You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@carbondata.apache.org by "Prasanna Ravichandran (Jira)" <ji...@apache.org> on 2020/08/11 11:42:00 UTC
[jira] [Updated] (CARBONDATA-3938) In Hive read table, we are
unable to read a projection column or read a full scan - select * query.
But the aggregate queries are working fine.
[ https://issues.apache.org/jira/browse/CARBONDATA-3938?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Prasanna Ravichandran updated CARBONDATA-3938:
----------------------------------------------
Description:
In Hive read table, we are unable to read a projection column or full scan query. But the aggregate queries are working fine.
Test query:
--spark beeline;
drop table if exists uniqdata;
drop table if exists uniqdata1;
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(36,10),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('DELIMITER'=',', 'QUOTECHAR'='"','BAD_RECORDS_ACTION'='FORCE','FILEHEADER'='CUST_ID,CUST_NAME,ACTIVE_EMUI_VERSION,DOB,DOJ,BIGINT_COLUMN1,BIGINT_COLUMN2,DECIMAL_COLUMN1,DECIMAL_COLUMN2,Double_COLUMN1,Double_COLUMN2,INTEGER_COLUMN1');
CREATE TABLE IF NOT EXISTS uniqdata1 (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(36,10),Double_COLUMN1 double, Double_COLUMN2 double,INTEGER_COLUMN1 int) ROW FORMAT SERDE 'org.apache.carbondata.hive.CarbonHiveSerDe' WITH SERDEPROPERTIES ('mapreduce.input.carboninputformat.databaseName'='default','mapreduce.input.carboninputformat.tableName'='uniqdata') STORED AS INPUTFORMAT 'org.apache.carbondata.hive.MapredCarbonInputFormat' OUTPUTFORMAT 'org.apache.carbondata.hive.MapredCarbonOutputFormat' LOCATION 'hdfs://hacluster/user/hive/warehouse/uniqdata';
select count(*) from uniqdata1;
--Hive Beeline;
select count(*) from uniqdata1; --Returns 2000;
select count(*) from uniqdata; --Returns 2000 - working fine;
select * from uniqdata1; --Return no rows;–Issue 1 on Hive read format table;
select * from uniqdata;–Returns no rows;–Issue 2 while reading a normal carbon table created in spark;
select cust_id from uniqdata1 limit 5;--Return no rows;
Attached the logs for your reference. With the Hive write table this issue is not seen. Issue is only seen in Hive read format table.
This issue also exists when a normal carbon table is created in Spark and read through Hive beeline.
was:
In Hive read table, we are unable to read a projection column or full scan query. But the aggregate queries are working fine.
Test query:
--spark beeline;
drop table if exists uniqdata;
drop table if exists uniqdata1;
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(36,10),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('DELIMITER'=',', 'QUOTECHAR'='"','BAD_RECORDS_ACTION'='FORCE','FILEHEADER'='CUST_ID,CUST_NAME,ACTIVE_EMUI_VERSION,DOB,DOJ,BIGINT_COLUMN1,BIGINT_COLUMN2,DECIMAL_COLUMN1,DECIMAL_COLUMN2,Double_COLUMN1,Double_COLUMN2,INTEGER_COLUMN1');
CREATE TABLE IF NOT EXISTS uniqdata1 (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(36,10),Double_COLUMN1 double, Double_COLUMN2 double,INTEGER_COLUMN1 int) ROW FORMAT SERDE 'org.apache.carbondata.hive.CarbonHiveSerDe' WITH SERDEPROPERTIES ('mapreduce.input.carboninputformat.databaseName'='default','mapreduce.input.carboninputformat.tableName'='uniqdata') STORED AS INPUTFORMAT 'org.apache.carbondata.hive.MapredCarbonInputFormat' OUTPUTFORMAT 'org.apache.carbondata.hive.MapredCarbonOutputFormat' LOCATION 'hdfs://hacluster/user/hive/warehouse/uniqdata';
select count(*) from uniqdata1;
--Hive Beeline;
select count(*) from uniqdata1; --Returns 2000;
select * from uniqdata1; --Return no rows;
select cust_id from uniqdata1 limit 5;--Return no rows;
Attached the logs for your reference. With the Hive write table this issue is not seen. Issue is only seen in Hive read format table.
> In Hive read table, we are unable to read a projection column or read a full scan - select * query. But the aggregate queries are working fine.
> -----------------------------------------------------------------------------------------------------------------------------------------------
>
> Key: CARBONDATA-3938
> URL: https://issues.apache.org/jira/browse/CARBONDATA-3938
> Project: CarbonData
> Issue Type: Bug
> Components: hive-integration
> Affects Versions: 2.0.0
> Reporter: Prasanna Ravichandran
> Priority: Major
> Attachments: Hive on MR - Read projection column issue.txt
>
>
> In Hive read table, we are unable to read a projection column or full scan query. But the aggregate queries are working fine.
>
> Test query:
>
> --spark beeline;
> drop table if exists uniqdata;
> drop table if exists uniqdata1;
> 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(36,10),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('DELIMITER'=',', 'QUOTECHAR'='"','BAD_RECORDS_ACTION'='FORCE','FILEHEADER'='CUST_ID,CUST_NAME,ACTIVE_EMUI_VERSION,DOB,DOJ,BIGINT_COLUMN1,BIGINT_COLUMN2,DECIMAL_COLUMN1,DECIMAL_COLUMN2,Double_COLUMN1,Double_COLUMN2,INTEGER_COLUMN1');
> CREATE TABLE IF NOT EXISTS uniqdata1 (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(36,10),Double_COLUMN1 double, Double_COLUMN2 double,INTEGER_COLUMN1 int) ROW FORMAT SERDE 'org.apache.carbondata.hive.CarbonHiveSerDe' WITH SERDEPROPERTIES ('mapreduce.input.carboninputformat.databaseName'='default','mapreduce.input.carboninputformat.tableName'='uniqdata') STORED AS INPUTFORMAT 'org.apache.carbondata.hive.MapredCarbonInputFormat' OUTPUTFORMAT 'org.apache.carbondata.hive.MapredCarbonOutputFormat' LOCATION 'hdfs://hacluster/user/hive/warehouse/uniqdata';
> select count(*) from uniqdata1;
>
>
> --Hive Beeline;
> select count(*) from uniqdata1; --Returns 2000;
> select count(*) from uniqdata; --Returns 2000 - working fine;
> select * from uniqdata1; --Return no rows;–Issue 1 on Hive read format table;
> select * from uniqdata;–Returns no rows;–Issue 2 while reading a normal carbon table created in spark;
> select cust_id from uniqdata1 limit 5;--Return no rows;
> Attached the logs for your reference. With the Hive write table this issue is not seen. Issue is only seen in Hive read format table.
> This issue also exists when a normal carbon table is created in Spark and read through Hive beeline.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)