1 | =head1 NAME |
1 | =head1 NAME |
2 | |
2 | |
3 | BDB::AIO - Asynchronous Berkeley DB access |
3 | BDB - Asynchronous Berkeley DB access |
4 | |
4 | |
5 | =head1 SYNOPSIS |
5 | =head1 SYNOPSIS |
6 | |
6 | |
7 | use BDB::AIO; |
7 | use BDB; |
|
|
8 | |
|
|
9 | my $env = db_env_create; |
|
|
10 | |
|
|
11 | mkdir "bdtest", 0700; |
|
|
12 | db_env_open |
|
|
13 | $env, |
|
|
14 | "bdtest", |
|
|
15 | BDB::INIT_LOCK | BDB::INIT_LOG | BDB::INIT_MPOOL |
|
|
16 | | BDB::INIT_TXN | BDB::RECOVER | BDB::USE_ENVIRON | BDB::CREATE, |
|
|
17 | 0600; |
|
|
18 | |
|
|
19 | $env->set_flags (BDB::AUTO_COMMIT | BDB::TXN_NOSYNC, 1); |
|
|
20 | |
|
|
21 | my $db = db_create $env; |
|
|
22 | db_open $db, undef, "table", undef, BDB::BTREE, BDB::AUTO_COMMIT | BDB::CREATE |
|
|
23 | | BDB::READ_UNCOMMITTED, 0600; |
|
|
24 | db_put $db, undef, "key", "data", 0, sub { |
|
|
25 | db_del $db, undef, "key"; |
|
|
26 | }; |
|
|
27 | db_sync $db; |
|
|
28 | |
|
|
29 | # when you also use Coro, management is easy: |
|
|
30 | use Coro::BDB; |
|
|
31 | |
|
|
32 | # automatic event loop intergration with AnyEvent: |
|
|
33 | use AnyEvent::BDB; |
|
|
34 | |
|
|
35 | # automatic result processing with EV: |
|
|
36 | my $WATCHER = EV::io BDB::poll_fileno, EV::READ, \&BDB::poll_cb; |
|
|
37 | |
|
|
38 | # with Glib: |
|
|
39 | add_watch Glib::IO BDB::poll_fileno, |
|
|
40 | in => sub { BDB::poll_cb; 1 }; |
|
|
41 | |
|
|
42 | # or simply flush manually |
|
|
43 | BDB::flush; |
|
|
44 | |
8 | |
45 | |
9 | =head1 DESCRIPTION |
46 | =head1 DESCRIPTION |
10 | |
47 | |
11 | =head2 EXAMPLE |
48 | See the BerkeleyDB documentation (L<http://www.oracle.com/technology/documentation/berkeley-db/db/index.html>). |
|
|
49 | The BDB API is very similar to the C API (the translation has been very faithful). |
|
|
50 | |
|
|
51 | See also the example sections in the document below and possibly the eg/ |
|
|
52 | subdirectory of the BDB distribution. Last not least see the IO::AIO |
|
|
53 | documentation, as that module uses almost the same asynchronous request |
|
|
54 | model as this module. |
|
|
55 | |
|
|
56 | I know this is woefully inadequate documentation. Send a patch! |
|
|
57 | |
12 | |
58 | |
13 | =head1 REQUEST ANATOMY AND LIFETIME |
59 | =head1 REQUEST ANATOMY AND LIFETIME |
14 | |
60 | |
15 | Every request method creates a request. which is a C data structure not |
61 | Every request method creates a request. which is a C data structure not |
16 | directly visible to Perl. |
62 | directly visible to Perl. |
… | |
… | |
55 | |
101 | |
56 | =back |
102 | =back |
57 | |
103 | |
58 | =cut |
104 | =cut |
59 | |
105 | |
60 | package BDB::AIO; |
106 | package BDB; |
61 | |
107 | |
62 | no warnings; |
108 | no warnings; |
63 | use strict 'vars'; |
109 | use strict 'vars'; |
64 | |
110 | |
65 | use base 'Exporter'; |
111 | use base 'Exporter'; |
66 | |
112 | |
67 | BEGIN { |
113 | BEGIN { |
68 | our $VERSION = '0.1'; |
114 | our $VERSION = '1.5'; |
69 | |
115 | |
70 | our @BDB_REQ = qw(); |
116 | our @BDB_REQ = qw( |
|
|
117 | db_env_open db_env_close db_env_txn_checkpoint db_env_lock_detect |
|
|
118 | db_env_memp_sync db_env_memp_trickle db_env_dbrename db_env_dbremove |
|
|
119 | db_open db_close db_compact db_sync db_upgrade |
|
|
120 | db_put db_get db_pget db_del db_key_range |
|
|
121 | db_txn_commit db_txn_abort db_txn_finish |
|
|
122 | db_c_close db_c_count db_c_put db_c_get db_c_pget db_c_del |
|
|
123 | db_sequence_open db_sequence_close |
|
|
124 | db_sequence_get db_sequence_remove |
|
|
125 | ); |
|
|
126 | our @EXPORT = (@BDB_REQ, qw(dbreq_pri dbreq_nice db_env_create db_create)); |
|
|
127 | our @EXPORT_OK = qw( |
71 | our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush |
128 | poll_fileno poll_cb poll_wait flush |
72 | min_parallel max_parallel max_idle |
129 | min_parallel max_parallel max_idle |
73 | nreqs nready npending nthreads |
130 | nreqs nready npending nthreads |
74 | max_poll_time max_poll_reqs); |
131 | max_poll_time max_poll_reqs |
|
|
132 | ); |
75 | |
133 | |
