[
https://issues.apache.org/jira/browse/HIVE-20563?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Matt McCline updated HIVE-20563:
--------------------------------
Status: In Progress (was: Patch Available)
As Ashutosh suggested, changed gears and having the vectorization handle CASE
WHEN / IF data type conversion.
The native vectorized EXPLAIN VECTORIZATION shows the IfExprColumnCondExpr
vector expression being used. This good. It conditionally executes the new
data type conversion (i.e. CAST) only for the rows of the THEN/ELSE.
Fixing VectorUDFAdaptor usage to handle data type conversion has not started
yet... so this patch isn't complete.
> Vectorization: CASE WHEN expression fails when THEN/ELSE type and result type
> are different
> -------------------------------------------------------------------------------------------
>
> Key: HIVE-20563
> URL: https://issues.apache.org/jira/browse/HIVE-20563
> Project: Hive
> Issue Type: Bug
> Affects Versions: 4.0.0
> Reporter: Jesus Camacho Rodriguez
> Assignee: Matt McCline
> Priority: Major
> Attachments: HIVE-20563.01.patch, HIVE-20563.02.patch
>
>
> With the following stacktrace:
> {code}
> java.lang.Exception: java.lang.RuntimeException:
> org.apache.hadoop.hive.ql.metadata.HiveException: Hive Runtime Error while
> processing row
> at
> org.apache.hadoop.mapred.LocalJobRunner$Job.runTasks(LocalJobRunner.java:492)
> ~[hadoop-mapreduce-client-common-3.1.0.jar:?]
> at
> org.apache.hadoop.mapred.LocalJobRunner$Job.run(LocalJobRunner.java:552)
> [hadoop-mapreduce-client-common-3.1.0.jar:?]
> Caused by: java.lang.RuntimeException:
> org.apache.hadoop.hive.ql.metadata.HiveException: Hive Runtime Error while
> processing row
> at
> org.apache.hadoop.hive.ql.exec.mr.ExecMapper.map(ExecMapper.java:163)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at org.apache.hadoop.mapred.MapRunner.run(MapRunner.java:54)
> ~[hadoop-mapreduce-client-core-3.1.0.jar:?]
> at
> org.apache.hadoop.hive.ql.exec.mr.ExecMapRunner.run(ExecMapRunner.java:37)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at org.apache.hadoop.mapred.MapTask.runOldMapper(MapTask.java:465)
> ~[hadoop-mapreduce-client-core-3.1.0.jar:?]
> at org.apache.hadoop.mapred.MapTask.run(MapTask.java:349)
> ~[hadoop-mapreduce-client-core-3.1.0.jar:?]
> at
> org.apache.hadoop.mapred.LocalJobRunner$Job$MapTaskRunnable.run(LocalJobRunner.java:271)
> ~[hadoop-mapreduce-client-common-3.1.0.jar:?]
> at
> java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:511)
> ~[?:1.8.0_181]
> at java.util.concurrent.FutureTask.run(FutureTask.java:266)
> ~[?:1.8.0_181]
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
> ~[?:1.8.0_181]
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
> ~[?:1.8.0_181]
> at java.lang.Thread.run(Thread.java:748) ~[?:1.8.0_181]
> Caused by: org.apache.hadoop.hive.ql.metadata.HiveException: Hive Runtime
> Error while processing row
> at
> org.apache.hadoop.hive.ql.exec.vector.VectorMapOperator.process(VectorMapOperator.java:973)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.ql.exec.mr.ExecMapper.map(ExecMapper.java:154)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at org.apache.hadoop.mapred.MapRunner.run(MapRunner.java:54)
> ~[hadoop-mapreduce-client-core-3.1.0.jar:?]
> at
> org.apache.hadoop.hive.ql.exec.mr.ExecMapRunner.run(ExecMapRunner.java:37)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at org.apache.hadoop.mapred.MapTask.runOldMapper(MapTask.java:465)
> ~[hadoop-mapreduce-client-core-3.1.0.jar:?]
> at org.apache.hadoop.mapred.MapTask.run(MapTask.java:349)
> ~[hadoop-mapreduce-client-core-3.1.0.jar:?]
> at
> org.apache.hadoop.mapred.LocalJobRunner$Job$MapTaskRunnable.run(LocalJobRunner.java:271)
> ~[hadoop-mapreduce-client-common-3.1.0.jar:?]
> at
> java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:511)
> ~[?:1.8.0_181]
> at java.util.concurrent.FutureTask.run(FutureTask.java:266)
> ~[?:1.8.0_181]
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
> ~[?:1.8.0_181]
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
> ~[?:1.8.0_181]
> at java.lang.Thread.run(Thread.java:748) ~[?:1.8.0_181]
> Caused by: org.apache.hadoop.hive.ql.metadata.HiveException: Error evaluating
> cstring1
> at
> org.apache.hadoop.hive.ql.exec.vector.VectorSelectOperator.process(VectorSelectOperator.java:149)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.ql.exec.Operator.vectorForward(Operator.java:965)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:938)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.ql.exec.vector.VectorFilterOperator.process(VectorFilterOperator.java:136)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.ql.exec.Operator.vectorForward(Operator.java:965)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:938)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.ql.exec.TableScanOperator.process(TableScanOperator.java:125)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.ql.exec.vector.VectorMapOperator.deliverVectorizedRowBatch(VectorMapOperator.java:812)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.ql.exec.vector.VectorMapOperator.process(VectorMapOperator.java:845)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.ql.exec.mr.ExecMapper.map(ExecMapper.java:154)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at org.apache.hadoop.mapred.MapRunner.run(MapRunner.java:54)
> ~[hadoop-mapreduce-client-core-3.1.0.jar:?]
