mirror of
https://github.com/MariaDB/server.git
synced 2025-02-04 21:02:17 +01:00
f307160218
This commit contains a merge from 10.5-MDEV-29293-squash
into 10.6.
Although the bug MDEV-29293 was not reproducible with 10.6,
the fix contains several improvements for wsrep KILL query and
BF abort handling, and addresses the following issues:
* MDEV-30307 KILL command issued inside a transaction is
problematic for galera replication:
This commit will remove KILL TOI replication, so Galera side
transaction context is not lost during KILL.
* MDEV-21075 KILL QUERY maintains nodes data consistency but
breaks GTID sequence: This is fixed as well as KILL does not
use TOI, and thus does not change GTID state.
* MDEV-30372 Assertion in wsrep-lib state: This was caused by
BF abort or KILL when local transaction was in the middle
of group commit. This commit disables THD::killed handling
during commit, so the problem is avoided.
* MDEV-30963 Assertion failure !lock.was_chosen_as_deadlock_victim
in trx0trx.h:1065: The assertion happened when the victim was
BF aborted via MDL while it was committing. This commit changes
MDL BF aborts so that transactions which are committing cannot
be BF aborted via MDL. The RQG grammar attached in the issue
could not reproduce the crash anymore.
Original commit message from 10.5 fix:
MDEV-29293 MariaDB stuck on starting commit state
The problem seems to be a deadlock between KILL command execution
and BF abort issued by an applier, where:
* KILL has locked victim's LOCK_thd_kill and LOCK_thd_data.
* Applier has innodb side global lock mutex and victim trx mutex.
* KILL is calling innobase_kill_query, and is blocked by innodb
global lock mutex.
* Applier is in wsrep_innobase_kill_one_trx and is blocked by
victim's LOCK_thd_kill.
The fix in this commit removes the TOI replication of KILL command
and makes KILL execution less intrusive operation. Aborting the
victim happens now by using awake_no_mutex() and ha_abort_transaction().
If the KILL happens when the transaction is committing, the
KILL operation is postponed to happen after the statement
has completed in order to avoid KILL to interrupt commit
processing.
Notable changes in this commit:
* wsrep client connections's error state may remain sticky after
client connection is closed. This error message will then pop
up for the next client session issuing first SQL statement.
This problem raised with test galera.galera_bf_kill.
The fix is to reset wsrep client error state, before a THD is
reused for next connetion.
* Release THD locks in wsrep_abort_transaction when locking
innodb mutexes. This guarantees same locking order as with applier
BF aborting.
* BF abort from MDL was changed to do BF abort on server/wsrep-lib
side first, and only then do the BF abort on InnoDB side. This
removes the need to call back from InnoDB for BF aborts which originate
from MDL and simplifies the locking.
* Removed wsrep_thd_set_wsrep_aborter() from service_wsrep.h.
The manipulation of the wsrep_aborter can be done solely on
server side. Moreover, it is now debug only variable and
could be excluded from optimized builds.
* Remove LOCK_thd_kill from wsrep_thd_LOCK/UNLOCK to allow more
fine grained locking for SR BF abort which may require locking
of victim LOCK_thd_kill. Added explicit call for
wsrep_thd_kill_LOCK/UNLOCK where appropriate.
* Wsrep-lib was updated to version which allows external
locking for BF abort calls.
Changes to MTR tests:
* Disable galera_bf_abort_group_commit. This test is going to
be removed (MDEV-30855).
* Make galera_var_retry_autocommit result more readable by echoing
cases and expectations into result. Only one expected result for
reap to verify that server returns expected status for query.
* Record galera_gcache_recover_manytrx as result file was incomplete.
Trivial change.
* Make galera_create_table_as_select more deterministic:
Wait until CTAS execution has reached MDL wait for multi-master
conflict case. Expected error from multi-master conflict is
ER_QUERY_INTERRUPTED. This is because CTAS does not yet have open
wsrep transaction when it is waiting for MDL, query gets interrupted
instead of BF aborted. This should be addressed in separate task.
