mirror of
https://github.com/apache/impala.git
synced 2026-01-22 18:02:34 -05:00
bbec8fa749
Adds additional tests to test_result_spooling.py to cover various edge cases when fetching query results (ensure all Impala types are returned properly, UDFs are evaluated correctly, etc.). A new QueryTest file result-spooling.test is added to encapsulate all these tests. Tests with a decreased ROW_BATCH_SIZE are added as well to validate that BufferedPlanRootSink buffers row batches correctly. BufferedPlanRootSink requires careful synchronization of the producer and consumer threads, especially when queries are cancelled. The TestResultSpoolingCancellation class is dedicated to running cancellation tests with SPOOL_QUERY_RESULTS = true. The implementation is heavily borrowed from test_cancellation.py and some of the logic is re-factored into a new utility class called cancel_utils.py to avoid code duplication between test_cancellation.py and test_result_spooling.py. Testing: * Looped test_result_spooling.py overnight with no failures * Core tests passed Change-Id: Ib3b3a1539c4a5fa9b43c8ca315cea16c9701e283 Reviewed-on: http://gerrit.cloudera.org:8080/13907 Reviewed-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com> Tested-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com>
114 lines
4.1 KiB
Plaintext
114 lines
4.1 KiB
Plaintext
====
|
|
---- QUERY
|
|
# Validate reading all types from a table when result spooling is enabled.
|
|
SET SPOOL_QUERY_RESULTS=true;
|
|
select * from alltypes order by id limit 10
|
|
---- RESULTS
|
|
0,true,0,0,0,0,0,0,'01/01/09','0',2009-01-01 00:00:00,2009,1
|
|
1,false,1,1,1,10,1.100000023841858,10.1,'01/01/09','1',2009-01-01 00:01:00,2009,1
|
|
2,true,2,2,2,20,2.200000047683716,20.2,'01/01/09','2',2009-01-01 00:02:00.100000000,2009,1
|
|
3,false,3,3,3,30,3.299999952316284,30.3,'01/01/09','3',2009-01-01 00:03:00.300000000,2009,1
|
|
4,true,4,4,4,40,4.400000095367432,40.4,'01/01/09','4',2009-01-01 00:04:00.600000000,2009,1
|
|
5,false,5,5,5,50,5.5,50.5,'01/01/09','5',2009-01-01 00:05:00.100000000,2009,1
|
|
6,true,6,6,6,60,6.599999904632568,60.59999999999999,'01/01/09','6',2009-01-01 00:06:00.150000000,2009,1
|
|
7,false,7,7,7,70,7.699999809265137,70.7,'01/01/09','7',2009-01-01 00:07:00.210000000,2009,1
|
|
8,true,8,8,8,80,8.800000190734863,80.8,'01/01/09','8',2009-01-01 00:08:00.280000000,2009,1
|
|
9,false,9,9,9,90,9.899999618530273,90.89999999999999,'01/01/09','9',2009-01-01 00:09:00.360000000,2009,1
