mirror of
https://github.com/MariaDB/server.git
synced 2025-07-27 18:02:13 +03:00
MDEV-31724 Compressed varchar values lost on joins when sorting on columns from joined table(s)
Field_varstring::get_copy_func() did not take into account
that functions do_varstring1[_mb], do_varstring2[_mb] do not support
compressed data.
Changing the return value of Field_varstring::get_copy_func()
to `do_field_string` if there is a compresion and truncation
at the same time. This fixes the problem, so now it works as follows:
- val_str() uncompresses the data
- The prefix is then calculated on the uncompressed data
Additionally, introducing two new copying functions
- do_varstring1_no_truncation()
- do_varstring2_no_truncation()
Using new copying functions in cases when:
- a Field_varstring with length_bytes==1 is changing to a longer
Field_varstring with length_bytes==1
- a Field_varstring with length_bytes==2 is changing to a longer
Field_varstring with length_bytes==2
In these cases we don't care neither of compression nor
of multi-byte prefixes: the entire data gets fully copied
from the source column to the target column as is.
This is a kind of new optimization, but this also was needed
to preserve existing MTR test results.
This commit is contained in:
Alexander Barkov
@ -266,3 +266,178 @@ SET column_compression_threshold=0;
|
||||
INSERT INTO t1 VALUES('aa');
|
||||
SET column_compression_threshold=DEFAULT;
|
||||
DROP TABLE t1;
|
||||
|
||||
|
||||
--echo #
|
||||
--echo # MDEV-31724 Compressed varchar values lost on joins when sorting on columns from joined table(s)
|
||||
--echo #
|
||||
|
||||
CREATE TABLE t1 (
|
||||
id int(10) unsigned not null,
|
||||
txt varchar(5000) COMPRESSED NOT NULL DEFAULT '',
|
||||
PRIMARY KEY (id)
|
||||
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb3 COLLATE=utf8mb3_bin;
|
||||
|
||||
CREATE TABLE t2 (
|
||||
id int(10) unsigned not null,
|
||||
n1 bigint(20) NOT NULL,
|
||||
n2 bigint(20) NOT NULL,
|
||||
n3 bigint(20) NOT NULL,
|
||||
PRIMARY KEY (id)
|
||||
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb3 COLLATE=utf8mb3_bin;
|
||||
|
||||
INSERT INTO t1 VALUES
|
||||
(1, 'short string < 100 chars'),
|
||||
(2, 'long string = 99 chars '),
|
||||
(3, 'long string = 100 chars !'),
|
||||
(4, 'long string = 101 chars !');
|
||||
|
||||
INSERT INTO t2 VALUES
|
||||
(1, 24, 1, 1),
|
||||
(2, 99, 2, 2),
|
||||
(3, 100, 3, 3),
|
||||
(4, 101, 4, 4);
|
||||
|
||||
SELECT txt, v.* FROM t1 LEFT JOIN t2 v ON t1.id = v.id;
|
||||
SELECT txt, v.* FROM t1 LEFT JOIN t2 v ON t1.id = v.id ORDER BY v.n1;
|
||||
SELECT txt, v.* FROM t1 JOIN t2 v ON t1.id = v.id;
|
||||