* A new test galera_bf_abort_registering to check that registering trx gets
BF aborted through MDL.
* A new test galera_kill_group_commit to verify correct behavior
when KILL is executed while the transaction is committing.
Co-authored-by: Seppo Jaakola <seppo.jaakola@iki.fi>
Co-authored-by: Jan Lindström <jan.lindstrom@galeracluster.com>
Signed-off-by: Julius Goryavsky <julius.goryavsky@mariadb.com>
163 lines
4.1 KiB
Text
163 lines
4.1 KiB
Text
#
|
|
# Test that the wsrep_retry_autocommit variable is respected.
|
|
#
|
|
|
|
--source include/galera_cluster.inc
|
|
--source include/have_innodb.inc
|
|
--source include/have_debug.inc
|
|
--source include/have_debug_sync.inc
|
|
--source include/galera_have_debug_sync.inc
|
|
|
|
--connect node_1a, 127.0.0.1, root, , test, $NODE_MYPORT_1
|
|
|
|
#
|
|
# With wsrep_retry_autocommit = 0, error is certain
|
|
#
|
|
|
|
--connection node_1
|
|
CREATE TABLE t1 (f1 INTEGER PRIMARY KEY) ENGINE=InnoDB;
|
|
|
|
SET SESSION wsrep_retry_autocommit = 0;
|
|
SET DEBUG_SYNC = 'wsrep_before_certification SIGNAL before_cert WAIT_FOR continue';
|
|
--send INSERT INTO t1 (f1) VALUES (2)
|
|
|
|
--connection node_1a
|
|
SET DEBUG_SYNC = 'now WAIT_FOR before_cert';
|
|
|
|
--connection node_2
|
|
--let $wait_condition = SELECT count(*)=1 FROM information_schema.TABLES WHERE TABLE_SCHEMA='test' AND TABLE_NAME='t1'
|
|
--source include/wait_condition.inc
|
|
TRUNCATE TABLE t1;
|
|
|
|
--connection node_1
|
|
--error ER_LOCK_DEADLOCK
|
|
--reap
|
|
SELECT COUNT(*) FROM t1;
|
|
|
|
SET DEBUG_SYNC = 'RESET';
|
|
DROP TABLE t1;
|
|
|
|
|
|
#
|
|
# With wsrep_retry_autocommit = 1, success against one TRUNCATE
|
|
#
|
|
|
|
--connection node_1
|
|
CREATE TABLE t1 (f1 INTEGER PRIMARY KEY) ENGINE=InnoDB;
|
|
|
|
SET SESSION wsrep_retry_autocommit = 1;
|
|
SET GLOBAL debug_dbug = '+d,sync.wsrep_retry_autocommit';
|
|
SET DEBUG_SYNC = 'wsrep_before_certification SIGNAL before_cert WAIT_FOR continue';
|
|
--send INSERT INTO t1 (f1) VALUES (3)
|
|
|
|
--connection node_1a
|
|
SET DEBUG_SYNC = 'now WAIT_FOR before_cert';
|
|
|
|
--connection node_2
|
|
--let $wait_condition = SELECT count(*)=1 FROM information_schema.TABLES WHERE TABLE_SCHEMA='test' AND TABLE_NAME='t1'
|
|
--source include/wait_condition.inc
|
|
TRUNCATE TABLE t1;
|
|
|
|
--connection node_1a
|
|
SET DEBUG_SYNC = 'now WAIT_FOR wsrep_retry_autocommit_reached';
|
|
SELECT COUNT(*) FROM t1;
|
|
SET DEBUG_SYNC = 'now SIGNAL wsrep_retry_autocommit_continue';
|
|
|
|
--connection node_1
|
|
--error 0,ER_LOCK_DEADLOCK
|
|
--reap
|
|
SELECT COUNT(*) FROM t1;
|
|
|
|
