMapOperator.deliverVectorizedRowBatch(VectorMapOperator.java:812)
> at
> org.apache.hadoop.hive.ql.exec.vector.VectorMapOperator.process(VectorMapOperator.java:845)
> at
> org.apache.hadoop.hive.ql.exec.tez.MapRecordSource.processRow(MapRecordSource.java:92)
> ... 19 more
> ]], Vertex did not succeed due to OWN_TASK_FAILURE, failedTasks:1
> killedTasks:0, Vertex vertex_1543326624484_8258_45_00 [Map 1] killed/failed
> due to:OWN_TASK_FAILURE]Vertex killed, vertexName=Reducer 2,
> vertexId=vertex_1543326624484_8258_45_01, diagnostics=[Vertex received Kill
> while in RUNNING state., Vertex did not succeed due to OTHER_VERTEX_FAILURE,
> failedTasks:0 killedTasks:2, Vertex vertex_1543326624484_8258_45_01 [Reducer
> 2] killed/failed due to:OTHER_VERTEX_FAILURE]DAG did not succeed due to
> VERTEX_FAILURE. failedVertices:1 killedVertices:1
> {noformat}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
