database/mariadb
1
0
Fork 0
mirror of https://github.com/MariaDB/server.git synced 2025-07-29 05:21:33 +03:00
Code Activity

MDEV-29621: Replica stopped by locks on sequence

Browse Source 
When using binlog_row_image=FULL with sequence table inserts, a
replica can deadlock because it treats full inserts in a sequence as DDL
statements by getting an exclusive lock on the sequence table. It
has been observed that with parallel replication, this exclusive
lock on the sequence table can lead to a deadlock where one
transaction has the exclusive lock and is waiting on a prior
transaction to commit, whereas this prior transaction is waiting on
the MDL lock.

This fix for this is on the master side, to raise FL_DDL
flag on the GTID of a full binlog_row_image write of a sequence table.
This forces the slave to execute the statement serially so a deadlock
cannot happen.

A test verifies the deadlock also to prove it happen on the OLD (pre-fixes)
slave.

OLD (buggy master) -replication-> NEW (fixed slave) is provided.
As the pre-fixes master's full row-image may represent both
SELECT NEXT VALUE and INSERT, the parallel slave pessimistically
waits for the prior transaction to have committed before to take on the
critical part of the second (like INSERT in the test) event execution.
The waiting exploits a parallel slave's retry mechanism which is
controlled by `@@global.slave_transaction_retries`.

Note that in order to avoid any persistent 'Deadlock found' 2013 error
in OLD -> NEW, `slave_transaction_retries` may need to be set to a
higher than the default value.
START-SLAVE is an effective work-around if this still happens.
This commit is contained in:
Andrei
2023-03-18 21:11:07 +02:00
parent 7e75f94ba1
commit 55a53949be
8 changed files with 190 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
mysql-test/suite/rpl/r/rpl_parallel_seq.result Normal file
View File

@ -0,0 +1,46 @@
include/master-slave.inc
[connection master]
connection slave;
include/stop_slave.inc
ALTER TABLE mysql.gtid_slave_pos ENGINE=InnoDB;
# MDEV-29621 the sequence engine binlog_row_image-full events
# MDL-deadlock on the parallel slave.
connection master;
CREATE SEQUENCE s1;
SET @@session.binlog_row_image=FULL;
SET @@session.debug_dbug="+d,binlog_force_commit_id";
SET @commit_id=7;
SET @@gtid_seq_no=100;
SELECT NEXT VALUE FOR s1;
NEXT VALUE FOR s1
1
INSERT INTO s1 VALUES(2, 1, 10, 1, 2, 1, 1, 0);
SET @@session.debug_dbug="";
connection slave;
SET @@global.slave_parallel_threads=2;
SET @@global.slave_parallel_mode=optimistic;
SET @@global.debug_dbug="+d,hold_worker_on_schedule";
include/start_slave.inc
SET DEBUG_SYNC = 'now SIGNAL continue_worker';
connection master;
DROP SEQUENCE s1;
connection slave;
include/stop_slave.inc
# Simulate buggy 10.3.36 master to prove the parallel applier
# does not deadlock now at replaying the above master load.
connection master;
include/rpl_stop_server.inc [server_number=1]
include/rpl_start_server.inc [server_number=1]
connection slave;
RESET MASTER;
SET @@global.gtid_slave_pos="";
CHANGE MASTER TO master_host='127.0.0.1', master_port=SERVER_MYPORT_1, master_user='root', master_use_gtid=slave_pos;
START SLAVE UNTIL MASTER_GTID_POS='0-1-102';
SET DEBUG_SYNC = 'now SIGNAL continue_worker';
include/wait_for_slave_to_stop.inc
SET debug_sync = RESET;
SET @@global.slave_parallel_threads= 0;
SET @@global.slave_parallel_mode= conservative;
SET @@global.debug_dbug = "";
include/start_slave.inc
include/rpl_end.inc