You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@hive.apache.org by "ASF GitHub Bot (Jira)" <ji...@apache.org> on 2023/05/02 08:15:00 UTC
[jira] [Work logged] (HIVE-27305) AssertionError in Calcite during planning for incremental rebuild of materialized view with aggregate on decimal column
[ https://issues.apache.org/jira/browse/HIVE-27305?focusedWorklogId=859987&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-859987 ]
ASF GitHub Bot logged work on HIVE-27305:
-----------------------------------------
Author: ASF GitHub Bot
Created on: 02/May/23 08:14
Start Date: 02/May/23 08:14
Worklog Time Spent: 10m
Work Description: kasakrisz commented on code in PR #4277:
URL: https://github.com/apache/hive/pull/4277#discussion_r1182227739
##########
ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/views/HiveAggregateIncrementalRewritingRuleBase.java:
##########
@@ -142,10 +142,13 @@ public void onMatch(RelOptRuleCall call) {
// Note: If both are null, we will fall into branch WHEN leftNull THEN rightRef
RexNode leftNull = rexBuilder.makeCall(SqlStdOperatorTable.IS_NULL, leftRef);
RexNode rightNull = rexBuilder.makeCall(SqlStdOperatorTable.IS_NULL, rightRef);
- projExprs.add(rexBuilder.makeCall(SqlStdOperatorTable.CASE,
+ RexNode caseExpression = rexBuilder.makeCall(SqlStdOperatorTable.CASE,
leftNull, rightRef,
rightNull, leftRef,
- elseReturn));
+ elseReturn);
+ RexNode cast = rexBuilder.makeCast(
Review Comment:
Yes, but expressions are simplified when added to `Project`
https://github.com/apache/calcite/blob/68b02dfd4af15bc94a91a0cd2a30655d04439555/core/src/main/java/org/apache/calcite/tools/RelBuilder.java#L1415
When source and destination types are equal this simplification removes the cast.
The MV rebuild CBO plan in `materialized_view_create_rewrite_6.q.out` shows that only the decimal type aggregates has cast.
```
HiveProject(
a=[$5],
_o__c1=[CAST(CASE(IS NULL($1), $6, +($6, $1))):DECIMAL(17, 2)],
_o__c2=[CASE(IS NULL($2), $7, +($7, $2))],
_o__c3=[CAST(/(CAST(CASE(IS NULL($1), $6, +($6, $1))):DECIMAL(17, 2), CASE(IS NULL($2), $7, +($7, $2)))):DECIMAL(11, 6)],
_o__c4=[CASE(IS NULL($3), $8, +($8, $3))])
```
Issue Time Tracking
-------------------
Worklog Id: (was: 859987)
Time Spent: 40m (was: 0.5h)
> AssertionError in Calcite during planning for incremental rebuild of materialized view with aggregate on decimal column
> -----------------------------------------------------------------------------------------------------------------------
>
> Key: HIVE-27305
> URL: https://issues.apache.org/jira/browse/HIVE-27305
> Project: Hive
> Issue Type: Bug
> Components: CBO, Materialized views
> Reporter: Krisztian Kasa
> Assignee: Krisztian Kasa
> Priority: Major
> Labels: pull-request-available
> Time Spent: 40m
> Remaining Estimate: 0h
>
> {code}
> set hive.support.concurrency=true;
> set hive.txn.manager=org.apache.hadoop.hive.ql.lockmgr.DbTxnManager;
> set hive.materializedview.rewriting.sql=false;
> create table t1(a int, b decimal(7,2)) stored as orc TBLPROPERTIES ('transactional'='true');
> insert into t1(a, b) values(1, 1);
> create materialized view mat1 stored as orc TBLPROPERTIES ('transactional'='true') as
> select t1.a, sum(t1.b) from t1
> group by t1.a;
> insert into t1(a,b) values(2, 5);
> explain cbo alter materialized view mat1 rebuild;
> {code}
> {code}
> java.lang.AssertionError:
> Cannot add expression of different type to set:
> set type is RecordType(INTEGER $f0, DECIMAL(17, 2) $f1) NOT NULL
> expression type is RecordType(INTEGER $f0, DECIMAL(18, 2) $f1) NOT NULL
> set is rel#388:HiveAggregate.HIVE.[].any(input=HepRelVertex#387,group={0},agg#0=sum($1))
> expression is HiveProject($f0=[$3], $f1=[CASE(IS NULL($1), $4, IS NULL($4), $1, +($4, $1))])
> HiveFilter(condition=[OR($2, IS NULL($2))])
> HiveJoin(condition=[IS NOT DISTINCT FROM($0, $3)], joinType=[right], algorithm=[none], cost=[not available])
> HiveProject(a=[$0], _c1=[$1], $f2=[true])
> HiveTableScan(table=[[default, mat1]], table:alias=[default.mat1])
> HiveAggregate(group=[{0}], agg#0=[sum($1)])
