mariadb/storage/blackhole/ha_blackhole.cc
Davi Arnaut a5efb91dea Bug#49938: Failing assertion: inode or deadlock in fsp/fsp0fsp.c
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.
2010-10-06 11:34:28 -03:00

453 lines
12 KiB
C++

/* Copyright 2005-2008 MySQL AB, 2008-2009 Sun Microsystems, Inc.
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, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */
#ifdef USE_PRAGMA_IMPLEMENTATION
#pragma implementation // gcc: Class implementation
#endif
#define MYSQL_SERVER 1
#include "sql_priv.h"
#include "unireg.h"
#include "probes_mysql.h"
#include "ha_blackhole.h"
#include "sql_class.h" // THD, SYSTEM_THREAD_SLAVE_SQL
/* Static declarations for handlerton */
static handler *blackhole_create_handler(handlerton *hton,
TABLE_SHARE *table,
MEM_ROOT *mem_root)
{
return new (mem_root) ha_blackhole(hton, table);
}
/* Static declarations for shared structures */
static mysql_mutex_t blackhole_mutex;
static HASH blackhole_open_tables;
static st_blackhole_share *get_share(const char *table_name);
static void free_share(st_blackhole_share *share);
/*****************************************************************************
** BLACKHOLE tables
*****************************************************************************/
ha_blackhole::ha_blackhole(handlerton *hton,
TABLE_SHARE *table_arg)
:handler(hton, table_arg)
{}
static const char *ha_blackhole_exts[] = {
NullS
};
const char **ha_blackhole::bas_ext() const
{
return ha_blackhole_exts;
}
int ha_blackhole::open(const char *name, int mode, uint test_if_locked)
{
DBUG_ENTER("ha_blackhole::open");
if (!(share= get_share(name)))
DBUG_RETURN(HA_ERR_OUT_OF_MEM);
thr_lock_data_init(&share->lock, &lock, NULL);
DBUG_RETURN(0);
}
int ha_blackhole::close(void)
{
DBUG_ENTER("ha_blackhole::close");
free_share(share);
DBUG_RETURN(0);
}
int ha_blackhole::create(const char *name, TABLE *table_arg,
HA_CREATE_INFO *create_info)
{
DBUG_ENTER("ha_blackhole::create");
DBUG_RETURN(0);
}
/*
Intended to support partitioning.
Allows a particular partition to be truncated.
*/
int ha_blackhole::truncate()
{
DBUG_ENTER("ha_blackhole::truncate");
DBUG_RETURN(0);
}
const char *ha_blackhole::index_type(uint key_number)
{
DBUG_ENTER("ha_blackhole::index_type");
DBUG_RETURN((table_share->key_info[key_number].flags & HA_FULLTEXT) ?
"FULLTEXT" :
(table_share->key_info[key_number].flags & HA_SPATIAL) ?
"SPATIAL" :
(table_share->key_info[key_number].algorithm ==
HA_KEY_ALG_RTREE) ? "RTREE" : "BTREE");
}
int ha_blackhole::write_row(uchar * buf)
{
DBUG_ENTER("ha_blackhole::write_row");
DBUG_RETURN(table->next_number_field ? update_auto_increment() : 0);
}
int ha_blackhole::update_row(const uchar *old_data, uchar *new_data)
{
DBUG_ENTER("ha_blackhole::update_row");
THD *thd= ha_thd();
if (thd->system_thread == SYSTEM_THREAD_SLAVE_SQL && thd->query() == NULL)
DBUG_RETURN(0);
DBUG_RETURN(HA_ERR_WRONG_COMMAND);
}
int ha_blackhole::delete_row(const uchar *buf)
{
DBUG_ENTER("ha_blackhole::delete_row");
THD *thd= ha_thd();
if (thd->system_thread == SYSTEM_THREAD_SLAVE_SQL && thd->query() == NULL)
DBUG_RETURN(0);
DBUG_RETURN(HA_ERR_WRONG_COMMAND);
}
int ha_blackhole::rnd_init(bool scan)
{
DBUG_ENTER("ha_blackhole::rnd_init");
DBUG_RETURN(0);
}
int ha_blackhole::rnd_next(uchar *buf)
{
int rc;
DBUG_ENTER("ha_blackhole::rnd_next");
MYSQL_READ_ROW_START(table_share->db.str, table_share->table_name.str,
TRUE);
THD *thd= ha_thd();
if (thd->system_thread == SYSTEM_THREAD_SLAVE_SQL && thd->query() == NULL)
rc= 0;
else
rc= HA_ERR_END_OF_FILE;
MYSQL_READ_ROW_DONE(rc);
DBUG_RETURN(rc);
}
int ha_blackhole::rnd_pos(uchar * buf, uchar *pos)
{
DBUG_ENTER("ha_blackhole::rnd_pos");
MYSQL_READ_ROW_START(table_share->db.str, table_share->table_name.str,
FALSE);
DBUG_ASSERT(0);
MYSQL_READ_ROW_DONE(0);
DBUG_RETURN(0);
}
void ha_blackhole::position(const uchar *record)
{
DBUG_ENTER("ha_blackhole::position");
DBUG_ASSERT(0);
DBUG_VOID_RETURN;
}
int ha_blackhole::info(uint flag)
{
DBUG_ENTER("ha_blackhole::info");
bzero((char*) &stats, sizeof(stats));
if (flag & HA_STATUS_AUTO)
stats.auto_increment_value= 1;
DBUG_RETURN(0);
}
int ha_blackhole::external_lock(THD *thd, int lock_type)
{
DBUG_ENTER("ha_blackhole::external_lock");
DBUG_RETURN(0);
}
THR_LOCK_DATA **ha_blackhole::store_lock(THD *thd,
THR_LOCK_DATA **to,
enum thr_lock_type lock_type)
{
DBUG_ENTER("ha_blackhole::store_lock");
if (lock_type != TL_IGNORE && lock.type == TL_UNLOCK)
{
/*
Here is where we get into the guts of a row level lock.
