[
https://issues.apache.org/jira/browse/CARBONDATA-3807?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Prasanna Ravichandran updated CARBONDATA-3807:
----------------------------------------------
Description:
Filter queries and projection queries with bloom columns are not hitting the
bloom datamap.
Bloom datamap is unused as per plan, even though created.
Test queries:
drop table if exists uniqdata;
CREATE TABLE uniqdata (cust_id int,cust_name String,active_emui_version
string, dob timestamp, doj timestamp, bigint_column1 bigint,bigint_column2
bigint,decimal_column1 decimal(30,10), decimal_column2
decimal(36,36),double_column1 double, double_column2 double,integer_column1
int) stored as carbondata;
load data inpath 'hdfs://hacluster/user/prasanna/2000_UniqData.csv' into table
uniqdata
options('fileheader'='cust_id,cust_name,active_emui_version,dob,doj,bigint_column1,bigint_column2,decimal_column1,decimal_column2,double_column1,double_column2,integer_column1','bad_records_action'='force');
create datamap datamapuniq_b1 on table uniqdata(cust_name) as 'bloomfilter'
PROPERTIES ('BLOOM_SIZE'='640000', 'BLOOM_FPP'='0.00001');
show indexes on uniqdata;
explain select count(*) from uniqdata where cust_name="CUST_NAME_00000"; --not
hitting;
explain select cust_name from uniqdata; --not hitting;
was:
Filter queries and projection queries with bloom columns are not hitting the
bloom datamap.
Test queries:
drop table if exists uniqdata;
CREATE TABLE uniqdata (cust_id int,cust_name String,active_emui_version string,
dob timestamp, doj timestamp, bigint_column1 bigint,bigint_column2
bigint,decimal_column1 decimal(30,10), decimal_column2
decimal(36,36),double_column1 double, double_column2 double,integer_column1
int) stored as carbondata;
load data inpath 'hdfs://hacluster/user/prasanna/2000_UniqData.csv' into table
uniqdata
options('fileheader'='cust_id,cust_name,active_emui_version,dob,doj,bigint_column1,bigint_column2,decimal_column1,decimal_column2,double_column1,double_column2,integer_column1','bad_records_action'='force');
create datamap datamapuniq_b1 on table uniqdata(cust_name) as 'bloomfilter'
PROPERTIES ('BLOOM_SIZE'='640000', 'BLOOM_FPP'='0.00001');
show indexes on uniqdata;
explain select count(*) from uniqdata where cust_name="CUST_NAME_00000"; --not
hitting;
explain select cust_name from uniqdata; --not hitting;
> Filter queries and projection queries with bloom columns are not hitting the
> bloom datamap.
> -------------------------------------------------------------------------------------------
>
> Key: CARBONDATA-3807
> URL: https://issues.apache.org/jira/browse/CARBONDATA-3807
> Project: CarbonData
> Issue Type: Bug
> Environment: Ant cluster - opensource
> Reporter: Prasanna Ravichandran
> Priority: Major
> Attachments: bloom-filtercolumn-plan.png, bloom-show index.png
>
>
> Filter queries and projection queries with bloom columns are not hitting the
> bloom datamap.
> Bloom datamap is unused as per plan, even though created.
> Test queries:
> drop table if exists uniqdata;
> CREATE TABLE uniqdata (cust_id int,cust_name String,active_emui_version
> string, dob timestamp, doj timestamp, bigint_column1 bigint,bigint_column2
> bigint,decimal_column1 decimal(30,10), decimal_column2
> decimal(36,36),double_column1 double, double_column2 double,integer_column1
> int) stored as carbondata;
> load data inpath 'hdfs://hacluster/user/prasanna/2000_UniqData.csv' into
> table uniqdata
> options('fileheader'='cust_id,cust_name,active_emui_version,dob,doj,bigint_column1,bigint_column2,decimal_column1,decimal_column2,double_column1,double_column2,integer_column1','bad_records_action'='force');
> create datamap datamapuniq_b1 on table uniqdata(cust_name) as 'bloomfilter'
> PROPERTIES ('BLOOM_SIZE'='640000', 'BLOOM_FPP'='0.00001');
> show indexes on uniqdata;
> explain select count(*) from uniqdata where cust_name="CUST_NAME_00000";
> --not hitting;
> explain select cust_name from uniqdata; --not hitting;
>
>
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
