[
https://issues.apache.org/jira/browse/HIVE-27315?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
FangBO updated HIVE-27315:
--------------------------
Description:
Hive version:
{code:java}
2.3.9
3.1.2{code}
Table definition:
{code:java}
CREATE TABLE `t`(
`emplid` string COMMENT '',
`effdt` string COMMENT '',
`mar_status` string COMMENT ''); {code}
Query:
{code:java}
SELECT t1.emplid, t1.effdt, t2.mar_status
FROM (
SELECT emplid, max(effdt) AS effdt
FROM t
GROUP BY emplid
) t1
LEFT JOIN t t2
ON t1.emplid = t2.emplid
AND t1.effdt = t2.effdt; {code}
Exception stacktrace:
{code:java}
java.lang.NullPointerException
at
org.apache.hadoop.hive.ql.optimizer.DynamicPartitionPruningOptimization.generateSemiJoinOperatorPlan(DynamicPartitionPruningOptimization.java:463)
at
org.apache.hadoop.hive.ql.optimizer.DynamicPartitionPruningOptimization.process(DynamicPartitionPruningOptimization.java:226)
at
org.apache.hadoop.hive.ql.lib.DefaultRuleDispatcher.dispatch(DefaultRuleDispatcher.java:90)
at
org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.dispatchAndReturn(DefaultGraphWalker.java:105)
at
org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.dispatch(DefaultGraphWalker.java:89)
at
org.apache.hadoop.hive.ql.lib.ForwardWalker.walk(ForwardWalker.java:74)
at
org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.startWalking(DefaultGraphWalker.java:120)
at
org.apache.hadoop.hive.ql.parse.TezCompiler.runDynamicPartitionPruning(TezCompiler.java:370)
at
org.apache.hadoop.hive.ql.parse.TezCompiler.optimizeOperatorPlan(TezCompiler.java:94)
at
org.apache.hadoop.hive.ql.parse.TaskCompiler.compile(TaskCompiler.java:140)
at
org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:11273)
at
org.apache.hadoop.hive.ql.parse.CalcitePlanner.analyzeInternal(CalcitePlanner.java:286)
at
org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:258)
at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:512)
at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:1317)
at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1457)
at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1237)
at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1227)
at
org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:233) {code}
was:
Hive version:
{code:java}
2.3.9{code}
Table definition:
{code:java}
CREATE TABLE `t`(
`emplid` string COMMENT '',
`effdt` string COMMENT '',
`mar_status` string COMMENT ''); {code}
Query:
{code:java}
SELECT t1.emplid, t1.effdt, t2.mar_status
FROM (
SELECT emplid, max(effdt) AS effdt
FROM t
GROUP BY emplid
) t1
LEFT JOIN t t2
ON t1.emplid = t2.emplid
AND t1.effdt = t2.effdt; {code}
Exception stacktrace:
{code:java}
java.lang.NullPointerException
at
org.apache.hadoop.hive.ql.optimizer.DynamicPartitionPruningOptimization.generateSemiJoinOperatorPlan(DynamicPartitionPruningOptimization.java:463)
at
org.apache.hadoop.hive.ql.optimizer.DynamicPartitionPruningOptimization.process(DynamicPartitionPruningOptimization.java:226)
at
org.apache.hadoop.hive.ql.lib.DefaultRuleDispatcher.dispatch(DefaultRuleDispatcher.java:90)
at
org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.dispatchAndReturn(DefaultGraphWalker.java:105)
at
org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.dispatch(DefaultGraphWalker.java:89)
at
org.apache.hadoop.hive.ql.lib.ForwardWalker.walk(ForwardWalker.java:74)
at
org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.startWalking(DefaultGraphWalker.java:120)
at
org.apache.hadoop.hive.ql.parse.TezCompiler.runDynamicPartitionPruning(TezCompiler.java:370)
at
org.apache.hadoop.hive.ql.parse.TezCompiler.optimizeOperatorPlan(TezCompiler.java:94)
at
org.apache.hadoop.hive.ql.parse.TaskCompiler.compile(TaskCompiler.java:140)
at
org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:11273)
at
org.apache.hadoop.hive.ql.parse.CalcitePlanner.analyzeInternal(CalcitePlanner.java:286)
at
org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:258)
at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:512)
at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:1317)
at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1457)
at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1237)
at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1227)
at
org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:233) {code}
> DynamicPartitionPruningOptimization.generateSemiJoinOperatorPlan throws NPE
> when hive.tez.dynamic.semijoin.reduction=true
> -------------------------------------------------------------------------------------------------------------------------
>
> Key: HIVE-27315
> URL: https://issues.apache.org/jira/browse/HIVE-27315
> Project: Hive
> Issue Type: Bug
> Components: CBO, Tez
> Affects Versions: 2.3.9, 3.1.2
> Reporter: FangBO
> Priority: Major
>
> Hive version:
> {code:java}
> 2.3.9
> 3.1.2{code}
>
> Table definition:
> {code:java}
> CREATE TABLE `t`(
> `emplid` string COMMENT '',
> `effdt` string COMMENT '',
> `mar_status` string COMMENT ''); {code}
> Query:
> {code:java}
> SELECT t1.emplid, t1.effdt, t2.mar_status
> FROM (
> SELECT emplid, max(effdt) AS effdt
> FROM t
> GROUP BY emplid
> ) t1
> LEFT JOIN t t2
> ON t1.emplid = t2.emplid
> AND t1.effdt = t2.effdt; {code}
> Exception stacktrace:
>
> {code:java}
> java.lang.NullPointerException
> at
> org.apache.hadoop.hive.ql.optimizer.DynamicPartitionPruningOptimization.generateSemiJoinOperatorPlan(DynamicPartitionPruningOptimization.java:463)
> at
> org.apache.hadoop.hive.ql.optimizer.DynamicPartitionPruningOptimization.process(DynamicPartitionPruningOptimization.java:226)
> at
> org.apache.hadoop.hive.ql.lib.DefaultRuleDispatcher.dispatch(DefaultRuleDispatcher.java:90)
> at
> org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.dispatchAndReturn(DefaultGraphWalker.java:105)
> at
> org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.dispatch(DefaultGraphWalker.java:89)
> at
> org.apache.hadoop.hive.ql.lib.ForwardWalker.walk(ForwardWalker.java:74)
> at
> org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.startWalking(DefaultGraphWalker.java:120)
> at
> org.apache.hadoop.hive.ql.parse.TezCompiler.runDynamicPartitionPruning(TezCompiler.java:370)
> at
> org.apache.hadoop.hive.ql.parse.TezCompiler.optimizeOperatorPlan(TezCompiler.java:94)
> at
> org.apache.hadoop.hive.ql.parse.TaskCompiler.compile(TaskCompiler.java:140)
> at
> org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:11273)
> at
> org.apache.hadoop.hive.ql.parse.CalcitePlanner.analyzeInternal(CalcitePlanner.java:286)
> at
> org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:258)
> at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:512)
> at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:1317)
> at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1457)
> at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1237)
> at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1227)
> at
> org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:233)
> {code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