If TL_UNLOCK is set
If we are not doing a LOCK TABLE or DISCARD/IMPORT
TABLESPACE, then allow multiple writers
*/
if ((lock_type >= TL_WRITE_CONCURRENT_INSERT &&
lock_type <= TL_WRITE) && !thd_in_lock_tables(thd)
&& !thd_tablespace_op(thd))
lock_type = TL_WRITE_ALLOW_WRITE;
/*
In queries of type INSERT INTO t1 SELECT ... FROM t2 ...
MySQL would use the lock TL_READ_NO_INSERT on t2, and that
would conflict with TL_WRITE_ALLOW_WRITE, blocking all inserts
to t2. Convert the lock to a normal read lock to allow
concurrent inserts to t2.
*/
if (lock_type == TL_READ_NO_INSERT && !thd_in_lock_tables(thd))
lock_type = TL_READ;
lock.type= lock_type;
}
*to++= &lock;
DBUG_RETURN(to);
}
int ha_blackhole::index_read_map(uchar * buf, const uchar * key,
key_part_map keypart_map,
enum ha_rkey_function find_flag)
{
int rc;
DBUG_ENTER("ha_blackhole::index_read");
MYSQL_INDEX_READ_ROW_START(table_share->db.str, table_share->table_name.str);
THD *thd= ha_thd();
if (thd->system_thread == SYSTEM_THREAD_SLAVE_SQL && thd->query() == NULL)
rc= 0;
else
rc= HA_ERR_END_OF_FILE;
MYSQL_INDEX_READ_ROW_DONE(rc);
DBUG_RETURN(rc);
}
int ha_blackhole::index_read_idx_map(uchar * buf, uint idx, const uchar * key,
key_part_map keypart_map,
enum ha_rkey_function find_flag)
{
int rc;
DBUG_ENTER("ha_blackhole::index_read_idx");
MYSQL_INDEX_READ_ROW_START(table_share->db.str, table_share->table_name.str);
THD *thd= ha_thd();
if (thd->system_thread == SYSTEM_THREAD_SLAVE_SQL && thd->query() == NULL)
rc= 0;
else
rc= HA_ERR_END_OF_FILE;
MYSQL_INDEX_READ_ROW_DONE(rc);
DBUG_RETURN(rc);
}
int ha_blackhole::index_read_last_map(uchar * buf, const uchar * key,
key_part_map keypart_map)
{
int rc;
DBUG_ENTER("ha_blackhole::index_read_last");
MYSQL_INDEX_READ_ROW_START(table_share->db.str, table_share->table_name.str);
THD *thd= ha_thd();
if (thd->system_thread == SYSTEM_THREAD_SLAVE_SQL && thd->query() == NULL)
rc= 0;
else
rc= HA_ERR_END_OF_FILE;
MYSQL_INDEX_READ_ROW_DONE(rc);
DBUG_RETURN(rc);
}
int ha_blackhole::index_next(uchar * buf)
{
int rc;
DBUG_ENTER("ha_blackhole::index_next");
MYSQL_INDEX_READ_ROW_START(table_share->db.str, table_share->table_name.str);
rc= HA_ERR_END_OF_FILE;
MYSQL_INDEX_READ_ROW_DONE(rc);
DBUG_RETURN(rc);
}
int ha_blackhole::index_prev(uchar * buf)
{
int rc;
DBUG_ENTER("ha_blackhole::index_prev");
MYSQL_INDEX_READ_ROW_START(table_share->db.str, table_share->table_name.str);
rc= HA_ERR_END_OF_FILE;
MYSQL_INDEX_READ_ROW_DONE(rc);
DBUG_RETURN(rc);
}
int ha_blackhole::index_first(uchar * buf)
{
int rc;
DBUG_ENTER("ha_blackhole::index_first");
MYSQL_INDEX_READ_ROW_START(table_share->db.str, table_share->table_name.str);
rc= HA_ERR_END_OF_FILE;
MYSQL_INDEX_READ_ROW_DONE(rc);
DBUG_RETURN(rc);
DBUG_RETURN(HA_ERR_END_OF_FILE);
}
int ha_blackhole::index_last(uchar * buf)
{
int rc;
DBUG_ENTER("ha_blackhole::index_last");
MYSQL_INDEX_READ_ROW_START(table_share->db.str, table_share->table_name.str);
