[jira] [Created] (CARBONDATA-2799) Query failed with bloom datamap on preagg table with dictionary column

[xuchuanyin (JIRA)]

xuchuanyin created CARBONDATA-2799:
--------------------------------------

             Summary: Query failed with bloom datamap on preagg table with 
dictionary column
                 Key: CARBONDATA-2799
                 URL: https://issues.apache.org/jira/browse/CARBONDATA-2799
             Project: CarbonData
          Issue Type: Bug
            Reporter: xuchuanyin
            Assignee: xuchuanyin


Steps to reproduce:


CREATE TABLE datamap_test (id int,name string,salary float,dob date)STORED BY 
'carbondata' TBLPROPERTIES('dictionary_include'='id');

LOAD DATA INPATH 'hdfs://hacluster/user/surbhi/datamap_test.csv' into table 
datamap_test OPTIONS('DELIMITER'=',', 
'QUOTECHAR'='"','BAD_RECORDS_ACTION'='FORCE','FILEHEADER'='id,name,salary,dob');

LOAD DATA INPATH 'hdfs://hacluster/user/surbhi/datamap_test.csv' into table 
datamap_test OPTIONS('DELIMITER'=',', 
'QUOTECHAR'='"','BAD_RECORDS_ACTION'='FORCE','FILEHEADER'='id,name,salary,dob');

LOAD DATA INPATH 'hdfs://hacluster/user/surbhi/datamap_test.csv' into table 
datamap_test OPTIONS('DELIMITER'=',', 
'QUOTECHAR'='"','BAD_RECORDS_ACTION'='FORCE','FILEHEADER'='id,name,salary,dob');

CREATE DATAMAP dm_datamap_test2 ON TABLE datamap_test USING 'bloomfilter' 
DMPROPERTIES ('INDEX_COLUMNS' = 'id', 'BLOOM_SIZE'='320000', 
'BLOOM_FPP'='0.01', 'BLOOM_COMPRESS'='true');

LOAD DATA INPATH 'hdfs://hacluster/user/surbhi/datamap_test.csv' into table 
datamap_test OPTIONS('DELIMITER'=',', 
'QUOTECHAR'='"','BAD_RECORDS_ACTION'='FORCE','FILEHEADER'='id,name,salary,dob');

create datamap datamap_preaggr ON TABLE datamap_test USING "preaggregate" as 
select id,count(id) from datamap_test group by id;

create datamap dm_preag_bloom_cust_id on table datamap_test_datamap_preaggr 
using 'bloomfilter' dmproperties('index_columns'='datamap_test_id');

select id,count(id) from datamap_test where id = 12 group by id;

QUERY FAILED：Error: 
org.apache.spark.sql.catalyst.errors.package$TreeNodeException: execute, tree: 

drop datamap dm_preag_bloom_cust_id on table datamap_test_datamap_preaggr;

select id,count(id) from datamap_test where id = 12 group by id; 
QUERY OK

create datamap dm_preag_bloom_cust_id on table datamap_test_datamap_preaggr 
using 'bloomfilter' dmproperties('index_columns'='datamap_test_id');

drop datamap dm_preag_bloom_cust_id on table datamap_test_datamap_preaggr;

select id,count(id) from datamap_test where id = 12 group by id;

QUERY FAILED：Error: org.apache.spark.SparkException: Job aborted due to stage 
failure: Task 0 in stage 117.0 failed 4 times



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)