76 | require XSLoader; |
134 | require XSLoader; |
77 | XSLoader::load ("BDB::AIO", $VERSION); |
135 | XSLoader::load ("BDB", $VERSION); |
78 | } |
136 | } |
79 | |
137 | |
|
|
138 | =head2 WIN32 FILENAMES/DATABASE NAME MESS |
|
|
139 | |
|
|
140 | Perl on Win32 supports only ASCII filenames (the reason is that it abuses |
|
|
141 | an internal flag to store wether a filename is Unicode or ANSI, but that |
|
|
142 | flag is used for somethign else in the perl core, so there is no way to |
|
|
143 | detect wether a filename is ANSI or Unicode-encoded). The BDB module |
|
|
144 | tries to work around this issue by assuming that the filename is an ANSI |
|
|
145 | filename and BDB was built for unicode support. |
|
|
146 | |
|
|
147 | =head2 BERKELEYDB FUNCTIONS |
|
|
148 | |
|
|
149 | All of these are functions. The create functions simply return a new |
|
|
150 | object and never block. All the remaining functions take an optional |
|
|
151 | callback as last argument. If it is missing, then the function will be |
|
|
152 | executed synchronously. In both cases, C<$!> will reflect the return value |
|
|
153 | of the function. |
|
|
154 | |
|
|
155 | BDB functions that cannot block (mostly functions that manipulate |
|
|
156 | settings) are method calls on the relevant objects, so the rule of thumb |
|
|
157 | is: if it's a method, it's not blocking, if it's a function, it takes a |
|
|
158 | callback as last argument. |
|
|
159 | |
|
|
160 | In the following, C<$int> signifies an integer return value, |
|
|
161 | C<bdb_filename> is a "filename" (octets on unix, madness on windows), |
|
|
162 | C<U32> is an unsigned 32 bit integer, C<int> is some integer, C<NV> is a |
|
|
163 | floating point value. |
|
|
164 | |
|
|
165 | The C<SV *> types are generic perl scalars (for input and output of data |
|
|
166 | values), and the C<SV *callback> is the optional callback function to call |
|
|
167 | when the request is completed. |
|
|
168 | |
|
|
169 | The various C<DB_ENV> etc. arguments are handles return by |
|
|
170 | C<db_env_create>, C<db_create>, C<txn_begin> and so on. If they have an |
|
|
171 | appended C<_ornull> this means they are optional and you can pass C<undef> |
|
|
172 | for them, resulting a NULL pointer on the C level. |
|
|
173 | |
|
|
174 | =head3 BDB functions |
|
|
175 | |
|
|
176 | Functions in the BDB namespace, exported by default: |
|
|
177 | |
|
|
178 | $env = db_env_create (U32 env_flags = 0) |
|
|
179 | flags: RPCCLIENT |
|
|
180 | |
|
|
181 | db_env_open (DB_ENV *env, bdb_filename db_home, U32 open_flags, int mode, SV *callback = &PL_sv_undef) |
|
|
182 | open_flags: INIT_CDB INIT_LOCK INIT_LOG INIT_MPOOL INIT_REP INIT_TXN RECOVER RECOVER_FATAL USE_ENVIRON USE_ENVIRON_ROOT CREATE LOCKDOWN PRIVATE REGISTER SYSTEM_MEM |
|
|
183 | db_env_close (DB_ENV *env, U32 flags = 0, SV *callback = &PL_sv_undef) |
|
|
184 | db_env_txn_checkpoint (DB_ENV *env, U32 kbyte = 0, U32 min = 0, U32 flags = 0, SV *callback = &PL_sv_undef) |
|
|
185 | flags: FORCE |
|
|
186 | db_env_lock_detect (DB_ENV *env, U32 flags = 0, U32 atype = DB_LOCK_DEFAULT, SV *dummy = 0, SV *callback = &PL_sv_undef) |
|
|
187 | atype: LOCK_DEFAULT LOCK_EXPIRE LOCK_MAXLOCKS LOCK_MAXWRITE LOCK_MINLOCKS LOCK_MINWRITE LOCK_OLDEST LOCK_RANDOM LOCK_YOUNGEST |
|
|
188 | db_env_memp_sync (DB_ENV *env, SV *dummy = 0, SV *callback = &PL_sv_undef) |
|
|
189 | db_env_memp_trickle (DB_ENV *env, int percent, SV *dummy = 0, SV *callback = &PL_sv_undef) |
|
|
190 | db_env_dbremove (DB_ENV *env, DB_TXN_ornull *txnid, bdb_filename file, bdb_filename database, U32 flags = 0, SV *callback = &PL_sv_undef) |
|
|
191 | db_env_dbrename (DB_ENV *env, DB_TXN_ornull *txnid, bdb_filename file, bdb_filename database, bdb_filename newname, U32 flags = 0, SV *callback = &PL_sv_undef) |
|
|
192 | |
|
|
193 | $db = db_create (DB_ENV *env = 0, U32 flags = 0) |
|
|
194 | flags: XA_CREATE |
|
|
195 | |
|
|
196 | db_open (DB *db, DB_TXN_ornull *txnid, bdb_filename file, bdb_filename database, int type, U32 flags, int mode, SV *callback = &PL_sv_undef) |
