mariadb/mysql-test/suite/galera/t/galera_UK_conflict.test
Jan Lindström 509c7f66bd MDEV-27977 : galera.galera_UK_conflict fails with wrong result
Add wait_condition so that all rows expected are really
replicated before we check it.
2023-01-25 09:08:15 +02:00

295 lines
10 KiB
Text

#
# This test tests the operation of transaction replay with a scenario
# where two subsequent write sets being applied conflict with local transaction
# in commit phase. The conflict is "false positive" confict on GAP lock in
# secondary unique index.
# The first applier will cause BF abort for the local committer, which
# starts replaying because of positive certification.
# In buggy version, the test scenario continues so that while the local transaction
# is replaying, the latter applier experiences similar UK GAP lock conflict
# and forces the replayer to abort second time.
# In fixed version, this latter replayer BF abort should not happen.
#
--source include/galera_cluster.inc
--source include/have_innodb.inc
--source include/have_debug_sync.inc
--source include/galera_have_debug_sync.inc
--let $expected_wsrep_local_replays = `SELECT VARIABLE_VALUE+1 FROM INFORMATION_SCHEMA.GLOBAL_STATUS WHERE VARIABLE_NAME = 'wsrep_local_replays'`
CREATE TABLE t1 (f1 INTEGER PRIMARY KEY, f2 int, f3 int, unique key keyj (f2));
INSERT INTO t1 VALUES (1, 1, 0);
INSERT INTO t1 VALUES (3, 3, 0);
INSERT INTO t1 VALUES (10, 10, 0);
# we will need 2 appliers threads for applyin two writes ets in parallel in node1
# and 1 applier thread for handling replaying
SET GLOBAL wsrep_slave_threads = 3;
SET GLOBAL DEBUG_DBUG = "d,sync.wsrep_apply_cb";
--connection node_1
# starting a transaction, which deletes and inserts the middle row in test table
# this will be victim of false positive conflict with appliers
SET SESSION wsrep_sync_wait=0;
START TRANSACTION;
DELETE FROM t1 WHERE f2 = 3;
INSERT INTO t1 VALUES (3, 3, 1);
# Control connection to manage sync points for appliers
--connect node_1a, 127.0.0.1, root, , test, $NODE_MYPORT_1
--connection node_1a
SET SESSION wsrep_sync_wait=0;
# send from node 2 first an INSERT transaction, which will conflict on GAP lock in node 1
--connection node_2
INSERT INTO t1 VALUES (5, 5, 2);
--connection node_1a
# wait to see the INSERT in apply_cb sync point
SET SESSION DEBUG_SYNC = "now WAIT_FOR sync.wsrep_apply_cb_reached";
# first applier seen in wait point, set sync point for the second INSERT
--let $galera_sync_point = apply_monitor_slave_enter_sync
--source include/galera_set_sync_point.inc
--connection node_2
# send second insert into same GAP in test table
INSERT INTO t1 VALUES (4, 4, 2);
--connection node_1a
# wait for the second insert to arrive in his sync point
--let $galera_sync_point = apply_monitor_slave_enter_sync
--source include/galera_wait_sync_point.inc
--source include/galera_clear_sync_point.inc
# both appliers are now waiting in separate sync points
# Block the local commit, send the COMMIT and wait until it gets blocked
--let $galera_sync_point = commit_monitor_master_enter_sync
--source include/galera_set_sync_point.inc
--connection node_1
--send COMMIT
--connection node_1a
# wait for the local commit to enter in commit monitor wait state
--let $galera_sync_point = apply_monitor_slave_enter_sync commit_monitor_master_enter_sync
--source include/galera_wait_sync_point.inc
--source include/galera_clear_sync_point.inc
# release the local transaction to continue with commit
--let $galera_sync_point = commit_monitor_master_enter_sync
--source include/galera_signal_sync_point.inc
--source include/galera_clear_sync_point.inc
