mariadb/sql/ha_berkeley.h
unknown de6f5ae5ab A fix and a test case for Bug#10760 and complementary cleanups.
The idea of the patch
is that every cursor gets its own lock id for table level locking.
Thus cursors are protected from updates performed within the same 
connection. Additionally a list of transient (must be closed at
commit) cursors is maintained and all transient cursors are closed
when necessary. Lastly, this patch adds support for deadlock
timeouts to TLL locking when using cursors.
+ post-review fixes.


include/thr_lock.h:
  - add a notion of lock owner to table level locking. When using
    cursors, lock owner can not be identified by a thread id any more, 
    as we must protect cursors from updates issued within the same 
    connection (thread). So, each cursor has its own lock identifier to 
    use with table level locking.
  - extend return values of thr_lock and thr_multi_lock with
    THR_LOCK_TIMEOUT and THR_LOCK_DEADLOCK, since these conditions
    are now possible (see comments to thr_lock.c)
mysys/thr_lock.c:
  Better support for cursors:
  - use THR_LOCK_OWNER * as lock identifier, not pthread_t.
  - check and return an error for a trivial deadlock case, when an
    update statement is issued to a table locked by a cursor which has 
    been previously opened in the same connection.
  - add support for locking timeouts: with use of cursors, trivial 
    deadlocks can occur. For now the only remedy is the lock wait timeout,
    which is initialized from a new global variable 'table_lock_wait_timeout'
    Example of a deadlock (assuming the storage engine does not downgrade 
    locks):
    con1: open cursor for select * from t1;
    con2: open cursor for select * from t2;
    con1: update t2 set id=id*2;  -- blocked
    con2: update t1 set id=id*2;  -- deadlock
    Lock timeouts are active only if a connection is using cursors.
  - the check in the wait_for_lock loop has been changed from
    data->cond != cond to data->cond != 0. data->cond is zeroed
    in every place it's changed. 
  - added comments
sql/examples/ha_archive.cc:
  - extend the handlerton with the info about cursor behaviour at commit.
sql/examples/ha_archive.h:
  - ctor moved to .cc to make use of archive handlerton
sql/examples/ha_example.cc:
  - add handlerton instance, init handler::ht with it
sql/examples/ha_example.h:
  - ctor moved to .cc to make use of ha_example handlerton
sql/examples/ha_tina.cc:
  - add handlerton instance, init handler::ht with it
sql/examples/ha_tina.h:
  - ctor moved to .cc to make use of CSV handlerton
sql/ha_berkeley.cc:
  - init handlerton::flags and handler::ht
sql/ha_berkeley.h:
  - ctor moved to .cc to make use of BerkeleyDB handlerton
sql/ha_blackhole.cc:
  - add handlerton instance, init handler::ht with it
sql/ha_blackhole.h:
  - ctor moved to .cc to make use of blackhole handlerton
sql/ha_federated.cc:
  - add handlerton instance, init handler::ht with it
sql/ha_federated.h:
  - ctor moved to .cc to make use of federated handlerton
sql/ha_heap.cc:
  - add handlerton instance, init handler::ht with it
sql/ha_heap.h:
  - ctor moved to .cc to make use of ha_heap handlerton
sql/ha_innodb.cc:
  - init handlerton::flags and handler::ht of innobase storage engine
sql/ha_innodb.h:
  - ctor moved to .cc to make use of archive handlerton
sql/ha_myisam.cc:
  - add handlerton instance, init handler::ht with it
sql/ha_myisam.h:
  - ctor moved to .cc to make use of MyISAM handlerton
sql/ha_myisammrg.cc:
  - init handler::ht in the ctor
sql/ha_myisammrg.h:
  - ctor moved to .cc to make use of MyISAM MERGE handlerton
sql/ha_ndbcluster.cc:
  - init handlerton::flags and handler::ht
sql/handler.cc:
  - drop support for ISAM storage engine, which was removed from 5.0
  - close all "transient" cursors at COMMIT/ROLLBACK. A "transient"
    SQL level cursor is a cursor that uses tables that have a transaction-
    specific state.