|
|
197 | flags: AUTO_COMMIT CREATE EXCL MULTIVERSION NOMMAP RDONLY READ_UNCOMMITTED THREAD TRUNCATE |
|
|
198 | db_close (DB *db, U32 flags = 0, SV *callback = &PL_sv_undef) |
|
|
199 | flags: DB_NOSYNC |
|
|
200 | db_upgrade (DB *db, bdb_filename file, U32 flags = 0, SV *callback = &PL_sv_undef) |
|
|
201 | db_compact (DB *db, DB_TXN_ornull *txn = 0, SV *start = 0, SV *stop = 0, SV *unused1 = 0, U32 flags = DB_FREE_SPACE, SV *unused2 = 0, SV *callback = &PL_sv_undef) |
|
|
202 | flags: FREELIST_ONLY FREE_SPACE |
|
|
203 | db_sync (DB *db, U32 flags = 0, SV *callback = &PL_sv_undef) |
|
|
204 | db_key_range (DB *db, DB_TXN_ornull *txn, SV *key, SV *key_range, U32 flags = 0, SV *callback = &PL_sv_undef) |
|
|
205 | db_put (DB *db, DB_TXN_ornull *txn, SV *key, SV *data, U32 flags = 0, SV *callback = &PL_sv_undef) |
|
|
206 | flags: APPEND NODUPDATA NOOVERWRITE |
|
|
207 | db_get (DB *db, DB_TXN_ornull *txn, SV *key, SV *data, U32 flags = 0, SV *callback = &PL_sv_undef) |
|
|
208 | flags: CONSUME CONSUME_WAIT GET_BOTH SET_RECNO MULTIPLE READ_COMMITTED READ_UNCOMMITTED RMW |
|
|
209 | db_pget (DB *db, DB_TXN_ornull *txn, SV *key, SV *pkey, SV *data, U32 flags = 0, SV *callback = &PL_sv_undef) |
|
|
210 | flags: CONSUME CONSUME_WAIT GET_BOTH SET_RECNO MULTIPLE READ_COMMITTED READ_UNCOMMITTED RMW |
|
|
211 | db_del (DB *db, DB_TXN_ornull *txn, SV *key, U32 flags = 0, SV *callback = &PL_sv_undef) |
|
|
212 | db_txn_commit (DB_TXN *txn, U32 flags = 0, SV *callback = &PL_sv_undef) |
|
|
213 | flags: TXN_NOSYNC TXN_SYNC |
|
|
214 | db_txn_abort (DB_TXN *txn, SV *callback = &PL_sv_undef) |
|
|
215 | |
|
|
216 | db_c_close (DBC *dbc, SV *callback = &PL_sv_undef) |
|
|
217 | db_c_count (DBC *dbc, SV *count, U32 flags = 0, SV *callback = &PL_sv_undef) |
|
|
218 | db_c_put (DBC *dbc, SV *key, SV *data, U32 flags = 0, SV *callback = &PL_sv_undef) |
|
|
219 | flags: AFTER BEFORE CURRENT KEYFIRST KEYLAST NODUPDATA |
|
|
220 | db_c_get (DBC *dbc, SV *key, SV *data, U32 flags = 0, SV *callback = &PL_sv_undef) |
|
|
221 | flags: CURRENT FIRST GET_BOTH GET_BOTH_RANGE GET_RECNO JOIN_ITEM LAST NEXT NEXT_DUP NEXT_NODUP PREV PREV_DUP PREV_NODUP SET SET_RANGE SET_RECNO READ_UNCOMMITTED MULTIPLE MULTIPLE_KEY RMW |
|
|
222 | db_c_pget (DBC *dbc, SV *key, SV *pkey, SV *data, U32 flags = 0, SV *callback = &PL_sv_undef) |
|
|
223 | db_c_del (DBC *dbc, U32 flags = 0, SV *callback = &PL_sv_undef) |
|
|
224 | |
|
|
225 | db_sequence_open (DB_SEQUENCE *seq, DB_TXN_ornull *txnid, SV *key, U32 flags = 0, SV *callback = &PL_sv_undef) |
|
|
226 | flags: CREATE EXCL |
|
|
227 | db_sequence_close (DB_SEQUENCE *seq, U32 flags = 0, SV *callback = &PL_sv_undef) |
|
|
228 | db_sequence_get (DB_SEQUENCE *seq, DB_TXN_ornull *txnid, int delta, SV *seq_value, U32 flags = DB_TXN_NOSYNC, SV *callback = &PL_sv_undef) |
|
|
229 | flags: TXN_NOSYNC |
|
|
230 | db_sequence_remove (DB_SEQUENCE *seq, DB_TXN_ornull *txnid = 0, U32 flags = 0, SV *callback = &PL_sv_undef) |
|
|
231 | flags: TXN_NOSYNC |
|
|
232 | |
|
|
233 | =head4 db_txn_finish (DB_TXN *txn, U32 flags = 0, SV *callback = &PL_sv_undef) |
|
|
234 | |
|
|
235 | This is not actually a Berkeley DB function but a BDB module |
|
|
236 | extension. The background for this exytension is: It is very annoying to |
|
|
237 | have to check every single BDB function for error returns and provide a |
|
|
238 | codepath out of your transaction. While the BDB module still makes this |
|
|
239 | possible, it contains the following extensions: |
|
|
240 | |
|
|
241 | When a transaction-protected function returns any operating system |
|
|
242 | error (errno > 0), BDB will set the C<TXN_DEADLOCK> flag on the |
|
|
243 | transaction. This flag is also set by Berkeley DB functions themselves |
|
|
244 | when an operation fails with LOCK_DEADLOCK, and it causes all further |
|
|
245 | operations on that transaction (including C<db_txn_commit>) to fail. |
|
|
246 | |
|
|
247 | The C<db_txn_finish> request will look at this flag, and, if it is set, |
