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

MDEV-5363: Make parallel replication waits killable

Add another test case. This one for killing a worker while its transaction is
waiting to start until the previous transaction has committed.

Fix setting reading_or_writing to 0 in worker threads so SHOW SLAVE STATUS can
show something more useful than "Reading from net".
This commit is contained in:
unknown
2013-12-18 16:26:22 +01:00
parent 245ab473a7
commit 86a2c03b51
3 changed files with 320 additions and 0 deletions

View File

@ -402,6 +402,7 @@ SELECT * FROM t3 WHERE a >= 30 ORDER BY a;
SET sql_log_bin=0;
CALL mtr.add_suppression("Query execution was interrupted");
CALL mtr.add_suppression("Commit failed due to failure of an earlier commit on which this one depends");
CALL mtr.add_suppression("Slave: Connection was killed");
SET sql_log_bin=1;
# Wait until T2 is inside executing its insert of 32, then find it in SHOW
# PROCESSLIST to know its thread id for KILL later.
@ -745,6 +746,201 @@ SET sql_log_bin=1;
--source include/stop_slave.inc
CHANGE MASTER TO master_use_gtid=slave_pos;
--source include/start_slave.inc
--connection server_2
# Respawn all worker threads to clear any left-over debug_sync or other stuff.
--source include/stop_slave.inc
SET GLOBAL binlog_format=@old_format;
SET GLOBAL slave_parallel_threads=0;
SET GLOBAL slave_parallel_threads=3;
--source include/start_slave.inc
--echo *** 4. Test killing thread that is waiting to start transaction until previous transaction commits ***
# We set up four transactions T1, T2, T3, and T4 on the master. T2, T3, and T4
# can run in parallel with each other (same group commit and commit id),
# but not in parallel with T1.
#
# We use three worker threads. T1 and T2 will be queued on the first, T3 on
# the second, and T4 on the third. We will delay T1 commit, T3 will wait for
# T1 to commit before it can start. We will kill T3 during this wait, and
# check that everything works correctly.
#
# It is rather tricky to get the correct thread id of the worker to kill.
# We start by injecting three dummy transactions in a debug_sync-controlled
# manner to be able to get known thread ids for the workers in a pool with
# just 3 worker threads. Then we let in each of the real test transactions
# T1-T4 one at a time in a way which allows us to know which transaction
# ends up with which thread id.
--connection server_1
SET binlog_format=statement;
SET gtid_domain_id=2;
INSERT INTO t3 VALUES (60, foo(60,
'ha_write_row_end SIGNAL d2_query WAIT_FOR d2_cont2',
'rpl_parallel_end_of_group SIGNAL d2_done WAIT_FOR d2_cont'));
SET gtid_domain_id=0;
--connection server_2
SET debug_sync='now WAIT_FOR d2_query';
--let $d2_thd_id= `SELECT ID FROM INFORMATION_SCHEMA.PROCESSLIST WHERE INFO LIKE '%foo(60%' AND INFO NOT LIKE '%LIKE%'`
--connection server_1
SET gtid_domain_id=1;
BEGIN;
# These debug_sync's will linger on and be used to control T3 later.
INSERT INTO t3 VALUES (61, foo(61,
'rpl_parallel_start_waiting_for_prior SIGNAL t3_waiting',
'rpl_parallel_start_waiting_for_prior_killed SIGNAL t3_killed'));
INSERT INTO t3 VALUES (62, foo(62,
'ha_write_row_end SIGNAL d1_query WAIT_FOR d1_cont2',
'rpl_parallel_end_of_group SIGNAL d1_done WAIT_FOR d1_cont'));
COMMIT;
SET gtid_domain_id=0;
--connection server_2
SET debug_sync='now WAIT_FOR d1_query';
--let $d1_thd_id= `SELECT ID FROM INFORMATION_SCHEMA.PROCESSLIST WHERE INFO LIKE '%foo(62%' AND INFO NOT LIKE '%LIKE%'`
--connection server_1
SET gtid_domain_id=0;
INSERT INTO t3 VALUES (63, foo(63,
'ha_write_row_end SIGNAL d0_query WAIT_FOR d0_cont2',
'rpl_parallel_end_of_group SIGNAL d0_done WAIT_FOR d0_cont'));
--connection server_2
SET debug_sync='now WAIT_FOR d0_query';
--let $d0_thd_id= `SELECT ID FROM INFORMATION_SCHEMA.PROCESSLIST WHERE INFO LIKE '%foo(63%' AND INFO NOT LIKE '%LIKE%'`
