[
https://issues.apache.org/jira/browse/HIVE-20660?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16633842#comment-16633842
]
Hive QA commented on HIVE-20660:
--------------------------------
Here are the results of testing the latest attachment:
https://issues.apache.org/jira/secure/attachment/12941911/HIVE-20660.1.patch
{color:green}SUCCESS:{color} +1 due to 1 test(s) being added or modified.
{color:red}ERROR:{color} -1 due to 114 failed/errored test(s), 15008 tests
executed
*Failed tests:*
{noformat}
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver[annotate_stats_groupby2]
(batchId=51)
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver[annotate_stats_groupby]
(batchId=52)
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver[annotate_stats_join]
(batchId=57)
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver[cbo_rp_annotate_stats_groupby]
(batchId=91)
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver[cbo_rp_auto_join1]
(batchId=4)
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver[topnkey] (batchId=43)
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver[vector_topnkey]
(batchId=45)
org.apache.hadoop.hive.cli.TestMiniLlapCliDriver.testCliDriver[except_distinct]
(batchId=155)
org.apache.hadoop.hive.cli.TestMiniLlapCliDriver.testCliDriver[explainuser_2]
(batchId=156)
org.apache.hadoop.hive.cli.TestMiniLlapCliDriver.testCliDriver[gby_stats_estimate]
(batchId=154)
org.apache.hadoop.hive.cli.TestMiniLlapCliDriver.testCliDriver[intersect_all]
(batchId=154)
org.apache.hadoop.hive.cli.TestMiniLlapCliDriver.testCliDriver[intersect_distinct]
(batchId=156)
org.apache.hadoop.hive.cli.TestMiniLlapCliDriver.testCliDriver[intersect_merge]
(batchId=154)
org.apache.hadoop.hive.cli.TestMiniLlapCliDriver.testCliDriver[llap_stats]
(batchId=152)
org.apache.hadoop.hive.cli.TestMiniLlapCliDriver.testCliDriver[llapdecider]
(batchId=152)
org.apache.hadoop.hive.cli.TestMiniLlapCliDriver.testCliDriver[mm_all]
(batchId=156)
org.apache.hadoop.hive.cli.TestMiniLlapCliDriver.testCliDriver[orc_merge10]
(batchId=155)
org.apache.hadoop.hive.cli.TestMiniLlapCliDriver.testCliDriver[orc_merge1]
(batchId=152)
org.apache.hadoop.hive.cli.TestMiniLlapCliDriver.testCliDriver[orc_merge_diff_fs]
(batchId=152)
org.apache.hadoop.hive.cli.TestMiniLlapCliDriver.testCliDriver[parallel_colstats]
(batchId=154)
org.apache.hadoop.hive.cli.TestMiniLlapCliDriver.testCliDriver[reduce_deduplicate_distinct]
(batchId=157)
org.apache.hadoop.hive.cli.TestMiniLlapCliDriver.testCliDriver[unionDistinct_1]
(batchId=154)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[acid_vectorization_original]
(batchId=179)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[bucket_groupby]
(batchId=182)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[bucket_map_join_tez2]
(batchId=161)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[check_constraint]
(batchId=162)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[column_table_stats_orc]
(batchId=159)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[constprog_semijoin]
(batchId=175)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[correlationoptimizer1]
(batchId=173)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[correlationoptimizer2]
(batchId=171)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[correlationoptimizer6]
(batchId=171)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[count_dist_rewrite]
(batchId=177)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[dynpart_sort_opt_vectorization]
(batchId=171)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[dynpart_sort_optimization2]
(batchId=158)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[enforce_constraint_notnull]
(batchId=162)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[explainuser_1]
(batchId=167)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[explainuser_4]
(batchId=169)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[filter_union]
(batchId=161)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[groupby_resolution]
(batchId=169)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[having]
(batchId=169)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[jdbc_handler]
(batchId=173)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[limit_pushdown3]
(batchId=166)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[limit_pushdown]
(batchId=176)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[llap_partitioned]
(batchId=163)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[load_dyn_part3]
(batchId=160)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[load_dyn_part5]
(batchId=169)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[materialized_view_rewrite_1]
(batchId=174)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[materialized_view_rewrite_4]
(batchId=159)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[materialized_view_rewrite_6]
(batchId=176)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[materialized_view_rewrite_no_join_opt_2]
(batchId=179)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[materialized_view_rewrite_part_1]
(batchId=162)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[materialized_view_rewrite_part_2]
(batchId=158)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[merge1]
(batchId=173)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[merge2]
(batchId=158)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[mrr]
(batchId=161)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[multiMapJoin2]
(batchId=178)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[offset_limit]
(batchId=168)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[offset_limit_ppd_optimizer]
(batchId=176)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[parallel]
(batchId=164)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[partialdhj]
(batchId=168)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[ptf]
(batchId=162)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[reduce_deduplicate_extended]
(batchId=174)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[results_cache_2]
(batchId=180)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[results_cache_capacity]
(batchId=159)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[results_cache_empty_result]
(batchId=170)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[selectDistinctStar]
(batchId=178)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[semijoin6]
(batchId=181)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[semijoin7]
(batchId=158)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[semijoin]
(batchId=163)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[sharedworkext]
(batchId=167)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[subquery_corr]
(batchId=173)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[subquery_exists]
(batchId=169)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[subquery_in]