> HiveProject($f0=[$0], $f1=[$1])
> HiveFilter(condition=[<(1, $4.writeid)])
> HiveTableScan(table=[[default, t1]], table:alias=[t1])
> at org.apache.calcite.plan.RelOptUtil.verifyTypeEquivalence(RelOptUtil.java:380)
> at org.apache.calcite.plan.hep.HepRuleCall.transformTo(HepRuleCall.java:58)
> at org.apache.calcite.plan.RelOptRuleCall.transformTo(RelOptRuleCall.java:268)
> at org.apache.calcite.plan.RelOptRuleCall.transformTo(RelOptRuleCall.java:283)
> at org.apache.hadoop.hive.ql.optimizer.calcite.rules.views.HiveAggregateIncrementalRewritingRuleBase.onMatch(HiveAggregateIncrementalRewritingRuleBase.java:161)
> at org.apache.calcite.plan.AbstractRelOptPlanner.fireRule(AbstractRelOptPlanner.java:333)
> at org.apache.calcite.plan.hep.HepPlanner.applyRule(HepPlanner.java:542)
> at org.apache.calcite.plan.hep.HepPlanner.applyRules(HepPlanner.java:407)
> at org.apache.calcite.plan.hep.HepPlanner.executeInstruction(HepPlanner.java:243)
> at org.apache.calcite.plan.hep.HepInstruction$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$CalcitePlannerAction.executeProgram(CalcitePlanner.java:2468)
> at org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.executeProgram(CalcitePlanner.java:2427)
> at org.apache.hadoop.hive.ql.ddl.view.materialized.alter.rebuild.AlterMaterializedViewRebuildAnalyzer$MVRebuildCalcitePlannerAction.applyIncrementalRebuild(AlterMaterializedViewRebuildAnalyzer.java:460)
> at org.apache.hadoop.hive.ql.ddl.view.materialized.alter.rebuild.AlterMaterializedViewRebuildAnalyzer$MVRebuildCalcitePlannerAction.applyAggregateInsertIncremental(AlterMaterializedViewRebuildAnalyzer.java:352)
> at org.apache.hadoop.hive.ql.ddl.view.materialized.alter.rebuild.AlterMaterializedViewRebuildAnalyzer$MVRebuildCalcitePlannerAction.applyRecordIncrementalRebuildPlan(AlterMaterializedViewRebuildAnalyzer.java:311)
> at org.apache.hadoop.hive.ql.ddl.view.materialized.alter.rebuild.AlterMaterializedViewRebuildAnalyzer$MVRebuildCalcitePlannerAction.applyMaterializedViewRewriting(AlterMaterializedViewRebuildAnalyzer.java:278)
> at org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.apply(CalcitePlanner.java:1722)
> at org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.apply(CalcitePlanner.java:1591)
> 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:1343)
> at org.apache.hadoop.hive.ql.parse.CalcitePlanner.genOPTree(CalcitePlanner.java:570)
> at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:12824)
> at org.apache.hadoop.hive.ql.parse.CalcitePlanner.analyzeInternal(CalcitePlanner.java:465)
> at org.apache.hadoop.hive.ql.ddl.view.materialized.alter.rebuild.AlterMaterializedViewRebuildAnalyzer.analyzeInternal(AlterMaterializedViewRebuildAnalyzer.java:135)
> at org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:326)
> at org.apache.hadoop.hive.ql.parse.ExplainSemanticAnalyzer.analyzeInternal(ExplainSemanticAnalyzer.java:180)
> at org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:326)
> at org.apache.hadoop.hive.ql.Compiler.analyze(Compiler.java:224)
> at org.apache.hadoop.hive.ql.Compiler.compile(Compiler.java:107)
> at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:519)
> at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:471)
> at org.apache.hadoop.hive.ql.Driver.compileAndRespond(Driver.java:436)
> at org.apache.hadoop.hive.ql.Driver.compileAndRespond(Driver.java:430)
> at org.apache.hadoop.hive.ql.reexec.ReExecDriver.compileAndRespond(ReExecDriver.java:121)
> at org.apache.hadoop.hive.ql.reexec.ReExecDriver.run(ReExecDriver.java:227)
> at org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:257)
> 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:425)
> at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:356)
> at org.apache.hadoop.hive.ql.QTestUtil.executeClientInternal(QTestUtil.java:733)
> at org.apache.hadoop.hive.ql.QTestUtil.executeClient(QTestUtil.java:703)
> at org.apache.hadoop.hive.cli.control.CoreCliDriver.runTest(CoreCliDriver.java:115)
> 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
(v8.20.10#820010)