jprdonnelly/impala
1
0
Fork 0
mirror of https://github.com/apache/impala.git synced 2026-02-01 21:00:29 -05:00
Code Issues Projects Releases Wiki Activity
Files
ca5de24d6ab035fee7089f4dcd473da37abf0d73
impala/testdata/workloads/functional-query/queries/QueryTest/kudu_insert.test
wzhou-code 40da36414f IMPALA-11809: Support non unique primary key for Kudu 
Kudu engine recently enables the auto-incrementing column feature
(KUDU-1945). The feature works by appending a system generated
auto-incrementing column to the primary key columns to guarantee the
uniqueness on primary key when the primary key columns can be non
unique. The non unique primary key columns and the auto-incrementing
column form the effective unique composite primary key.

This auto-incrementing column is named as 'auto_incrementing_id' with
big int type. The assignment to it during insertion is automatic so
insertion statements should not specify values for auto-incrementing
column. In current Kudu implementation, there is no central key provider
for auto-incrementing columns. It uses a per tablet-server global
counter to assign values for auto-incrementing columns. So the values
of auto-incrementing columns are not unique in a Kudu table, but unique
within a continuous region of the table served by a tablet-server.

This patch also upgraded Kudu version to 345fd44ca3 to pick up Kudu
changes needed for supporting non-unique primary key. It added
syntactic support for creating Kudu table with non unique primary key.
When creating a Kudu table, specifying PRIMARY KEY is optional.
If there is no primary key attribute specified, the partition key
columns will be promoted as non unique primary key if those columns
are the beginning columns of the table.
New column "key_unique" is added to the output of 'describe' table
command for Kudu table.

Examples of CREATE TABLE statement with non unique primary key:
  CREATE TABLE tbl (i INT NON UNIQUE PRIMARY KEY, s STRING)
  PARTITION BY HASH (i) PARTITIONS 3
  STORED as KUDU;

  CREATE TABLE tbl (i INT, s STRING, NON UNIQUE PRIMARY KEY(i))
  PARTITION BY HASH (i) PARTITIONS 3
  STORED as KUDU;

  CREATE TABLE tbl NON UNIQUE PRIMARY KEY(id)
  PARTITION BY HASH (id) PARTITIONS 3
  STORED as KUDU
  AS SELECT id, string_col FROM functional.alltypes WHERE id = 10;

  CREATE TABLE tbl NON UNIQUE PRIMARY KEY(id)
  PARTITION BY RANGE (id)
  (PARTITION VALUES <= 1000,
   PARTITION 1000 < VALUES <= 2000,
   PARTITION 2000 < VALUES <= 3000,
   PARTITION 3000 < VALUES)
  STORED as KUDU
  AS SELECT id, int_col FROM functional.alltypestiny ORDER BY id ASC
   LIMIT 4000;

  CREATE TABLE tbl (id INT, name STRING, NON UNIQUE PRIMARY KEY(id))
  STORED as KUDU;

  CREATE TABLE tbl (a INT, b STRING, c FLOAT)
  PARTITION BY HASH (a, b) PARTITIONS 3
  STORED as KUDU;

SELECT statement does not show the system generated auto-incrementing
column unless the column is explicitly specified in the select list.
Auto-incrementing column cannot be added, removed or renamed with
ALTER TABLE statements.
UPSERT operation is not supported now for Kudu tables with auto
incrementing column due to limitation in Kudu engine.

Testing:
 - Ran manual test in impala-shell with queries to create Kudu tables
   with non unique primary key, and tested insert/update/delete
   operations for these tables with non unique primary key.
 - Added front end tests, and end to end unit tests for Kudu tables
   with non unique primary key.
 - Passed exhaustive test.

Change-Id: I4d7882bf3d01a3492cc9827c072d1f3200d9eebd
Reviewed-on: http://gerrit.cloudera.org:8080/19383
Reviewed-by: Riza Suminto <riza.suminto@cloudera.com>
Reviewed-by: Wenzhe Zhou <wzhou@cloudera.com>
Tested-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com>
2023-02-04 07:34:56 +00:00

682 lines
25 KiB
Plaintext
Raw Blame History

====
---- QUERY
create table tdata
(id int primary key, valf float null, vali bigint null, valv string null,
valb boolean null, valt tinyint null, vals smallint null, vald double null,
ts timestamp, decimal4 decimal(9,9) null, decimal8 decimal(18,2) null,
decimal16 decimal(38, 0) null, valdate date null, valvc varchar(10) null)
PARTITION BY RANGE (PARTITION VALUES < 10, PARTITION 10 <= VALUES < 30,
PARTITION 30 <= VALUES) STORED AS KUDU
---- RESULTS
'Table has been created.'
