mirror of
https://github.com/MariaDB/server.git
synced 2025-01-16 03:52:35 +01:00
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.
172 lines
4.4 KiB
Text
172 lines
4.4 KiB
Text
set @old_innodb_lock_wait_timeout=@@global.innodb_lock_wait_timeout;
|
|
set global innodb_lock_wait_timeout=300;
|
|
set session innodb_lock_wait_timeout=300;
|
|
call mtr.add_suppression("Deadlock found when trying to get lock; try restarting transaction");
|
|
#
|
|
# Bug #22876 Four-way deadlock
|
|
#
|
|
DROP TABLE IF EXISTS t1;
|
|
connect con1,localhost,root,,;
|
|
connect con2,localhost,root,,;
|
|
connect con3,localhost,root,,;
|
|
connection con1;
|
|
set @@autocommit=0;
|
|
CREATE TABLE t1(s1 INT UNIQUE) ENGINE=innodb;
|
|
INSERT INTO t1 VALUES (100);
|
|
COMMIT;
|
|
INSERT INTO t1 VALUES (1);
|
|
connection con2;
|
|
set @@autocommit=0;
|
|
INSERT INTO t1 VALUES (2);
|
|
INSERT INTO t1 VALUES (1);
|
|
connection con3;
|
|
set @@autocommit=0;
|
|
DROP TABLE t1;
|
|
connection con1;
|
|
# Waiting for until transaction will be locked inside innodb subsystem
|
|
# Connection 1 is now holding the lock.
|
|
# Issuing insert from connection 1 while connection 2&3
|
|
# is waiting for the lock should give a deadlock error.
|
|
INSERT INTO t1 VALUES (2);
|
|
ERROR 40001: Deadlock found when trying to get lock; try restarting transaction
|
|
# Cleanup
|
|
connection con2;
|
|
commit;
|
|
set @@autocommit=1;
|
|
connection con1;
|
|
commit;
|
|
set @@autocommit=1;
|
|
connection con3;
|
|
set @@autocommit=1;
|
|
connection default;
|
|
disconnect con1;
|
|
disconnect con2;
|
|
disconnect con3;
|
|
#
|
|
# Test for bug #37346 "innodb does not detect deadlock between update
|
|
# and alter table".
|
|
#
|
|
drop table if exists t1;
|
|
create table t1 (c1 int primary key, c2 int, c3 int) engine=InnoDB;
|
|
insert into t1 values (1,1,0),(2,2,0),(3,3,0),(4,4,0),(5,5,0);
|
|
begin;
|
|
# Run statement which acquires X-lock on one of table's rows.
|
|
update t1 set c3=c3+1 where c2=3;
|
|
#
|
|
connect con37346,localhost,root,,test,,;
|
|
connection con37346;
|
|
# The below ALTER TABLE statement should wait till transaction
|
|
# in connection 'default' is complete and then succeed.
|
|
# It should not deadlock or fail with ER_LOCK_DEADLOCK error.
|
|
# Sending:
|
|
alter table t1 add column c4 int;;
|
|
#
|
|
connection default;
|
|
# Wait until the above ALTER TABLE gets blocked because this
|
|
# connection holds SW metadata lock on table to be altered.
|
|
# The below statement should succeed. It should not
|
|
# deadlock or end with ER_LOCK_DEADLOCK error.
|
|
update t1 set c3=c3+1 where c2=4;
|
|
# Unblock ALTER TABLE by committing transaction.
|
|
commit;
|
|
#
|
|
connection con37346;
|
|
# Reaping ALTER TABLE.
|
|
#
|
|
connection default;
|
|
disconnect con37346;
|
|
drop table t1;
|
|
#
|
|
# Bug#53798 OPTIMIZE TABLE breaks repeatable read
|
|
#
|
|
DROP TABLE IF EXISTS t1;
|
|
CREATE TABLE t1 (a INT) engine=innodb;
|
|
INSERT INTO t1 VALUES (1), (2), (3);
|
|
connect con1, localhost, root;
|
|
START TRANSACTION WITH CONSISTENT SNAPSHOT;
|
|
SELECT * FROM t1;
|
|
a
|
|
1
|
|
2
|
|
3
|
|
connection default;
|
|
# This should block
|
|
# Sending:
|
|
OPTIMIZE TABLE t1;
|
|
connection con1;
|
|
SELECT * FROM t1;
|
|
a
|
|
1
|
|
2
|
|
3
|
|
COMMIT;
|
|
connection default;
|
|
# Reaping OPTIMIZE TABLE t1
|
|
Table Op Msg_type Msg_text
|
|
test.t1 optimize note Table does not support optimize, doing recreate + analyze instead
|
|
test.t1 optimize status OK
|
|
disconnect con1;
|
|
DROP TABLE t1;
|
|
#
|
|
# Bug#49891 View DDL breaks REPEATABLE READ
|
|
#
|
|
DROP TABLE IF EXISTS t1, t2;
|
|
DROP VIEW IF EXISTS v2;
|
|
CREATE TABLE t1 ( f1 INTEGER ) ENGINE = innodb;
|
|
CREATE TABLE t2 ( f1 INTEGER );
|
|
CREATE VIEW v1 AS SELECT 1 FROM t1;
|
|
connect con2, localhost, root;
|
|
connect con3, localhost, root;
|
|
connection con3;
|
|
LOCK TABLE t1 WRITE;
|
|
connection default;
|
|
START TRANSACTION;
|
|
# Sending:
|
|
SELECT * FROM v1;
|
|
connection con2;
|
|
# Waiting for 'SELECT * FROM v1' to sync in.
|
|
# Sending:
|
|
ALTER VIEW v1 AS SELECT 2 FROM t2;
|
|
connection con3;
|
|
# Waiting for 'ALTER VIEW v1 AS SELECT 2 FROM t2' to sync in.
|
|
UNLOCK TABLES;
|
|
connection default;
|
|
# Reaping: SELECT * FROM v1
|
|
1
|
|
SELECT * FROM v1;
|
|
1
|
|
COMMIT;
|
|
connection con2;
|
|
# Reaping: ALTER VIEW v1 AS SELECT 2 FROM t2
|
|
connection default;
|
|
DROP TABLE t1, t2;
|
|
DROP VIEW v1;
|
|
disconnect con2;
|
|
disconnect con3;
|
|
#
|
|
# Bug#11815600 [ERROR] INNODB COULD NOT FIND INDEX PRIMARY
|
|
# KEY NO 0 FOR TABLE IN ERROR LOG
|
|
#
|
|
DROP TABLE IF EXISTS t1;
|
|
connect con1,localhost,root;
|
|
connection default;
|
|
CREATE TABLE t1 (id INT PRIMARY KEY, value INT) ENGINE = InnoDB;
|
|
INSERT INTO t1 VALUES (1, 12345);
|
|
START TRANSACTION;
|
|
SELECT * FROM t1;
|
|
id value
|
|
1 12345
|
|
connection con1;
|
|
SET lock_wait_timeout=1;
|
|
ALTER TABLE t1 ADD INDEX idx(value);
|
|
ERROR HY000: Lock wait timeout exceeded; try restarting transaction
|
|
ALTER TABLE t1 ADD INDEX idx(value);
|
|
ERROR HY000: Lock wait timeout exceeded; try restarting transaction
|
|
connection default;
|
|
SELECT * FROM t1;
|
|
id value
|
|
1 12345
|
|
COMMIT;
|
|
DROP TABLE t1;
|
|
disconnect con1;
|
|
set global innodb_lock_wait_timeout=@old_innodb_lock_wait_timeout;
|