mirror of
https://github.com/MariaDB/server.git
synced 2025-10-24 16:38:14 +02:00
0a68328673
This is actually an existing problem in the old binlog implementation, and this patch is applicable to old binlog also. The problem is that RESET MASTER can run concurrently with binlog dump threads / connected slaves. This will remove the binlog from under the feet of the reader, which can cause all sorts of strange behaviour. This patch fixes the problem by disallowing to run RESET MASTER when dump threads (or other RESET MASTER or SHOW BINARY LOGS) are running. An error is thrown in this case, user must stop slaves and/or kill dump threads to make the RESET MASTER go through. A slave that connects in the middle of RESET MASTER will wait for it to complete. Fix a lot of test cases to kill any lingering dump threads before doing RESET MASTER, mostly just by sourcing include/kill_binlog_dump_threads.inc. Signed-off-by: Kristian Nielsen <knielsen@knielsen-hq.org>
374 lines
9.2 KiB
Text
374 lines
9.2 KiB
Text
include/rpl_init.inc [topology=1->2]
|
|
*** Test crashing master, causing slave IO thread to reconnect while SQL thread is running ***
|
|
connection server_1;
|
|
call mtr.add_suppression("Checking table:");
|
|
call mtr.add_suppression("client is using or hasn't closed the table properly");
|
|
call mtr.add_suppression("Table .* is marked as crashed and should be repaired");
|
|
call mtr.add_suppression("Could not read packet:.* errno: 11");
|
|
flush tables;
|
|
ALTER TABLE mysql.gtid_slave_pos ENGINE=InnoDB;
|
|
CREATE TABLE t1 (a INT PRIMARY KEY, b INT) ENGINE=InnoDB;
|
|
INSERT INTO t1 VALUES (1, 0);
|
|
connection server_2;
|
|
SET sql_log_bin=0;
|
|
call mtr.add_suppression('Master command COM_REGISTER_SLAVE failed: failed registering on master, reconnecting to try again');
|
|
call mtr.add_suppression('Slave I/O: .*Lost connection to server during query');
|
|
call mtr.add_suppression("Slave I/O thread couldn't register on master");
|
|
SET sql_log_bin=1;
|
|
include/stop_slave.inc
|
|
CHANGE MASTER TO master_host = '127.0.0.1', master_port = MASTER_PORT,
|
|
MASTER_USE_GTID=SLAVE_POS;
|
|
connection server_1;
|
|
INSERT INTO t1 VALUES (2,1);
|
|
INSERT INTO t1 VALUES (3,1);
|
|
connection server_2;
|
|
include/start_slave.inc
|
|
connection server_1;
|
|
include/save_master_gtid.inc
|
|
SET SESSION debug_dbug="+d,crash_dispatch_command_before";
|
|
SELECT 1;
|
|
Got one of the listed errors
|
|
connection server_2;
|
|
include/sync_with_master_gtid.inc
|
|
connection server_1;
|
|
INSERT INTO t1 VALUES (1000, 3);
|
|
include/save_master_gtid.inc
|
|
connection server_2;
|
|
include/sync_with_master_gtid.inc
|
|
connection server_1;
|
|
DROP TABLE t1;
|
|
*** Test crashing the master mysqld and check that binlog state is recovered. ***
|
|
connection server_2;
|
|
include/stop_slave.inc
|
|
RESET MASTER;
|
|
SET GLOBAL gtid_slave_pos='';
|
|
connection server_1;
|
|
include/kill_binlog_dump_threads.inc
|
|
RESET MASTER;
|
|
SHOW BINLOG EVENTS IN 'master-bin.000001' LIMIT 1,1;
|
|
Log_name Pos Event_type Server_id End_log_pos Info
|
|
master-bin.000001 # Gtid_list # # []
|
|
CREATE TABLE t1 (a INT PRIMARY KEY) ENGINE=InnoDB;
|
|
connection server_2;
|
|
include/start_slave.inc
|
|
connection server_1;
|
|
SET gtid_domain_id= 1;
|
|
