You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@hive.apache.org by "Nemon Lou (Jira)" <ji...@apache.org> on 2020/09/15 01:48:00 UTC
[jira] [Updated] (HIVE-24165) CBO: Query fails after multiple count
distinct rewrite
[ https://issues.apache.org/jira/browse/HIVE-24165?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Nemon Lou updated HIVE-24165:
-----------------------------
Description:
One way to reproduce:
{code:sql}
CREATE TABLE test(
`device_id` string,
`level` string,
`site_id` string,
`user_id` string,
`first_date` string,
`last_date` string,
`dt` string) ;
set hive.execution.engine=tez;
set hive.optimize.distinct.rewrite=true;
set hive.cli.print.header=true;
select
dt,
site_id,
count(DISTINCT t1.device_id) as device_tol_cnt,
count(DISTINCT case when t1.first_date='2020-09-15' then t1.device_id else null end) as device_add_cnt
from test t1 where dt='2020-09-15'
group by
dt,
site_id
;
{code}
Error log:
```
Exception in thread "main" java.lang.AssertionError: Cannot add expression of different type to set:
set type is RecordType(VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary" $f2, VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary" $f3, BIGINT $f2_0, BIGINT $f3_0) NOT NULL
expression type is RecordType(VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary" $f2, BIGINT $f3, BIGINT $f2_0, BIGINT $f3_0) NOT NULL
set is rel#85:HiveAggregate.HIVE.[](input=HepRelVertex#84,group={2, 3},agg#0=count($0),agg#1=count($1))
expression is HiveProject#95
at org.apache.calcite.plan.RelOptUtil.verifyTypeEquivalence(RelOptUtil.java:411)
at org.apache.calcite.plan.hep.HepRuleCall.transformTo(HepRuleCall.java:57)
at org.apache.calcite.plan.RelOptRuleCall.transformTo(RelOptRuleCall.java:234)
at org.apache.calcite.rel.rules.AggregateProjectPullUpConstantsRule.onMatch(AggregateProjectPullUpConstantsRule.java:186)
at org.apache.calcite.plan.AbstractRelOptPlanner.fireRule(AbstractRelOptPlanner.java:317)
at org.apache.calcite.plan.hep.HepPlanner.applyRule(HepPlanner.java:556)
at org.apache.calcite.plan.hep.HepPlanner.applyRules(HepPlanner.java:415)
at org.apache.calcite.plan.hep.HepPlanner.executeInstruction(HepPlanner.java:280)
at org.apache.calcite.plan.hep.HepInstruction$RuleCollection.execute(HepInstruction.java:74)
at org.apache.calcite.plan.hep.HepPlanner.executeProgram(HepPlanner.java:211)
at org.apache.calcite.plan.hep.HepPlanner.findBestExp(HepPlanner.java:198)
at org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.hepPlan(CalcitePlanner.java:2273)
at org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.applyPreJoinOrderingTransforms(CalcitePlanner.java:2002)
at org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.apply(CalcitePlanner.java:1709)
at org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.apply(CalcitePlanner.java:1609)
at org.apache.calcite.tools.Frameworks$1.apply(Frameworks.java:118)
at org.apache.calcite.prepare.CalcitePrepareImpl.perform(CalcitePrepareImpl.java:1052)
at org.apache.calcite.tools.Frameworks.withPrepare(Frameworks.java:154)
at org.apache.calcite.tools.Frameworks.withPlanner(Frameworks.java:111)
at org.apache.hadoop.hive.ql.parse.CalcitePlanner.logicalPlan(CalcitePlanner.java:1414)
at org.apache.hadoop.hive.ql.parse.CalcitePlanner.getOptimizedAST(CalcitePlanner.java:1430)
at org.apache.hadoop.hive.ql.parse.CalcitePlanner.genOPTree(CalcitePlanner.java:450)
at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:12164)
at org.apache.hadoop.hive.ql.parse.CalcitePlanner.analyzeInternal(CalcitePlanner.java:330)
at org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:285)
at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:659)
at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:1826)
at org.apache.hadoop.hive.ql.Driver.compileAndRespond(Driver.java:1773)
at org.apache.hadoop.hive.ql.Driver.compileAndRespond(Driver.java:1768)
at org.apache.hadoop.hive.ql.reexec.ReExecDriver.compileAndRespond(ReExecDriver.java:126)
at org.apache.hadoop.hive.ql.reexec.ReExecDriver.run(ReExecDriver.java:214)
at org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:239)
at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:188)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:402)
at org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:821)
at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:759)
at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:683)
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.apache.hadoop.util.RunJar.run(RunJar.java:318)
