mirror of
https://github.com/MariaDB/server.git
synced 2025-02-22 13:23:07 +01:00
706a7101bf
Problem:- rpl_parallel2 was failing non-deterministically
Analysis:-
When FLUSH TABLES WITH READ LOCK is executed, it will allow all worker
threads to complete their ongoing transactions and then it will pause them.
At this state FTWRL will proceed to acquire global read lock. FTWRL first
blocks threads from starting new commits, then upgrades the lock to block
commit of existing transactions.
Step1:
FLUSH TABLES WITH READ LOCK - Blocks new commits
Step2:
* STOP SLAVE command enables 'force_abort=1' which unblocks workers,
they continue to execute events.
* T1: Waits in 'record_gtid' call to update 'gtid_slave_pos' table with
its current GTID, but it is blocked becuase of Step1.
* T2: Holds COMMIT lock and waits for T1 to commit.
Step3:
FLUSH TABLES WITH READ LOCK - Waiting to get BLOCK_COMMIT.
This results in deadlock. When STOP SLAVE command allows paused workers to
proceed, workers should skip the execution of all further events, similar
to 'conservative' parallel mode.
Solution:-
We will assign 1 to skip_event_group when we are aborted in do_ftwrl_wait.
rpl_parallel_entry->pause_sub_id is only reset when force_abort is off in
rpl_pause_after_ftwrl.
166 lines
4.1 KiB
Text
166 lines
4.1 KiB
Text
include/rpl_init.inc [topology=1->2]
|
|
*** MDEV-5509: Incorrect value for Seconds_Behind_Master if parallel replication ***
|
|
connection server_2;
|
|
SET @old_parallel_threads=@@GLOBAL.slave_parallel_threads;
|
|
set @old_parallel_mode= @@GLOBAL.slave_parallel_mode;
|
|
include/stop_slave.inc
|
|
SET GLOBAL slave_parallel_threads=5;
|
|
set global slave_parallel_mode= optimistic;
|
|
include/start_slave.inc
|
|
connection server_1;
|
|
CREATE TABLE t1 (a INT PRIMARY KEY, b INT);
|
|
CALL mtr.add_suppression("Unsafe statement written to the binary log using statement format since BINLOG_FORMAT = STATEMENT. Statement is unsafe because it uses a system function that may return a different value on the slave");
|
|
connection server_2;
|
|
connection server_1;
|
|
INSERT INTO t1 VALUES (1,sleep(2));
|
|
Warnings:
|
|
Note 1592 Unsafe statement written to the binary log using statement format since BINLOG_FORMAT = STATEMENT. Statement is unsafe because it uses a system function that may return a different value on the slave
|
|
connection server_2;
|
|
include/wait_for_slave_param.inc [Seconds_Behind_Master]
|
|
Seconds_Behind_Master should be zero here because the slave is fully caught up and idle.
|
|
Seconds_Behind_Master = '0'
|
|
*** MDEV-8294: Inconsistent behavior of slave parallel threads at runtime ***
|
|
connection server_1;
|
|
INSERT INTO t1 VALUES (10,0);
|
|
SET sql_log_bin= 0;
|
|
DELETE FROM t1 WHERE a=10;
|
|
SET sql_log_bin= 1;
|
|
INSERT INTO t1 VALUES (10,0);
|
|
SELECT * FROM t1 WHERE a >= 10 ORDER BY a;
|
|
a b
|
|
10 0
|
|
connection server_2;
|
|
include/wait_for_slave_sql_error.inc [errno=1062]
|
|
SET GLOBAL slave_parallel_threads=8;
|
|
STOP SLAVE;
|
|
SET GLOBAL sql_slave_skip_counter= 1;
|
|