SET debug_sync='now SIGNAL d2_cont2';
SET debug_sync='now WAIT_FOR d2_done';
SET debug_sync='now SIGNAL d1_cont2';
SET debug_sync='now WAIT_FOR d1_done';
SET debug_sync='now SIGNAL d0_cont2';
SET debug_sync='now WAIT_FOR d0_done';
# Now prepare the real transactions T1, T2, T3, T4 on the master.
--connection con_temp3
# Create transaction T1.
SET binlog_format=statement;
INSERT INTO t3 VALUES (64, foo(64,
'commit_before_prepare_ordered SIGNAL t1_waiting WAIT_FOR t1_cont', ''));
# Create transaction T2, as a group commit leader on the master.
SET debug_sync='commit_after_release_LOCK_prepare_ordered SIGNAL master_queued2 WAIT_FOR master_cont2';
send INSERT INTO t3 VALUES (65, foo(65, '', ''));
--connection server_1
SET debug_sync='now WAIT_FOR master_queued2';
--connection con_temp4
# Create transaction T3, participating in T2's group commit.
SET debug_sync='commit_after_release_LOCK_prepare_ordered SIGNAL master_queued3';
send INSERT INTO t3 VALUES (66, foo(66, '', ''));
--connection server_1
SET debug_sync='now WAIT_FOR master_queued3';
--connection con_temp5
# Create transaction T4, participating in group commit with T2 and T3.
SET debug_sync='commit_after_release_LOCK_prepare_ordered SIGNAL master_queued4';
send INSERT INTO t3 VALUES (67, foo(67, '', ''));
--connection server_1
SET debug_sync='now WAIT_FOR master_queued4';
SET debug_sync='now SIGNAL master_cont2';
--connection con_temp3
REAP;
--connection con_temp4
REAP;
--connection con_temp5
REAP;
--connection server_1
SELECT * FROM t3 WHERE a >= 60 ORDER BY a;
--connection server_2
# Now we have the four transactions pending for replication on the slave.
# Let them be queued for our three worker threads in a controlled fashion.
# We put them at a stage where T1 is delayed and T3 is waiting for T1 to
# commit before T3 can start. Then we kill T3.
# Make the worker D0 free, and wait for T1 to be queued in it.
SET debug_sync='now SIGNAL d0_cont';
SET debug_sync='now WAIT_FOR t1_waiting';
# T2 will be queued on the same worker D0 as T1.
# Now release worker D1, and wait for T3 to be queued in it.
# T3 will wait for T1 to commit before it can start.
SET debug_sync='now SIGNAL d1_cont';
SET debug_sync='now WAIT_FOR t3_waiting';
# Release worker D2. T4 may or may not have time to be queued on it, but
# it will not be able to complete due to T3 being killed.
SET debug_sync='now SIGNAL d2_cont';
# Now we kill the waiting transaction T3 in worker D1.
--replace_result $d1_thd_id THD_ID
eval KILL $d1_thd_id;
# Wait until T3 has reacted on the kill.
SET debug_sync='now WAIT_FOR t3_killed';
# Now we can allow T1 to proceed.
SET debug_sync='now SIGNAL t1_cont';
--let $slave_sql_errno= 1317,1927,1963
--source include/wait_for_slave_sql_error.inc
STOP SLAVE IO_THREAD;
SELECT * FROM t3 WHERE a >= 60 ORDER BY a;
# Now we have to disable the debug_sync statements, so they do not trigger
# when the events are retried.
SET GLOBAL slave_parallel_threads=0;
SET GLOBAL slave_parallel_threads=10;
SET sql_log_bin=0;
DROP FUNCTION foo;
--delimiter ||
CREATE FUNCTION foo(x INT, d1 VARCHAR(500), d2 VARCHAR(500))
RETURNS INT DETERMINISTIC
BEGIN
RETURN x;
END
||
--delimiter ;
SET sql_log_bin=1;
--connection server_1
INSERT INTO t3 VALUES (69,0);
--save_master_pos
--connection server_2
--source include/start_slave.inc
--sync_with_master
SELECT * FROM t3 WHERE a >= 60 ORDER BY a;
# Restore the foo() function.
SET sql_log_bin=0;
DROP FUNCTION foo;
--delimiter ||
CREATE FUNCTION foo(x INT, d1 VARCHAR(500), d2 VARCHAR(500))
RETURNS INT DETERMINISTIC
BEGIN
IF d1 != '' THEN
SET debug_sync = d1;
END IF;
IF d2 != '' THEN
SET debug_sync = d2;
END IF;
RETURN x;
END
||
--delimiter ;
SET sql_log_bin=1;
--connection server_2
--source include/stop_slave.inc
SET GLOBAL binlog_format=@old_format;