|
|
---- TYPES
|
|
INT,BOOLEAN,TINYINT,SMALLINT,INT,BIGINT,FLOAT,DOUBLE,STRING,STRING,TIMESTAMP,INT,INT
|
|
====
|
|
---- QUERY
|
|
# Validates that column ordering is preserved when result spooling is enabled.
|
|
SET SPOOL_QUERY_RESULTS=true;
|
|
select month, year, timestamp_col, string_col, date_string_col, double_col, float_col,
|
|
bigint_col, int_col, smallint_col, tinyint_col, bool_col, id from alltypes
|
|
order by id limit 10
|
|
---- RESULTS
|
|
1,2009,2009-01-01 00:00:00,'0','01/01/09',0,0,0,0,0,0,true,0
|
|
1,2009,2009-01-01 00:01:00,'1','01/01/09',10.1,1.100000023841858,10,1,1,1,false,1
|
|
1,2009,2009-01-01 00:02:00.100000000,'2','01/01/09',20.2,2.200000047683716,20,2,2,2,true,2
|
|
1,2009,2009-01-01 00:03:00.300000000,'3','01/01/09',30.3,3.299999952316284,30,3,3,3,false,3
|
|
1,2009,2009-01-01 00:04:00.600000000,'4','01/01/09',40.4,4.400000095367432,40,4,4,4,true,4
|
|
1,2009,2009-01-01 00:05:00.100000000,'5','01/01/09',50.5,5.5,50,5,5,5,false,5
|
|
1,2009,2009-01-01 00:06:00.150000000,'6','01/01/09',60.59999999999999,6.599999904632568,60,6,6,6,true,6
|
|
1,2009,2009-01-01 00:07:00.210000000,'7','01/01/09',70.7,7.699999809265137,70,7,7,7,false,7
|
|
1,2009,2009-01-01 00:08:00.280000000,'8','01/01/09',80.8,8.800000190734863,80,8,8,8,true,8
|
|
1,2009,2009-01-01 00:09:00.360000000,'9','01/01/09',90.89999999999999,9.899999618530273,90,9,9,9,false,9
|
|
---- TYPES
|
|
INT,INT,TIMESTAMP,STRING,STRING,DOUBLE,FLOAT,BIGINT,INT,SMALLINT,TINYINT,BOOLEAN,INT
|
|
====
|
|
---- QUERY
|
|
# Validates that UDFs are properly evaluated when result spooling is enabled.
|
|
SET SPOOL_QUERY_RESULTS=true;
|
|
select abs(id), abs(int_col) + abs(int_col) from alltypes order by id limit 10
|
|
---- RESULTS
|
|
0,0
|
|
1,2
|
|
2,4
|
|
3,6
|
|
4,8
|
|
5,10
|
|
6,12
|
|
7,14
|
|
8,16
|
|
9,18
|
|
---- TYPES
|
|
BIGINT,BIGINT
|
|
====
|
|
---- QUERY
|
|
# Validates that queries with Agg nodes return correct results when result spooling is
|
|
# enabled.
|
|
SET SPOOL_QUERY_RESULTS=true;
|
|
select avg(int_col) + avg(bigint_col) from alltypes
|
|
---- RESULTS
|
|
49.5
|
|
---- TYPES
|
|
DOUBLE
|
|
====
|
|
---- QUERY
|
|
# Validates that queries with Join nodes return correct results when result spooling is
|
|
# enabled.
|
|
SET SPOOL_QUERY_RESULTS=true;
|
|
select j.test_name, d.name from jointbl j inner join dimtbl d on
|
|
(j.test_id = d.id)
|
|
---- RESULTS
|
|
'Name1','Name1'
|
|
'Name2','Name2'
|
|
'Name3','Name3'
|
|
'Name4','Name4'
|
|
'Name5','Name5'
|
|
'Name16','Name6'
|
|
'Name6','Name6'
|
|
'Name16','Name6'
|
|
'Name16','Name6'
|
|
'Name6','Name6'
|
|
'Name16','Name6'
|
|
---- TYPES
|
|
STRING,STRING
|
|
====
|
|
---- QUERY
|
|
# Validates that NULLs are properly handled when result spooling is enabled.
|
|
SET SPOOL_QUERY_RESULTS=true;
|
|
select * from nullrows order by id limit 10
|
|
---- RESULTS
|
|
'a','','NULL',NULL,NULL,'a','a',true
|
|
'b','','NULL',NULL,NULL,'a','NULL',false
|
|
'c','','NULL',NULL,NULL,'a','NULL',NULL
|
|
'd','','NULL',NULL,NULL,'a','NULL',NULL
|
|
'e','','NULL',NULL,NULL,'a','NULL',NULL
|
|
'f','','NULL',NULL,NULL,'f','f',true
|
|
'g','','NULL',NULL,NULL,'f','NULL',false
|
|
'h','','NULL',NULL,NULL,'f','NULL',NULL
|
|
'i','','NULL',NULL,NULL,'f','NULL',NULL
|
|
'j','','NULL',NULL,NULL,'f','NULL',NULL
|
|
---- TYPES
|
|
STRING,STRING,STRING,INT,DOUBLE,STRING,STRING,BOOLEAN
|
|
====
|
|
---- QUERY
|
|
SET SPOOL_QUERY_RESULTS=true;
|
|
select * from emptytable;
|
|
---- RESULTS
|
|
---- TYPES
|
|
STRING,INT
|
|
====
|