[
https://issues.apache.org/jira/browse/HIVE-10996?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14593410#comment-14593410
]
Hive QA commented on HIVE-10996:
--------------------------------
{color:red}Overall{color}: -1 at least one tests failed
Here are the results of testing the latest attachment:
https://issues.apache.org/jira/secure/attachment/12740625/HIVE-10996.04.patch
{color:red}ERROR:{color} -1 due to 125 failed/errored test(s), 9011 tests
executed
*Failed tests:*
{noformat}
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_auto_join18
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_auto_join18_multi_distinct
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_auto_join32
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_bucket_groupby
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_cbo_gby
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_cbo_limit
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_cbo_semijoin
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_cbo_udf_udaf
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_cbo_views
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_correlationoptimizer8
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_count
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_distinct_stats
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_fold_eq_with_case_when
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_groupby12
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_groupby2_map
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_groupby2_map_multi_distinct
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_groupby2_map_skew
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_groupby3_map
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_groupby3_map_multi_distinct
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_groupby3_map_skew
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_groupby8_map_skew
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_groupby9
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_groupby_cube1
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_groupby_distinct_samekey
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_groupby_duplicate_key
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_groupby_grouping_id2
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_groupby_map_ppr
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_groupby_map_ppr_multi_distinct
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_groupby_multi_insert_common_distinct
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_groupby_multi_single_reducer
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_groupby_position
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_groupby_rollup1
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_groupby_sort_11
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_groupby_sort_8
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_infer_bucket_sort
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_join18
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_join18_multi_distinct
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_lateral_view
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_limit_pushdown
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_mapjoin_mapjoin
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_metadataOnlyOptimizer
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_metadataonly1
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_multiMapJoin1
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_multi_insert_gby3
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_multi_insert_lateral_view
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_nullgroup4
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_nullgroup4_multi_distinct
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_optimize_nullscan
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_reduce_deduplicate_extended
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_semijoin
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_subquery_multiinsert
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_subquery_unqual_corr_expr
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_table_access_keys_stats
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_truncate_column_merge
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_udf_count
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_union17
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_unionDistinct_1
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_vector_count_distinct
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_vector_groupby_reduce
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_vector_join30
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_vector_leftsemi_mapjoin
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_vectorization_limit
org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver_vectorized_distinct_gby
org.apache.hadoop.hive.cli.TestMiniSparkOnYarnCliDriver.testCliDriver_bucket5
org.apache.hadoop.hive.cli.TestMiniSparkOnYarnCliDriver.testCliDriver_infer_bucket_sort_reducers_power_two
org.apache.hadoop.hive.cli.TestMiniSparkOnYarnCliDriver.testCliDriver_ql_rewrite_gbtoidx
org.apache.hadoop.hive.cli.TestMiniSparkOnYarnCliDriver.testCliDriver_ql_rewrite_gbtoidx_cbo_1
org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver_cbo_gby
org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver_cbo_limit
org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver_cbo_semijoin
org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver_cbo_udf_udaf
org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver_cbo_views
org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver_count
org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver_dynamic_partition_pruning
org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver_explainuser_1
org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver_explainuser_2
org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver_limit_pushdown
org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver_mapjoin_mapjoin
org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver_metadataonly1
org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver_optimize_nullscan
org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver_tez_join_hash
org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver_tez_union_multiinsert
org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver_unionDistinct_1
org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver_vector_groupby_reduce
org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver_vector_leftsemi_mapjoin
org.apache.hadoop.hive.cli.TestMiniTezCliDriver.testCliDriver_vectorized_dynamic_partition_pruning
org.apache.hadoop.hive.cli.TestMinimrCliDriver.testCliDriver_bucket5
org.apache.hadoop.hive.cli.TestMinimrCliDriver.testCliDriver_infer_bucket_sort_reducers_power_two
org.apache.hadoop.hive.cli.TestMinimrCliDriver.testCliDriver_ql_rewrite_gbtoidx
org.apache.hadoop.hive.cli.TestMinimrCliDriver.testCliDriver_ql_rewrite_gbtoidx_cbo_1
org.apache.hadoop.hive.cli.TestMinimrCliDriver.testCliDriver_ql_rewrite_gbtoidx_cbo_2
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_auto_join18
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_auto_join18_multi_distinct
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_auto_join32
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_cbo_gby
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_cbo_limit
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_cbo_semijoin
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_cbo_udf_udaf
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_count
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_groupby3_map
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_groupby3_map_multi_distinct
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_groupby3_map_skew
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_groupby8_map_skew
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_groupby9
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_groupby_cube1
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_groupby_map_ppr
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_groupby_map_ppr_multi_distinct
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_groupby_multi_insert_common_distinct
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_groupby_multi_single_reducer
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_groupby_position
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_groupby_rollup1
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_having
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_join18
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_join18_multi_distinct
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_join28
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_limit_pushdown
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_mapjoin_mapjoin
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_multi_insert_gby3
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_multi_insert_lateral_view
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_optimize_nullscan
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_semijoin
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_subquery_multiinsert
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_table_access_keys_stats
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_union17
org.apache.hadoop.hive.cli.TestSparkCliDriver.testCliDriver_vector_count_distinct
{noformat}
Test results:
http://ec2-174-129-184-35.compute-1.amazonaws.com/jenkins/job/PreCommit-HIVE-TRUNK-Build/4320/testReport
Console output:
http://ec2-174-129-184-35.compute-1.amazonaws.com/jenkins/job/PreCommit-HIVE-TRUNK-Build/4320/console
Test logs:
http://ec2-174-129-184-35.compute-1.amazonaws.com/logs/PreCommit-HIVE-TRUNK-Build-4320/
Messages:
{noformat}
Executing org.apache.hive.ptest.execution.PrepPhase
Executing org.apache.hive.ptest.execution.ExecutionPhase
Executing org.apache.hive.ptest.execution.ReportingPhase
Tests exited with: TestsFailedException: 125 tests failed
{noformat}
This message is automatically generated.
