Uploaded image for project: 'Hive'
  1. Hive
  2. HIVE-25369

Handle Sum0 when rebuilding materialized view incrementally

    XMLWordPrintableJSON

Details

    Description

      When rewriting MV insert overwrite plan to incremental rebuild plan a Sum0 aggregate function is used when aggregating count function subresults coming from the existing MV data and the aggregated newly inserted/deleted records since the last rebuild

      create materialized view mat1 stored as orc TBLPROPERTIES ('transactional'='true') as
      select t1.a, count(*) from t1
      

      Insert overwrite plan:

      HiveAggregate(group=[{0}], agg#0=[$SUM0($1)])
        HiveUnion(all=[true])
          HiveAggregate(group=[{0}], agg#0=[count()])
            HiveProject($f0=[$0])
              HiveFilter(condition=[<(2, $5.writeid)])
                HiveTableScan(table=[[default, t1]], table:alias=[t1])
          HiveTableScan(table=[[default, mat1]], table:alias=[default.mat1])
      

      AssertionError when rewriting the plan to incremental rebuild

      java.lang.AssertionError: Found an aggregation that could not be recognized: $SUM0
      	at org.apache.hadoop.hive.ql.optimizer.calcite.rules.views.HiveAggregateIncrementalRewritingRuleBase.createAggregateNode(HiveAggregateIncrementalRewritingRuleBase.java:183)
      	at org.apache.hadoop.hive.ql.optimizer.calcite.rules.views.HiveAggregateInsertIncrementalRewritingRule.createAggregateNode(HiveAggregateInsertIncrementalRewritingRule.java:128)
      	at org.apache.hadoop.hive.ql.optimizer.calcite.rules.views.HiveAggregateIncrementalRewritingRuleBase.onMatch(HiveAggregateIncrementalRewritingRuleBase.java:138)
      	at org.apache.calcite.plan.AbstractRelOptPlanner.fireRule(AbstractRelOptPlanner.java:333)
      	at org.apache.calcite.plan.hep.HepPlanner.applyRule(HepPlanner.java:542)
      	at org.apache.calcite.plan.hep.HepPlanner.applyRules(HepPlanner.java:407)
      	at org.apache.calcite.plan.hep.HepPlanner.executeInstruction(HepPlanner.java:243)
      	at org.apache.calcite.plan.hep.HepInstruction$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.ddl.view.materialized.alter.rebuild.AlterMaterializedViewRebuildAnalyzer$MVRebuildCalcitePlannerAction.applyIncrementalRebuild(AlterMaterializedViewRebuildAnalyzer.java:407)
      	at org.apache.hadoop.hive.ql.ddl.view.materialized.alter.rebuild.AlterMaterializedViewRebuildAnalyzer$MVRebuildCalcitePlannerAction.applyAggregateInsertIncremental(AlterMaterializedViewRebuildAnalyzer.java:334)
      	at org.apache.hadoop.hive.ql.ddl.view.materialized.alter.rebuild.AlterMaterializedViewRebuildAnalyzer$MVRebuildCalcitePlannerAction.applyRecordIncrementalRebuildPlan(AlterMaterializedViewRebuildAnalyzer.java:309)
      	at org.apache.hadoop.hive.ql.ddl.view.materialized.alter.rebuild.AlterMaterializedViewRebuildAnalyzer$MVRebuildCalcitePlannerAction.applyMaterializedViewRewriting(AlterMaterializedViewRebuildAnalyzer.java:267)
      	at org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.apply(CalcitePlanner.java:1716)
      	at org.apache.hadoop.hive.ql.parse.CalcitePlanner$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:12512)
      	at org.apache.hadoop.hive.ql.parse.CalcitePlanner.analyzeInternal(CalcitePlanner.java:452)
      	at org.apache.hadoop.hive.ql.ddl.view.materialized.alter.rebuild.AlterMaterializedViewRebuildAnalyzer.analyzeInternal(AlterMaterializedViewRebuildAnalyzer.java:128)
      	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)
      

      Attachments

        Issue Links

          Activity

            People

              kkasa Krisztian Kasa
              kkasa Krisztian Kasa
              Votes:
              0 Vote for this issue
              Watchers:
              1 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved:

                Time Tracking

                  Estimated:
                  Original Estimate - Not Specified
                  Not Specified
                  Remaining:
                  Remaining Estimate - 0h
                  0h
                  Logged:
                  Time Spent - 20m
                  20m