|
|
248 | will automatically call C<db_txn_abort> (setting errno to C<LOCK_DEADLOCK> |
|
|
249 | if it isn't set to something else yet). If it isn't set, it will call |
|
|
250 | C<db_txn_commit> and return the error normally. |
|
|
251 | |
|
|
252 | How to use this? Easy: just write your transaction normally: |
|
|
253 | |
|
|
254 | my $txn = $db_env->txn_begin; |
|
|
255 | db_get $db, $txn, "key", my $data; |
|
|
256 | db_put $db, $txn, "key", $data + 1 unless $! == BDB::NOTFOUND; |
|
|
257 | db_txn_finish $txn; |
|
|
258 | die "transaction failed" if $!; |
|
|
259 | |
|
|
260 | That is, handle only the expected errors. If something unexpected happens |
|
|
261 | (EIO, LOCK_NOTGRANTED or a deadlock in either db_get or db_put), then the remaining |
|
|
262 | requests (db_put in this case) will simply be skipped (they will fail with |
|
|
263 | LOCK_DEADLOCK) and the transaction will be aborted. |
|
|
264 | |
|
|
265 | You can use the C<< $txn->failed >> method to check wether a transaction |
|
|
266 | has failed in this way and abort further processing (excluding |
|
|
267 | C<db_txn_finish>). |
|
|
268 | |
|
|
269 | =head3 DB_ENV/database environment methods |
|
|
270 | |
|
|
271 | Methods available on DB_ENV/$env handles: |
|
|
272 | |
|
|
273 | DESTROY (DB_ENV_ornull *env) |
|
|
274 | CODE: |
|
|
275 | if (env) |
|
|
276 | env->close (env, 0); |
|
|
277 | |
|
|
278 | $int = $env->set_data_dir (const char *dir) |
|
|
279 | $int = $env->set_tmp_dir (const char *dir) |
|
|
280 | $int = $env->set_lg_dir (const char *dir) |
|
|
281 | $int = $env->set_shm_key (long shm_key) |
|
|
282 | $int = $env->set_cachesize (U32 gbytes, U32 bytes, int ncache = 0) |
|
|
283 | $int = $env->set_flags (U32 flags, int onoff) |
|
|
284 | $env->set_errfile (FILE *errfile = 0) |
|
|
285 | $env->set_msgfile (FILE *msgfile = 0) |
|
|
286 | $int = $env->set_verbose (U32 which, int onoff = 1) |
|
|
287 | $int = $env->set_encrypt (const char *password, U32 flags = 0) |
|
|
288 | $int = $env->set_timeout (NV timeout_seconds, U32 flags = SET_TXN_TIMEOUT) |
|
|
289 | $int = $env->set_mp_max_openfd (int maxopenfd); |
|
|
290 | $int = $env->set_mp_max_write (int maxwrite, int maxwrite_sleep); |
|
|
291 | $int = $env->set_mp_mmapsize (int mmapsize_mb) |
|
|
292 | $int = $env->set_lk_detect (U32 detect = DB_LOCK_DEFAULT) |
|
|
293 | $int = $env->set_lk_max_lockers (U32 max) |
|
|
294 | $int = $env->set_lk_max_locks (U32 max) |
|
|
295 | $int = $env->set_lk_max_objects (U32 max) |
|
|
296 | $int = $env->set_lg_bsize (U32 max) |
|
|
297 | $int = $env->set_lg_max (U32 max) |
|
|
298 | $int = $env->mutex_set_increment (U32 increment) |
|
|
299 | $int = $env->mutex_set_tas_spins (U32 tas_spins) |
|
|
300 | $int = $env->mutex_set_max (U32 max) |
|
|
301 | $int = $env->mutex_set_align (U32 align) |
|
|
302 | |
|
|
303 | $txn = $env->txn_begin (DB_TXN_ornull *parent = 0, U32 flags = 0) |
|
|
304 | flags: READ_COMMITTED READ_UNCOMMITTED TXN_NOSYNC TXN_NOWAIT TXN_SNAPSHOT TXN_SYNC TXN_WAIT TXN_WRITE_NOSYNC |
|
|
305 | |
|
|
306 | =head4 Example: |
|
|
307 | |
|
|
308 | use AnyEvent; |
|
|
309 | use BDB; |
|
|
310 | |
|
|
311 | our $FH; open $FH, "<&=" . BDB::poll_fileno; |
|
|
312 | our $WATCHER = AnyEvent->io (fh => $FH, poll => 'r', cb => \&BDB::poll_cb); |
|
|
313 | |
|
|
314 | BDB::min_parallel 8; |
|
|
315 | |
|
|
316 | my $env = db_env_create; |
|
|
317 | |
|
|
318 | mkdir "bdtest", 0700; |
|
|
319 | db_env_open |
|
|
320 | $env, |
|
|
321 | "bdtest", |
|
|
322 | BDB::INIT_LOCK | BDB::INIT_LOG | BDB::INIT_MPOOL | BDB::INIT_TXN | BDB::RECOVER | BDB::USE_ENVIRON | BDB::CREATE, |
|
|
323 | 0600; |
|
|
324 | |
|
|
325 | $env->set_flags (BDB::AUTO_COMMIT | BDB::TXN_NOSYNC, 1); |
|
|
326 | |
|
|
327 | |
|
|
328 | =head3 DB/database methods |
|
|
329 | |
|
|
330 | Methods available on DB/$db handles: |
|
|
331 | |
|
|
332 | DESTROY (DB_ornull *db) |
|
|
333 | CODE: |
|
|
334 | if (db) |
|
|
335 | { |
|
|
336 | SV *env = (SV *)db->app_private; |
|
|
337 | db->close (db, 0); |
|
|
