mirror of
https://github.com/MariaDB/server.git
synced 2025-04-24 18:27:21 +03:00
3cef4f8f0f
We implement an idea that was suggested by Michael 'Monty' Widenius in October 2017: When InnoDB is inserting into an empty table or partition, we can write a single undo log record TRX_UNDO_EMPTY, which will cause ROLLBACK to clear the table. For this to work, the insert into an empty table or partition must be covered by an exclusive table lock that will be held until the transaction has been committed or rolled back, or the INSERT operation has been rolled back (and the table is empty again), in lock_table_x_unlock(). Clustered index records that are covered by the TRX_UNDO_EMPTY record will carry DB_TRX_ID=0 and DB_ROLL_PTR=1<<55, and thus they cannot be distinguished from what MDEV-12288 leaves behind after purging the history of row-logged operations. Concurrent non-locking reads must be adjusted: If the read view was created before the INSERT into an empty table, then we must continue to imagine that the table is empty, and not try to read any records. If the read view was created after the INSERT was committed, then all records must be visible normally. To implement this, we introduce the field dict_table_t::bulk_trx_id. This special handling only applies to the very first INSERT statement of a transaction for the empty table or partition. If a subsequent statement in the transaction is modifying the initially empty table again, we must enable row-level undo logging, so that we will be able to roll back to the start of the statement in case of an error (such as duplicate key). INSERT IGNORE will continue to use row-level logging and locking, because implementing it would require the ability to roll back the latest row. Since the undo log that we write only allows us to roll back the entire statement, we cannot support INSERT IGNORE. We will introduce a handler::extra() parameter HA_EXTRA_IGNORE_INSERT to indicate to storage engines that INSERT IGNORE is being executed. In many test cases, we add an extra record to the table, so that during the 'interesting' part of the test, row-level locking and logging will be used. Replicas will continue to use row-level logging and locking until MDEV-24622 has been addressed. Likewise, this optimization will be disabled in Galera cluster until MDEV-24623 enables it. dict_table_t::bulk_trx_id: The latest active or committed transaction that initiated an insert into an empty table or partition. Protected by exclusive table lock and a clustered index leaf page latch. ins_node_t::bulk_insert: Whether bulk insert was initiated. trx_t::mod_tables: Use C++11 style accessors (emplace instead of insert). Unlike earlier, this collection will cover also temporary tables. trx_mod_table_time_t: Add start_bulk_insert(), end_bulk_insert(), is_bulk_insert(), was_bulk_insert(). trx_undo_report_row_operation(): Before accessing any undo log pages, invoke trx->mod_tables.emplace() in order to determine whether undo logging was disabled, or whether this is the first INSERT and we are supposed to write a TRX_UNDO_EMPTY record. row_ins_clust_index_entry_low(): If we are inserting into an empty clustered index leaf page, set the ins_node_t::bulk_insert flag for the subsequent trx_undo_report_row_operation() call. lock_rec_insert_check_and_lock(), lock_prdt_insert_check_and_lock(): Remove the redundant parameter 'flags' that can be checked in the caller. btr_cur_ins_lock_and_undo(): Simplify the logic. Correctly write DB_TRX_ID,DB_ROLL_PTR after invoking trx_undo_report_row_operation(). trx_mark_sql_stat_end(), ha_innobase::extra(HA_EXTRA_IGNORE_INSERT), ha_innobase::external_lock(): Invoke trx_t::end_bulk_insert() so that the next statement will not be covered by table-level undo logging. ReadView::changes_visible(trx_id_t) const: New accessor for the case where the trx_id_t is not read from a potentially corrupted index page but directly from the memory. In this case, we can skip a sanity check. row_sel(), row_sel_try_search_shortcut(), row_search_mvcc(): row_sel_try_search_shortcut_for_mysql(), row_merge_read_clustered_index(): Check dict_table_t::bulk_trx_id. row_sel_clust_sees(): Replaces lock_clust_rec_cons_read_sees(). lock_sec_rec_cons_read_sees(): Replaced with lower-level code. btr_root_page_init(): Refactored from btr_create(). dict_index_t::clear(), dict_table_t::clear(): Empty an index or table, for the ROLLBACK of an INSERT operation. ROW_T_EMPTY, ROW_OP_EMPTY: Note a concurrent ROLLBACK of an INSERT into an empty table. This is joint work with Thirunarayanan Balathandayuthapani, who created a working prototype. Thanks to Matthias Leich for extensive testing.
