mirror of
https://github.com/MariaDB/server.git
synced 2025-01-20 05:52:27 +01:00
a5efb91dea
Bug#54678: InnoDB, TRUNCATE, ALTER, I_S SELECT, crash or deadlock - Incompatible change: truncate no longer resorts to a row by row delete if the storage engine does not support the truncate method. Consequently, the count of affected rows does not, in any case, reflect the actual number of rows. - Incompatible change: it is no longer possible to truncate a table that participates as a parent in a foreign key constraint, unless it is a self-referencing constraint (both parent and child are in the same table). To work around this incompatible change and still be able to truncate such tables, disable foreign checks with SET foreign_key_checks=0 before truncate. Alternatively, if foreign key checks are necessary, please use a DELETE statement without a WHERE condition. Problem description: The problem was that for storage engines that do not support truncate table via a external drop and recreate, such as InnoDB which implements truncate via a internal drop and recreate, the delete_all_rows method could be invoked with a shared metadata lock, causing problems if the engine needed exclusive access to some internal metadata. This problem originated with the fact that there is no truncate specific handler method, which ended up leading to a abuse of the delete_all_rows method that is primarily used for delete operations without a condition. Solution: The solution is to introduce a truncate handler method that is invoked when the engine does not support truncation via a table drop and recreate. This method is invoked under a exclusive metadata lock, so that there is only a single instance of the table when the method is invoked. Also, the method is not invoked and a error is thrown if the table is a parent in a non-self-referencing foreign key relationship. This was necessary to avoid inconsistency as some integrity checks are bypassed. This is inline with the fact that truncate is primarily a DDL operation that was designed to quickly remove all data from a table. mysql-test/suite/innodb/t/innodb-truncate.test: Add test cases for truncate and foreign key checks. Also test that InnoDB resets auto-increment on truncate. mysql-test/suite/innodb/t/innodb.test: FK is not necessary, test is related to auto-increment. Update error number, truncate is no longer invoked if table is parent in a FK relationship. mysql-test/suite/innodb/t/innodb_mysql.test: Update error number, truncate is no longer invoked if table is parent in a FK relationship. Use delete instead of truncate, test is used to check the interaction of FKs, triggers and delete. mysql-test/suite/parts/inc/partition_check.inc: Fix typo. mysql-test/suite/sys_vars/t/foreign_key_checks_func.test: Update error number, truncate is no longer invoked if table is parent in a FK relationship. mysql-test/t/mdl_sync.test: Modify test case to reflect and ensure that truncate takes a exclusive metadata lock. mysql-test/t/trigger-trans.test: Update error number, truncate is no longer invoked if table is parent in a FK relationship. sql/ha_partition.cc: Reorganize the various truncate methods. delete_all_rows is now passed directly to the underlying engines, so as truncate. The code responsible for truncating individual partitions is moved to ha_partition::truncate_partition, which is invoked when a ALTER TABLE t1 TRUNCATE PARTITION p statement is executed. Since the partition truncate no longer can be invoked via delete, the bitmap operations are not necessary anymore. The explicit reset of the auto-increment value is also removed as the underlying engines are now responsible for reseting the value. sql/handler.cc: Wire up the handler truncate method. sql/handler.h: Introduce and document the truncate handler method. It assumes certain use cases of delete_all_rows. Add method to retrieve the list of foreign keys referencing a table. Method is used to avoid truncating tables that are parent in a foreign key relationship. sql/share/errmsg-utf8.txt: Add error message for truncate and FK. sql/sql_lex.h: Introduce a flag so that the partition engine can detect when a partition is being truncated. Used to give a special error. sql/sql_parse.cc: Function mysql_truncate_table no longer exists. sql/sql_partition_admin.cc: Implement the TRUNCATE PARTITION statement. sql/sql_truncate.cc: Change the truncate table implementation to use the new truncate handler method and to not rely on row-by-row delete anymore. The truncate handler method is always invoked with a exclusive metadata lock. Also, it is no longer possible to truncate a table that is parent in some non-self-referencing foreign key. storage/archive/ha_archive.cc: Rename method as the description indicates that in the future this could be a truncate operation. storage/blackhole/ha_blackhole.cc: Implement truncate as no operation for the blackhole engine in order to remain compatible with older releases. storage/federated/ha_federated.cc: Introduce truncate method that invokes delete_all_rows. This is required to support partition truncate as this form of truncate does not implement the drop and recreate protocol. storage/heap/ha_heap.cc: Introduce truncate method that invokes delete_all_rows. This is required to support partition truncate as this form of truncate does not implement the drop and recreate protocol. storage/ibmdb2i/ha_ibmdb2i.cc: Introduce truncate method that invokes delete_all_rows. This is required to support partition truncate as this form of truncate does not implement the drop and recreate protocol. storage/innobase/handler/ha_innodb.cc: Rename delete_all_rows to truncate. InnoDB now does truncate under a exclusive metadata lock. Introduce and reorganize methods used to retrieve the list of foreign keys referenced by a or referencing a table. storage/myisammrg/ha_myisammrg.cc: Introduce truncate method that invokes delete_all_rows. This is required in order to remain compatible with earlier releases where truncate would resort to a row-by-row delete.
