mirror of
https://github.com/MariaDB/server.git
synced 2025-08-09 22:24:09 +03:00
72cc58bb71
for large transaction
Description
===========
When a transaction commits, it copies the binlog events from
binlog cache to binlog file. Very large transactions
(eg. gigabytes) can stall other transactions for a long time
because the data is copied while holding LOCK_log, which blocks
other commits from binlogging.
The solution in this patch is to rename the binlog cache file to
a binlog file instead of copy, if the commiting transaction has
large binlog cache. Rename is a very fast operation, it doesn't
block other transactions a long time.
Design
======
* binlog_large_commit_threshold
type: ulonglong
scope: global
dynamic: yes
default: 128MB
Only the binlog cache temporary files large than 128MB are
renamed to binlog file.
* #binlog_cache_files directory
To support rename, all binlog cache temporary files are managed
as normal files now. `#binlog_cache_files` directory is in the same
directory with binlog files. It is created at server startup if it doesn't
exist. Otherwise, all files in the directory is deleted at startup.
The temporary files are named with ML_ prefix and the memorary address
of the binlog_cache_data object which guarantees it is unique.
* Reserve space
To supprot rename feature, It must reserve enough space at the
begin of the binlog cache file. The space is required for
Format description, Gtid list, checkpoint and Gtid events when
renaming it to a binlog file.
Since binlog_cache_data's cache_log is directly accessed by binlog log,
online alter and wsrep. It is not easy to update all the code. Thus
binlog cache will not reserve space if it is not session binlog cache or
wsrep session is enabled.
- m_file_reserved_bytes
Stores the bytes reserved at the begin of the cache file.
It is initialized in write_prepare() and cleared by reset().
The reserved file header is hide to callers. Thus there is no
change for callers. E.g.
- get_byte_position() still get the length of binlog data
written to the cache, but not the file length.
- truncate(0) will truncate the file to m_file_reserved_bytes but not 0.
- write_prepare()
write_prepare() is called everytime when anything is being written
into the cache. It will call init_file_reserved_bytes() to create
the cache file (if it doesn't exist) and reserve suitable space if
the data written exceeds buffer's size.
* Binlog_commit_by_rotate
It is used to encapsulate the code for remaing a binlog cache
tempoary file to binlog file.
- should_commit_by_rotate()
it is called by write_transaction_to_binlog_events() to check if
a binlog cache should be rename to a binlog file.
- commit()
That is the entry to rename a binlog cache and commit the
transaction. Both rename and commit are protected by LOCK_log,
Thus not other transactions can write anything into the renamed
binlog before it.
Rename happens in a rotation. After the new binlog file is generated,
replace_binlog_file() is called to:
- copy data from the new binlog file to its binlog cache file.
- write gtid event.
- rename the binlog cache file to binlog file.
After that the rotation will continue to succeed. Then the transaction
is committed in a seperated group itself. Its cache file will be
detached and cache log will be reset before calling
trx_group_commit_with_engines(). Thus only Xid event be written.
144 lines
4.6 KiB
Plaintext
144 lines
4.6 KiB
Plaintext
################################################################################
|
|
# MDEV-32014 Rename binlog cache to binlog file
|
|
#
|
|
# It verifies that the rename logic is handled correct if error happens.
|
|
################################################################################
|
|
--source include/have_binlog_format_row.inc
|
|
--source include/have_innodb.inc
|
|
--source include/have_debug.inc
|
|
--source include/have_debug_sync.inc
|
|
RESET MASTER;
|
|
|
|
--echo #
|
|
--echo # binlog cache file is created in #binlog_cache_files directory
|
|
--echo # and it is deleted at disconnect
|
|
--echo #
|
|
--connect(con1,localhost,root,,)
|
|
CREATE TABLE t1 (c1 LONGTEXT) ENGINE = InnoDB;
|
|
|
|
--echo # list binlog_cache_files/
|
|
--let $datadir= `SELECT @@datadir`
|
|
--list_files $datadir/#binlog_cache_files
|
|
|
|
INSERT INTO t1 values(repeat("1", 5242880));
|
|
INSERT INTO t1 values(repeat("1", 5242880));
|
|
FLUSH BINARY LOGS;
|
|
|
|
--echo # list #binlog_cache_files/
|
|
--replace_regex /ML_[0-9]+/ML_BINLOG_CACHE_FILE/
|
|
--list_files $datadir/#binlog_cache_files
|
|
|
|
SET debug_sync = "thread_end SIGNAL signal.thread_end";
|
|
--disconnect con1
|
|
--connection default
|
|
# Wait until the connection is closed completely.
|
|
SET debug_sync = "now WAIT_FOR signal.thread_end";
|
|
|
|
--echo # binlog cache file is deleted at disconnection
|
|
--echo # list #binlog_cache_files/
|
|
--list_files $datadir/#binlog_cache_files
|
|
|
|
--echo #
|
|
--echo # Reserved space is not big enough, rename will not happen. But rotate
|
|
--echo # will succeed.