ATTACHMENT ID: 12740625 - PreCommit-HIVE-TRUNK-Build
> Aggregation / Projection over Multi-Join Inner Query producing incorrect
> results
> --------------------------------------------------------------------------------
>
> Key: HIVE-10996
> URL: https://issues.apache.org/jira/browse/HIVE-10996
> Project: Hive
> Issue Type: Bug
> Components: Hive
> Affects Versions: 1.0.0, 1.2.0, 1.1.0, 1.3.0, 2.0.0
> Reporter: Gautam Kowshik
> Assignee: Jesus Camacho Rodriguez
> Priority: Critical
> Attachments: HIVE-10996.01.patch, HIVE-10996.02.patch,
> HIVE-10996.03.patch, HIVE-10996.04.patch, HIVE-10996.patch, explain_q1.txt,
> explain_q2.txt
>
>
> We see the following problem on 1.1.0 and 1.2.0 but not 0.13 which seems like
> a regression.
> The following query (Q1) produces no results:
> {code}
> select s
> from (
> select last.*, action.st2, action.n
> from (
> select purchase.s, purchase.timestamp, max (mevt.timestamp) as
> last_stage_timestamp
> from (select * from purchase_history) purchase
> join (select * from cart_history) mevt
> on purchase.s = mevt.s
> where purchase.timestamp > mevt.timestamp
> group by purchase.s, purchase.timestamp
> ) last
> join (select * from events) action
> on last.s = action.s and last.last_stage_timestamp = action.timestamp
> ) list;
> {code}
> While this one (Q2) does produce results :
> {code}
> select *
> from (
> select last.*, action.st2, action.n
> from (
> select purchase.s, purchase.timestamp, max (mevt.timestamp) as
> last_stage_timestamp
> from (select * from purchase_history) purchase
> join (select * from cart_history) mevt
> on purchase.s = mevt.s
> where purchase.timestamp > mevt.timestamp
> group by purchase.s, purchase.timestamp
> ) last
> join (select * from events) action
> on last.s = action.s and last.last_stage_timestamp = action.timestamp
> ) list;
> 1 21 20 Bob 1234
> 1 31 30 Bob 1234
> 3 51 50 Jeff 1234
> {code}
> The setup to test this is:
> {code}
> create table purchase_history (s string, product string, price double,
> timestamp int);
> insert into purchase_history values ('1', 'Belt', 20.00, 21);
> insert into purchase_history values ('1', 'Socks', 3.50, 31);
> insert into purchase_history values ('3', 'Belt', 20.00, 51);
> insert into purchase_history values ('4', 'Shirt', 15.50, 59);
> create table cart_history (s string, cart_id int, timestamp int);
> insert into cart_history values ('1', 1, 10);
> insert into cart_history values ('1', 2, 20);
> insert into cart_history values ('1', 3, 30);
> insert into cart_history values ('1', 4, 40);
> insert into cart_history values ('3', 5, 50);
> insert into cart_history values ('4', 6, 60);
> create table events (s string, st2 string, n int, timestamp int);
> insert into events values ('1', 'Bob', 1234, 20);
> insert into events values ('1', 'Bob', 1234, 30);
> insert into events values ('1', 'Bob', 1234, 25);
> insert into events values ('2', 'Sam', 1234, 30);
> insert into events values ('3', 'Jeff', 1234, 50);
> insert into events values ('4', 'Ted', 1234, 60);
> {code}
> I realize select * and select s are not all that interesting in this context
> but what lead us to this issue was select count(distinct s) was not returning
> results. The above queries are the simplified queries that produce the issue.
> I will note that if I convert the inner join to a table and select from that
> the issue does not appear.
> Update: Found that turning off hive.optimize.remove.identity.project fixes
> this issue. This optimization was introduced in
> https://issues.apache.org/jira/browse/HIVE-8435
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