at org.apache.hadoop.util.RunJar.main(RunJar.java:232)
```
was:
One way to reproduce:
```
drop table test;
CREATE TABLE test(
`device_id` string,
`level` string,
`site_id` string,
`user_id` string,
`first_date` string,
`last_date` string,
`dt` string) ;
set hive.execution.engine=tez;
set hive.optimize.distinct.rewrite=true;
set hive.cli.print.header=true;
select
dt,
site_id,
count(DISTINCT t1.device_id) as device_tol_cnt,
count(DISTINCT case when t1.first_date='2020-09-15' then t1.device_id else null end) as device_add_cnt
from test t1 where dt='2020-09-15'
group by
dt,
site_id
;
```
Error log:
```
Exception in thread "main" java.lang.AssertionError: Cannot add expression of different type to set:Exception in thread "main" java.lang.AssertionError: Cannot add expression of different type to set:set type is RecordType(VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary" $f2, VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary" $f3, BIGINT $f2_0, BIGINT $f3_0) NOT NULLexpression type is RecordType(VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary" $f2, BIGINT $f3, BIGINT $f2_0, BIGINT $f3_0) NOT NULLset is rel#85:HiveAggregate.HIVE.[](input=HepRelVertex#84,group=\{2, 3},agg#0=count($0),agg#1=count($1))expression is HiveProject#95 at org.apache.calcite.plan.RelOptUtil.verifyTypeEquivalence(RelOptUtil.java:411) at org.apache.calcite.plan.hep.HepRuleCall.transformTo(HepRuleCall.java:57) at org.apache.calcite.plan.RelOptRuleCall.transformTo(RelOptRuleCall.java:234) at org.apache.calcite.rel.rules.AggregateProjectPullUpConstantsRule.onMatch(AggregateProjectPullUpConstantsRule.java:186) at org.apache.calcite.plan.AbstractRelOptPlanner.fireRule(AbstractRelOptPlanner.java:317) at org.apache.calcite.plan.hep.HepPlanner.applyRule(HepPlanner.java:556) at org.apache.calcite.plan.hep.HepPlanner.applyRules(HepPlanner.java:415) at org.apache.calcite.plan.hep.HepPlanner.executeInstruction(HepPlanner.java:280) at org.apache.calcite.plan.hep.HepInstruction$RuleCollection.execute(HepInstruction.java:74) at org.apache.calcite.plan.hep.HepPlanner.executeProgram(HepPlanner.java:211) at org.apache.calcite.plan.hep.HepPlanner.findBestExp(HepPlanner.java:198) at org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.hepPlan(CalcitePlanner.java:2273) at org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.applyPreJoinOrderingTransforms(CalcitePlanner.java:2002) at org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.apply(CalcitePlanner.java:1709) at org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.apply(CalcitePlanner.java:1609) at org.apache.calcite.tools.Frameworks$1.apply(Frameworks.java:118) at org.apache.calcite.prepare.CalcitePrepareImpl.perform(CalcitePrepareImpl.java:1052) at org.apache.calcite.tools.Frameworks.withPrepare(Frameworks.java:154) at org.apache.calcite.tools.Frameworks.withPlanner(Frameworks.java:111) at org.apache.hadoop.hive.ql.parse.CalcitePlanner.logicalPlan(CalcitePlanner.java:1414) at org.apache.hadoop.hive.ql.parse.CalcitePlanner.getOptimizedAST(CalcitePlanner.java:1430) at org.apache.hadoop.hive.ql.parse.CalcitePlanner.genOPTree(CalcitePlanner.java:450) at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:12164) at org.apache.hadoop.hive.ql.parse.CalcitePlanner.analyzeInternal(CalcitePlanner.java:330) at org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:285) at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:659) at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:1826) at org.apache.hadoop.hive.ql.Driver.compileAndRespond(Driver.java:1773) at org.apache.hadoop.hive.ql.Driver.compileAndRespond(Driver.java:1768) at org.apache.hadoop.hive.ql.reexec.ReExecDriver.compileAndRespond(ReExecDriver.java:126) at org.apache.hadoop.hive.ql.reexec.ReExecDriver.run(ReExecDriver.java:214) at org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:239) at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:188) at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:402) at org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:821) at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:759) at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:683) 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.apache.hadoop.util.RunJar.run(RunJar.java:318) at org.apache.hadoop.util.RunJar.main(RunJar.java:232)
```
> CBO: Query fails after multiple count distinct rewrite
> -------------------------------------------------------
>
> Key: HIVE-24165
> URL: https://issues.apache.org/jira/browse/HIVE-24165
