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

Bug#11747416 : 32228 A disk full makes binary log corrupt

Binary log of master can get a partially logged event if the server
runs out of disk space and, while waiting for some space to be freed,
is shut down (or crashes). If the server is not stopped, it will just
wait endlessly for space to be freed, thus no partial event anomaly
occurs.  The restarted master server has had a dubious policy to send
the incomplete event to slave which it apparently can't handle.
Although an error was printed out the fact of sending with unclear
error message is a source of confusion.
Actually the problem of presence an incomplete event in the binary log
was already fixed by WL 5493 (which was merged to our current trunk
branch, major version 5.6). The fix makes the server truncate the
binary log on server restart and recovery.

However 5.5 master can't do that. So the current issue is a problem of
sending incomplete events to the slave by 5.5 master.

It is fixed in this patch by changing the policy so that only complete
events are pushed by the dump thread to the IO thread. In addition,
the error text that master sends to the slave when an incomplete event
is found, now states that incomplete event may have been caused by an
out-of-disk space situation and provides coordinates of
the first and the last event bytes read.
This commit is contained in:
Andrei Elkin
2011-09-29 14:14:43 +03:00
parent b140784fbc
commit b426043b7c
8 changed files with 110 additions and 27 deletions

Binary file not shown.

View File

@ -0,0 +1,19 @@
include/master-slave.inc
[connection master]
call mtr.add_suppression("Error in Log_event::read_log_event()");
include/rpl_stop_server.inc [server_number=1]
include/rpl_start_server.inc [server_number=1]
show binlog events;
ERROR HY000: Error when executing command SHOW BINLOG EVENTS: Wrong offset or I/O error
call mtr.add_suppression("Slave I/O: Got fatal error 1236 from master when reading data from binary log");
stop slave;
reset slave;
start slave;
include/wait_for_slave_param.inc [Last_IO_Errno]
Last_IO_Errno = '1236'
Last_IO_Error = 'Got fatal error 1236 from master when reading data from binary log: 'binlog truncated in the middle of event; consider out of disk space on master; the last event was read from ./master-bin.000001 at 316, the last byte read was read from ./master-bin.000001 at 335.''
reset master;
stop slave;
reset slave;
drop table t;
End of the tests

View File

@ -9,7 +9,7 @@ change master to master_log_pos=MASTER_LOG_POS;
Read_Master_Log_Pos = '75'
start slave;
include/wait_for_slave_io_error.inc [errno=1236]
Last_IO_Error = 'Got fatal error 1236 from master when reading data from binary log: 'log event entry exceeded max_allowed_packet; Increase max_allowed_packet on master''
Last_IO_Error = 'Got fatal error 1236 from master when reading data from binary log: 'log event entry exceeded max_allowed_packet; Increase max_allowed_packet on master; the last event was read from ./master-bin.000001 at 75, the last byte read was read from ./master-bin.000001 at 94.''
include/stop_slave_sql.inc
show master status;
File Position Binlog_Do_DB Binlog_Ignore_DB

View File

@ -5,7 +5,7 @@ CREATE TABLE t1(c1 INT);
FLUSH LOGS;
call mtr.add_suppression('Got fatal error 1236 from master when reading data from binary log: .*could not find next log');
include/wait_for_slave_io_error.inc [errno=1236]
Last_IO_Error = 'Got fatal error 1236 from master when reading data from binary log: 'could not find next log''
Last_IO_Error = 'Got fatal error 1236 from master when reading data from binary log: 'could not find next log; the last event was read from ./master-bin.000002 at 237, the last byte read was read from ./master-bin.000002 at 237.''
CREATE TABLE t2(c1 INT);
FLUSH LOGS;
CREATE TABLE t3(c1 INT);

View File

@ -37,7 +37,7 @@ DROP TABLE t1;
CREATE TABLE t1 (f1 int PRIMARY KEY, f2 LONGTEXT, f3 LONGTEXT) ENGINE=MyISAM;
INSERT INTO t1(f1, f2, f3) VALUES(1, REPEAT('a', @@global.max_allowed_packet), REPEAT('b', @@global.max_allowed_packet));
include/wait_for_slave_io_error.inc [errno=1236]
Last_IO_Error = 'Got fatal error 1236 from master when reading data from binary log: 'log event entry exceeded max_allowed_packet; Increase max_allowed_packet on master''
Last_IO_Error = 'Got fatal error 1236 from master when reading data from binary log: 'log event entry exceeded max_allowed_packet; Increase max_allowed_packet on master; the last event was read from ./master-bin.000001 at 463, the last byte read was read from ./master-bin.000001 at 482.''
STOP SLAVE;
RESET SLAVE;
RESET MASTER;

View File

@ -0,0 +1,64 @@
#
# Bug#11747416 : 32228 A disk full makes binary log corrupt.
#
#
# The test demonstrates reading from binlog error propagation to slave
# and reporting there.
# Conditions for the bug include a crash at time of the last event to
# the binlog was written partly. With the fixes the event is not sent out
# any longer, but rather the dump thread sends out a sound error message.
#
# Crash is not simulated. A binlog with partly written event in its end is installed
# and replication is started from it.
#
--source include/master-slave.inc
--source include/have_binlog_format_mixed.inc
call mtr.add_suppression("Error in Log_event::read_log_event()");
--connection master
--let $datadir= `SELECT @@datadir`
--let $rpl_server_number= 1
--source include/rpl_stop_server.inc
--remove_file $datadir/master-bin.000001
--copy_file $MYSQL_TEST_DIR/std_data/bug11747416_32228_binlog.000001 $datadir/master-bin.000001
--let $rpl_server_number= 1
--source include/rpl_start_server.inc
--source include/wait_until_connected_again.inc
# evidence of the partial binlog
--error ER_ERROR_WHEN_EXECUTING_COMMAND
show binlog events;
--connection slave
call mtr.add_suppression("Slave I/O: Got fatal error 1236 from master when reading data from binary log");
stop slave;
reset slave;
start slave;
# ER_MASTER_FATAL_ERROR_READING_BINLOG 1236
--let $slave_param=Last_IO_Errno
--let $slave_param_value=1236
--source include/wait_for_slave_param.inc
--let $status_items= Last_IO_Errno, Last_IO_Error
--source include/show_slave_status.inc
#
# Cleanup
#
--connection master
reset master;
--connection slave
stop slave;
reset slave;
drop table t; # table was created from binlog. it does not exist on master.
--echo End of the tests