sql/handler.h:
  - extend struct handlerton with flags, add handlerton *ht to every
    handler instance.
sql/lock.cc:
  - extend mysql_lock_tables to send error to the client if 
    thr_multi_lock returns a timeout or a deadlock error.
sql/mysqld.cc:
  - add server option --table_lock_wait_timeout (in seconds)
sql/set_var.cc:
  - add new global variable 'table_lock_wait_timeout' to specify
  a wait timeout for table-level locks of MySQL (in seconds). The default
  timeout is 50 seconds. The timeout is active only if the connection
  has open cursors.
sql/sql_class.cc:
  - implement Statement_map::close_transient_cursors
  - safety suggests that we need an assert ensuring 
   llock_info->n_cursors is functioning properly, adjust destruction of
   the Statement_map to allow such assert in THD::~THD
sql/sql_class.h:
  - add support for Cursors registry to Statement map.
sql/sql_prepare.cc:
  - maintain a list of cursors that must be closed at commit/rollback.
sql/sql_select.cc:
  - extend class Cursor to support specific at-COMMIT/ROLLBACK behavior.
  If a cursor uses tables of a storage engine that 
  invalidates all open tables at COMMIT/ROLLBACK, it must be closed
  before COMMIT/ROLLBACK is executed.
sql/sql_select.h:
  - add an own lock_id and commit/rollback status flag to class Cursor
tests/mysql_client_test.c:
  A test case for Bug#10760 and complementary issues: test a simple
  deadlock case too.
mysql-test/var:
  New BitKeeper file ``mysql-test/var''
2005-07-19 22:21:12 +04:00

168 lines
6.1 KiB
C++

/* Copyright (C) 2000 MySQL AB & MySQL Finland AB & TCX DataKonsult AB
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; either version 2 of the License, or
(at your option) any later version.
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_INTERFACE
#pragma interface /* gcc class implementation */
#endif
/* class for the the myisam handler */
#include <db.h>
#define BDB_HIDDEN_PRIMARY_KEY_LENGTH 5
typedef struct st_berkeley_share {
ulonglong auto_ident;
ha_rows rows, org_rows;
ulong *rec_per_key;
THR_LOCK lock;
pthread_mutex_t mutex;
char *table_name;
DB *status_block, *file, **key_file;
u_int32_t *key_type;
uint table_name_length,use_count;
uint status,version;
uint ref_length;
bool fixed_length_primary_key, fixed_length_row;
} BDB_SHARE;
class ha_berkeley: public handler
{
THR_LOCK_DATA lock;
DBT last_key,current_row;
gptr alloc_ptr;
byte *rec_buff;
char *key_buff, *key_buff2, *primary_key_buff;
DB *file, **key_file;
DB_TXN *transaction;
u_int32_t *key_type;
DBC *cursor;
BDB_SHARE *share;
ulong int_table_flags;
ulong alloced_rec_buff_length;
ulong changed_rows;
uint primary_key,last_dup_key, hidden_primary_key, version;
bool key_read, using_ignore;
bool fix_rec_buff_for_blob(ulong length);
byte current_ident[BDB_HIDDEN_PRIMARY_KEY_LENGTH];
ulong max_row_length(const byte *buf);
int pack_row(DBT *row,const byte *record, bool new_row);
void unpack_row(char *record, DBT *row);
void unpack_key(char *record, DBT *key, uint index);
DBT *create_key(DBT *key, uint keynr, char *buff, const byte *record,
int key_length = MAX_KEY_LENGTH);
DBT *pack_key(DBT *key, uint keynr, char *buff, const byte *key_ptr,
uint key_length);
int remove_key(DB_TXN *trans, uint keynr, const byte *record, DBT *prim_key);
int remove_keys(DB_TXN *trans,const byte *record, DBT *new_record,
DBT *prim_key, key_map *keys);
int restore_keys(DB_TXN *trans, key_map *changed_keys, uint primary_key,