====
---- QUERY
# VALUES, single row, all target cols, no errors
insert into tdata values (1, 1, 1, 'one', true, 1, 1, 1,
cast('1987-05-19 00:00:00' as timestamp), 0.000000001, 1.00, 1, DATE '1970-01-01', cast('one' as varchar(10)))
---- RUNTIME_PROFILE
NumModifiedRows: 1
NumRowErrors: 0
---- LABELS
ID, VALF, VALI, VALV, VALB, VALT, VALS, VALD, TS, DECIMAL4, DECIMAL8, DECIMAL16, VALDATE, VALVC
---- DML_RESULTS: tdata
1,1,1,'one',true,1,1,1,1987-05-19 00:00:00,0.000000001,1.00,1,1970-01-01,'one'
---- TYPES
INT,FLOAT,BIGINT,STRING,BOOLEAN,TINYINT,SMALLINT,DOUBLE,TIMESTAMP,DECIMAL,DECIMAL,DECIMAL,DATE,STRING
====
---- QUERY
# VALUES, single row, all target cols, NULL
insert into tdata values (2, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL)
---- RUNTIME_PROFILE
NumModifiedRows: 1
NumRowErrors: 0
---- LABELS
ID, VALF, VALI, VALV, VALB, VALT, VALS, VALD, TS, DECIMAL4, DECIMAL8, DECIMAL16, VALDATE, VALVC
---- DML_RESULTS: tdata
1,1,1,'one',true,1,1,1,1987-05-19 00:00:00,0.000000001,1.00,1,1970-01-01,'one'
2,NULL,NULL,'NULL',NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'NULL'
---- TYPES
INT,FLOAT,BIGINT,STRING,BOOLEAN,TINYINT,SMALLINT,DOUBLE,TIMESTAMP,DECIMAL,DECIMAL,DECIMAL,DATE,STRING
====
---- QUERY
# VALUES, single row, all target cols, boundary values. The timestamp value is the max
# possible value that Impala can represent; it gets truncated rather than rounded up to
# the nearest microsecond. If it were rounded up, it wouldn't be readable by Impala.
insert into tdata values
(3, cast('nan' as float), max_bigint(), '', true, min_tinyint(), max_smallint(),
cast('-inf' as double),
nanoseconds_add(cast('9999-12-31 23:59:59' as timestamp), 999999999),
0.999999999, 9999999999999999.99, 99999999999999999999999999999999999999, DATE '9999-12-31', cast('' as varchar(10)))
---- RUNTIME_PROFILE
NumModifiedRows: 1
NumRowErrors: 0
---- LABELS
ID, VALF, VALI, VALV, VALB, VALT, VALS, VALD, TS, DECIMAL4, DECIMAL8, DECIMAL16, VALDATE, VALVC
---- DML_RESULTS: tdata
1,1,1,'one',true,1,1,1,1987-05-19 00:00:00,0.000000001,1.00,1,1970-01-01,'one'
2,NULL,NULL,'NULL',NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'NULL'
3,NaN,9223372036854775807,'',true,-128,32767,-Infinity,9999-12-31 23:59:59.999999000,0.999999999,9999999999999999.99,99999999999999999999999999999999999999,9999-12-31,''
---- TYPES
INT,FLOAT,BIGINT,STRING,BOOLEAN,TINYINT,SMALLINT,DOUBLE,TIMESTAMP,DECIMAL,DECIMAL,DECIMAL,DATE,STRING
====
---- QUERY
# VALUES, single row, subset of target cols
insert into tdata (valb, vald, id) values (true, 0, 4)
---- RUNTIME_PROFILE
NumModifiedRows: 1
NumRowErrors: 0
---- LABELS
ID, VALF, VALI, VALV, VALB, VALT, VALS, VALD, TS, DECIMAL4, DECIMAL8, DECIMAL16, VALDATE, VALVC
---- DML_RESULTS: tdata
1,1,1,'one',true,1,1,1,1987-05-19 00:00:00,0.000000001,1.00,1,1970-01-01,'one'
2,NULL,NULL,'NULL',NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'NULL'
3,NaN,9223372036854775807,'',true,-128,32767,-Infinity,9999-12-31 23:59:59.999999000,0.999999999,9999999999999999.99,99999999999999999999999999999999999999,9999-12-31,''
4,NULL,NULL,'NULL',true,NULL,NULL,0,NULL,NULL,NULL,NULL,NULL,'NULL'
---- TYPES
INT,FLOAT,BIGINT,STRING,BOOLEAN,TINYINT,SMALLINT,DOUBLE,TIMESTAMP,DECIMAL,DECIMAL,DECIMAL,DATE,STRING
====
---- QUERY
# VALUES, multiple rows, all target cols
insert into tdata values
(5, 5.0, 5, 'five', false, NULL, NULL, NULL, NULL, NULL, NULL, NULL,NULL, cast('five' as varchar(10))),
