Stamatis Zampetakis created HIVE-24104:
------------------------------------------

             Summary: NPE due to null key columns in ReduceSink after 
deduplication
                 Key: HIVE-24104
                 URL: https://issues.apache.org/jira/browse/HIVE-24104
             Project: Hive
          Issue Type: Bug
          Components: Physical Optimizer
            Reporter: Stamatis Zampetakis
            Assignee: Stamatis Zampetakis


In some cases the {{ReduceSinkDeDuplication}} optimization creates ReduceSink 
operators where the key columns are null. This can lead to NPE in various 
places in the code. 

The following stracktrace shows an example where NPE is raised due to key 
columns being null.

{noformat}
java.lang.NullPointerException
        at 
org.apache.hadoop.hive.ql.plan.ExprNodeDesc$ExprNodeDescEqualityWrapper.equals(ExprNodeDesc.java:141)
        at java.util.AbstractList.equals(AbstractList.java:523)
        at 
org.apache.hadoop.hive.ql.optimizer.SetReducerParallelism.process(SetReducerParallelism.java:101)
        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.runStatsDependentOptimizations(TezCompiler.java:492)
        at 
org.apache.hadoop.hive.ql.parse.TezCompiler.optimizeOperatorPlan(TezCompiler.java:226)
        at 
org.apache.hadoop.hive.ql.parse.TaskCompiler.compile(TaskCompiler.java:161)
        at 
org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:12643)
        at 
org.apache.hadoop.hive.ql.parse.CalcitePlanner.analyzeInternal(CalcitePlanner.java:443)
        at 
org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:301)
        at 
org.apache.hadoop.hive.ql.parse.ExplainSemanticAnalyzer.analyzeInternal(ExplainSemanticAnalyzer.java:171)
        at 
org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:301)
        at org.apache.hadoop.hive.ql.Compiler.analyze(Compiler.java:220)
        at org.apache.hadoop.hive.ql.Compiler.compile(Compiler.java:104)
        at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:173)
        at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:414)
        at org.apache.hadoop.hive.ql.Driver.compileAndRespond(Driver.java:363)
        at org.apache.hadoop.hive.ql.Driver.compileAndRespond(Driver.java:357)
        at 
org.apache.hadoop.hive.ql.reexec.ReExecDriver.compileAndRespond(ReExecDriver.java:129)
        at 
org.apache.hadoop.hive.ql.reexec.ReExecDriver.run(ReExecDriver.java:231)
        at 
org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:258)
        at org.apache.hadoop.hive.cli.CliDriver.processCmd1(CliDriver.java:203)
        at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:129)
        at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:424)
        at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:355)
        at 
org.apache.hadoop.hive.ql.QTestUtil.executeClientInternal(QTestUtil.java:740)
        at org.apache.hadoop.hive.ql.QTestUtil.executeClient(QTestUtil.java:710)
        at 
org.apache.hadoop.hive.cli.control.CoreCliDriver.runTest(CoreCliDriver.java:170)
        at 
org.apache.hadoop.hive.cli.control.CliAdapter.runTest(CliAdapter.java:157)
        at 
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver(TestMiniLlapLocalCliDriver.java:62)
        at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
        at 
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
        at 
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
        at java.lang.reflect.Method.invoke(Method.java:498)
        at 
org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:59)
        at 
org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12)
        at 
org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:56)
        at 
org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17)
        at 
org.apache.hadoop.hive.cli.control.CliAdapter$2$1.evaluate(CliAdapter.java:135)
        at org.junit.runners.ParentRunner$3.evaluate(ParentRunner.java:306)
        at 
org.junit.runners.BlockJUnit4ClassRunner$1.evaluate(BlockJUnit4ClassRunner.java:100)
        at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:366)
        at 
org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:103)
        at 
org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:63)
        at org.junit.runners.ParentRunner$4.run(ParentRunner.java:331)
        at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:79)
        at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:329)
        at org.junit.runners.ParentRunner.access$100(ParentRunner.java:66)
        at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:293)
        at org.junit.runners.ParentRunner.run(ParentRunner.java:413)
        at org.junit.runners.Suite.runChild(Suite.java:128)
        at org.junit.runners.Suite.runChild(Suite.java:27)
        at org.junit.runners.ParentRunner$4.run(ParentRunner.java:331)
        at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:79)
        at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:329)
        at org.junit.runners.ParentRunner.access$100(ParentRunner.java:66)
        at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:293)
        at 
org.apache.hadoop.hive.cli.control.CliAdapter$1$1.evaluate(CliAdapter.java:95)
        at org.junit.rules.RunRules.evaluate(RunRules.java:20)
        at org.junit.runners.ParentRunner$3.evaluate(ParentRunner.java:306)
        at org.junit.runners.ParentRunner.run(ParentRunner.java:413)
        at 
org.apache.maven.surefire.junit4.JUnit4Provider.execute(JUnit4Provider.java:365)
        at 
org.apache.maven.surefire.junit4.JUnit4Provider.executeWithRerun(JUnit4Provider.java:273)
        at 
org.apache.maven.surefire.junit4.JUnit4Provider.executeTestSet(JUnit4Provider.java:238)
        at 
org.apache.maven.surefire.junit4.JUnit4Provider.invoke(JUnit4Provider.java:159)
        at 
org.apache.maven.surefire.booter.ForkedBooter.runSuitesInProcess(ForkedBooter.java:377)
        at 
org.apache.maven.surefire.booter.ForkedBooter.execute(ForkedBooter.java:138)
        at 
org.apache.maven.surefire.booter.ForkedBooter.run(ForkedBooter.java:465)
        at 
org.apache.maven.surefire.booter.ForkedBooter.main(ForkedBooter.java:451)
{noformat}




--
This message was sent by Atlassian Jira
(v8.3.4#803005)

Reply via email to