> Project: Hive
> Issue Type: Bug
> Components: CBO
> Affects Versions: 4.0.0
> Reporter: Nemon Lou
> Priority: Major
>
> One way to reproduce:
>
> {code:sql}
> CREATE TABLE test(
> `device_id` string,
> `level` string,
> `site_id` string,
> `user_id` string,
> `first_date` string,
> `last_date` string,
> `dt` string) ;
> set hive.execution.engine=tez;
> set hive.optimize.distinct.rewrite=true;
> set hive.cli.print.header=true;
> select
> dt,
> site_id,
> count(DISTINCT t1.device_id) as device_tol_cnt,
> count(DISTINCT case when t1.first_date='2020-09-15' then t1.device_id else null end) as device_add_cnt
> from test t1 where dt='2020-09-15'
> group by
> dt,
> site_id
> ;
> {code}
>
> Error log:
> ```
> Exception in thread "main" java.lang.AssertionError: Cannot add expression of different type to set:
> set type is RecordType(VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary" $f2, VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary" $f3, BIGINT $f2_0, BIGINT $f3_0) NOT NULL
> expression type is RecordType(VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary" $f2, BIGINT $f3, BIGINT $f2_0, BIGINT $f3_0) NOT NULL
> set is rel#85:HiveAggregate.HIVE.[](input=HepRelVertex#84,group={2, 3},agg#0=count($0),agg#1=count($1))
> expression is HiveProject#95
> at org.apache.calcite.plan.RelOptUtil.verifyTypeEquivalence(RelOptUtil.java:411)
> at org.apache.calcite.plan.hep.HepRuleCall.transformTo(HepRuleCall.java:57)
> at org.apache.calcite.plan.RelOptRuleCall.transformTo(RelOptRuleCall.java:234)
> at org.apache.calcite.rel.rules.AggregateProjectPullUpConstantsRule.onMatch(AggregateProjectPullUpConstantsRule.java:186)
> at org.apache.calcite.plan.AbstractRelOptPlanner.fireRule(AbstractRelOptPlanner.java:317)
> at org.apache.calcite.plan.hep.HepPlanner.applyRule(HepPlanner.java:556)
> at org.apache.calcite.plan.hep.HepPlanner.applyRules(HepPlanner.java:415)
> at org.apache.calcite.plan.hep.HepPlanner.executeInstruction(HepPlanner.java:280)
> at org.apache.calcite.plan.hep.HepInstruction$RuleCollection.execute(HepInstruction.java:74)
> at org.apache.calcite.plan.hep.HepPlanner.executeProgram(HepPlanner.java:211)
> at org.apache.calcite.plan.hep.HepPlanner.findBestExp(HepPlanner.java:198)
> at org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.hepPlan(CalcitePlanner.java:2273)
> at org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.applyPreJoinOrderingTransforms(CalcitePlanner.java:2002)
> at org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.apply(CalcitePlanner.java:1709)
> at org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.apply(CalcitePlanner.java:1609)
> at org.apache.calcite.tools.Frameworks$1.apply(Frameworks.java:118)
> at org.apache.calcite.prepare.CalcitePrepareImpl.perform(CalcitePrepareImpl.java:1052)
> at org.apache.calcite.tools.Frameworks.withPrepare(Frameworks.java:154)
> at org.apache.calcite.tools.Frameworks.withPlanner(Frameworks.java:111)
> at org.apache.hadoop.hive.ql.parse.CalcitePlanner.logicalPlan(CalcitePlanner.java:1414)
> at org.apache.hadoop.hive.ql.parse.CalcitePlanner.getOptimizedAST(CalcitePlanner.java:1430)
> at org.apache.hadoop.hive.ql.parse.CalcitePlanner.genOPTree(CalcitePlanner.java:450)
> at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:12164)
> at org.apache.hadoop.hive.ql.parse.CalcitePlanner.analyzeInternal(CalcitePlanner.java:330)
> at org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:285)
> at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:659)
> at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:1826)
> at org.apache.hadoop.hive.ql.Driver.compileAndRespond(Driver.java:1773)
> at org.apache.hadoop.hive.ql.Driver.compileAndRespond(Driver.java:1768)
> at org.apache.hadoop.hive.ql.reexec.ReExecDriver.compileAndRespond(ReExecDriver.java:126)
> at org.apache.hadoop.hive.ql.reexec.ReExecDriver.run(ReExecDriver.java:214)
> at org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:239)
> at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:188)
> at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:402)
> at org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:821)
> at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:759)
> at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:683)
> 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.apache.hadoop.util.RunJar.run(RunJar.java:318)
> at org.apache.hadoop.util.RunJar.main(RunJar.java:232)
> ```
>
--
This message was sent by Atlassian Jira
(v8.3.4#803005)