include/start_slave.inc
|
|
SELECT * FROM t1 WHERE a >= 10 ORDER BY a;
|
|
a b
|
|
10 0
|
|
*** MDEV-7818: Deadlock occurring with parallel replication and FTWRL ***
|
|
connection server_1;
|
|
CREATE TABLE t2 (a INT PRIMARY KEY, b INT) ENGINE=InnoDB;
|
|
INSERT INTO t2 VALUES (1,0), (2,0), (3,0);
|
|
connection server_2;
|
|
include/stop_slave.inc
|
|
connection server_1;
|
|
SET @old_dbug= @@SESSION.debug_dbug;
|
|
SET @commit_id= 4242;
|
|
SET SESSION debug_dbug="+d,binlog_force_commit_id";
|
|
BEGIN;
|
|
UPDATE t2 SET b=b+1 WHERE a=2;
|
|
COMMIT;
|
|
BEGIN;
|
|
INSERT INTO t2 VALUES (4,10);
|
|
COMMIT;
|
|
SET SESSION debug_dbug= @old_dbug;
|
|
INSERT INTO t2 VALUES (5,0);
|
|
INSERT INTO t2 VALUES (6,0);
|
|
INSERT INTO t2 VALUES (7,0);
|
|
INSERT INTO t2 VALUES (8,0);
|
|
INSERT INTO t2 VALUES (9,0);
|
|
INSERT INTO t2 VALUES (10,0);
|
|
INSERT INTO t2 VALUES (11,0);
|
|
INSERT INTO t2 VALUES (12,0);
|
|
INSERT INTO t2 VALUES (13,0);
|
|
INSERT INTO t2 VALUES (14,0);
|
|
INSERT INTO t2 VALUES (15,0);
|
|
INSERT INTO t2 VALUES (16,0);
|
|
INSERT INTO t2 VALUES (17,0);
|
|
INSERT INTO t2 VALUES (18,0);
|
|
INSERT INTO t2 VALUES (19,0);
|
|
connection server_2;
|
|
connect s1, 127.0.0.1, root,, test, $SLAVE_MYPORT,;
|
|
BEGIN;
|
|
SELECT * FROM t2 WHERE a=2 FOR UPDATE;
|
|
a b
|
|
2 0
|
|
connection server_2;
|
|
include/start_slave.inc
|
|
connect s2, 127.0.0.1, root,, test, $SLAVE_MYPORT,;
|
|
FLUSH TABLES WITH READ LOCK;
|
|
connection s1;
|
|
COMMIT;
|
|
connection s1;
|
|
STOP SLAVE;
|
|
connection s2;
|
|
connection server_1;
|
|
SELECT * FROM t2 ORDER BY a;
|
|
a b
|
|
1 0
|
|
2 1
|
|
3 0
|
|
4 10
|
|
5 0
|
|
6 0
|
|
7 0
|
|
8 0
|
|
9 0
|
|
10 0
|
|
11 0
|
|
12 0
|
|
13 0
|
|
14 0
|
|
15 0
|
|
16 0
|
|
17 0
|
|
18 0
|
|
19 0
|
|
connection s2;
|
|
UNLOCK TABLES;
|
|
SELECT "after UNLOCK TABLES" as state;
|
|
state
|
|
after UNLOCK TABLES
|
|
connection s1;
|
|
SELECT "after reap of STOP SLAVE" as state;
|
|
state
|
|
after reap of STOP SLAVE
|
|
connection server_2;
|
|
include/wait_for_slave_to_stop.inc
|
|
include/start_slave.inc
|
|
SELECT * FROM t2 ORDER BY a;
|
|
a b
|
|
1 0
|
|
2 1
|
|
3 0
|
|
4 10
|
|
5 0
|
|
6 0
|
|
7 0
|
|
8 0
|
|
9 0
|
|
10 0
|
|
11 0
|
|
12 0
|
|
13 0
|
|
14 0
|
|
15 0
|
|
16 0
|
|
17 0
|
|
18 0
|
|
19 0
|
|
*** MDEV-8318: Assertion `!pool->busy' failed in pool_mark_busy(rpl_parallel_thread_pool*) on concurrent FTWRL ***
|
|
connection server_1;
|
|
LOCK TABLE t2 WRITE;
|
|
connect m1,localhost,root,,test;
|
|
connection m1;
|
|
FLUSH TABLES WITH READ LOCK;
|
|
connect m2,localhost,root,,test;
|
|
FLUSH TABLES WITH READ LOCK;
|
|
connection server_1;
|
|
KILL QUERY CID;
|
|
connection m1;
|
|
ERROR 70100: Query execution was interrupted
|
|
connection server_1;
|
|
UNLOCK TABLES;
|
|
connection m2;
|
|
UNLOCK TABLES;
|
|
connection server_2;
|
|
include/stop_slave.inc
|
|
SET GLOBAL slave_parallel_threads=@old_parallel_threads;
|
|
set global slave_parallel_mode= @old_parallel_mode;
|
|
include/start_slave.inc
|
|
connection server_1;
|
|
DROP TABLE t1, t2;
|
|
include/rpl_end.inc
|