INSERT INTO t1 VALUES (1);
|
|
INSERT INTO t1 VALUES (2);
|
|
FLUSH LOGS;
|
|
SET gtid_domain_id= 2;
|
|
INSERT INTO t1 VALUES (3);
|
|
FLUSH LOGS;
|
|
show binary logs;
|
|
Log_name File_size
|
|
master-bin.000001 #
|
|
master-bin.000002 #
|
|
master-bin.000003 #
|
|
SHOW BINLOG EVENTS IN 'master-bin.000003' LIMIT 1,1;
|
|
Log_name Pos Event_type Server_id End_log_pos Info
|
|
master-bin.000003 # Gtid_list # # #
|
|
SET SESSION debug_dbug="+d,crash_dispatch_command_before";
|
|
SELECT 1;
|
|
Got one of the listed errors
|
|
show binary logs;
|
|
Log_name File_size
|
|
master-bin.000001 #
|
|
master-bin.000002 #
|
|
master-bin.000003 #
|
|
master-bin.000004 #
|
|
SHOW BINLOG EVENTS IN 'master-bin.000004' LIMIT 1,1;
|
|
Log_name Pos Event_type Server_id End_log_pos Info
|
|
master-bin.000004 # Gtid_list # # #
|
|
connection server_2;
|
|
SELECT * FROM t1 ORDER BY a;
|
|
a
|
|
1
|
|
2
|
|
3
|
|
*** Test crashing slave at various points and check that it recovers crash-safe. ***
|
|
include/stop_slave.inc
|
|
SET GLOBAL debug_dbug="+d,inject_crash_before_write_rpl_slave_state";
|
|
START SLAVE;
|
|
connection server_1;
|
|
INSERT INTO t1 VALUES (4);
|
|
include/save_master_gtid.inc
|
|
connection server_2;
|
|
include/sync_with_master_gtid.inc
|
|
include/stop_slave.inc
|
|
START SLAVE;
|
|
SET GLOBAL debug_dbug="+d,crash_commit_before";
|
|
connection server_1;
|
|
INSERT INTO t1 VALUES (5);
|
|
include/save_master_gtid.inc
|
|
connection server_2;
|
|
include/sync_with_master_gtid.inc
|
|
include/stop_slave.inc
|
|
START SLAVE;
|
|
SET GLOBAL debug_dbug="+d,crash_commit_after";
|
|
connection server_1;
|
|
INSERT INTO t1 VALUES (6);
|
|
include/save_master_gtid.inc
|
|
connection server_2;
|
|
include/sync_with_master_gtid.inc
|
|
include/stop_slave.inc
|
|
SET GLOBAL debug_dbug="+d,inject_crash_before_flush_rli";
|
|
START SLAVE;
|
|
connection server_1;
|
|
INSERT INTO t1 VALUES (7);
|
|
include/save_master_gtid.inc
|
|
connection server_2;
|
|
include/sync_with_master_gtid.inc
|
|
include/stop_slave.inc
|
|
SET GLOBAL debug_dbug="+d,inject_crash_after_flush_rli";
|
|
START SLAVE;
|
|
connection server_1;
|
|
INSERT INTO t1 VALUES (8);
|
|
include/save_master_gtid.inc
|
|
connection server_2;
|
|
include/sync_with_master_gtid.inc
|
|
SELECT * FROM t1 ORDER BY a;
|
|
a
|
|
1
|
|
2
|
|
3
|
|
4
|
|
5
|
|
6
|
|
7
|
|
8
|
|
*** MDEV-4725: Incorrect recovery when crash in the middle of writing an event group ***
|
|
connection server_2;
|
|
SET GLOBAL debug_dbug="+d,crash_before_writing_xid";
|
|
connection server_1;
|
|
INSERT INTO t1 VALUES (9), (10);
|
|
connection server_2;
|
|
SHOW VARIABLES like 'gtid_strict_mode';
|
|
Variable_name Value
|
|
gtid_strict_mode ON
|
|
include/start_slave.inc
|
|
*** MDEV-6462: Incorrect recovery on a slave reconnecting to crashed master ***
|
|
connection server_1;
|
|
set sql_log_bin= 0;
|
|
call mtr.add_suppression("Error writing file 'master-bin'");
|
|
set sql_log_bin= 1;
|
|
connection server_2;
|
|
set sql_log_bin= 0;
|
|
call mtr.add_suppression("The server_id of master server changed in the middle of GTID");
|
|
call mtr.add_suppression("Unexpected change of master binlog file name in the middle of GTID");
|
|
set sql_log_bin= 1;
|
|
connection server_1;
|
|
SET GLOBAL debug_dbug="+d,inject_error_writing_xid";
