1
0
mirror of https://github.com/MariaDB/server.git synced 2025-08-08 11:22:35 +03:00

MDEV-6589: Incorrect relay log start position when restarting SQL thread after error in parallel replication

The problem occurs in parallel replication in GTID mode, when we are using
multiple replication domains. In this case, if the SQL thread stops, the
slave GTID position may refer to a different point in the relay log for each
domain.

The bug was that when the SQL thread was stopped and restarted (but the IO
thread was kept running), the SQL thread would resume applying the relay log
from the point of the most advanced replication domain, silently skipping all
earlier events within other domains. This caused replication corruption.

This patch solves the problem by storing, when the SQL thread stops with
multiple parallel replication domains active, the current GTID
position. Additionally, the current position in the relay logs is moved back
to a point known to be earlier than the current position of any replication
domain. Then when the SQL thread restarts from the earlier position, GTIDs
encountered are compared against the stored GTID position. Any GTID that was
already applied before the stop is skipped to avoid duplicate apply.

This patch should have no effect if multi-domain GTID parallel replication is
not used. Similarly, if both SQL and IO thread are stopped and restarted, the
patch has no effect, as in this case the existing relay logs are removed and
re-fetched from the master at the current global @@gtid_slave_pos.
This commit is contained in:
Kristian Nielsen
2015-02-18 12:22:50 +01:00
parent fb71449b10
commit ad0d203f2e
10 changed files with 541 additions and 16 deletions

View File

@@ -0,0 +1,147 @@
include/master-slave.inc
[connection master]
SET @old_parallel_threads=@@GLOBAL.slave_parallel_threads;
include/stop_slave.inc
SET GLOBAL slave_parallel_threads=10;
CHANGE MASTER TO master_use_gtid=current_pos;
include/start_slave.inc
*** MDEV-6589: Incorrect relay log start position when restarting SQL thread after error in parallel replication ***
ALTER TABLE mysql.gtid_slave_pos ENGINE=InnoDB;
CREATE TABLE t1 (a int PRIMARY KEY) ENGINE=MyISAM;
CREATE TABLE t2 (a int PRIMARY KEY) ENGINE=InnoDB;
INSERT INTO t1 VALUES (1);
INSERT INTO t2 VALUES (1);
SELECT * FROM t1;
a
1
SELECT * FROM t2;
a
1
SET sql_log_bin=0;
BEGIN;
INSERT INTO t2 VALUES (5);
SET gtid_domain_id=0;
INSERT INTO t1 VALUES (2);
INSERT INTO t2 VALUES (3);
FLUSH LOGS;
INSERT INTO t1 VALUES (4);
SET gtid_domain_id=1;
INSERT INTO t2 VALUES (5);
SET gtid_domain_id=0;
INSERT INTO t1 VALUES (6);
INSERT INTO t1 VALUES (7);
SET gtid_domain_id=2;
INSERT INTO t2 VALUES (8);
INSERT INTO t1 VALUES (9);
FLUSH LOGS;
SET gtid_domain_id=3;
INSERT INTO t2 VALUES (10);
INSERT INTO t1 VALUES (11);
SET gtid_domain_id=1;
INSERT INTO t1 VALUES (12);
INSERT INTO t2 VALUES (13);
SET gtid_domain_id=0;
INSERT INTO t2 VALUES (14);
FLUSH LOGS;
SET gtid_domain_id=3;
INSERT INTO t2 VALUES (15);
SET gtid_domain_id=2;
INSERT INTO t2 VALUES (16);
SET gtid_domain_id=0;
INSERT INTO t1 VALUES (17);
SET @gtid0 = @@last_gtid;
SET gtid_domain_id=2;
INSERT INTO t1 VALUES (18);
SET @gtid2 = @@last_gtid;
SET gtid_domain_id=3;
INSERT INTO t1 VALUES (19);
SET @gtid3 = @@last_gtid;
SELECT * FROM t1 ORDER BY a;
a
1
2
4
6
7
9
11
12
17
18
19
SELECT * FROM t2 ORDER BY a;
a
1
3
5
8
10
13
14
15
16
include/save_master_gtid.inc
SELECT MASTER_GTID_WAIT('WAIT_POS');
MASTER_GTID_WAIT('WAIT_POS')
0
COMMIT;
SET sql_log_bin=1;
include/wait_for_slave_sql_error.inc [errno=1062]
SELECT * FROM t1 ORDER BY a;
a
1
2
4
6
7
9
11
17
18
19
SELECT * FROM t2 ORDER BY a;
a
1
3
5
8
10
14
15
16
SET sql_log_bin=0;
DELETE FROM t2 WHERE a=5;
SET sql_log_bin=1;
include/start_slave.inc
include/sync_with_master_gtid.inc
SELECT * FROM t1 ORDER BY a;
a
1
2
4
6
7
9
11
12
17
18
19
SELECT * FROM t2 ORDER BY a;
a
1
3
5
8
10
13
14
15
16
include/stop_slave.inc
SET GLOBAL slave_parallel_threads=@old_parallel_threads;
include/start_slave.inc
SET DEBUG_SYNC= 'RESET';
DROP TABLE t1,t2;
SET DEBUG_SYNC= 'RESET';
include/rpl_end.inc