SELECT txt, v.* FROM t1 JOIN t2 v ON t1.id = v.id ORDER BY v.n1;
|
||||
|
||||
DROP TABLE t1, t2;
|
||||
|
||||
CREATE OR REPLACE TABLE t1 (
|
||||
id INT NOT NULL PRIMARY KEY,
|
||||
txt varchar(5000) COMPRESSED NOT NULL DEFAULT ''
|
||||
) CHARSET=utf8mb3;
|
||||
|
||||
INSERT INTO t1 VALUES
|
||||
(1, REPEAT('a', 10)),
|
||||
(2, REPEAT('b', 99)),
|
||||
(3, REPEAT('c', 100)),
|
||||
(4, REPEAT('d', 121));
|
||||
|
||||
--replace_column 2 <sysdate>
|
||||
--sorted_result
|
||||
SELECT txt, sysdate(6) FROM t1 ORDER BY 2;
|
||||
DROP TABLE t1;
|
||||
|
||||
|
||||
DELIMITER $$;
|
||||
CREATE FUNCTION f1(imax INT, jmax INT) RETURNS TEXT
|
||||
BEGIN
|
||||
DECLARE res TEXT DEFAULT 'x';
|
||||
FOR i IN 0..imax
|
||||
DO
|
||||
FOR j IN 0..jmax
|
||||
DO
|
||||
SET res=CONCAT(res, ' ', i, ' ', j);
|
||||
END FOR;
|
||||
END FOR;
|
||||
RETURN res;
|
||||
END;
|
||||
$$
|
||||
DELIMITER ;$$
|
||||
|
||||
|
||||
# Let's override the default threshold (100) to force
|
||||
# comression for VARCHAR1+MB, for example, for:
|
||||
# VARCHAR(80) CHARACTER SET utf8mb3
|
||||
|
||||
SET @@column_compression_threshold=32;
|
||||
|
||||
--echo # VARCHAR1, 8bit, truncation
|
||||
CREATE TABLE t1 (a VARCHAR(254) COMPRESSED CHARACTER SET latin1);
|
||||
INSERT INTO t1 VALUES (f1(6,6));
|
||||
SELECT LENGTH(a), LEFT(a,30), RIGHT(a,30) FROM t1;
|
||||
FLUSH STATUS;
|
||||
ALTER IGNORE TABLE t1 MODIFY a VARCHAR(4) COMPRESSED CHARACTER SET latin1;
|
||||
SHOW STATUS LIKE 'Column%compressions';
|
||||
SELECT LENGTH(a), a FROM t1;
|
||||
DROP TABLE t1;
|
||||
|
||||
CREATE TABLE t1 (a VARCHAR(254) COMPRESSED CHARACTER SET latin1);
|
||||
INSERT INTO t1 VALUES (REPEAT('a',254));
|
||||
SELECT LENGTH(a), LEFT(a,30), RIGHT(a,30) FROM t1;
|
||||
FLUSH STATUS;
|
||||
ALTER IGNORE TABLE t1 MODIFY a VARCHAR(4) COMPRESSED CHARACTER SET latin1;
|
||||
SHOW STATUS LIKE 'Column%compressions';
|
||||
SELECT LENGTH(a), a FROM t1;
|
||||
DROP TABLE t1;
|
||||
|
||||
--echo # VARCHAR1, 8bit, no truncation
|
||||
CREATE TABLE t1 (a VARCHAR(250) COMPRESSED CHARACTER SET latin1);
|
||||
INSERT INTO t1 VALUES (f1(6,6));
|
||||
SELECT LENGTH(a), LEFT(a,30), RIGHT(a,30) FROM t1;
|
||||
FLUSH STATUS;
|
||||
ALTER IGNORE TABLE t1 MODIFY a VARCHAR(254) COMPRESSED CHARACTER SET latin1;
|
||||
SHOW STATUS LIKE 'Column%compressions';
|
||||
SELECT LENGTH(a), LEFT(a,30), RIGHT(a,30) FROM t1;
|
||||
DROP TABLE t1;
|
||||
|
||||
--echo # VARCHAR2, 8bit, truncation
|
||||
CREATE TABLE t1 (a VARCHAR(32000) COMPRESSED CHARACTER SET latin1);
|
||||
INSERT INTO t1 VALUES (f1(31,31));
|
||||
SELECT LENGTH(a), LEFT(a,30), RIGHT(a,30) FROM t1;
|
||||
FLUSH STATUS;
|
||||
ALTER IGNORE TABLE t1 MODIFY a VARCHAR(256) COMPRESSED CHARACTER SET latin1;