# and now release the first applier, it should force local trx to abort
SET GLOBAL DEBUG_DBUG = "";
SET DEBUG_SYNC = "now SIGNAL signal.wsrep_apply_cb";
SET GLOBAL debug_dbug = NULL;
SET debug_sync='RESET';
# wait for BF abort to happen and replaying begin
--let $wait_condition = SELECT VARIABLE_VALUE= $expected_wsrep_local_replays FROM INFORMATION_SCHEMA.GLOBAL_STATUS WHERE VARIABLE_NAME = 'wsrep_local_replays';
--let $wait_condition_on_error_output= SELECT VARIABLE_VALUE FROM INFORMATION_SCHEMA.GLOBAL_STATUS WHERE VARIABLE_NAME = 'wsrep_local_replays';
--source include/wait_condition_with_debug.inc
# set another sync point for second applier
SET GLOBAL DEBUG_DBUG = "d,sync.wsrep_apply_cb";
# letting the second appier to move forward
--let $galera_sync_point = apply_monitor_slave_enter_sync
--source include/galera_signal_sync_point.inc
# waiting until second applier is in wait state
SET SESSION DEBUG_SYNC = "now WAIT_FOR sync.wsrep_apply_cb_reached";
# stopping second applier before commit
--let $galera_sync_point = commit_monitor_slave_enter_sync
--source include/galera_set_sync_point.inc
--source include/galera_clear_sync_point.inc
# releasing the second insert, with buggy version it will conflict with
# replayer
SET GLOBAL DEBUG_DBUG = "";
SET DEBUG_SYNC = "now SIGNAL signal.wsrep_apply_cb";
SET GLOBAL debug_dbug = NULL;
SET debug_sync='RESET';
# with fixed version, second applier has reached comit monitor, and we can
# release it to complete
--let $galera_sync_point = commit_monitor_slave_enter_sync
--source include/galera_signal_sync_point.inc
--source include/galera_clear_sync_point.inc
# local commit should succeed
--connection node_1
--reap
SELECT * FROM t1;
# returning original slave thread count
SET GLOBAL wsrep_slave_threads = DEFAULT;
--connection node_2
SELECT * FROM t1;
# replicate some transactions, so that wsrep slave thread count can reach
# original state in node 1
INSERT INTO t1 VALUES (7,7,7);
INSERT INTO t1 VALUES (8,8,8);
SELECT COUNT(*) FROM t1;
SELECT * FROM t1;
--connection node_1
--let $wait_condition = SELECT COUNT(*) = 7 FROM t1
--source include/wait_condition.inc
SELECT COUNT(*) FROM t1;
SELECT * FROM t1;
DROP TABLE t1;
##################################################################################
# test scenario 2
#
# commit order is now: INSERT-1, local COMMIT, INSERT-2
# while local trx is replaying, the latter applier has applied and is waiting
# for commit.
# The point in this scenario is to verify that replayer does not try to abort
# the latter applier
#################################################################################
--echo test scenario 2
--connection node_1
--let $expected_wsrep_local_replays = `SELECT VARIABLE_VALUE+1 FROM INFORMATION_SCHEMA.GLOBAL_STATUS WHERE VARIABLE_NAME = 'wsrep_local_replays'`
CREATE TABLE t1 (f1 INTEGER PRIMARY KEY, f2 int, f3 int, unique key keyj (f2));
INSERT INTO t1 VALUES (1, 1, 0);
INSERT INTO t1 VALUES (3, 3, 0);
INSERT INTO t1 VALUES (10, 10, 0);
# we will need 2 appliers threads for applyin two writes sets in parallel in node1
# and 1 applier thread for handling replaying
SET GLOBAL wsrep_slave_threads = 3;
# set sync point for the first INSERT applier
--let $galera_sync_point = apply_monitor_slave_enter_sync
--source include/galera_set_sync_point.inc
--connection node_1
# starting a transaction, which deletes and inserts the middle row in test table
# this will be victim of false positive conflict with appliers
SET SESSION wsrep_sync_wait=0;
START TRANSACTION;
DELETE FROM t1 WHERE f2 = 3;
INSERT INTO t1 VALUES (3, 3, 1);
# Control connection to manage sync points for appliers
--connection node_1a
SET SESSION wsrep_sync_wait=0;