338 | SvREFCNT_dec (env); |
|
|
339 | } |
|
|
340 | |
|
|
341 | $int = $db->set_cachesize (U32 gbytes, U32 bytes, int ncache = 0) |
|
|
342 | $int = $db->set_flags (U32 flags) |
|
|
343 | flags: CHKSUM ENCRYPT TXN_NOT_DURABLE |
|
|
344 | Btree: DUP DUPSORT RECNUM REVSPLITOFF |
|
|
345 | Hash: DUP DUPSORT |
|
|
346 | Queue: INORDER |
|
|
347 | Recno: RENUMBER SNAPSHOT |
|
|
348 | |
|
|
349 | $int = $db->set_encrypt (const char *password, U32 flags) |
|
|
350 | $int = $db->set_lorder (int lorder) |
|
|
351 | $int = $db->set_bt_minkey (U32 minkey) |
|
|
352 | $int = $db->set_re_delim (int delim) |
|
|
353 | $int = $db->set_re_pad (int re_pad) |
|
|
354 | $int = $db->set_re_source (char *source) |
|
|
355 | $int = $db->set_re_len (U32 re_len) |
|
|
356 | $int = $db->set_h_ffactor (U32 h_ffactor) |
|
|
357 | $int = $db->set_h_nelem (U32 h_nelem) |
|
|
358 | $int = $db->set_q_extentsize (U32 extentsize) |
|
|
359 | |
|
|
360 | $dbc = $db->cursor (DB_TXN_ornull *txn = 0, U32 flags = 0) |
|
|
361 | flags: READ_COMMITTED READ_UNCOMMITTED WRITECURSOR TXN_SNAPSHOT |
|
|
362 | $seq = $db->sequence (U32 flags = 0) |
|
|
363 | |
|
|
364 | =head4 Example: |
|
|
365 | |
|
|
366 | my $db = db_create $env; |
|
|
367 | db_open $db, undef, "table", undef, BDB::BTREE, BDB::AUTO_COMMIT | BDB::CREATE | BDB::READ_UNCOMMITTED, 0600; |
|
|
368 | |
|
|
369 | for (1..1000) { |
|
|
370 | db_put $db, undef, "key $_", "data $_"; |
|
|
371 | |
|
|
372 | db_key_range $db, undef, "key $_", my $keyrange; |
|
|
373 | my ($lt, $eq, $gt) = @$keyrange; |
|
|
374 | } |
|
|
375 | |
|
|
376 | db_del $db, undef, "key $_" for 1..1000; |
|
|
377 | |
|
|
378 | db_sync $db; |
|
|
379 | |
|
|
380 | |
|
|
381 | =head3 DB_TXN/transaction methods |
|
|
382 | |
|
|
383 | Methods available on DB_TXN/$txn handles: |
|
|
384 | |
|
|
385 | DESTROY (DB_TXN_ornull *txn) |
|
|
386 | CODE: |
|
|
387 | if (txn) |
|
|
388 | txn->abort (txn); |
|
|
389 | |
|
|
390 | $int = $txn->set_timeout (NV timeout_seconds, U32 flags = SET_TXN_TIMEOUT) |
|
|
391 | flags: SET_LOCK_TIMEOUT SET_TXN_TIMEOUT |
|
|
392 | |
|
|
393 | $bool = $txn->failed |
|
|
394 | # see db_txn_finish documentation, above |
|
|
395 | |
|
|
396 | |
|
|
397 | =head3 DBC/cursor methods |
|
|
398 | |
|
|
399 | Methods available on DBC/$dbc handles: |
|
|
400 | |
|
|
401 | DESTROY (DBC_ornull *dbc) |
|
|
402 | CODE: |
|
|
403 | if (dbc) |
|
|
404 | dbc->c_close (dbc); |
|
|
405 | |
|
|
406 | $int = $cursor->set_priority ($priority = PRIORITY_*) |
|
|
407 | |
|
|
408 | =head4 Example: |
|
|
409 | |
|
|
410 | my $c = $db->cursor; |
|
|
411 | |
|
|
412 | for (;;) { |
|
|
413 | db_c_get $c, my $key, my $data, BDB::NEXT; |
|
|
414 | warn "<$!,$key,$data>"; |
|
|
415 | last if $!; |
|
|
416 | } |
|
|
417 | |
|
|
418 | db_c_close $c; |
|
|
419 | |
|
|
420 | |
|
|
421 | =head3 DB_SEQUENCE/sequence methods |
|
|
422 | |
|
|
423 | Methods available on DB_SEQUENCE/$seq handles: |
|
|
424 | |
|
|
425 | DESTROY (DB_SEQUENCE_ornull *seq) |
|
|
426 | CODE: |
|
|
427 | if (seq) |
|
|
428 | seq->close (seq, 0); |
|
|
429 | |
|
|
430 | $int = $seq->initial_value (db_seq_t value) |
|
|
431 | $int = $seq->set_cachesize (U32 size) |
|
|
432 | $int = $seq->set_flags (U32 flags) |
|
|
433 | flags: SEQ_DEC SEQ_INC SEQ_WRAP |
|
|
434 | $int = $seq->set_range (db_seq_t min, db_seq_t max) |
|
|
435 | |
|
|
436 | =head4 Example: |
|
|
437 | |
|
|
438 | my $seq = $db->sequence; |
|
|
439 | |
|
|
440 | db_sequence_open $seq, undef, "seq", BDB::CREATE; |
|
|
441 | db_sequence_get $seq, undef, 1, my $value; |
|
|
442 | |
|
|
443 | |
80 | =head2 SUPPORT FUNCTIONS |
444 | =head2 SUPPORT FUNCTIONS |
81 | |
445 | |
82 | =head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION |
446 | =head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION |
83 | |
447 | |
84 | =over 4 |
448 | =over 4 |
85 | |
449 | |
|
|
450 | =item $msg = BDB::strerror [$errno] |
|
|
451 | |
|
|
452 | Returns the string corresponding to the given errno value. If no argument |
|
|
453 | is given, use C<$!>. |
|
|