|
|
BEGIN;
|
|
INSERT INTO t1 VALUES (11);
|
|
COMMIT;
|
|
ERROR HY000: Error writing file 'master-bin' (errno: 28 "No space left on device")
|
|
SET GLOBAL debug_dbug="+d,crash_dispatch_command_before";
|
|
COMMIT;
|
|
Got one of the listed errors
|
|
SELECT @@GLOBAL.server_id;
|
|
@@GLOBAL.server_id
|
|
3
|
|
SELECT * from t1 WHERE a > 10 ORDER BY a;
|
|
a
|
|
gtid_check
|
|
Binlog pos ok
|
|
# Wait 60 seconds for SQL thread to catch up with IO thread
|
|
connection server_2;
|
|
SELECT * from t1 WHERE a > 10 ORDER BY a;
|
|
a
|
|
gtid_check
|
|
Binlog pos ok
|
|
gtid_check
|
|
Slave pos ok
|
|
gtid_check
|
|
Current pos ok
|
|
# Repeat this with additional transactions on the master
|
|
connection server_1;
|
|
SET GLOBAL debug_dbug="+d,inject_error_writing_xid";
|
|
BEGIN;
|
|
INSERT INTO t1 VALUES (12);
|
|
COMMIT;
|
|
ERROR HY000: Error writing file 'master-bin' (errno: 28 "No space left on device")
|
|
SET GLOBAL debug_dbug="+d,crash_dispatch_command_before";
|
|
COMMIT;
|
|
Got one of the listed errors
|
|
SELECT @@GLOBAL.server_id;
|
|
@@GLOBAL.server_id
|
|
1
|
|
INSERT INTO t1 VALUES (13);
|
|
INSERT INTO t1 VALUES (14);
|
|
SELECT * from t1 WHERE a > 10 ORDER BY a;
|
|
a
|
|
13
|
|
14
|
|
include/save_master_gtid.inc
|
|
connection server_2;
|
|
include/sync_with_master_gtid.inc
|
|
SELECT * from t1 WHERE a > 10 ORDER BY a;
|
|
a
|
|
13
|
|
14
|
|
connection server_1;
|
|
SET GLOBAL debug_dbug="+d,inject_error_writing_xid";
|
|
BEGIN;
|
|
INSERT INTO t1 VALUES (21);
|
|
COMMIT;
|
|
ERROR HY000: Error writing file 'master-bin' (errno: 28 "No space left on device")
|
|
SET GLOBAL debug_dbug="+d,crash_dispatch_command_before";
|
|
COMMIT;
|
|
Got one of the listed errors
|
|
SELECT @@GLOBAL.server_id;
|
|
@@GLOBAL.server_id
|
|
1
|
|
SELECT * from t1 WHERE a > 10 ORDER BY a;
|
|
a
|
|
13
|
|
14
|
|
gtid_check
|
|
Binlog pos ok
|
|
gtid_check
|
|
Current pos ok
|
|
# Wait 60 seconds for SQL thread to catch up with IO thread
|
|
connection server_2;
|
|
SELECT * from t1 WHERE a > 10 ORDER BY a;
|
|
a
|
|
13
|
|
14
|
|
gtid_check
|
|
Binlog pos ok
|
|
gtid_check
|
|
Slave pos ok
|
|
gtid_check
|
|
Current pos ok
|
|
# Repeat this with additional transactions on the master
|
|
connection server_1;
|
|
SET GLOBAL debug_dbug="+d,inject_error_writing_xid";
|
|
BEGIN;
|
|
INSERT INTO t1 VALUES (22);
|
|
COMMIT;
|
|
ERROR HY000: Error writing file 'master-bin' (errno: 28 "No space left on device")
|
|
SET GLOBAL debug_dbug="+d,crash_dispatch_command_before";
|
|
COMMIT;
|
|
Got one of the listed errors
|
|
INSERT INTO t1 VALUES (23);
|
|
INSERT INTO t1 VALUES (24);
|
|
SELECT * from t1 WHERE a > 10 ORDER BY a;
|
|
a
|
|
13
|
|
14
|
|
23
|
|
24
|
|
include/save_master_gtid.inc
|
|
connection server_2;
|
|
include/sync_with_master_gtid.inc
|
|
SELECT * from t1 WHERE a > 10 ORDER BY a;
|
|
a
|
|
13
|
|
14
|
|
23
|
|
24
|
|
# Repeat this with slave restart
|
|
connection server_1;
|
|
SET GLOBAL debug_dbug="+d,inject_error_writing_xid";
|
|
BEGIN;
|
|
INSERT INTO t1 VALUES (25);
|
|
COMMIT;
|
|
ERROR HY000: Error writing file 'master-bin' (errno: 28 "No space left on device")
|
|
SET GLOBAL debug_dbug="+d,crash_dispatch_command_before";
|
|
COMMIT;
|
|
Got one of the listed errors
|
|
connection server_1;
|
|
connection server_2;
