[
https://issues.apache.org/jira/browse/HIVE-19097?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16513057#comment-16513057
]
Hive QA commented on HIVE-19097:
--------------------------------
Here are the results of testing the latest attachment:
https://issues.apache.org/jira/secure/attachment/12927667/HIVE-19097.02.patch
{color:green}SUCCESS:{color} +1 due to 1 test(s) being added or modified.
{color:red}ERROR:{color} -1 due to 92 failed/errored test(s), 14523 tests
executed
*Failed tests:*
{noformat}
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver[cbo_rp_simple_select]
(batchId=48)
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver[cbo_simple_select]
(batchId=18)
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver[constant_prop_3]
(batchId=45)
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver[druid_basic3]
(batchId=63)
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver[druid_intervals]
(batchId=24)
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver[filter_cond_pushdown]
(batchId=63)
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver[remove_exprs_stats]
(batchId=91)
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver[stat_estimate_related_col]
(batchId=42)
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver[vector_date_1]
(batchId=22)
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver[vector_mr_diff_schema_alias]
(batchId=67)
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver[vector_non_constant_in_expr]
(batchId=79)
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver[vectorized_timestamp]
(batchId=81)
org.apache.hadoop.hive.cli.TestMiniLlapCliDriver.testCliDriver[dynamic_partition_pruning_2]
(batchId=151)
org.apache.hadoop.hive.cli.TestMiniLlapCliDriver.testCliDriver[explainuser_2]
(batchId=152)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[bucketpruning1]
(batchId=176)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[cbo_simple_select]
(batchId=158)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[cross_prod_1]
(batchId=172)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[vector_between_in]
(batchId=168)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[vector_date_1]
(batchId=158)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[vector_mr_diff_schema_alias]
(batchId=170)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[vector_string_decimal]
(batchId=154)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[vectorized_dynamic_semijoin_reduction]
(batchId=155)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[vectorized_timestamp]
(batchId=173)
org.apache.hadoop.hive.cli.TestMiniSparkOnYarnCliDriver.testCliDriver[spark_dynamic_partition_pruning_2]
(batchId=185)
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver[cbo_simple_select]
(batchId=115)
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver[vector_between_in]
(batchId=133)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query10]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query12]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query13]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query15]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query16]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query17]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query18]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query20]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query23]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query27]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query29]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query34]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query36]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query37]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query45]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query46]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query48]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query53]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query56]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query63]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query66]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query68]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query69]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query73]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query74]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query79]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query82]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query83]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query85]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query89]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query8]
(batchId=258)
org.apache.hadoop.hive.cli.TestSparkPerfCliDriver.testCliDriver[query98]
(batchId=258)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query10]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query12]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query13]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query15]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query16]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query17]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query18]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query20]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query23]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query27]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query29]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query34]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query36]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query37]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query45]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query46]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query48]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query53]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query56]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query63]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query64]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query66]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query68]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query69]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query73]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query74]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query79]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query82]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query83]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query85]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query89]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query8]
(batchId=256)
org.apache.hadoop.hive.cli.TestTezPerfCliDriver.testCliDriver[query98]
(batchId=256)
org.apache.hadoop.hive.ql.plan.mapping.TestStatEstimations.testFilterIntIn
(batchId=302)
{noformat}
Test results:
https://builds.apache.org/job/PreCommit-HIVE-Build/11787/testReport
Console output: https://builds.apache.org/job/PreCommit-HIVE-Build/11787/console
Test logs: http://104.198.109.242/logs/PreCommit-HIVE-Build-11787/
Messages:
{noformat}
Executing org.apache.hive.ptest.execution.TestCheckPhase
Executing org.apache.hive.ptest.execution.PrepPhase
Executing org.apache.hive.ptest.execution.YetusPhase
Executing org.apache.hive.ptest.execution.ExecutionPhase
Executing org.apache.hive.ptest.execution.ReportingPhase
Tests exited with: TestsFailedException: 92 tests failed
{noformat}
This message is automatically generated.
ATTACHMENT ID: 12927667 - PreCommit-HIVE-Build
> related equals and in operators may cause inaccurate stats estimations
> ----------------------------------------------------------------------
>
> Key: HIVE-19097
> URL: https://issues.apache.org/jira/browse/HIVE-19097
> Project: Hive
> Issue Type: Bug
> Reporter: Zoltan Haindrich
> Assignee: Zoltan Haindrich
> Priority: Major
> Attachments: HIVE-19097.01.patch, HIVE-19097.02.patch,
> HIVE-19097.partial.patch
>
>
> tpcds#74 is optimized in a way that for date_dim the condition contains IN
> and = for the same column
> {code:java}
> | Map Operator Tree: |
> | TableScan |
> | alias: date_dim |
> | filterExpr: (((d_year) IN (2001, 2002) and (d_year =
> 2002) and d_date_sk is not null) or ((d_year) IN (2001, 2002) and (d_year =
> 2001) and d_date_sk is not null)) (type: boolean) |
> | Statistics: Num rows: 73049 Data size: 876588 Basic
> stats: COMPLETE Column stats: COMPLETE |
> | Filter Operator |
> | predicate: ((d_year) IN (2001, 2002) and (d_year =
> 2002) and d_date_sk is not null) (type: boolean) |
> | Statistics: Num rows: 4 Data size: 48 Basic stats:
> COMPLETE Column stats: COMPLETE |
> {code}
> the "real" row count will be 365
> for separate {{IN}} and {{=}} the estimation is very good; but if both are
> present it becomes (very) underestimated.
> {code:java}
> set hive.query.results.cache.enabled=false;
> drop table if exists t1;
> drop table if exists t8;
> create table t1 (a integer,b integer);
> create table t8 like t1;
> insert into t1 values (1,1),(2,2),(3,3),(4,4),(5,5);
> insert into t8
> select * from t1 union all select * from t1 union all select * from t1 union
> all select * from t1 union all
> select * from t1 union all select * from t1 union all select * from t1 union
> all select * from t1
> ;
> analyze table t1 compute statistics for columns;
> analyze table t8 compute statistics for columns;
> explain analyze select sum(a) from t8 where b in (2,3) group by b;
> explain analyze select sum(a) from t8 where b=2 group by b;
> explain analyze select sum(a) from t1 where b in (2,3) and b=2 group by b;
> explain analyze select sum(a) from t8 where b in (2,3) and b=2 group by b;
> {code}
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)