454 | |
|
|
455 | Note that the BDB module also patches the C<$!> variable directly, so you |
|
|
456 | should be able to get a bdb error string by simply stringifying C<$!>. |
|
|
457 | |
86 | =item $fileno = BDB::AIO::poll_fileno |
458 | =item $fileno = BDB::poll_fileno |
87 | |
459 | |
88 | Return the I<request result pipe file descriptor>. This filehandle must be |
460 | Return the I<request result pipe file descriptor>. This filehandle must be |
89 | polled for reading by some mechanism outside this module (e.g. Event or |
461 | polled for reading by some mechanism outside this module (e.g. Event or |
90 | select, see below or the SYNOPSIS). If the pipe becomes readable you have |
462 | select, see below or the SYNOPSIS). If the pipe becomes readable you have |
91 | to call C<poll_cb> to check the results. |
463 | to call C<poll_cb> to check the results. |
92 | |
464 | |
93 | See C<poll_cb> for an example. |
465 | See C<poll_cb> for an example. |
94 | |
466 | |
95 | =item BDB::AIO::poll_cb |
467 | =item BDB::poll_cb |
96 | |
468 | |
97 | Process some outstanding events on the result pipe. You have to call this |
469 | Process some outstanding events on the result pipe. You have to call this |
98 | regularly. Returns the number of events processed. Returns immediately |
470 | regularly. Returns the number of events processed. Returns immediately |
99 | when no events are outstanding. The amount of events processed depends on |
471 | when no events are outstanding. The amount of events processed depends on |
100 | the settings of C<BDB::AIO::max_poll_req> and C<BDB::AIO::max_poll_time>. |
472 | the settings of C<BDB::max_poll_req> and C<BDB::max_poll_time>. |
101 | |
473 | |
102 | If not all requests were processed for whatever reason, the filehandle |
474 | If not all requests were processed for whatever reason, the filehandle |
103 | will still be ready when C<poll_cb> returns. |
475 | will still be ready when C<poll_cb> returns. |
104 | |
476 | |
105 | Example: Install an Event watcher that automatically calls |
477 | Example: Install an Event watcher that automatically calls |
106 | BDB::AIO::poll_cb with high priority: |
478 | BDB::poll_cb with high priority: |
107 | |
479 | |
108 | Event->io (fd => BDB::AIO::poll_fileno, |
480 | Event->io (fd => BDB::poll_fileno, |
109 | poll => 'r', async => 1, |
481 | poll => 'r', async => 1, |
110 | cb => \&BDB::AIO::poll_cb); |
482 | cb => \&BDB::poll_cb); |
111 | |
483 | |
112 | =item BDB::AIO::max_poll_reqs $nreqs |
484 | =item BDB::max_poll_reqs $nreqs |
113 | |
485 | |
114 | =item BDB::AIO::max_poll_time $seconds |
486 | =item BDB::max_poll_time $seconds |
115 | |
487 | |
116 | These set the maximum number of requests (default C<0>, meaning infinity) |
488 | These set the maximum number of requests (default C<0>, meaning infinity) |
117 | that are being processed by C<BDB::AIO::poll_cb> in one call, respectively |
489 | that are being processed by C<BDB::poll_cb> in one call, respectively |
118 | the maximum amount of time (default C<0>, meaning infinity) spent in |
490 | the maximum amount of time (default C<0>, meaning infinity) spent in |
119 | C<BDB::AIO::poll_cb> to process requests (more correctly the mininum amount |
491 | C<BDB::poll_cb> to process requests (more correctly the mininum amount |
120 | of time C<poll_cb> is allowed to use). |
492 | of time C<poll_cb> is allowed to use). |
121 | |
493 | |
122 | Setting C<max_poll_time> to a non-zero value creates an overhead of one |
494 | Setting C<max_poll_time> to a non-zero value creates an overhead of one |
123 | syscall per request processed, which is not normally a problem unless your |
495 | syscall per request processed, which is not normally a problem unless your |
124 | callbacks are really really fast or your OS is really really slow (I am |
496 | callbacks are really really fast or your OS is really really slow (I am |
… | |
… | |
128 | interactiveness when perl is not fast enough to process all requests in |
