mirror of
https://github.com/MariaDB/server.git
synced 2025-01-30 18:41:56 +01:00
7762ee5dbe
MDEV-25604 Atomic DDL: Binlog event written upon recovery does not
have default database
The purpose of this task is to ensure that ALTER TABLE is atomic even if
the MariaDB server would be killed at any point of the alter table.
This means that either the ALTER TABLE succeeds (including that triggers,
the status tables and the binary log are updated) or things should be
reverted to their original state.
If the server crashes before the new version is fully up to date and
commited, it will revert to the original table and remove all
temporary files and tables.
If the new version is commited, crash recovery will use the new version,
and update triggers, the status tables and the binary log.
The one execption is ALTER TABLE .. RENAME .. where no changes are done
to table definition. This one will work as RENAME and roll back unless
the whole statement completed, including updating the binary log (if
enabled).
Other changes:
- Added handlerton->check_version() function to allow the ddl recovery
code to check, in case of inplace alter table, if the table in the
storage engine is of the new or old version.
- Added handler->table_version() so that an engine can report the current
version of the table. This should be changed each time the table
definition changes.
- Added ha_signal_ddl_recovery_done() and
handlerton::signal_ddl_recovery_done() to inform all handlers when
ddl recovery has been done. (Needed by InnoDB).
- Added handlerton call inplace_alter_table_committed, to signal engine
that ddl_log has been closed for the alter table query.
- Added new handerton flag
HTON_REQUIRES_NOTIFY_TABLEDEF_CHANGED_AFTER_COMMIT to signal when we
should call hton->notify_tabledef_changed() during
mysql_inplace_alter_table. This was required as MyRocks and InnoDB
needed the call at different times.
- Added function server_uuid_value() to be able to generate a temporary
xid when ddl recovery writes the query to the binary log. This is
needed to be able to handle crashes during ddl log recovery.
- Moved freeing of the frm definition to end of mysql_alter_table() to
remove duplicate code and have a common exit strategy.
-------
InnoDB part of atomic ALTER TABLE
(Implemented by Marko Mäkelä)
innodb_check_version(): Compare the saved dict_table_t::def_trx_id
to determine whether an ALTER TABLE operation was committed.
We must correctly recover dict_table_t::def_trx_id for this to work.
Before purge removes any trace of DB_TRX_ID from system tables, it
will make an effort to load the user table into the cache, so that
the dict_table_t::def_trx_id can be recovered.
ha_innobase::table_version(): return garbage, or the trx_id that would
be used for committing an ALTER TABLE operation.
In InnoDB, table names starting with #sql-ib will remain special:
they will be dropped on startup. This may be revisited later in
MDEV-18518 when we implement proper undo logging and rollback
for creating or dropping multiple tables in a transaction.
Table names starting with #sql will retain some special meaning:
dict_table_t::parse_name() will not consider such names for
MDL acquisition, and dict_table_rename_in_cache() will treat such
names specially when handling FOREIGN KEY constraints.
Simplify InnoDB DROP INDEX.
Prevent purge wakeup
To ensure that dict_table_t::def_trx_id will be recovered correctly
in case the server is killed before ddl_log_complete(), we will block
the purge of any history in SYS_TABLES, SYS_INDEXES, SYS_COLUMNS
between ha_innobase::commit_inplace_alter_table(commit=true)
(purge_sys.stop_SYS()) and purge_sys.resume_SYS().
The completion callback purge_sys.resume_SYS() must be between
ddl_log_complete() and MDL release.
--------
MyRocks support for atomic ALTER TABLE
(Implemented by Sergui Petrunia)
Implement these SE API functions:
- ha_rocksdb::table_version()
- hton->check_version = rocksdb_check_versionMyRocks data dictionary
now stores table version for each table.
(Absence of table version record is interpreted as table_version=0,
that is, which means no upgrade changes are needed)
- For inplace alter table of a partitioned table, call the underlying
handlerton when checking if the table is ok. This assumes that the
partition engine commits all changes at once.