|
||||
SHOW STATUS LIKE 'Column%compressions';
|
||||
SELECT LENGTH(a), LEFT(a,30), RIGHT(a,30) FROM t1;
|
||||
DROP TABLE t1;
|
||||
|
||||
--echo # VARCHAR2, 8bit, no truncation
|
||||
CREATE TABLE t1 (a VARCHAR(32000) COMPRESSED CHARACTER SET latin1);
|
||||
INSERT INTO t1 VALUES (f1(31,31));
|
||||
SELECT LENGTH(a), LEFT(a,30), RIGHT(a, 30) FROM t1;
|
||||
FLUSH STATUS;
|
||||
ALTER IGNORE TABLE t1 MODIFY a VARCHAR(32001) COMPRESSED CHARACTER SET latin1;
|
||||
SHOW STATUS LIKE 'Column%compressions';
|
||||
SELECT LENGTH(a), LEFT(a,30), RIGHT(a, 30) FROM t1;
|
||||
DROP TABLE t1;
|
||||
|
||||
--echo # VARCHAR1, multi-byte, truncation
|
||||
CREATE TABLE t1 (a VARCHAR(80) COMPRESSED CHARACTER SET utf8mb3);
|
||||
INSERT INTO t1 VALUES (f1(3,3));
|
||||
SELECT LENGTH(a), LEFT(a,30), RIGHT(a,30) FROM t1;
|
||||
FLUSH STATUS;
|
||||
ALTER IGNORE TABLE t1 MODIFY a VARCHAR(1) COMPRESSED CHARACTER SET utf8mb3;
|
||||
SHOW STATUS LIKE 'Column%compressions';
|
||||
SELECT LENGTH(a), a FROM t1;
|
||||
DROP TABLE t1;
|
||||
|
||||
--echo # VARCHAR1, multi-byte, no truncation
|
||||
CREATE TABLE t1 (a VARCHAR(80) COMPRESSED CHARACTER SET utf8mb3);
|
||||
INSERT INTO t1 VALUES (f1(3,3));
|
||||
SELECT LENGTH(a), LEFT(a,30), RIGHT(a,30) FROM t1;
|
||||
FLUSH STATUS;
|
||||
ALTER IGNORE TABLE t1 MODIFY a VARCHAR(81) COMPRESSED CHARACTER SET utf8mb3;
|
||||
SHOW STATUS LIKE 'Column%compressions';
|
||||
SELECT LENGTH(a), LEFT(a,30), RIGHT(a,30) FROM t1;
|
||||
DROP TABLE t1;
|
||||
|
||||
--echo # VARCHAR2, multi-byte, truncation
|
||||
CREATE TABLE t1 (a VARCHAR(10000) COMPRESSED CHARACTER SET utf8mb3);
|
||||
INSERT INTO t1 VALUES (f1(31,31));
|
||||
SELECT LENGTH(a), LEFT(a,30), RIGHT(a,30) FROM t1;
|
||||
FLUSH STATUS;
|
||||
ALTER IGNORE TABLE t1 MODIFY a VARCHAR(256) COMPRESSED CHARACTER SET utf8mb3;
|
||||
SHOW STATUS LIKE 'Column%compressions';
|
||||
SELECT LENGTH(a), LEFT(a,30), RIGHT(a,30) FROM t1;
|
||||
DROP TABLE t1;
|
||||
|
||||
--echo # VARCHAR2, multi-byte, no truncation
|
||||
CREATE TABLE t1 (a VARCHAR(10000) COMPRESSED CHARACTER SET utf8mb3);
|
||||
INSERT INTO t1 VALUES (f1(31,31));
|
||||
SELECT LENGTH(a), LEFT(a,30), RIGHT(a,30) FROM t1;
|
||||
FLUSH STATUS;
|
||||
ALTER IGNORE TABLE t1 MODIFY a VARCHAR(10001) COMPRESSED CHARACTER SET utf8mb3;
|
||||
SHOW STATUS LIKE 'Column%compressions';
|
||||
SELECT LENGTH(a), LEFT(a,30), RIGHT(a,30) FROM t1;
|
||||
DROP TABLE t1;
|
||||
|
||||
SET @@column_compression_threshold=DEFAULT;
|
||||
|
||||
DROP FUNCTION f1;
|
||||
|
||||
--echo #
|
||||
--echo # End of 10.4 tests
|
||||
--echo #
|
||||
|
||||
Reference in New Issue
Block a user