(6, 16, 60, '', true, 0, -1, -6, cast('2010-12-31 23:59:59' as timestamp), -0.000000001, -1.00, -1, DATE '1970-01-01', cast ('' as varchar(10))),
(7, NULL, 10, NULL, false, max_tinyint(), -7, 2, cast('1400-01-01 00:00:00' as timestamp), 0.000000000, 0.00, 0, DATE '1970-01-01', NULL)
---- RUNTIME_PROFILE
NumModifiedRows: 3
NumRowErrors: 0
---- LABELS
ID, VALF, VALI, VALV, VALB, VALT, VALS, VALD, TS, DECIMAL4, DECIMAL8, DECIMAL16, VALDATE, VALVC
---- DML_RESULTS: tdata
1,1,1,'one',true,1,1,1,1987-05-19 00:00:00,0.000000001,1.00,1,1970-01-01,'one'
2,NULL,NULL,'NULL',NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'NULL'
3,NaN,9223372036854775807,'',true,-128,32767,-Infinity,9999-12-31 23:59:59.999999000,0.999999999,9999999999999999.99,99999999999999999999999999999999999999,9999-12-31,''
4,NULL,NULL,'NULL',true,NULL,NULL,0,NULL,NULL,NULL,NULL,NULL,'NULL'
5,5.0,5,'five',false,NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'five'
6,16,60,'',true,0,-1,-6,2010-12-31 23:59:59,-0.000000001,-1.00,-1,1970-01-01,''
7,NULL,10,'NULL',false,127,-7,2,1400-01-01 00:00:00,0.000000000,0.00,0,1970-01-01,'NULL'
---- TYPES
INT,FLOAT,BIGINT,STRING,BOOLEAN,TINYINT,SMALLINT,DOUBLE,TIMESTAMP,DECIMAL,DECIMAL,DECIMAL,DATE,STRING
====
---- QUERY
# VALUES, multiple rows, subset of cols
insert into tdata (valv, valf, vali, id) values
('eight', 88, 888, 8),
(NULL, -9, -99, 9)
---- RUNTIME_PROFILE
NumModifiedRows: 2
NumRowErrors: 0
---- LABELS
ID, VALF, VALI, VALV, VALB, VALT, VALS, VALD, TS, DECIMAL4, DECIMAL8, DECIMAL16, VALDATE, VALVC
---- DML_RESULTS: tdata
1,1,1,'one',true,1,1,1,1987-05-19 00:00:00,0.000000001,1.00,1,1970-01-01,'one'
2,NULL,NULL,'NULL',NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'NULL'
3,NaN,9223372036854775807,'',true,-128,32767,-Infinity,9999-12-31 23:59:59.999999000,0.999999999,9999999999999999.99,99999999999999999999999999999999999999,9999-12-31,''
4,NULL,NULL,'NULL',true,NULL,NULL,0,NULL,NULL,NULL,NULL,NULL,'NULL'
5,5.0,5,'five',false,NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'five'
6,16,60,'',true,0,-1,-6,2010-12-31 23:59:59,-0.000000001,-1.00,-1,1970-01-01,''
7,NULL,10,'NULL',false,127,-7,2,1400-01-01 00:00:00,0.000000000,0.00,0,1970-01-01,'NULL'
8,88,888,'eight',NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'NULL'
9,-9,-99,'NULL',NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'NULL'
---- TYPES
INT,FLOAT,BIGINT,STRING,BOOLEAN,TINYINT,SMALLINT,DOUBLE,TIMESTAMP,DECIMAL,DECIMAL,DECIMAL,DATE,STRING
====
---- QUERY
# SELECT, single row, all target cols
insert into tdata
select id, float_col, bigint_col, string_col, bool_col, tinyint_col, smallint_col,
double_col, timestamp_col, NULL, NULL, NULL, NULL, NULL
from functional.alltypes where id = 10
---- RUNTIME_PROFILE
NumModifiedRows: 1
NumRowErrors: 0
---- LABELS
ID, VALF, VALI, VALV, VALB, VALT, VALS, VALD, TS, DECIMAL4, DECIMAL8, DECIMAL16, VALDATE, VALVC
---- DML_RESULTS: tdata
1,1,1,'one',true,1,1,1,1987-05-19 00:00:00,0.000000001,1.00,1,1970-01-01,'one'
2,NULL,NULL,'NULL',NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'NULL'
3,NaN,9223372036854775807,'',true,-128,32767,-Infinity,9999-12-31 23:59:59.999999000,0.999999999,9999999999999999.99,99999999999999999999999999999999999999,9999-12-31,''
4,NULL,NULL,'NULL',true,NULL,NULL,0,NULL,NULL,NULL,NULL,NULL,'NULL'
5,5.0,5,'five',false,NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'five'
6,16,60,'',true,0,-1,-6,2010-12-31 23:59:59,-0.000000001,-1.00,-1,1970-01-01,''