> at
> org.apache.hadoop.hive.ql.exec.mr.ExecMapRunner.run(ExecMapRunner.java:37)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at org.apache.hadoop.mapred.MapTask.runOldMapper(MapTask.java:465)
> ~[hadoop-mapreduce-client-core-3.1.0.jar:?]
> at org.apache.hadoop.mapred.MapTask.run(MapTask.java:349)
> ~[hadoop-mapreduce-client-core-3.1.0.jar:?]
> at
> org.apache.hadoop.mapred.LocalJobRunner$Job$MapTaskRunnable.run(LocalJobRunner.java:271)
> ~[hadoop-mapreduce-client-common-3.1.0.jar:?]
> at
> java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:511)
> ~[?:1.8.0_181]
> at java.util.concurrent.FutureTask.run(FutureTask.java:266)
> ~[?:1.8.0_181]
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
> ~[?:1.8.0_181]
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
> ~[?:1.8.0_181]
> at java.lang.Thread.run(Thread.java:748) ~[?:1.8.0_181]
> Caused by: java.lang.ClassCastException: org.apache.hadoop.io.FloatWritable
> cannot be cast to org.apache.hadoop.io.Text
> at
> org.apache.hadoop.hive.ql.exec.vector.VectorAssignRow.assignRowColumn(VectorAssignRow.java:471)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.ql.exec.vector.VectorAssignRow.assignRowColumn(VectorAssignRow.java:350)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.ql.exec.vector.udf.VectorUDFAdaptor.setResult(VectorUDFAdaptor.java:205)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.ql.exec.vector.udf.VectorUDFAdaptor.evaluate(VectorUDFAdaptor.java:146)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.ql.exec.vector.expressions.IfExprCondExprBase.conditionalEvaluate(IfExprCondExprBase.java:68)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.ql.exec.vector.expressions.IfExprColumnCondExpr.evaluate(IfExprColumnCondExpr.java:113)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.ql.exec.vector.VectorSelectOperator.process(VectorSelectOperator.java:146)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.ql.exec.Operator.vectorForward(Operator.java:965)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:938)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.ql.exec.vector.VectorFilterOperator.process(VectorFilterOperator.java:136)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.ql.exec.Operator.vectorForward(Operator.java:965)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:938)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.ql.exec.TableScanOperator.process(TableScanOperator.java:125)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.ql.exec.vector.VectorMapOperator.deliverVectorizedRowBatch(VectorMapOperator.java:812)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.ql.exec.vector.VectorMapOperator.process(VectorMapOperator.java:845)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at
> org.apache.hadoop.hive.ql.exec.mr.ExecMapper.map(ExecMapper.java:154)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at org.apache.hadoop.mapred.MapRunner.run(MapRunner.java:54)
> ~[hadoop-mapreduce-client-core-3.1.0.jar:?]
> at
> org.apache.hadoop.hive.ql.exec.mr.ExecMapRunner.run(ExecMapRunner.java:37)
> ~[hive-exec-4.0.0-SNAPSHOT.jar:4.0.0-SNAPSHOT]
> at org.apache.hadoop.mapred.MapTask.runOldMapper(MapTask.java:465)
> ~[hadoop-mapreduce-client-core-3.1.0.jar:?]
> at org.apache.hadoop.mapred.MapTask.run(MapTask.java:349)
> ~[hadoop-mapreduce-client-core-3.1.0.jar:?]
> at
> org.apache.hadoop.mapred.LocalJobRunner$Job$MapTaskRunnable.run(LocalJobRunner.java:271)
> ~[hadoop-mapreduce-client-common-3.1.0.jar:?]
> at
> java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:511)
> ~[?:1.8.0_181]
> ...
> {code}
> To repro:
> {code:sql}
> --! qt:dataset:alltypesorc
> set hive.stats.fetch.column.stats=true;
> set hive.explain.user=false;
> SET hive.vectorized.execution.enabled=true;
> set hive.fetch.task.conversion=none;
> -- SORT_QUERY_RESULTS
> EXPLAIN VECTORIZATION ONLY EXPRESSION SELECT cdouble, cstring1, cint, cfloat,
> csmallint,
> case
> when (cdouble is not null) then cdouble
> when (cstring1 is not null) then cstring1
> when (cint is not null) then cint
> when (cfloat is not null) then cfloat
> when (csmallint is not null) then csmallint
> else null
> end as c
> FROM alltypesorc
> WHERE (cdouble IS NULL)
> ORDER BY cdouble, cstring1, cint, cfloat, csmallint, c
> LIMIT 10;
> SELECT cdouble, cstring1, cint, cfloat, csmallint,
> case
> when (cdouble is not null) then cdouble
> when (cstring1 is not null) then cstring1
> when (cint is not null) then cint
> when (cfloat is not null) then cfloat
> when (csmallint is not null) then csmallint
> else null
> end as c
> FROM alltypesorc
> WHERE (cdouble IS NULL)
> ORDER BY cdouble, cstring1, cint, cfloat, csmallint, c
> LIMIT 10;
> {code}
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
