[
https://issues.apache.org/jira/browse/HIVE-25364?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Stamatis Zampetakis updated HIVE-25364:
---------------------------------------
Summary: NPE while estimating row count in external JDBC tables (was: Null
Pointer Exception while estimating row count in external tables.)
> NPE while estimating row count in external JDBC tables
> ------------------------------------------------------
>
> Key: HIVE-25364
> URL: https://issues.apache.org/jira/browse/HIVE-25364
> Project: Hive
> Issue Type: Bug
> Reporter: Soumyakanti Das
> Assignee: Soumyakanti Das
> Priority: Major
>
> Running the query below for external tables produces NPE because of missing
> APIs to handle JDBC Converter and JdbcHiveTableScan in
> [RelMdDistinctRowCount.java|https://github.com/apache/calcite/blob/master/core/src/main/java/org/apache/calcite/rel/metadata/RelMdDistinctRowCount.java]
> (calcite). The catch-all method
> [getDistinctRowCount|https://github.com/apache/calcite/blob/master/core/src/main/java/org/apache/calcite/rel/metadata/RelMdDistinctRowCount.java#L76]
> returns null for HiveJdbcConverter and JdbcHiveTableScan, which ultimately
> results in a null value for *computeInnerJoinSelectivity(j, mq, predicate)*
> method at
> [HiveRelMdSelectivity.java|https://github.com/apache/hive/blob/master/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/stats/HiveRelMdSelectivity.java#L78]
> {code:java}
> double innerJoinSelectivity = computeInnerJoinSelectivity(j, mq, predicate);
> {code}
> Query:
> {code:java}
> explain cbo
> with t1 as (select fkey, ikey, sum(dkey) as dk_sum, sum(dkey2) as dk2_sum
> from ext_simple_derby_table1 left join ext_simple_derby_table3
> on ikey = ikey2
> where fkey2 is null
> group by fkey, ikey),
> t2 as (select datekey, fkey, ikey, sum(dkey) as dk_sum2, sum(dkey2) as
> dk2_sum2
> from ext_simple_derby_table2 left join ext_simple_derby_table4
> on ikey = ikey2
> where fkey2 is null
> group by datekey, fkey, ikey)
> select t1.fkey, t2.ikey, sum(t1.ikey)
> from t1 left join t2
> on t1.ikey = t2.ikey AND t1.fkey = t2.fkey
> where t2.fkey is null
> group by t2.datekey, t1.fkey, t2.ikey
> {code}
> The stacktrace:
> {code:java}
> java.lang.NullPointerException
> at
> org.apache.hadoop.hive.ql.optimizer.calcite.stats.HiveRelMdSelectivity.getSelectivity(HiveRelMdSelectivity.java:78)
> at GeneratedMetadataHandler_Selectivity.getSelectivity_$(Unknown Source)
> at GeneratedMetadataHandler_Selectivity.getSelectivity(Unknown Source)
> at GeneratedMetadataHandler_Selectivity.getSelectivity_$(Unknown Source)
> at GeneratedMetadataHandler_Selectivity.getSelectivity(Unknown Source)
> at
> org.apache.calcite.rel.metadata.RelMetadataQuery.getSelectivity(RelMetadataQuery.java:426)
> at
> org.apache.calcite.rel.metadata.RelMdUtil.estimateFilteredRows(RelMdUtil.java:765)
> at
> org.apache.calcite.rel.metadata.RelMdRowCount.getRowCount(RelMdRowCount.java:131)
> at
> org.apache.hadoop.hive.ql.optimizer.calcite.stats.HiveRelMdRowCount.getRowCount(HiveRelMdRowCount.java:175)
> at
> org.apache.hadoop.hive.ql.optimizer.calcite.stats.HiveRelMdRuntimeRowCount.getRowCount(HiveRelMdRuntimeRowCount.java:53)
> at GeneratedMetadataHandler_RowCount.getRowCount_$(Unknown Source)
> at GeneratedMetadataHandler_RowCount.getRowCount(Unknown Source)
> at GeneratedMetadataHandler_RowCount.getRowCount_$(Unknown Source)
> at GeneratedMetadataHandler_RowCount.getRowCount(Unknown Source)
> at
> org.apache.calcite.rel.metadata.RelMetadataQuery.getRowCount(RelMetadataQuery.java:212)
> at
> org.apache.calcite.rel.metadata.RelMdRowCount.getRowCount(RelMdRowCount.java:205)
> at GeneratedMetadataHandler_RowCount.getRowCount_$(Unknown Source)
> at GeneratedMetadataHandler_RowCount.getRowCount(Unknown Source)
> at GeneratedMetadataHandler_RowCount.getRowCount_$(Unknown Source)
> at GeneratedMetadataHandler_RowCount.getRowCount(Unknown Source)
> at
> org.apache.calcite.rel.metadata.RelMetadataQuery.getRowCount(RelMetadataQuery.java:212)
> at
> org.apache.calcite.rel.metadata.RelMdRowCount.getRowCount(RelMdRowCount.java:140)
> at GeneratedMetadataHandler_RowCount.getRowCount_$(Unknown Source)
> at GeneratedMetadataHandler_RowCount.getRowCount(Unknown Source)
> at GeneratedMetadataHandler_RowCount.getRowCount_$(Unknown Source)
> at GeneratedMetadataHandler_RowCount.getRowCount(Unknown Source)
> at