7,NULL,10,'NULL',false,127,-7,2,1400-01-01 00:00:00,0.000000000,0.00,0,1970-01-01,'NULL'
8,88,888,'eight',NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'NULL'
9,-9,-99,'NULL',NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'NULL'
10,0,0,'0',true,0,0,0,2009-01-02 00:10:00.450000000,NULL,NULL,NULL,NULL,'NULL'
---- TYPES
INT,FLOAT,BIGINT,STRING,BOOLEAN,TINYINT,SMALLINT,DOUBLE,TIMESTAMP,DECIMAL,DECIMAL,DECIMAL,DATE,STRING
====
---- QUERY
# SELECT, single row, subset of cols
insert into tdata (id, vald, valb, vali, ts)
select id, double_col, bool_col, bigint_col, timestamp_col
from functional.alltypes where id = 11
---- RUNTIME_PROFILE
NumModifiedRows: 1
NumRowErrors: 0
---- LABELS
ID, VALF, VALI, VALV, VALB, VALT, VALS, VALD, TS, DECIMAL4, DECIMAL8, DECIMAL16, VALDATE, VALVC
---- DML_RESULTS: tdata
1,1,1,'one',true,1,1,1,1987-05-19 00:00:00,0.000000001,1.00,1,1970-01-01,'one'
2,NULL,NULL,'NULL',NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'NULL'
3,NaN,9223372036854775807,'',true,-128,32767,-Infinity,9999-12-31 23:59:59.999999000,0.999999999,9999999999999999.99,99999999999999999999999999999999999999,9999-12-31,''
4,NULL,NULL,'NULL',true,NULL,NULL,0,NULL,NULL,NULL,NULL,NULL,'NULL'
5,5.0,5,'five',false,NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'five'
6,16,60,'',true,0,-1,-6,2010-12-31 23:59:59,-0.000000001,-1.00,-1,1970-01-01,''
7,NULL,10,'NULL',false,127,-7,2,1400-01-01 00:00:00,0.000000000,0.00,0,1970-01-01,'NULL'
8,88,888,'eight',NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'NULL'
9,-9,-99,'NULL',NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,'NULL'
10,0,0,'0',true,0,0,0,2009-01-02 00:10:00.450000000,NULL,NULL,NULL,NULL,'NULL'
11,NULL,10,'NULL',false,NULL,NULL,10.1,2009-01-02 00:11:00.450000000,NULL,NULL,NULL,NULL,'NULL'
---- TYPES
INT,FLOAT,BIGINT,STRING,BOOLEAN,TINYINT,SMALLINT,DOUBLE,TIMESTAMP,DECIMAL,DECIMAL,DECIMAL,DATE,STRING
====
---- QUERY
delete tdata
---- DML_RESULTS: tdata
====
---- QUERY
# SELECT, multiple rows, all target cols
insert into tdata
select id, float_col, bigint_col, string_col, bool_col, tinyint_col, smallint_col,
double_col, timestamp_col, NULL, NULL, NULL, NULL, cast(string_col as varchar(10))
from functional.alltypes where id < 2
---- RUNTIME_PROFILE
NumModifiedRows: 2
NumRowErrors: 0
---- LABELS
ID, VALF, VALI, VALV, VALB, VALT, VALS, VALD, TS, DECIMAL4, DECIMAL8, DECIMAL16, VALDATE, VALVC
---- DML_RESULTS: tdata
0,0,0,'0',true,0,0,0,2009-01-01 00:00:00,NULL,NULL,NULL,NULL,'0'
1,1.100000023841858,10,'1',false,1,1,10.1,2009-01-01 00:01:00,NULL,NULL,NULL,NULL,'1'
---- TYPES
INT,FLOAT,BIGINT,STRING,BOOLEAN,TINYINT,SMALLINT,DOUBLE,TIMESTAMP,DECIMAL,DECIMAL,DECIMAL,DATE,STRING
====
---- QUERY
# SELECT, multiple rows, subset of cols
insert into tdata (vals, id, valt, vald, ts)
select smallint_col, id, tinyint_col, double_col, timestamp_col
from functional.alltypes where id > 2 and id < 6
---- RUNTIME_PROFILE
NumModifiedRows: 3
NumRowErrors: 0
---- LABELS
ID, VALF, VALI, VALV, VALB, VALT, VALS, VALD, TS, DECIMAL4, DECIMAL8, DECIMAL16, VALDATE, VALVC
---- DML_RESULTS: tdata
0,0,0,'0',true,0,0,0,2009-01-01 00:00:00,NULL,NULL,NULL,NULL,'0'
1,1.100000023841858,10,'1',false,1,1,10.1,2009-01-01 00:01:00,NULL,NULL,NULL,NULL,'1'
3,NULL,NULL,'NULL',NULL,3,3,30.3,2009-01-01 00:03:00.300000000,NULL,NULL,NULL,NULL,'NULL'
4,NULL,NULL,'NULL',NULL,4,4,40.4,2009-01-01 00:04:00.600000000,NULL,NULL,NULL,NULL,'NULL'
5,NULL,NULL,'NULL',NULL,5,5,50.5,2009-01-01 00:05:00.100000000,NULL,NULL,NULL,NULL,'NULL'