const byte *old_row, DBT *old_key,
const byte *new_row, DBT *new_key,
ulong thd_options);
int key_cmp(uint keynr, const byte * old_row, const byte * new_row);
int update_primary_key(DB_TXN *trans, bool primary_key_changed,
const byte * old_row, DBT *old_key,
const byte * new_row, DBT *prim_key,
ulong thd_options, bool local_using_ignore);
int read_row(int error, char *buf, uint keynr, DBT *row, DBT *key, bool);
DBT *get_pos(DBT *to, byte *pos);
public:
ha_berkeley(TABLE *table_arg);
~ha_berkeley() {}
const char *table_type() const { return "BerkeleyDB"; }
ulong index_flags(uint idx, uint part, bool all_parts) const;
const char *index_type(uint key_number) { return "BTREE"; }
const char **bas_ext() const;
ulong table_flags(void) const { return int_table_flags; }
uint max_supported_keys() const { return MAX_KEY-1; }
uint extra_rec_buf_length() { return BDB_HIDDEN_PRIMARY_KEY_LENGTH; }
ha_rows estimate_rows_upper_bound();
const key_map *keys_to_use_for_scanning() { return &key_map_full; }
bool has_transactions() { return 1;}
int open(const char *name, int mode, uint test_if_locked);
int close(void);
double scan_time();
int write_row(byte * buf);
int update_row(const byte * old_data, byte * new_data);
int delete_row(const byte * buf);
int index_init(uint index);
int index_end();
int index_read(byte * buf, const byte * key,
uint key_len, enum ha_rkey_function find_flag);
int index_read_idx(byte * buf, uint index, const byte * key,
uint key_len, enum ha_rkey_function find_flag);
int index_read_last(byte * buf, const byte * key, uint key_len);
int index_next(byte * buf);
int index_next_same(byte * buf, const byte *key, uint keylen);
int index_prev(byte * buf);
int index_first(byte * buf);
int index_last(byte * buf);
int rnd_init(bool scan);
int rnd_end();
int rnd_next(byte *buf);
int rnd_pos(byte * buf, byte *pos);
void position(const byte *record);
void info(uint);
int extra(enum ha_extra_function operation);
int reset(void);
int external_lock(THD *thd, int lock_type);
int start_stmt(THD *thd);
void position(byte *record);
int analyze(THD* thd,HA_CHECK_OPT* check_opt);
int optimize(THD* thd, HA_CHECK_OPT* check_opt);
int check(THD* thd, HA_CHECK_OPT* check_opt);
ha_rows records_in_range(uint inx, key_range *min_key, key_range *max_key);
int create(const char *name, register TABLE *form,
HA_CREATE_INFO *create_info);
int delete_table(const char *name);
int rename_table(const char* from, const char* to);
THR_LOCK_DATA **store_lock(THD *thd, THR_LOCK_DATA **to,
enum thr_lock_type lock_type);
void get_status();
inline void get_auto_primary_key(byte *to)
{
pthread_mutex_lock(&share->mutex);
share->auto_ident++;
int5store(to,share->auto_ident);
pthread_mutex_unlock(&share->mutex);
}
ulonglong get_auto_increment();
void print_error(int error, myf errflag);
uint8 table_cache_type() { return HA_CACHE_TBL_TRANSACT; }
bool primary_key_is_clustered() { return true; }
int cmp_ref(const byte *ref1, const byte *ref2);
};
extern bool berkeley_shared_data;
extern u_int32_t berkeley_init_flags,berkeley_env_flags, berkeley_lock_type,
berkeley_lock_types[];
extern ulong berkeley_cache_size, berkeley_max_lock, berkeley_log_buffer_size;
extern char *berkeley_home, *berkeley_tmpdir, *berkeley_logdir;
extern long berkeley_lock_scan_time;
extern TYPELIB berkeley_lock_typelib;
handlerton *berkeley_init(void);
bool berkeley_end(void);
bool berkeley_flush_logs(void);
int berkeley_show_logs(Protocol *protocol);