264 lines
7.2 KiB
Plaintext
264 lines
7.2 KiB
Plaintext
*** Test killing thread that is waiting to start transaction until previous transaction commits ***
|
|
include/master-slave.inc
|
|
[connection master]
|
|
connection server_2;
|
|
SET @old_parallel_threads=@@GLOBAL.slave_parallel_threads;
|
|
SET @old_parallel_mode= @@GLOBAL.slave_parallel_mode;
|
|
include/stop_slave.inc
|
|
SET sql_log_bin=0;
|
|
CALL mtr.add_suppression("Query execution was interrupted");
|
|
CALL mtr.add_suppression("Slave: Connection was killed");
|
|
CALL mtr.add_suppression("Commit failed due to failure of an earlier commit on which this one depends");
|
|
SET sql_log_bin=1;
|
|
SET GLOBAL slave_parallel_threads=10;
|
|
SET GLOBAL slave_parallel_mode= 'conservative';
|
|
CHANGE MASTER TO master_use_gtid=slave_pos;
|
|
include/start_slave.inc
|
|
connection server_1;
|
|
connect con_temp3,127.0.0.1,root,,test,$SERVER_MYPORT_1,;
|
|
connect con_temp4,127.0.0.1,root,,test,$SERVER_MYPORT_1,;
|
|
connect con_temp5,127.0.0.1,root,,test,$SERVER_MYPORT_1,;
|
|
ALTER TABLE mysql.gtid_slave_pos ENGINE=InnoDB;
|
|
CREATE TABLE t3 (a INT PRIMARY KEY, b INT) ENGINE=InnoDB;
|
|
INSERT INTO t3 VALUES(100, 100);
|
|
connection server_2;
|
|
connection server_1;
|
|
SET sql_log_bin=0;
|
|
CREATE FUNCTION foo(x INT, d1 VARCHAR(500), d2 VARCHAR(500))
|
|
RETURNS INT DETERMINISTIC
|
|
BEGIN
|
|
RETURN x;
|
|
END
|
|
||
|
|
SET sql_log_bin=1;
|
|
connection server_2;
|
|
SET sql_log_bin=0;
|
|
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
|
|
||
|
|
SET sql_log_bin=1;
|
|
include/stop_slave.inc
|
|
SET GLOBAL slave_parallel_threads=0;
|
|
SET GLOBAL slave_parallel_threads=4;
|
|
include/start_slave.inc
|
|
connection server_1;
|
|
SET gtid_domain_id=2;
|
|
BEGIN;
|
|
INSERT INTO t3 VALUES (70, foo(70,
|
|
'rpl_parallel_start_waiting_for_prior SIGNAL t4_waiting', ''));
|
|
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'));
|
|
COMMIT;
|
|
SET gtid_domain_id=0;
|
|
connection server_2;
|
|
SET debug_sync='now WAIT_FOR d2_query';
|
|
connection server_1;
|
|
SET gtid_domain_id=1;
|
|
BEGIN;
|
|
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';
|
|
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';
|
|
connection server_1;
|
|
SET gtid_domain_id=3;
|
|
BEGIN;
|
|
INSERT INTO t3 VALUES (68, foo(68,
|
|
'rpl_parallel_start_waiting_for_prior SIGNAL t2_waiting', ''));
|
|
INSERT INTO t3 VALUES (69, foo(69,
|
|
'ha_write_row_end SIGNAL d3_query WAIT_FOR d3_cont2',
|
|
'rpl_parallel_end_of_group SIGNAL d3_done WAIT_FOR d3_cont'));
|
|
COMMIT;
|
|
SET gtid_domain_id=0;
|
|
connection server_2;
|
|
SET debug_sync='now WAIT_FOR d3_query';
|
|
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';
|
|
SET debug_sync='now SIGNAL d3_cont2';
|
|
SET debug_sync='now WAIT_FOR d3_done';
|
|
connection con_temp3;
|
|
INSERT INTO t3 VALUES (64, foo(64,
|
|
'rpl_parallel_before_mark_start_commit SIGNAL t1_waiting WAIT_FOR t1_cont', ''));
|
|
SET debug_sync='commit_after_release_LOCK_prepare_ordered SIGNAL master_queued2 WAIT_FOR master_cont2';
|
|
INSERT INTO t3 VALUES (65, foo(65, '', ''));
|
|
connection server_1;
|
|
SET debug_sync='now WAIT_FOR master_queued2';
|
|
connection con_temp4;
|
|
SET debug_sync='commit_after_release_LOCK_prepare_ordered SIGNAL master_queued3';
|
|
INSERT INTO t3 VALUES (66, foo(66, '', ''));
|
|
connection server_1;
|
|
SET debug_sync='now WAIT_FOR master_queued3';
|
|
connection con_temp5;
|
|
SET debug_sync='commit_after_release_LOCK_prepare_ordered SIGNAL master_queued4';
|
|