163 lines
4.3 KiB
Text
163 lines
4.3 KiB
Text
# Test for COALESCE PARTITION, ALTER TABLE and ADD PARTITIONS
|
|
# for tables with HASH partitions
|
|
CREATE TABLE t1 (
|
|
c1 INT DEFAULT NULL
|
|
) ENGINE=Aria
|
|
PARTITION BY HASH (c1)
|
|
PARTITIONS 3;
|
|
INSERT INTO t1 VALUE (1), (2), (101), (102), (201), (202);
|
|
ALTER TABLE t1 ENGINE=S3;
|
|
SELECT count(*) FROM t1;
|
|
count(*)
|
|
6
|
|
SHOW TABLES;
|
|
Tables_in_s3
|
|
t1
|
|
ALTER TABLE t1 COALESCE PARTITION 2;
|
|
ERROR 42000: Table 't1' uses an extension that doesn't exist in this MariaDB version
|
|
SHOW WARNINGS;
|
|
Level Code Message
|
|
Error 1112 Table 't1' uses an extension that doesn't exist in this MariaDB version
|
|
ALTER TABLE t1 ADD PARTITION PARTITIONS 6;
|
|
SELECT count(*) FROM t1;
|
|
count(*)
|
|
6
|
|
ALTER TABLE t1 ADD COLUMN c INT;
|
|
SELECT count(*) FROM t1;
|
|
count(*)
|
|
6
|
|
DROP TABLE t1;
|
|
# Test for simple change engine to S3
|
|
CREATE TABLE t1 (
|
|
c1 int DEFAULT NULL,
|
|
c2 int DEFAULT NULL
|
|
) ENGINE=Aria
|
|
PARTITION BY RANGE (c1)
|
|
SUBPARTITION BY HASH(c2)
|
|
SUBPARTITIONS 2
|
|
(PARTITION p0 VALUES LESS THAN (100),
|
|
PARTITION p1 VALUES LESS THAN (200),
|
|
PARTITION p3 VALUES LESS THAN (300));
|
|
INSERT INTO t1 VALUE (1,1), (2,2), (101,101), (102,102), (201,201), (202,202);
|
|
ALTER TABLE t1 ENGINE=S3;
|
|
SELECT count(*) FROM t1;
|
|
count(*)
|
|
6
|
|
# Test for rename table
|
|
RENAME TABLE t1 TO t2;
|
|
SELECT count(*) FROM t2;
|
|
count(*)
|
|
6
|
|
# Test for TRUNCATE, ANALYZE, CHECK, REBUILD, OPTIMIZE, REPAIR,
|
|
# ADD, DROP, REORGANIZE partition
|
|
ALTER TABLE t2 TRUNCATE PARTITION p3;
|
|
ERROR HY000: Table 't2' is read only
|
|
ALTER TABLE t2 ANALYZE PARTITION p3;
|
|
Table Op Msg_type Msg_text
|
|
s3.t2 analyze error Table 's3.t2' is read only
|
|
SELECT count(*) FROM t2;
|
|
count(*)
|
|
6
|
|
ALTER TABLE t2 CHECK PARTITION p3;
|
|
Table Op Msg_type Msg_text
|
|
s3.t2 check error Subpartition p3sp0 returned error
|
|
s3.t2 check error Unknown - internal error 165 during operation
|
|
SELECT count(*) FROM t2;
|
|
count(*)
|
|
6
|
|
ALTER TABLE t2 REBUILD PARTITION p0, p1;
|
|
ERROR 42000: Table 't2' uses an extension that doesn't exist in this MariaDB version
|
|
ALTER TABLE t2 OPTIMIZE PARTITION p0, p1;
|
|
Table Op Msg_type Msg_text
|
|
s3.t2 optimize Error Table 't2' is read only
|
|
s3.t2 optimize status Operation failed
|
|
SELECT count(*) FROM t2;
|
|
count(*)
|
|
6
|
|
ALTER TABLE t2 REPAIR PARTITION p0, p1;
|
|
Table Op Msg_type Msg_text
|
|
s3.t2 repair Error Table 't2' is read only
