[
https://issues.apache.org/jira/browse/HIVE-27876?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Naresh P R updated HIVE-27876:
------------------------------
Description:
Repro:
{code:java}
create external table test_bucket(age int, name string, dept string) clustered
by (age, name) sorted by (age asc, name asc) into 2 buckets stored as orc;
insert into test_bucket values (1, 'user1', 'dept1'), ( 2, 'user2' , 'dept2');
insert into test_bucket values (1, 'user1', 'dept1'), ( 2, 'user2' , 'dept2');
//empty wrong results
select age, name, count(*) from test_bucket group by age, name having count(*)
> 1;
+------+-------+------+
| age | name | _c2 |
+------+-------+------+
+------+-------+------+
// Workaround
set hive.map.aggr=false;
select age, name, count(*) from test_bucket group by age, name having count(*)
> 1;
+------+--------+------+
| age | name | _c2 |
+------+--------+------+
| 1 | user1 | 2 |
| 2 | user2 | 2 |
+------+--------+------+ {code}
was:
Repro:
{code:java}
create external table test_bucket(age int, name string, dept string) clustered
by (age, name) sorted by (age asc, name asc) into 2 buckets stored as orc;
insert into test_bucket values (1, 'user1', 'dept1'), ( 2, 'user2' , 'dept2');
insert into test_bucket values (1, 'user1', 'dept1'), ( 2, 'user2' , 'dept2');
//empty wrong results with default CDP configs
select age, name, count(*) from test_bucket group by age, name having count(*)
> 1;
+------+-------+------+
| age | name | _c2 |
+------+-------+------+
+------+-------+------+
// Workaround
set hive.map.aggr=false;
select age, name, count(*) from test_bucket group by age, name having count(*)
> 1;
+------+--------+------+
| age | name | _c2 |
+------+--------+------+
| 1 | user1 | 2 |
| 2 | user2 | 2 |
+------+--------+------+ {code}
> Incorrect query results on tables with ClusterBy & SortBy
> ---------------------------------------------------------
>
> Key: HIVE-27876
> URL: https://issues.apache.org/jira/browse/HIVE-27876
> Project: Hive
> Issue Type: Bug
> Reporter: Naresh P R
> Priority: Major
>
> Repro:
>
> {code:java}
> create external table test_bucket(age int, name string, dept string)
> clustered by (age, name) sorted by (age asc, name asc) into 2 buckets stored
> as orc;
> insert into test_bucket values (1, 'user1', 'dept1'), ( 2, 'user2' , 'dept2');
> insert into test_bucket values (1, 'user1', 'dept1'), ( 2, 'user2' , 'dept2');
> //empty wrong results
> select age, name, count(*) from test_bucket group by age, name having
> count(*) > 1;
> +------+-------+------+
> | age | name | _c2 |
> +------+-------+------+
> +------+-------+------+
> // Workaround
> set hive.map.aggr=false;
> select age, name, count(*) from test_bucket group by age, name having
> count(*) > 1;
> +------+--------+------+
> | age | name | _c2 |
> +------+--------+------+
> | 1 | user1 | 2 |
> | 2 | user2 | 2 |
> +------+--------+------+ {code}
>
>
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