---- TYPES
INT,FLOAT,BIGINT,STRING,BOOLEAN,TINYINT,SMALLINT,DOUBLE,TIMESTAMP,DECIMAL,DECIMAL,DECIMAL,DATE,STRING
====
---- QUERY
# Make sure we can insert empty strings into string columns and that we can scan them
# back.
insert into tdata values (320, 2.0, 932, cast('' as string), false, 0, 0, 0, NULL, NULL, NULL, NULL, NULL, cast('' as varchar(10)))
---- RESULTS
: 1
---- RUNTIME_PROFILE
NumModifiedRows: 1
NumRowErrors: 0
====
---- QUERY
select id, valv, valb, valvc from tdata where id = 320;
---- RESULTS
320,'',false,''
---- TYPES
INT,STRING,BOOLEAN,STRING
====
---- QUERY
insert into tdata values
(666, cast(1.2 as float), 43, cast('z' as string), true, 0, 0, 0, NULL, NULL, NULL, NULL, NULL, NULL)
---- RESULTS
: 1
---- RUNTIME_PROFILE
NumModifiedRows: 1
NumRowErrors: 0
====
---- QUERY
# insert row with primary key that already exists
insert into tdata values
(666, cast(1.2 as float), 43, cast('z' as VARCHAR(20)), true, 0, 0, 0, NULL, NULL, NULL, NULL, NULL, NULL)
---- RESULTS
: 0
---- RUNTIME_PROFILE
NumModifiedRows: 0
NumRowErrors: 1
====
---- QUERY
create table kudu_test_tbl primary key(id)
partition by range(id) (partition values < 100, partition 100 <= values <= 10000)
stored as kudu as
select * from functional_kudu.alltypes where id < 100;
---- RESULTS
'Inserted 100 row(s)'
---- RUNTIME_PROFILE
NumModifiedRows: 100
NumRowErrors: 0
====
---- QUERY
insert into kudu_test_tbl
select * from functional_kudu.alltypes where id < 100;
---- RESULTS
: 0
---- RUNTIME_PROFILE
NumModifiedRows: 0
NumRowErrors: 100
====
---- QUERY
# large insert - 100 rows were already inserted above and result in errors
insert into kudu_test_tbl
select * from functional_kudu.alltypes;
---- RESULTS
: 7200
---- RUNTIME_PROFILE
NumModifiedRows: 7200
NumRowErrors: 100
====
---- QUERY
# Insert rows that are not covered by any of the existing range partitions
# Only the row at 10000 is inserted.
insert into kudu_test_tbl SELECT cast(id + 10000 as int), bool_col, tinyint_col,
smallint_col, int_col, bigint_col, float_col, double_col, date_string_col, string_col,
timestamp_col, year, month
from functional_kudu.alltypes
---- RUNTIME_PROFILE
NumModifiedRows: 1
NumRowErrors: 7299
====
---- QUERY
# Table with all supported types as primary key and distribution columns
create table allkeytypes (i1 tinyint, i2 smallint, i3 int, i4 bigint, name string,
valt timestamp, valvc varchar(10), valf float, vald double,
primary key (i1, i2, i3, i4, name, valt, valvc))
partition by hash partitions 3, range
(partition value = (1,1,1,1,'1','2009-01-01 00:01:00',cast('1' as varchar(10))),
partition value = (2,2,2,2,'2','2009-01-01 00:02:00.100000000',cast('2' as varchar(10))),
partition value = (3,3,3,3,'3','2009-01-01 00:03:00.300000000',cast('3' as varchar(10)))) stored as kudu
---- RESULTS
'Table has been created.'
====
---- QUERY
insert into allkeytypes select cast(id as tinyint), smallint_col, int_col,
cast (bigint_col/10 as bigint), string_col, timestamp_col, cast(string_col as varchar(10)), float_col, double_col