|
|
s3.t2 repair status Operation failed
|
|
SELECT count(*) FROM t2;
|
|
count(*)
|
|
6
|
|
ALTER TABLE t2 ADD PARTITION (PARTITION p4 VALUES LESS THAN (400));
|
|
SHOW CREATE TABLE t2;
|
|
Table Create Table
|
|
t2 CREATE TABLE `t2` (
|
|
`c1` int(11) DEFAULT NULL,
|
|
`c2` int(11) DEFAULT NULL
|
|
) ENGINE=S3 DEFAULT CHARSET=latin1
|
|
PARTITION BY RANGE (`c1`)
|
|
SUBPARTITION BY HASH (`c2`)
|
|
SUBPARTITIONS 2
|
|
(PARTITION `p0` VALUES LESS THAN (100) ENGINE = S3,
|
|
PARTITION `p1` VALUES LESS THAN (200) ENGINE = S3,
|
|
PARTITION `p3` VALUES LESS THAN (300) ENGINE = S3,
|
|
PARTITION `p4` VALUES LESS THAN (400) ENGINE = S3)
|
|
ALTER TABLE t2
|
|
REORGANIZE PARTITION p4 INTO (
|
|
PARTITION n0 VALUES LESS THAN (500),
|
|
PARTITION n1 VALUES LESS THAN (600)
|
|
);
|
|
ERROR 42000: Table 't2' uses an extension that doesn't exist in this MariaDB version
|
|
ALTER TABLE t2 DROP PARTITION p3;
|
|
SHOW CREATE TABLE t2;
|
|
Table Create Table
|
|
t2 CREATE TABLE `t2` (
|
|
`c1` int(11) DEFAULT NULL,
|
|
`c2` int(11) DEFAULT NULL
|
|
) ENGINE=S3 DEFAULT CHARSET=latin1
|
|
PARTITION BY RANGE (`c1`)
|
|
SUBPARTITION BY HASH (`c2`)
|
|
SUBPARTITIONS 2
|
|
(PARTITION `p0` VALUES LESS THAN (100) ENGINE = S3,
|
|
PARTITION `p1` VALUES LESS THAN (200) ENGINE = S3,
|
|
PARTITION `p4` VALUES LESS THAN (400) ENGINE = S3)
|
|
SELECT count(*) from t2;
|
|
count(*)
|
|
4
|
|
# Test for ALTER TABLE
|
|
ALTER TABLE t2 ADD COLUMN c INT;
|
|
SELECT count(*) FROM t2;
|
|
count(*)
|
|
4
|
|
ALTER TABLE t2 DROP COLUMN c;
|
|
SELECT count(*) FROM t2;
|
|
count(*)
|
|
4
|
|
# Test for REMOVE PARTITIONING
|
|
ALTER TABLE t2 REMOVE PARTITIONING;
|
|
SHOW CREATE TABLE t2;
|
|
Table Create Table
|
|
t2 CREATE TABLE `t2` (
|
|
`c1` int(11) DEFAULT NULL,
|
|
`c2` int(11) DEFAULT NULL
|
|
) ENGINE=S3 DEFAULT CHARSET=latin1 PAGE_CHECKSUM=1
|
|
SELECT count(*) FROM t2;
|
|
count(*)
|
|
4
|
|
DROP TABLE t2;
|
|
# Test for EXCHANGE PARTITION
|
|
CREATE TABLE t1 (
|
|
c1 int DEFAULT NULL
|
|
) ENGINE=Aria
|
|
PARTITION BY RANGE (c1)
|
|
(PARTITION p0 VALUES LESS THAN (100),
|
|
PARTITION p1 VALUES LESS THAN (200));
|
|
INSERT INTO t1 VALUE (1), (2), (101), (102);
|
|
ALTER TABLE t1 ENGINE=S3;
|
|
CREATE TABLE t_part (
|
|
c1 int DEFAULT NULL
|
|
) ENGINE=Aria;
|
|
INSERT INTO t_part VALUE (120), (130), (140);
|
|
ALTER TABLE t_part ENGINE=S3;
|
|
ALTER TABLE t1 EXCHANGE PARTITION p1 WITH TABLE t_part;
|
|
SELECT count(*) FROM t_part;
|
|
count(*)
|
|
2
|
|
SELECT count(*) FROM t1;
|
|
count(*)
|
|
5
|
|
DROP TABLE t1;
|
|
DROP TABLE t_part;
|