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-6917: Parallel replication: "Commit failed due to failure of an earlier commit on which this one depends", but no prior failure seen

Browse Source 
This bug was seen when parallel replication experienced a deadlock between
transactions T1 and T2, where T2 has reached the commit phase and is waiting
for T1 to commit first. In this case, the deadlock is broken by sending a kill
to T2; that kill error is then later detected and converted to a deadlock
error, which causes T2 to be rolled back and retried.

The problem was that the kill caused ha_commit_trans() to errorneously call
wakeup_subsequent_commits() on T3, signalling it to abort because T2 failed
during commit. This is incorrect, because the error in T2 is only a temporary
error, which will be resolved by normal transaction retry. We should not
signal error to the next transaction until we have executed the code that
handles such temporary errors.

So this patch just removes the calls to wakeup_subsequent_commits() from
ha_commit_trans(). They are incorrect in this case, and they are not needed in
general, as wakeup_subsequent_commits() must in any case be called in
finish_event_group() to wakeup any transactions that may have started to wait
after ha_commit_trans(). And normally, wakeup will in fact have happened
earlier, either from the binlog group commit code, or (in case of no
binlogging) after the fast part of InnoDB/XtraDB group commit.

The symptom of this bug was that replication would break on some transaction
with "Commit failed due to failure of an earlier commit on which this one
depends", but with no such failure of an earlier commit visible anywhere.
This commit is contained in:
Kristian Nielsen
2014-11-13 11:01:31 +01:00
parent 3dcd01e5e6
commit 26b1113032
4 changed files with 181 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

67
mysql-test/suite/rpl/r/rpl_parallel_retry.result
View File

@ -234,9 +234,74 @@ a b
107 1
108 1
109 1
*** MDEV-6917: Parallel replication: "Commit failed due to failure of an earlier commit on which this one depends", but no prior failure seen **
CREATE TABLE t3 (a INT PRIMARY KEY, b INT, KEY b_idx(b)) ENGINE=InnoDB;
INSERT INTO t3 VALUES (1,NULL), (2,2), (3,NULL), (4,4), (5, NULL), (6, 6);
CREATE TABLE t4 (a INT PRIMARY KEY, b INT) ENGINE=InnoDB;
SET @old_format= @@SESSION.binlog_format;
SET binlog_format='statement';
include/stop_slave.inc
CHANGE MASTER TO master_use_gtid=no;
SET @old_format= @@SESSION.binlog_format;
SET binlog_format='statement';
BEGIN;
INSERT INTO t4 VALUES (10, foo(1, 'before_execute_sql_command WAIT_FOR t1_start', ''));
UPDATE t3 SET b=NULL WHERE a=6;
SET debug_sync='commit_after_release_LOCK_prepare_ordered SIGNAL master_queued1 WAIT_FOR master_cont1';
COMMIT;
SET debug_sync='now WAIT_FOR master_queued1';
SET @old_format= @@SESSION.binlog_format;
SET binlog_format='statement';
BEGIN;
INSERT INTO t4 VALUES (20, foo(2, 'group_commit_waiting_for_prior SIGNAL t2_waiting', ''));
DELETE FROM t3 WHERE b <= 3;
SET debug_sync='commit_after_release_LOCK_prepare_ordered SIGNAL master_queued2';
COMMIT;
SET debug_sync='now WAIT_FOR master_queued2';
SET @old_format= @@SESSION.binlog_format;
SET binlog_format='statement';
BEGIN;
INSERT INTO t4 VALUES (30, foo(3, 'before_execute_sql_command WAIT_FOR t3_start', 'group_commit_waiting_for_prior SIGNAL t3_waiting'));
INSERT INTO t3 VALUES (7,7);
SET debug_sync='commit_after_release_LOCK_prepare_ordered SIGNAL master_queued3';
COMMIT;
SET debug_sync='now WAIT_FOR master_queued3';
SET debug_sync='now SIGNAL master_cont1';
SET binlog_format=@old_format;
SET binlog_format=@old_format;
SET debug_sync='RESET';
SET binlog_format=@old_format;
SELECT * FROM t3 ORDER BY a;
a b
1 NULL
3 NULL
4 4
5 NULL
6 NULL
7 7
SET @old_dbug=@@GLOBAL.debug_dbug;
SET GLOBAL debug_dbug="+d,thd_need_ordering_with_force";
include/start_slave.inc
SET debug_sync='now WAIT_FOR t2_waiting';
SET debug_sync='now SIGNAL t3_start';
SET debug_sync='now WAIT_FOR t3_waiting';
SET debug_sync='now SIGNAL t1_start';
SET GLOBAL debug_dbug=@old_dbug;
SET debug_sync='RESET';
retries
1
SELECT * FROM t3 ORDER BY a;
a b
1 NULL
3 NULL
4 4
5 NULL
6 NULL
7 7
SET binlog_format=@old_format;
include/stop_slave.inc
SET GLOBAL slave_parallel_threads=@old_parallel_threads;
include/start_slave.inc
DROP TABLE t1, t2;
DROP TABLE t1, t2, t3, t4;
DROP function foo;
include/rpl_end.inc