from functional.alltypes where id > 1 and id < 10
---- RESULTS
: 2
---- RUNTIME_PROFILE
NumModifiedRows: 2
NumRowErrors: 6
====
---- QUERY
# IMPALA-5871 - test that a cast is correctly added when inserting a string into a Kudu
# timestamp partition column with distributed exec.
insert into allkeytypes values (1,1,1,1,'1','2009-01-01 00:01:00',cast('1' as varchar(10)),null,null)
---- RESULTS
: 1
---- RUNTIME_PROFILE
NumModifiedRows: 1
NumRowErrors: 0
row_regex: .*EXEC_SINGLE_NODE_ROWS_THRESHOLD=0.*
====
---- QUERY
create table timestampkey (t timestamp primary key)
partition by hash(t) PARTITIONS 2 stored as kudu;
====
---- QUERY
# Regression test for IMPALA-8909 (used to hit a DCHECK in debug builds).
insert into timestampkey select concat(string_col, " ") from functional.alltypessmall;
---- RESULTS
: 0
---- RUNTIME_PROFILE
NumModifiedRows: 0
NumRowErrors: 100
====
---- QUERY
# Table with default values
create table tbl_with_defaults (a int primary key, b int null default 10,
c int not null default 100, d int default 1000, e int null, f int not null,
g string default 'test', h boolean default true,
i decimal(9, 2) default 1111.11, j varchar(10) default cast('foo' as varchar(10)))
partition by hash (a) partitions 3 stored as kudu
---- RESULTS
'Table has been created.'
====
---- QUERY
insert into tbl_with_defaults (a, f) values (1, 1), (2, 2), (3, 3), (4, 4)
---- RUNTIME_PROFILE
NumModifiedRows: 4
NumRowErrors: 0
---- LABELS
A, B, C, D, E, F, G, H, I, J
---- DML_RESULTS: tbl_with_defaults
1,10,100,1000,NULL,1,'test',true,1111.11,'foo'
2,10,100,1000,NULL,2,'test',true,1111.11,'foo'
3,10,100,1000,NULL,3,'test',true,1111.11,'foo'
4,10,100,1000,NULL,4,'test',true,1111.11,'foo'
---- TYPES
INT,INT,INT,INT,INT,INT,STRING,BOOLEAN,DECIMAL,STRING
====
---- QUERY
insert into tbl_with_defaults values (5, 5, 5, 5, 5, 5, 'row', false, 55555.55, cast('row' as varchar(10)))
---- RUNTIME_PROFILE
NumModifiedRows: 1
NumRowErrors: 0
---- LABELS
A, B, C, D, E, F, G, H, I, J
---- DML_RESULTS: tbl_with_defaults
1,10,100,1000,NULL,1,'test',true,1111.11,'foo'
2,10,100,1000,NULL,2,'test',true,1111.11,'foo'
3,10,100,1000,NULL,3,'test',true,1111.11,'foo'
4,10,100,1000,NULL,4,'test',true,1111.11,'foo'
5,5,5,5,5,5,'row',false,55555.55,'row'
---- TYPES
INT,INT,INT,INT,INT,INT,STRING,BOOLEAN,DECIMAL,STRING
====
---- QUERY
alter table tbl_with_defaults add columns (k int null, l int not null default 10000)
---- RESULTS
'Column(s) have been added.'
====
---- QUERY
select * from tbl_with_defaults
---- RESULTS
1,10,100,1000,NULL,1,'test',true,1111.11,'foo',NULL,10000
2,10,100,1000,NULL,2,'test',true,1111.11,'foo',NULL,10000
3,10,100,1000,NULL,3,'test',true,1111.11,'foo',NULL,10000
4,10,100,1000,NULL,4,'test',true,1111.11,'foo',NULL,10000
5,5,5,5,5,5,'row',false,55555.55,'row',NULL,10000
---- TYPES
INT,INT,INT,INT,INT,INT,STRING,BOOLEAN,DECIMAL,STRING,INT,INT
====
---- QUERY
insert into tbl_with_defaults values (6,6,6,6,6,6,'another row',false,66666.66,cast('another' as varchar(10)),6,6)
---- RUNTIME_PROFILE
NumModifiedRows: 1
NumRowErrors: 0
---- LABELS
A, B, C, D, E, F, G, H, I, J, K, L
---- DML_RESULTS: tbl_with_defaults
1,10,100,1000,NULL,1,'test',true,1111.11,'foo',NULL,10000
2,10,100,1000,NULL,2,'test',true,1111.11,'foo',NULL,10000
3,10,100,1000,NULL,3,'test',true,1111.11,'foo',NULL,10000
4,10,100,1000,NULL,4,'test',true,1111.11,'foo',NULL,10000
5,5,5,5,5,5,'row',false,55555.55,'row',NULL,10000
6,6,6,6,6,6,'another row',false,66666.66,'another',6,6
---- TYPES
INT,INT,INT,INT,INT,INT,STRING,BOOLEAN,DECIMAL,STRING,INT,INT
====
---- QUERY
# IMPALA-5217: Try to insert NULL to a 'NOT NULL' col with a target col list that leaves
# out some cols.
insert into tbl_with_defaults (a, c, f) values (0, null, 1)