rc= HA_ERR_END_OF_FILE;
MYSQL_INDEX_READ_ROW_DONE(rc);
DBUG_RETURN(rc);
}
static st_blackhole_share *get_share(const char *table_name)
{
st_blackhole_share *share;
uint length;
length= (uint) strlen(table_name);
mysql_mutex_lock(&blackhole_mutex);
if (!(share= (st_blackhole_share*)
my_hash_search(&blackhole_open_tables,
(uchar*) table_name, length)))
{
if (!(share= (st_blackhole_share*) my_malloc(sizeof(st_blackhole_share) +
length,
MYF(MY_WME | MY_ZEROFILL))))
goto error;
share->table_name_length= length;
strmov(share->table_name, table_name);
if (my_hash_insert(&blackhole_open_tables, (uchar*) share))
{
my_free(share);
share= NULL;
goto error;
}
thr_lock_init(&share->lock);
}
share->use_count++;
error:
mysql_mutex_unlock(&blackhole_mutex);
return share;
}
static void free_share(st_blackhole_share *share)
{
mysql_mutex_lock(&blackhole_mutex);
if (!--share->use_count)
my_hash_delete(&blackhole_open_tables, (uchar*) share);
mysql_mutex_unlock(&blackhole_mutex);
}
static void blackhole_free_key(st_blackhole_share *share)
{
thr_lock_delete(&share->lock);
my_free(share);
}
static uchar* blackhole_get_key(st_blackhole_share *share, size_t *length,
my_bool not_used __attribute__((unused)))
{
*length= share->table_name_length;
return (uchar*) share->table_name;
}
#ifdef HAVE_PSI_INTERFACE
static PSI_mutex_key bh_key_mutex_blackhole;
static PSI_mutex_info all_blackhole_mutexes[]=
{
{ &bh_key_mutex_blackhole, "blackhole", PSI_FLAG_GLOBAL}
};
void init_blackhole_psi_keys()
{
const char* category= "blackhole";
int count;
if (PSI_server == NULL)
return;
count= array_elements(all_blackhole_mutexes);
PSI_server->register_mutex(category, all_blackhole_mutexes, count);
}
#endif
static int blackhole_init(void *p)
{
handlerton *blackhole_hton;
#ifdef HAVE_PSI_INTERFACE
init_blackhole_psi_keys();
#endif
blackhole_hton= (handlerton *)p;
blackhole_hton->state= SHOW_OPTION_YES;
blackhole_hton->db_type= DB_TYPE_BLACKHOLE_DB;
blackhole_hton->create= blackhole_create_handler;
blackhole_hton->flags= HTON_CAN_RECREATE;
mysql_mutex_init(bh_key_mutex_blackhole,
&blackhole_mutex, MY_MUTEX_INIT_FAST);
(void) my_hash_init(&blackhole_open_tables, system_charset_info,32,0,0,
(my_hash_get_key) blackhole_get_key,
(my_hash_free_key) blackhole_free_key, 0);
return 0;
}
static int blackhole_fini(void *p)
{
my_hash_free(&blackhole_open_tables);
mysql_mutex_destroy(&blackhole_mutex);
return 0;
}
struct st_mysql_storage_engine blackhole_storage_engine=
{ MYSQL_HANDLERTON_INTERFACE_VERSION };
mysql_declare_plugin(blackhole)
{
MYSQL_STORAGE_ENGINE_PLUGIN,
&blackhole_storage_engine,
"BLACKHOLE",
"MySQL AB",
"/dev/null storage engine (anything you write to it disappears)",
PLUGIN_LICENSE_GPL,
blackhole_init, /* Plugin Init */
blackhole_fini, /* Plugin Deinit */
0x0100 /* 1.0 */,
NULL, /* status variables */
NULL, /* system variables */
NULL /* config options */
}
mysql_declare_plugin_end;