SET DEBUG_SYNC = 'RESET';
|
|
SET GLOBAL debug_dbug = NULL;
|
|
DROP TABLE t1;
|
|
|
|
|
|
#
|
|
# With wsrep_retry_autcommit = 1, failure against multiple TRUNCATEs
|
|
#
|
|
|
|
--connection node_1
|
|
CREATE TABLE t1 (f1 INTEGER PRIMARY KEY) ENGINE=InnoDB;
|
|
|
|
SET SESSION wsrep_retry_autocommit = 1;
|
|
SET GLOBAL debug_dbug = '+d,sync.wsrep_retry_autocommit';
|
|
SET DEBUG_SYNC = 'wsrep_before_certification SIGNAL before_cert WAIT_FOR continue EXECUTE 2';
|
|
|
|
--send INSERT INTO t1 VALUES (4);
|
|
|
|
--connection node_1a
|
|
SET DEBUG_SYNC = 'now WAIT_FOR before_cert';
|
|
|
|
--connection node_2
|
|
--let $wait_condition = SELECT count(*)=1 FROM information_schema.TABLES WHERE TABLE_SCHEMA='test' AND TABLE_NAME='t1'
|
|
--source include/wait_condition.inc
|
|
TRUNCATE TABLE t1;
|
|
|
|
--connection node_1a
|
|
SET DEBUG_SYNC = 'now WAIT_FOR wsrep_retry_autocommit_reached';
|
|
SELECT COUNT(*) FROM t1;
|
|
SET DEBUG_SYNC = 'now SIGNAL wsrep_retry_autocommit_continue WAIT_FOR before_cert';
|
|
|
|
--connection node_2
|
|
TRUNCATE TABLE t1;
|
|
|
|
--connection node_1a
|
|
SELECT COUNT(*) FROM t1;
|
|
|
|
--connection node_1
|
|
--error 0,ER_LOCK_DEADLOCK
|
|
--reap
|
|
|
|
SET DEBUG_SYNC = 'RESET';
|
|
SET GLOBAL debug_dbug = NULL;
|
|
DROP TABLE t1;
|
|
|
|
|
|
#
|
|
# With wsrep_retry_autocommit = 64, success against 64 TRUNCATEs
|
|
#
|
|
|
|
--connection node_1
|
|
CREATE TABLE t1 (f1 INTEGER PRIMARY KEY) ENGINE=InnoDB;
|
|
|
|
SET SESSION wsrep_retry_autocommit = 64;
|
|
SET GLOBAL debug_dbug = '+d,sync.wsrep_retry_autocommit';
|
|
SET DEBUG_SYNC = 'wsrep_before_certification SIGNAL before_cert WAIT_FOR continue EXECUTE 64';
|
|
|
|
--send INSERT INTO t1 VALUES (5)
|
|
|
|
--connection node_2
|
|
--let $wait_condition = SELECT count(*)=1 FROM information_schema.TABLES WHERE TABLE_SCHEMA='test' AND TABLE_NAME='t1'
|
|
--source include/wait_condition.inc
|
|
|
|
--connection node_1
|
|
--disable_query_log
|
|
--disable_result_log
|
|
--let $count = 64
|
|
while ($count)
|
|
{
|
|
--connection node_1a
|
|
SET DEBUG_SYNC = 'now WAIT_FOR before_cert';
|
|
|
|
--connection node_2
|
|
TRUNCATE TABLE t1;
|
|
|
|
--connection node_1a
|
|
SET DEBUG_SYNC = 'now WAIT_FOR wsrep_retry_autocommit_reached';
|
|
SELECT COUNT(*) FROM t1;
|
|
SET DEBUG_SYNC = 'now SIGNAL wsrep_retry_autocommit_continue';
|
|
|
|
--dec $count
|
|
}
|
|
--enable_result_log
|
|
--enable_query_log
|
|
|
|
--connection node_1
|
|
--error 0,ER_LOCK_DEADLOCK
|
|
--reap
|
|
SELECT COUNT(*) FROM t1;
|
|
|
|
SET DEBUG_SYNC = 'RESET';
|
|
SET GLOBAL debug_dbug = NULL;
|
|
DROP TABLE t1;
|