500 | interactiveness when perl is not fast enough to process all requests in |
129 | time. |
501 | time. |
130 | |
502 | |
131 | For interactive programs, values such as C<0.01> to C<0.1> should be fine. |
503 | For interactive programs, values such as C<0.01> to C<0.1> should be fine. |
132 | |
504 | |
133 | Example: Install an Event watcher that automatically calls |
505 | Example: Install an EV watcher that automatically calls |
134 | BDB::AIO::poll_cb with low priority, to ensure that other parts of the |
506 | BDB::poll_cb with low priority, to ensure that other parts of the |
135 | program get the CPU sometimes even under high AIO load. |
507 | program get the CPU sometimes even under high load. |
136 | |
508 | |
137 | # try not to spend much more than 0.1s in poll_cb |
509 | # try not to spend much more than 0.1s in poll_cb |
138 | BDB::AIO::max_poll_time 0.1; |
510 | BDB::max_poll_time 0.1; |
139 | |
511 | |
140 | # use a low priority so other tasks have priority |
512 | my $bdb_poll = EV::io BDB::poll_fileno, EV::READ, \&BDB::poll_cb); |
141 | Event->io (fd => BDB::AIO::poll_fileno, |
|
|
142 | poll => 'r', nice => 1, |
|
|
143 | cb => &BDB::AIO::poll_cb); |
|
|
144 | |
513 | |
145 | =item BDB::AIO::poll_wait |
514 | =item BDB::poll_wait |
146 | |
515 | |
147 | If there are any outstanding requests and none of them in the result |
516 | If there are any outstanding requests and none of them in the result |
148 | phase, wait till the result filehandle becomes ready for reading (simply |
517 | phase, wait till the result filehandle becomes ready for reading (simply |
149 | does a C<select> on the filehandle. This is useful if you want to |
518 | does a C<select> on the filehandle. This is useful if you want to |
150 | synchronously wait for some requests to finish). |
519 | synchronously wait for some requests to finish). |
151 | |
520 | |
152 | See C<nreqs> for an example. |
521 | See C<nreqs> for an example. |
153 | |
522 | |
154 | =item BDB::AIO::poll |
523 | =item BDB::poll |
155 | |
524 | |
156 | Waits until some requests have been handled. |
525 | Waits until some requests have been handled. |
157 | |
526 | |
158 | Returns the number of requests processed, but is otherwise strictly |
527 | Returns the number of requests processed, but is otherwise strictly |
159 | equivalent to: |
528 | equivalent to: |
160 | |
529 | |
161 | BDB::AIO::poll_wait, BDB::AIO::poll_cb |
530 | BDB::poll_wait, BDB::poll_cb |
162 | |
531 | |
163 | =item BDB::AIO::flush |
532 | =item BDB::flush |
164 | |
533 | |
165 | Wait till all outstanding AIO requests have been handled. |
534 | Wait till all outstanding BDB requests have been handled. |
166 | |
535 | |
167 | Strictly equivalent to: |
536 | Strictly equivalent to: |
168 | |
537 | |
169 | BDB::AIO::poll_wait, BDB::AIO::poll_cb |
538 | BDB::poll_wait, BDB::poll_cb |
170 | while BDB::AIO::nreqs; |
539 | while BDB::nreqs; |
|
|
540 | |
|
|
541 | =back |
171 | |
542 | |
172 | =head3 CONTROLLING THE NUMBER OF THREADS |
543 | =head3 CONTROLLING THE NUMBER OF THREADS |
173 | |
544 | |
|
|
545 | =over 4 |
|
|
546 | |
174 | =item BDB::AIO::min_parallel $nthreads |
547 | =item BDB::min_parallel $nthreads |
175 | |
548 | |
176 | Set the minimum number of AIO threads to C<$nthreads>. The current |
549 | Set the minimum number of BDB threads to C<$nthreads>. The current |
177 | default is C<8>, which means eight asynchronous operations can execute |
550 | default is C<8>, which means eight asynchronous operations can execute |
178 | concurrently at any one time (the number of outstanding requests, |
551 | concurrently at any one time (the number of outstanding requests, |
179 | however, is unlimited). |
552 | however, is unlimited). |
180 | |
553 | |
181 | BDB::AIO starts threads only on demand, when an AIO request is queued and |
554 | BDB starts threads only on demand, when an BDB request is queued and |
182 | no free thread exists. Please note that queueing up a hundred requests can |
555 | no free thread exists. Please note that queueing up a hundred requests can |