---- RUNTIME_PROFILE
NumModifiedRows: 0
NumRowErrors: 1
====
---- QUERY
# IMPALA-5217: Insert NULL into a nullable col when a non-nullable col has been left out
# of the target col list.
insert into tbl_with_defaults (a, b, d, f) values (0, 0, null, 0)
---- RUNTIME_PROFILE
NumModifiedRows: 1
NumRowErrors: 0
---- LABELS
A, B, C, D, E, F, G, H, I, J, K, L
---- DML_RESULTS: tbl_with_defaults
0,0,100,NULL,NULL,0,'test',true,1111.11,'foo',NULL,10000
1,10,100,1000,NULL,1,'test',true,1111.11,'foo',NULL,10000
2,10,100,1000,NULL,2,'test',true,1111.11,'foo',NULL,10000
3,10,100,1000,NULL,3,'test',true,1111.11,'foo',NULL,10000
4,10,100,1000,NULL,4,'test',true,1111.11,'foo',NULL,10000
5,5,5,5,5,5,'row',false,55555.55,'row',NULL,10000
6,6,6,6,6,6,'another row',false,66666.66,'another',6,6
---- TYPES
INT,INT,INT,INT,INT,INT,STRING,BOOLEAN,DECIMAL,STRING,INT,INT
====
---- QUERY
# Test VARCHAR truncation
insert into tbl_with_defaults values (7,7,7,7,7,7,'another row',false,77777.77,cast('sevensevensevenseven' as varchar(10)),7,7)
---- RUNTIME_PROFILE
NumModifiedRows: 1
NumRowErrors: 0
---- LABELS
A, B, C, D, E, F, G, H, I, J, K, L
---- DML_RESULTS: tbl_with_defaults
0,0,100,NULL,NULL,0,'test',true,1111.11,'foo',NULL,10000
1,10,100,1000,NULL,1,'test',true,1111.11,'foo',NULL,10000
2,10,100,1000,NULL,2,'test',true,1111.11,'foo',NULL,10000
3,10,100,1000,NULL,3,'test',true,1111.11,'foo',NULL,10000
4,10,100,1000,NULL,4,'test',true,1111.11,'foo',NULL,10000
5,5,5,5,5,5,'row',false,55555.55,'row',NULL,10000
6,6,6,6,6,6,'another row',false,66666.66,'another',6,6
7,7,7,7,7,7,'another row',false,77777.77,'sevenseven',7,7
---- TYPES
INT,INT,INT,INT,INT,INT,STRING,BOOLEAN,DECIMAL,STRING,INT,INT
====
---- QUERY
create table multiple_partition_cols (x bigint, y bigint, z string, primary key(x, y))
partition by hash(x, y) partitions 8 stored as kudu
---- RESULTS
'Table has been created.'
====
---- QUERY
# SELECT with constant
insert into multiple_partition_cols select 0, bigint_col, string_col
from functional.alltypes where id = 0
---- RUNTIME_PROFILE
NumModifiedRows: 1
NumRowErrors: 0
---- LABELS
X,Y,Z
---- DML_RESULTS: multiple_partition_cols
0,0,'0'
---- TYPES
BIGINT,BIGINT,STRING
====
---- QUERY
# SELECT with constant NULL
insert into multiple_partition_cols select bigint_col, null, string_col
from functional.alltypes where id = 1
---- RESULTS
: 0
---- RUNTIME_PROFILE
NumModifiedRows: 0
NumRowErrors: 1
====
---- QUERY
create table dates (valdate date primary key) stored as kudu
---- RESULTS
'Table has been created.'
---- ERRORS
Unpartitioned Kudu tables are inefficient for large data sizes.
====
---- QUERY
insert into dates values
(date '1970-01-01'),
(date '0001-01-01'),
(date '9999-12-31')
---- RUNTIME_PROFILE
NumModifiedRows: 3
NumRowErrors: 0
---- LABELS
VALDATE
---- DML_RESULTS: dates
1970-01-01
0001-01-01
9999-12-31
---- TYPES
DATE
====
---- QUERY
create table orders_key_only (o_orderkey bigint primary key)
partition by range(o_orderkey) (
partition values <= 1000000,
partition 1000000 < values <= 2000000,
partition 2000000 < values <= 3000000,
partition 3000000 < values <= 4000000,
partition 4000000 < values <= 5000000,
partition 5000000 < values )
stored as kudu;
---- RESULTS
'Table has been created.'
====
---- QUERY
# Very large insert to test concurrency and partitioning. Regression test for IMPALA-9782
# when run with mt_dop > 1. Note that we need to run against the kudu version of the table
# so that there's enough parallelism to reproduce the bug.
insert into orders_key_only
select o_orderkey from tpch_kudu.orders;
---- RESULTS
: 1500000
---- RUNTIME_PROFILE
NumModifiedRows: 1500000
NumRowErrors: 0
====
---- QUERY
# Create Kudu table with non unique primary key
create table insert_non_unique_key_test_tbl1
(id int non unique primary key, vali bigint null, valv string null)
PARTITION BY RANGE (PARTITION VALUES < 10, PARTITION 10 <= VALUES < 30,
PARTITION 30 <= VALUES) STORED AS KUDU
---- RESULTS
'Table has been created.'