|
|
# Wait 60 seconds for IO thread to connect and SQL thread to catch up
|
|
# with IO thread.
|
|
include/stop_slave.inc
|
|
connection server_1;
|
|
gtid_check
|
|
Binlog pos ok
|
|
gtid_check
|
|
Current pos ok
|
|
INSERT INTO t1 VALUES (26);
|
|
INSERT INTO t1 VALUES (27);
|
|
SELECT * from t1 WHERE a > 10 ORDER BY a;
|
|
a
|
|
13
|
|
14
|
|
23
|
|
24
|
|
26
|
|
27
|
|
include/save_master_gtid.inc
|
|
connection server_2;
|
|
gtid_check
|
|
Binlog pos ok
|
|
gtid_check
|
|
Slave pos ok
|
|
gtid_check
|
|
Current pos ok
|
|
include/start_slave.inc
|
|
include/sync_with_master_gtid.inc
|
|
SELECT * from t1 WHERE a > 10 ORDER BY a;
|
|
a
|
|
13
|
|
14
|
|
23
|
|
24
|
|
26
|
|
27
|
|
*** MDEV-6391: GTID binlog state not recovered if mariadb-bin.state is removed ***
|
|
connection server_2;
|
|
include/stop_slave.inc
|
|
connection server_1;
|
|
INSERT INTO t1 VALUES (30);
|
|
SET @old_server_id= @@server_id;
|
|
SET @old_domain_id= @@gtid_domain_id;
|
|
SET SESSION server_id= 10;
|
|
INSERT INTO t1 VALUES (31);
|
|
INSERT INTO t1 VALUES (32);
|
|
SET SESSION gtid_domain_id= 1;
|
|
SET SESSION server_id=11;
|
|
INSERT INTO t1 VALUES (33);
|
|
SET SESSION gtid_domain_id= 2;
|
|
INSERT INTO t1 VALUES (34);
|
|
SET SESSION server_id= 10;
|
|
INSERT INTO t1 VALUES (35);
|
|
INSERT INTO t1 VALUES (36);
|
|
SET SESSION gtid_domain_id= 0;
|
|
SET SESSION server_id= 12;
|
|
INSERT INTO t1 VALUES (37);
|
|
SET SESSION gtid_domain_id= @old_domain_id;
|
|
SET SESSION server_id= @old_server_id;
|
|
INSERT INTO t1 VALUES (38);
|
|
INSERT INTO t1 VALUES (39);
|
|
SELECT * FROM t1 WHERE a >= 30 ORDER BY a;
|
|
a
|
|
30
|
|
31
|
|
32
|
|
33
|
|
34
|
|
35
|
|
36
|
|
37
|
|
38
|
|
39
|
|
include/save_master_gtid.inc
|
|
connection server_2;
|
|
include/start_slave.inc
|
|
include/sync_with_master_gtid.inc
|
|
SELECT * FROM t1 WHERE a >= 30 ORDER BY a;
|
|
a
|
|
30
|
|
31
|
|
32
|
|
33
|
|
34
|
|
35
|
|
36
|
|
37
|
|
38
|
|
39
|
|
connection server_1;
|
|
DROP TABLE t1;
|
|
connection default;
|
|
include/rpl_end.inc
|