163 lines
4.5 KiB
C++
163 lines
4.5 KiB
C++
/* Copyright (c) 2008, 2010, Oracle and/or its affiliates. All rights reserved.
|
|
|
|
This program is free software; you can redistribute it and/or modify
|
|
it under the terms of the GNU General Public License as published by
|
|
the Free Software Foundation; version 2 of the License.
|
|
|
|
This program is distributed in the hope that it will be useful,
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
GNU General Public License for more details.
|
|
|
|
You should have received a copy of the GNU General Public License
|
|
along with this program; if not, write to the Free Software Foundation,
|
|
51 Franklin Street, Suite 500, Boston, MA 02110-1335 USA */
|
|
|
|
#ifndef HA_PERFSCHEMA_H
|
|
#define HA_PERFSCHEMA_H
|
|
|
|
#include "handler.h" /* class handler */
|
|
|
|
#ifdef USE_PRAGMA_INTERFACE
|
|
#pragma interface /* gcc class implementation */
|
|
#endif
|
|
|
|
/**
|
|
@file storage/perfschema/ha_perfschema.h
|
|
Performance schema storage engine (declarations).
|
|
|
|
@defgroup Performance_schema_engine Performance Schema Engine
|
|
@ingroup Performance_schema_implementation
|
|
@{
|
|
*/
|
|
struct PFS_engine_table_share;
|
|
class PFS_engine_table;
|
|
extern const char *pfs_engine_name;
|
|
|
|
/** A handler for a PERFORMANCE_SCHEMA table. */
|
|
class ha_perfschema : public handler
|
|
{
|
|
public:
|
|
ha_perfschema(handlerton *hton, TABLE_SHARE *share);
|
|
|
|
~ha_perfschema();
|
|
|
|
const char *table_type(void) const { return pfs_engine_name; }
|
|
|
|
const char *index_type(uint) { return ""; }
|
|
|
|
const char **bas_ext(void) const;
|
|
|
|
/** Capabilities of the performance schema tables. */
|
|
ulonglong table_flags(void) const
|
|
{
|
|
/*
|
|
About HA_FAST_KEY_READ:
|
|
|
|
The storage engine ::rnd_pos() method is fast to locate records by key,
|
|
so HA_FAST_KEY_READ is technically true, but the record content can be
|
|
overwritten between ::rnd_next() and ::rnd_pos(), because all the P_S
|
|
data is volatile.
|
|
The HA_FAST_KEY_READ flag is not advertised, to force the optimizer
|
|
to cache records instead, to provide more consistent records.
|
|
For example, consider the following statement:
|
|
- select * from P_S.EVENTS_WAITS_HISTORY_LONG where THREAD_ID=<n>
|
|
order by ...
|
|
With HA_FAST_KEY_READ, it can return records where "THREAD_ID=<n>"
|
|
is false, because the where clause was evaluated to true after
|
|
::rnd_pos(), then the content changed, then the record was fetched by
|
|
key using ::rnd_pos().
|
|
Without HA_FAST_KEY_READ, the optimizer reads all columns and never
|
|
calls ::rnd_pos(), so it is guaranteed to return only thread <n>
|
|
records.
|
|
*/
|
|
return HA_NO_TRANSACTIONS | HA_REC_NOT_IN_SEQ | HA_NO_AUTO_INCREMENT |
|
|
HA_BINLOG_ROW_CAPABLE | HA_BINLOG_STMT_CAPABLE | HA_NO_BLOBS;
|
|
}
|
|
|
|
/**
|
|
Operations supported by indexes.
|
|
None, there are no indexes.
|
|
*/
|
|
ulong index_flags(uint , uint , bool ) const
|
|
{ return 0; }
|
|
|
|
uint max_supported_record_length(void) const
|
|
{ return HA_MAX_REC_LENGTH; }
|
|
|
|
uint max_supported_keys(void) const
|
|
{ return 0; }
|
|
|
|
uint max_supported_key_parts(void) const
|
|
{ return 0; }
|
|
|
|
uint max_supported_key_length(void) const
|
|
{ return 0; }
|
|
|
|
ha_rows estimate_rows_upper_bound(void)
|
|
{ return HA_POS_ERROR; }
|
|
|
|
double scan_time(void)
|
|
{ return 1.0; }
|
|
|
|
double read_time(ha_rows)
|
|
{ return 1.0; }
|
|
|
|
int open(const char *name, int mode, uint test_if_locked);
|
|
|
|
int close(void);
|
|
|
|
int write_row(uchar *buf);
|
|
|
|
void use_hidden_primary_key();
|
|
|
|
int update_row(const uchar *old_data, uchar *new_data);
|
|
|
|
int rnd_init(bool scan);
|
|
|
|
int rnd_end(void);
|
|
|
|
int rnd_next(uchar *buf);
|
|
|
|
int rnd_pos(uchar *buf, uchar *pos);
|
|
|
|
void position(const uchar *record);
|
|
|
|
int info(uint);
|
|
|
|
int delete_all_rows(void);
|
|
|
|
int truncate();
|
|
|
|
int delete_table(const char *from);
|
|
|
|
int rename_table(const char * from, const char * to);
|
|
|
|
int create(const char *name, TABLE *form,
|
|
HA_CREATE_INFO *create_info);
|
|
|
|
THR_LOCK_DATA **store_lock(THD *thd, THR_LOCK_DATA **to,
|
|
enum thr_lock_type lock_type);
|
|
|
|
virtual uint8 table_cache_type(void)
|
|
{ return HA_CACHE_TBL_NOCACHE; }
|
|
|
|
virtual my_bool register_query_cache_table
|
|
(THD *, char *, uint , qc_engine_callback *engine_callback, ulonglong *)
|
|
{
|
|
*engine_callback= 0;
|
|
return FALSE;
|
|
}
|
|
|
|
private:
|
|
/** MySQL lock */
|
|
THR_LOCK_DATA m_thr_lock;
|
|
/** Performance schema table share for this table handler. */
|
|
const PFS_engine_table_share *m_table_share;
|
|
/** Performance schema table cursor. */
|
|
PFS_engine_table *m_table;
|
|
};
|
|
|
|
/** @} */
|
|
#endif
|
|
|