|
|
--echo #
|
|
SET GLOBAL binlog_large_commit_threshold = 10 * 1024 * 1024;
|
|
SET debug = 'd,simulate_required_size_too_big';
|
|
UPDATE t1 SET c1 = repeat('2', 5242880);
|
|
|
|
--let $gtid_end_pos= query_get_value(SHOW BINLOG EVENTS IN 'master-bin.000002' LIMIT 4, End_log_pos, 4)
|
|
--let $assert_cond= $gtid_end_pos < 4096
|
|
--let $assert_text= Binlog is rotated, but rename is not executed.
|
|
--source include/assert.inc
|
|
|
|
--echo #
|
|
--echo # Error happens when renaming binlog cache to binlog file, rename will
|
|
--echo # not happen. Since the original binlog is delete, the rotate will failed
|
|
--echo # too. binlog will be closed.
|
|
--echo #
|
|
SET debug = 'd,simulate_rename_binlog_cache_to_binlog_error';
|
|
--error ER_CANT_OPEN_FILE
|
|
UPDATE t1 SET c1 = repeat('3', 5242880);
|
|
SELECT count(*) FROM t1 WHERE c1 like "3%";
|
|
|
|
--echo # Binlog is closed
|
|
--source include/show_master_status.inc
|
|
|
|
--source include/restart_mysqld.inc
|
|
--source include/show_master_status.inc
|
|
|
|
--echo #
|
|
--echo # Crash happens before rename the file
|
|
--echo #
|
|
SET GLOBAL binlog_large_commit_threshold = 10 * 1024 * 1024;
|
|
|
|
SET debug = 'd,binlog_commit_by_rotate_crash_before_rename';
|
|
--source include/expect_crash.inc
|
|
--error 2013
|
|
UPDATE t1 SET c1 = repeat('4', 5242880);
|
|
|
|
--write_file $datadir/#binlog_cache_files/non_binlog_cache
|
|
It is not a binlog cache file
|
|
EOF
|
|
|
|
--echo # One cache file left afte crash
|
|
--echo # list #binlog_cache_files/
|
|
--replace_regex /ML_[0-9]+/ML_BINLOG_CACHE_FILE/
|
|
--list_files $datadir/#binlog_cache_files
|
|
|
|
--source include/start_mysqld.inc
|
|
--echo # The cache file is deleted at startup.
|
|
--echo # list #binlog_cache_files/
|
|
--list_files $datadir/#binlog_cache_files
|
|
|
|
--let $assert_text= warning: non_binlog_cache file is in #binlog_cache_files/
|
|
--let $assert_file= $MYSQLTEST_VARDIR/log/mysqld.1.err
|
|
--let $assert_select= non_binlog_cache.*#binlog_cache_files/
|
|
--let $assert_count= 1
|
|
--let $assert_only_after= CURRENT_TEST: binlog.binlog_commit_by_rotate_atomic
|
|
--source include/assert_grep.inc
|
|
|
|
--remove_file $datadir/#binlog_cache_files/non_binlog_cache
|
|
|
|
--let $binlog_file= LAST
|
|
--let $binlog_start= 4
|
|
--let $skip_checkpoint_events= 1
|
|
--source include/show_binlog_events.inc
|
|
|
|
--echo #
|
|
--echo # Crash happens just after rotation is finished, binlog commit is not
|
|
--echo # started yet, so there is no Xid_log_event in the log, no garbage at
|
|
--echo # the end of the file.
|
|
--echo #
|
|
SET GLOBAL binlog_large_commit_threshold = 10 * 1024 * 1024;
|
|
|
|
BEGIN;
|
|
UPDATE t1 SET c1 = repeat('5', 5242880);
|
|
SAVEPOINT s1;
|
|
UPDATE t1 SET c1 = repeat('6', 5242880);
|
|
UPDATE t1 SET c1 = repeat('7', 5242880);
|
|
ROLLBACK TO SAVEPOINT s1;
|
|
INSERT INTO t1 VALUES('a');
|
|
|
|
SET debug = 'd,binlog_commit_by_rotate_crash_after_rotate';
|
|
--source include/expect_crash.inc
|
|
--error 2013
|
|
COMMIT;
|
|
|
|
--echo # No cache file left afte crash
|
|
--echo # list #binlog_cache_files/
|
|
--replace_regex /ML_[0-9]+/ML_BINLOG_CACHE_FILE/
|
|
--list_files $datadir/#binlog_cache_files
|
|
|
|
--source include/start_mysqld.inc
|
|
|
|
--let $binlog_file= master-bin.000006
|
|
--let $binlog_start= 4
|
|
--let $skip_checkpoint_events= 1
|
|
--source include/show_binlog_events.inc
|
|
|
|
call mtr.add_suppression(".*Turning logging off for the whole duration.*");
|
|
call mtr.add_suppression(".*non_binlog_cache is in #binlog_cache_files/.*");
|
|
DROP TABLE t1;
|
|
|