(batchId=175)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[subquery_in_having]
(batchId=174)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[subquery_multi]
(batchId=162)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[subquery_notin]
(batchId=177)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[subquery_scalar]
(batchId=169)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[subquery_select]
(batchId=168)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[subquery_views]
(batchId=161)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[tez_dml]
(batchId=166)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[tez_input_counters]
(batchId=179)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[tez_join_hash]
(batchId=172)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[tez_smb_reduce_side]
(batchId=172)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[tez_union2]
(batchId=159)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[tez_union_multiinsert]
(batchId=167)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[topnkey]
(batchId=168)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[union7]
(batchId=175)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[unionDistinct_3]
(batchId=170)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[union_remove_26]
(batchId=171)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[vector_adaptor_usage_mode]
(batchId=179)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[vector_char_2]
(batchId=176)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[vector_coalesce_2]
(batchId=177)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[vector_distinct_2]
(batchId=172)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[vector_groupby_3]
(batchId=175)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[vector_groupby_grouping_sets2]
(batchId=167)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[vector_groupby_mapjoin]
(batchId=178)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[vector_groupby_reduce]
(batchId=173)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[vector_groupby_sort_11]
(batchId=180)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[vector_mapjoin_reduce]
(batchId=179)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[vector_outer_reference_windowed]
(batchId=166)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[vector_topnkey]
(batchId=169)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[vector_when_case_null]
(batchId=167)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[vector_windowing]
(batchId=182)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[vector_windowing_gby2]
(batchId=176)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[vectorization_limit]
(batchId=167)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[vectorization_short_regress]
(batchId=171)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[vectorized_ptf]
(batchId=175)
org.apache.hadoop.hive.cli.TestMiniLlapLocalCliDriver.testCliDriver[windowing]
(batchId=172)
org.apache.hadoop.hive.cli.TestMiniSparkOnYarnCliDriver.testCliDriver[spark_explainuser_1]
(batchId=189)
org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver[acid_vectorization_original_tez]
(batchId=109)
org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver[topnkey]
(batchId=108)
org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver[vector_join_part_col_char]
(batchId=108)
org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver[vector_topnkey]
(batchId=108)
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver[annotate_stats_join]
(batchId=134)
{noformat}
Test results:
https://builds.apache.org/job/PreCommit-HIVE-Build/14153/testReport
Console output: https://builds.apache.org/job/PreCommit-HIVE-Build/14153/console
Test logs: http://104.198.109.242/logs/PreCommit-HIVE-Build-14153/
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: 114 tests failed
{noformat}
This message is automatically generated.
ATTACHMENT ID: 12941911 - PreCommit-HIVE-Build
> Group by statistics estimation could be improved by bounding the total number
> of rows to source table
> -----------------------------------------------------------------------------------------------------
>
> Key: HIVE-20660
> URL: https://issues.apache.org/jira/browse/HIVE-20660
> Project: Hive
> Issue Type: Improvement
> Components: Statistics
> Affects Versions: 4.0.0
> Reporter: Vineet Garg
> Assignee: Vineet Garg
> Priority: Major
> Attachments: HIVE-20660.1.patch
>
>
> Currently the stats for group by is estimated by taking product of NDVs of
> all the keys and bounding it by the number of rows of its input. This bound
> could be improved by using the source table instead of immediate input, the
> insight in this case is that cardinality/ndvs of a table can not go beyond
> the original (outer joins will only add NULLs thereby increasing the
> cardinality by 1).
> Note that the assumption here is that group by keys all belong to the same
> source table/input.
> This will improve the estimation in situations where group by is executed
> after joins wherein Hive could end up estimating the number of rows.
> *Reproducer*
> {code:sql}
> set hive.stats.fetch.column.stats=true;
> create table t1(i int, j int);
> alter table t1 update statistics set('numRows'='10000',
> 'rawDataSize'='18000');
> alter table t1 update statistics for column i
> set('numDVs'='2500','numNulls'='50','highValue'='1000','lowValue'='0');
> alter table t1 update statistics for column j
> set('numDVs'='500','numNulls'='30','highValue'='100','lowValue'='50');
> create table t2(i2 int, j2 int);
> alter table t2 update statistics set('numRows'='100000000',
> 'rawDataSize'='10000');
> alter table t2 update statistics for column i2
> set('numDVs'='10000000','numNulls'='0','highValue'='8000','lowValue'='0');
> alter table t2 update statistics for column j2
> set('numDVs'='10','numNulls'='0','highValue'='800','lowValue'='-1');
> explain select count (1) from t1,t2
> where t1.j=t2.i2
> group by t1.i, t1.j;
> {code}
> {code:sql}
> Reducer 2
> Reduce Operator Tree:
> Merge Join Operator
> condition map:
> Inner Join 0 to 1
> keys:
> 0 _col1 (type: int)
> 1 _col0 (type: int)
> outputColumnNames: _col0, _col1
> Statistics: Num rows: 99700 Data size: 797288 Basic stats:
> COMPLETE Column stats: COMPLETE
> Group By Operator
> aggregations: count()
> keys: _col0 (type: int), _col1 (type: int)
> mode: hash
> outputColumnNames: _col0, _col1, _col2
> Statistics: Num rows: 49850 Data size: 797448 Basic stats:
> COMPLETE Column stats: COMPLETE <==========
> Reduce Output Operator
> key expressions: _col0 (type: int), _col1 (type: int)
> sort order: ++
> Map-reduce partition columns: _col0 (type: int), _col1
> (type: int)
> Statistics: Num rows: 49850 Data size: 797448 Basic
> stats: COMPLETE Column stats: COMPLETE
> value expressions: _col2 (type: bigint)
> .....................
> {code}
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