> org.apache.calcite.rel.metadata.RelMetadataQuery.getRowCount(RelMetadataQuery.java:212)
> at
> org.apache.calcite.rel.metadata.RelMdUtil.getJoinRowCount(RelMdUtil.java:723)
> at org.apache.calcite.rel.core.Join.estimateRowCount(Join.java:205)
> at
> org.apache.hadoop.hive.ql.optimizer.calcite.stats.HiveRelMdRowCount.getRowCount(HiveRelMdRowCount.java:113)
> at GeneratedMetadataHandler_RowCount.getRowCount_$(Unknown Source)
> at GeneratedMetadataHandler_RowCount.getRowCount(Unknown Source)
> at
> org.apache.calcite.rel.metadata.RelMetadataQuery.getRowCount(RelMetadataQuery.java:212)
> at
> org.apache.hadoop.hive.ql.optimizer.calcite.stats.FilterSelectivityEstimator.<init>(FilterSelectivityEstimator.java:62)
> at
> org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveFilterSortPredicates$RexSortPredicatesShuttle.<init>(HiveFilterSortPredicates.java:126)
> at
> org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveFilterSortPredicates$RexSortPredicatesShuttle.<init>(HiveFilterSortPredicates.java:120)
> at
> org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveFilterSortPredicates.onMatch(HiveFilterSortPredicates.java:91)
> at
> org.apache.calcite.plan.AbstractRelOptPlanner.fireRule(AbstractRelOptPlanner.java:333)
> at org.apache.calcite.plan.hep.HepPlanner.applyRule(HepPlanner.java:542)
> at
> org.apache.calcite.plan.hep.HepPlanner.applyRules(HepPlanner.java:407)
> at
> org.apache.calcite.plan.hep.HepPlanner.executeInstruction(HepPlanner.java:243)
> at
> org.apache.calcite.plan.hep.HepInstruction$RuleInstance.execute(HepInstruction.java:127)
> at
> org.apache.calcite.plan.hep.HepPlanner.executeProgram(HepPlanner.java:202)
> at
> org.apache.calcite.plan.hep.HepPlanner.findBestExp(HepPlanner.java:189)
> at
> org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.executeProgram(CalcitePlanner.java:2440)
> at
> org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.executeProgram(CalcitePlanner.java:2406)
> at
> org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.applyPostJoinOrderingTransform(CalcitePlanner.java:2326)
> at
> org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.apply(CalcitePlanner.java:1735)
> at
> org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.apply(CalcitePlanner.java:1588)
> at
> org.apache.calcite.tools.Frameworks.lambda$withPlanner$0(Frameworks.java:131)
> at
> org.apache.calcite.prepare.CalcitePrepareImpl.perform(CalcitePrepareImpl.java:914)
> at org.apache.calcite.tools.Frameworks.withPrepare(Frameworks.java:180)
> at org.apache.calcite.tools.Frameworks.withPlanner(Frameworks.java:126)
> at
> org.apache.hadoop.hive.ql.parse.CalcitePlanner.logicalPlan(CalcitePlanner.java:1340)
> at
> org.apache.hadoop.hive.ql.parse.CalcitePlanner.genOPTree(CalcitePlanner.java:559)
> at
> org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:12513)
> at
> org.apache.hadoop.hive.ql.parse.CalcitePlanner.analyzeInternal(CalcitePlanner.java:452)
> at
> org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:317)
> at
> org.apache.hadoop.hive.ql.parse.ExplainSemanticAnalyzer.analyzeInternal(ExplainSemanticAnalyzer.java:175)
> at
> org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:317)
> at org.apache.hadoop.hive.ql.Compiler.analyze(Compiler.java:223)
> at org.apache.hadoop.hive.ql.Compiler.compile(Compiler.java:105)
> at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:500)
> at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:453)
> at org.apache.hadoop.hive.ql.Driver.compileAndRespond(Driver.java:417)
> at org.apache.hadoop.hive.ql.Driver.compileAndRespond(Driver.java:411)
> at
> org.apache.hadoop.hive.ql.reexec.ReExecDriver.compileAndRespond(ReExecDriver.java:125)
> at
> org.apache.hadoop.hive.ql.reexec.ReExecDriver.run(ReExecDriver.java:229)
> at
> org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:256)
> at org.apache.hadoop.hive.cli.CliDriver.processCmd1(CliDriver.java:201)
> at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:127)
> at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:422)
> at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:353)
> at
> org.apache.hadoop.hive.ql.QTestUtil.executeClientInternal(QTestUtil.java:744)
> at org.apache.hadoop.hive.ql.QTestUtil.executeClient(QTestUtil.java:714)
> 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)
> {code}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