# send from node 2 first an INSERT transaction, which will conflict on GAP lock in node 1
--connection node_2
INSERT INTO t1 VALUES (5, 5, 2);
--connection node_1a
# wait to see the INSERT in apply_cb sync point
--let $galera_sync_point = apply_monitor_slave_enter_sync
--source include/galera_wait_sync_point.inc
--source include/galera_clear_sync_point.inc
# Block the local commit, send the COMMIT and wait until it gets blocked
--let $galera_sync_point = commit_monitor_master_enter_sync
--source include/galera_set_sync_point.inc
--connection node_1
--send COMMIT
--connection node_1a
# wait for the local commit to enter in commit monitor wait state
--let $galera_sync_point = apply_monitor_slave_enter_sync commit_monitor_master_enter_sync
--source include/galera_wait_sync_point.inc
--source include/galera_clear_sync_point.inc
# first applier is now waiting in before commit, and local trx in commit monitor
# set sync point before replaying
SET GLOBAL DEBUG_DBUG = "d,sync.wsrep_replay_cb";
# release the local transaction to continue with commit
# it should advance and end up waiting in commit monitor for his turn
--let $galera_sync_point = commit_monitor_master_enter_sync
--source include/galera_signal_sync_point.inc
--source include/galera_clear_sync_point.inc
# and now release the first applier, it should force local trx to abort
--let $galera_sync_point = apply_monitor_slave_enter_sync
--source include/galera_signal_sync_point.inc
--source include/galera_clear_sync_point.inc
# wait for BF abort to happen and replaying begin
--let $wait_condition = SELECT VARIABLE_VALUE= $expected_wsrep_local_replays FROM INFORMATION_SCHEMA.GLOBAL_STATUS WHERE VARIABLE_NAME = 'wsrep_local_replays';
--let $wait_condition_on_error_output= SELECT VARIABLE_VALUE FROM INFORMATION_SCHEMA.GLOBAL_STATUS WHERE VARIABLE_NAME = 'wsrep_local_replays';
--source include/wait_condition_with_debug.inc
# replayer should now be in stopped in sync point
SET SESSION DEBUG_SYNC = "now WAIT_FOR sync.wsrep_replay_cb_reached";
# set sync point for the second INSERT
--let $galera_sync_point = commit_monitor_slave_enter_sync
--source include/galera_set_sync_point.inc
--connection node_2
# send second insert into same GAP in test table
INSERT INTO t1 VALUES (4, 4, 2);
--connection node_1a
# wait for the second applier to enter in commit monitor wait state
--let $galera_sync_point = commit_monitor_slave_enter_sync
--source include/galera_wait_sync_point.inc
--source include/galera_clear_sync_point.inc
# and, letting the second appier to move forward, it will stop naturally
# to wait for commit order after replayer's commit
--let $galera_sync_point = commit_monitor_slave_enter_sync
--source include/galera_signal_sync_point.inc
--source include/galera_clear_sync_point.inc
# and now release the replayer, if all is good,it will commit before the second applier
SET GLOBAL DEBUG_DBUG = "";
SET DEBUG_SYNC = "now SIGNAL signal.wsrep_replay_cb";
SET GLOBAL debug_dbug = NULL;
SET debug_sync='RESET';
# local commit should succeed
--connection node_1
--reap
--let $wait_condition = SELECT COUNT(*)=5 FROM t1;
--source include/wait_condition.inc
# returning original slave thread count
SET GLOBAL wsrep_slave_threads = DEFAULT;
--connection node_2
SELECT * FROM t1;
# replicate some transactions, so that wsrep slave thread count can reach
# original state in node 1
INSERT INTO t1 VALUES (7,7,7);
INSERT INTO t1 VALUES (8,8,8);
SELECT COUNT(*) FROM t1;
SELECT * FROM t1;
--connection node_1
--let $wait_condition = SELECT COUNT(*) = 7 FROM t1
--source include/wait_condition.inc
SELECT COUNT(*) FROM t1;
SELECT * FROM t1;
DROP TABLE t1;