[
https://issues.apache.org/jira/browse/HUDI-6941?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
xy updated HUDI-6941:
---------------------
Description:
version: hudi-0.14.0-rc1，hudi-0.14.0-rc2
CREATE TABLE `hudi_test`.`tmp_hudi_test_1` (
`id` string,
`name` string,
`dt` bigint,
`day` STRING COMMENT '日期分区',
`hour` INT COMMENT '小时分区'
)using hudi
OPTIONS ('hoodie.datasource.write.hive_style_partitioning' 'false',
'hoodie.datasource.meta.sync.enable' 'false',
'hoodie.datasource.hive_sync.enable' 'false')
tblproperties (
'primaryKey' = 'id',
'type' = 'mor',
'preCombineField'='dt',
'hoodie.index.type' = 'BUCKET',
'hoodie.bucket.index.hash.field' = 'id',
'hoodie.bucket.index.num.buckets'=512
)
PARTITIONED BY (`day`,`hour`);
insert into `hudi_test`.`tmp_hudi_test_1` select '1' as id, 'aa' as name, 123
as dt, '2023-10-12' as `day`, 10 as `hour`;
insert into `hudi_test`.`tmp_hudi_test_1` select '1' as id, 'aa' as name, 123
as dt, '2023-10-12' as `day`, 11 as `hour`;
insert into `hudi_test`.`tmp_hudi_test_1` select '1' as id, 'aa' as name, 123
as dt, '2023-10-12' as `day`, 12 as `hour`;
select * from `hudi_test`.`tmp_hudi_test_1` where day='2023-10-12' and hour=11;
right stage task number show be 1
was:
version: hudi-0.14.0-rc1，hudi-0.14.0-rc2
CREATE TABLE `hudi_test`.`tmp_hudi_test_1` (
`id` string,
`name` string,
`dt` bigint,
`day` STRING COMMENT '日期分区',
`hour` INT COMMENT '小时分区'
)using hudi
OPTIONS ('hoodie.datasource.write.hive_style_partitioning' 'false',
'hoodie.datasource.meta.sync.enable' 'false',
'hoodie.datasource.hive_sync.enable' 'false')
tblproperties (
'primaryKey' = 'id',
'type' = 'mor',
'preCombineField'='dt',
'hoodie.index.type' = 'BUCKET',
'hoodie.bucket.index.hash.field' = 'id',
'hoodie.bucket.index.num.buckets'=512
)
PARTITIONED BY (`day`,`hour`);
insert into `hudi_test`.`tmp_hudi_test_1` select '1' as id, 'aa' as name, 123
as dt, '2023-10-12' as `day`, 10 as `hour`;
insert into `hudi_test`.`tmp_hudi_test_1` select '1' as id, 'aa' as name, 123
as dt, '2023-10-12' as `day`, 11 as `hour`;
insert into `hudi_test`.`tmp_hudi_test_1` select '1' as id, 'aa' as name, 123
as dt, '2023-10-12' as `day`, 12 as `hour`;
select * from `hudi_test`.`tmp_hudi_test_1` where day='2023-10-12' and hour=11;
> sparksql query perfermance cost more in hudi 0.14-release
> ---------------------------------------------------------
>
> Key: HUDI-6941
> URL: https://issues.apache.org/jira/browse/HUDI-6941
> Project: Apache Hudi
> Issue Type: Bug
> Components: spark-sql
> Reporter: xy
> Priority: Major
> Attachments: paritions_not_pushdown.jpg, test (1).html
>
>
> version: hudi-0.14.0-rc1，hudi-0.14.0-rc2
>
> CREATE TABLE `hudi_test`.`tmp_hudi_test_1` (
> `id` string,
> `name` string,
> `dt` bigint,
> `day` STRING COMMENT '日期分区',
> `hour` INT COMMENT '小时分区'
> )using hudi
> OPTIONS ('hoodie.datasource.write.hive_style_partitioning' 'false',
> 'hoodie.datasource.meta.sync.enable' 'false',
> 'hoodie.datasource.hive_sync.enable' 'false')
> tblproperties (
> 'primaryKey' = 'id',
> 'type' = 'mor',
> 'preCombineField'='dt',
> 'hoodie.index.type' = 'BUCKET',
> 'hoodie.bucket.index.hash.field' = 'id',
> 'hoodie.bucket.index.num.buckets'=512
> )
> PARTITIONED BY (`day`,`hour`);
> insert into `hudi_test`.`tmp_hudi_test_1` select '1' as id, 'aa' as name, 123
> as dt, '2023-10-12' as `day`, 10 as `hour`;
> insert into `hudi_test`.`tmp_hudi_test_1` select '1' as id, 'aa' as name, 123
> as dt, '2023-10-12' as `day`, 11 as `hour`;
> insert into `hudi_test`.`tmp_hudi_test_1` select '1' as id, 'aa' as name, 123
> as dt, '2023-10-12' as `day`, 12 as `hour`;
> select * from `hudi_test`.`tmp_hudi_test_1` where day='2023-10-12' and
> hour=11;
>
>
> right stage task number show be 1
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