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;
|
|
connection con_temp4;
|
|
connection con_temp5;
|
|
connection server_1;
|
|
SELECT * FROM t3 WHERE a >= 60 ORDER BY a;
|
|
a b
|
|
60 60
|
|
61 61
|
|
62 62
|
|
63 63
|
|
64 64
|
|
65 65
|
|
66 66
|
|
67 67
|
|
68 68
|
|
69 69
|
|
70 70
|
|
100 100
|
|
SET debug_sync='RESET';
|
|
connection server_2;
|
|
SET debug_sync='now SIGNAL d0_cont';
|
|
SET debug_sync='now WAIT_FOR t1_waiting';
|
|
SET debug_sync='now SIGNAL d3_cont';
|
|
SET debug_sync='now WAIT_FOR t2_waiting';
|
|
SET debug_sync='now SIGNAL d1_cont';
|
|
SET debug_sync='now WAIT_FOR t3_waiting';
|
|
SET debug_sync='now SIGNAL d2_cont';
|
|
SET debug_sync='now WAIT_FOR t4_waiting';
|
|
KILL THD_ID;
|
|
SET debug_sync='now WAIT_FOR t3_killed';
|
|
SET debug_sync='now SIGNAL t1_cont';
|
|
include/wait_for_slave_sql_error.inc [errno=1317,1927,1964]
|
|
STOP SLAVE IO_THREAD;
|
|
SELECT * FROM t3 WHERE a >= 60 AND a != 65 ORDER BY a;
|
|
a b
|
|
60 60
|
|
61 61
|
|
62 62
|
|
63 63
|
|
64 64
|
|
68 68
|
|
69 69
|
|
70 70
|
|
100 100
|
|
SET debug_sync='RESET';
|
|
SET GLOBAL slave_parallel_threads=0;
|
|
SET GLOBAL slave_parallel_threads=10;
|
|
SET sql_log_bin=0;
|
|
DROP FUNCTION foo;
|
|
CREATE FUNCTION foo(x INT, d1 VARCHAR(500), d2 VARCHAR(500))
|
|
RETURNS INT DETERMINISTIC
|
|
BEGIN
|
|
RETURN x;
|
|
END
|
|
||
|
|
SET sql_log_bin=1;
|
|
connection server_1;
|
|
UPDATE t3 SET b=b+1 WHERE a=60;
|
|
connection server_2;
|
|
include/start_slave.inc
|
|
SELECT * FROM t3 WHERE a >= 60 ORDER BY a;
|
|
a b
|
|
60 61
|
|
61 61
|
|
62 62
|
|
63 63
|
|
64 64
|
|
65 65
|
|
66 66
|
|
67 67
|
|
68 68
|
|
69 69
|
|
70 70
|
|
100 100
|
|
SET sql_log_bin=0;
|
|
DROP FUNCTION foo;
|
|
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
|
|
||
|
|
SET sql_log_bin=1;
|
|
connection server_2;
|
|
include/stop_slave.inc
|
|
SET GLOBAL slave_parallel_threads=0;
|
|
SET GLOBAL slave_parallel_threads=10;
|
|
include/start_slave.inc
|
|
*** 5. Test killing thread that is waiting for queue of max length to shorten ***
|
|
SET @old_max_queued= @@GLOBAL.slave_parallel_max_queued;
|
|
SET GLOBAL slave_parallel_max_queued=9000;
|
|
connection server_1;
|
|
INSERT INTO t3 VALUES (80, foo(0,
|
|
'ha_write_row_end SIGNAL query_waiting WAIT_FOR query_cont', ''));
|
|
connection server_2;
|
|
SET debug_sync='now WAIT_FOR query_waiting';
|
|
SET @old_dbug= @@GLOBAL.debug_dbug;
|
|
SET GLOBAL debug_dbug="+d,rpl_parallel_wait_queue_max";
|
|
connection server_1;
|
|
SELECT * FROM t3 WHERE a >= 80 ORDER BY a;
|
|
a b
|
|
80 0
|
|
81 10000
|
|
100 100
|
|
connection server_2;
|
|
SET debug_sync='now WAIT_FOR wait_queue_ready';
|
|
KILL THD_ID;
|
|
SET debug_sync='now WAIT_FOR wait_queue_killed';
|
|
SET debug_sync='now SIGNAL query_cont';
|
|
include/wait_for_slave_sql_error.inc [errno=1317,1927,1964]
|
|
STOP SLAVE IO_THREAD;
|
|
SET GLOBAL debug_dbug=@old_dbug;
|
|
SET GLOBAL slave_parallel_max_queued= @old_max_queued;
|
|
connection server_1;
|
|
INSERT INTO t3 VALUES (82,0);
|
|
connection server_2;
|
|
SET debug_sync='RESET';
|
|
include/start_slave.inc
|
|
SELECT * FROM t3 WHERE a >= 80 ORDER BY a;
|
|
a b
|
|
80 0
|
|
81 10000
|
|
82 0
|
|
100 100
|
|
connection server_2;
|
|
include/stop_slave.inc
|
|
SET GLOBAL slave_parallel_mode=@old_parallel_mode;
|
|
SET GLOBAL slave_parallel_threads=@old_parallel_threads;
|
|
include/start_slave.inc
|
|
SET DEBUG_SYNC= 'RESET';
|
|
connection server_1;
|
|
DROP function foo;
|
|
DROP TABLE t3;
|
|
SET DEBUG_SYNC= 'RESET';
|
|
include/rpl_end.inc
|