====
---- QUERY
# Insert VALUES with single row
insert into insert_non_unique_key_test_tbl1 values (1, 1, 'one')
---- RUNTIME_PROFILE
NumModifiedRows: 1
NumRowErrors: 0
---- LABELS
ID, VALI, VALV
---- DML_RESULTS: insert_non_unique_key_test_tbl1
1,1,'one'
---- TYPES
INT,BIGINT,STRING
====
---- QUERY
# Insert VALUES with multiple rows
insert into insert_non_unique_key_test_tbl1
(id, vali, valv) values (2, 2, 'two'), (3, 3, 'three')
---- RUNTIME_PROFILE
NumModifiedRows: 2
NumRowErrors: 0
====
---- QUERY
# Try to insert a row with value for auto_incrementing_id column
insert into insert_non_unique_key_test_tbl1
(id, auto_incrementing_id, vali, valv) values (4, 4, 4, 'four')
---- CATCH
auto-incrementing column is incorrectly set
====
---- QUERY
# Try to insert a row with value for auto_incrementing_id column
insert into insert_non_unique_key_test_tbl1
(id, auto_incrementing_id) values (5, 50000)
---- CATCH
auto-incrementing column is incorrectly set
====
---- QUERY
# Try to insert a row without value for key column
insert into insert_non_unique_key_test_tbl1
(vali, valv) values (6, 'six')
---- CATCH
AnalysisException: All primary key columns must be specified for INSERTing into Kudu tables. Missing columns are: id
====
---- QUERY
# Insert VALUES with SELECT from other table
insert into insert_non_unique_key_test_tbl1
select id, bigint_col, string_col from functional.alltypes where id = 10
---- RUNTIME_PROFILE
NumModifiedRows: 1
NumRowErrors: 0
====
---- QUERY
select * from insert_non_unique_key_test_tbl1 order by id;
---- RESULTS
1,1,'one'
2,2,'two'
3,3,'three'
10,0,'0'
---- TYPES
INT,BIGINT,STRING
====
---- QUERY
# Create Kudu table in CTAS statement with non unique primary key
create table insert_non_unique_key_test_tbl2 non unique primary key (id)
partition by hash (id) partitions 3
stored as kudu
as select * from insert_non_unique_key_test_tbl1;
select * from insert_non_unique_key_test_tbl2 order by id;
---- RESULTS
1,1,'one'
2,2,'two'
3,3,'three'
10,0,'0'
---- TYPES
INT,BIGINT,STRING
====
---- QUERY
# Create Kudu table with non unique primary key
create table insert_non_unique_key_test_tbl3
(id int non unique primary key, vali bigint null, valv string null)
partition by hash (id) partitions 3 stored as kudu
---- RESULTS
'Table has been created.'
====
---- QUERY
# Insert VALUES with SELECT from other table
insert into insert_non_unique_key_test_tbl3
select * from insert_non_unique_key_test_tbl2
---- RUNTIME_PROFILE
NumModifiedRows: 4
NumRowErrors: 0
====
---- QUERY
select * from insert_non_unique_key_test_tbl3 order by id;
---- RESULTS
1,1,'one'
2,2,'two'
3,3,'three'
10,0,'0'
---- TYPES
INT,BIGINT,STRING
====
---- QUERY
# Create Kudu table with non unique primary key
create table insert_non_unique_key_test_tbl4
(id int non unique primary key, vali bigint null, valv string null)
partition by range (id)
(partition value = 0, partition value = 1,
partition value = 2, partition value = 3)
stored as kudu
---- RESULTS
'Table has been created.'
====
---- QUERY
# Insert two rows
insert into insert_non_unique_key_test_tbl4 values (1, 1, 'one'), (2, 2, 'two');
---- RUNTIME_PROFILE
NumModifiedRows: 2
NumRowErrors: 0
====
---- QUERY
# Insert two rows with duplicated values for non unique primary key
insert into insert_non_unique_key_test_tbl4 values (1, 10, 'ten'), (1, 11, 'eleven');
---- RUNTIME_PROFILE
NumModifiedRows: 2
NumRowErrors: 0
====
---- QUERY
select id, vali, valv, auto_incrementing_id from insert_non_unique_key_test_tbl4
order by id, auto_incrementing_id;
---- RESULTS
1,1,'one',1
1,10,'ten',2
1,11,'eleven',3
2,2,'two',1
---- TYPES
INT,BIGINT,STRING,BIGINT
====
Reference in New Issue View Git Blame Copy Permalink