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

MDEV-32444 Data from orphaned XA transaction is lost after online alter

XA support for online alter was totally missing.

Tying on binlog_hton made this hardly visible: simply having binlog_commit
called from xa_commit made an impression that it will automagically work
for online alter, which turns out wrong: all binlog does is writes
"XA END" into trx cache and flushes it to a real binlog.

In comparison, online alter can't do the same, since online replication
happens in a single transaction.

Solution: make a dedicated XA support.
* Extend struct xid_t with a pointer to Online_alter_cache_list
* On prepare: move online alter cache from THD::ha_data to XID passed
* On XA commit/rollback: use the online alter cache stored in this XID.
  This makes us pass xid_cache_element->xid to xa_commit/xa_rollback
  instead of lex->xid
* Use manual memory management for online alter cache list, instead of
  mem_root allocation, since we don't have mem_root connected to the XA
  transaction.
This commit is contained in:
Nikita Malyavin
2023-10-11 12:37:24 +04:00
parent a569515a9d
commit 23f9e34256
8 changed files with 337 additions and 22 deletions

View File

@ -1563,6 +1563,116 @@ connection default;
drop table t1, t2;
set @@binlog_format=default;
set debug_sync= reset;
# MDEV-32444 Data from orphaned XA transaction is lost after online alter
create table t (a int primary key) engine=innodb;
insert into t values (1);
# XA commit
set debug_sync= 'alter_table_online_downgraded signal downgraded wait_for go';
alter table t force, algorithm=copy, lock=none;
connection con1;
set debug_sync= 'now wait_for downgraded';
xa begin 'x1';
update t set a = 2 where a = 1;
xa end 'x1';
xa prepare 'x1';
set debug_sync= 'THD_cleanup_after_trans_cleanup signal xa_detach';
disconnect con1;
connection con2;
set debug_sync= 'now wait_for xa_detach';
xa commit 'x1';
set debug_sync= 'now signal go';
connection default;
select * from t;
a
2
# XA rollback
set debug_sync= 'alter_table_online_downgraded signal downgraded wait_for go';
alter table t force, algorithm=copy, lock=none;
connect con1, localhost, root,,;
set debug_sync= 'now wait_for downgraded';
xa begin 'x2';
insert into t values (53);
xa end 'x2';
xa prepare 'x2';
set debug_sync= 'THD_cleanup_after_trans_cleanup signal xa_detach';
disconnect con1;
connection con2;
set debug_sync= 'now wait_for xa_detach';
xa rollback 'x2';
set debug_sync= 'now signal go';
connection default;
select * from t;
a
2
# XA transaction is left uncommitted
# end then is rollbacked after alter fails
set debug_sync= 'alter_table_online_downgraded signal downgraded wait_for go';
set statement innodb_lock_wait_timeout=0, lock_wait_timeout= 0
for alter table t force, algorithm=copy, lock=none;
connect con1, localhost, root,,;
set debug_sync= 'now wait_for downgraded';
xa begin 'xuncommitted';
insert into t values (3);
xa end 'xuncommitted';
xa prepare 'xuncommitted';
set debug_sync= 'now signal go';
set debug_sync= 'THD_cleanup_after_trans_cleanup signal xa_detach';
disconnect con1;
connection default;
ERROR HY000: Lock wait timeout exceeded; try restarting transaction
set debug_sync= 'now wait_for xa_detach';
xa rollback 'xuncommitted';
select * from t;
a
2
# Same, but commit
set debug_sync= 'alter_table_online_downgraded signal downgraded wait_for go';
set statement innodb_lock_wait_timeout=0, lock_wait_timeout= 0
for alter table t force, algorithm=copy, lock=none;
connect con1, localhost, root,,;
set debug_sync= 'now wait_for downgraded';
xa begin 'committed_later';
insert into t values (3);
xa end 'committed_later';
xa prepare 'committed_later';
set debug_sync= 'now signal go';
set debug_sync= 'THD_cleanup_after_trans_cleanup signal xa_detach';
disconnect con1;
connection default;
ERROR HY000: Lock wait timeout exceeded; try restarting transaction
set debug_sync= 'now wait_for xa_detach';
xa commit 'committed_later';
select * from t;
a
2
3
# Commit, but error in statement, and there is some stmt data to rollback
set debug_sync= 'alter_table_online_downgraded signal downgraded wait_for go';
alter table t force, algorithm=copy, lock=none;
connect con1, localhost, root,,;
set debug_sync= 'now wait_for downgraded';
xa begin 'x1';
insert into t values (4), (3);
ERROR 23000: Duplicate entry '3' for key 'PRIMARY'
insert into t values (5);
xa end 'x1';
xa prepare 'x1';
set debug_sync= 'THD_cleanup_after_trans_cleanup signal xa_detach';
disconnect con1;
connection con2;
set debug_sync= 'now wait_for xa_detach';
xa commit 'x1';
set debug_sync= 'now signal go';
connection default;
select * from t;
a
2
3
5
connect con1, localhost, root,,;
connection default;
drop table t;
set debug_sync= reset;
disconnect con1;
disconnect con2;
#