183 | create demand for a hundred threads, even if it turns out that everything |
556 | create demand for a hundred threads, even if it turns out that everything |
184 | is in the cache and could have been processed faster by a single thread. |
557 | is in the cache and could have been processed faster by a single thread. |
185 | |
558 | |
186 | It is recommended to keep the number of threads relatively low, as some |
559 | It is recommended to keep the number of threads relatively low, as some |
… | |
… | |
189 | versions, 4-32 threads should be fine. |
562 | versions, 4-32 threads should be fine. |
190 | |
563 | |
191 | Under most circumstances you don't need to call this function, as the |
564 | Under most circumstances you don't need to call this function, as the |
192 | module selects a default that is suitable for low to moderate load. |
565 | module selects a default that is suitable for low to moderate load. |
193 | |
566 | |
194 | =item BDB::AIO::max_parallel $nthreads |
567 | =item BDB::max_parallel $nthreads |
195 | |
568 | |
196 | Sets the maximum number of AIO threads to C<$nthreads>. If more than the |
569 | Sets the maximum number of BDB threads to C<$nthreads>. If more than the |
197 | specified number of threads are currently running, this function kills |
570 | specified number of threads are currently running, this function kills |
198 | them. This function blocks until the limit is reached. |
571 | them. This function blocks until the limit is reached. |
199 | |
572 | |
200 | While C<$nthreads> are zero, aio requests get queued but not executed |
573 | While C<$nthreads> are zero, aio requests get queued but not executed |
201 | until the number of threads has been increased again. |
574 | until the number of threads has been increased again. |
… | |
… | |
203 | This module automatically runs C<max_parallel 0> at program end, to ensure |
576 | This module automatically runs C<max_parallel 0> at program end, to ensure |
204 | that all threads are killed and that there are no outstanding requests. |
577 | that all threads are killed and that there are no outstanding requests. |
205 | |
578 | |
206 | Under normal circumstances you don't need to call this function. |
579 | Under normal circumstances you don't need to call this function. |
207 | |
580 | |
208 | =item BDB::AIO::max_idle $nthreads |
581 | =item BDB::max_idle $nthreads |
209 | |
582 | |
210 | Limit the number of threads (default: 4) that are allowed to idle (i.e., |
583 | Limit the number of threads (default: 4) that are allowed to idle (i.e., |
211 | threads that did not get a request to process within 10 seconds). That |
584 | threads that did not get a request to process within 10 seconds). That |
212 | means if a thread becomes idle while C<$nthreads> other threads are also |
585 | means if a thread becomes idle while C<$nthreads> other threads are also |
213 | idle, it will free its resources and exit. |
586 | idle, it will free its resources and exit. |
… | |
… | |
218 | |
591 | |
219 | The default is probably ok in most situations, especially if thread |
592 | The default is probably ok in most situations, especially if thread |
220 | creation is fast. If thread creation is very slow on your system you might |
593 | creation is fast. If thread creation is very slow on your system you might |
221 | want to use larger values. |
594 | want to use larger values. |
222 | |
595 | |
223 | =item $oldmaxreqs = BDB::AIO::max_outstanding $maxreqs |
596 | =item $oldmaxreqs = BDB::max_outstanding $maxreqs |
224 | |
597 | |
225 | This is a very bad function to use in interactive programs because it |
598 | This is a very bad function to use in interactive programs because it |
226 | blocks, and a bad way to reduce concurrency because it is inexact: Better |
599 | blocks, and a bad way to reduce concurrency because it is inexact: Better |
227 | use an C<aio_group> together with a feed callback. |
600 | use an C<aio_group> together with a feed callback. |
228 | |
601 | |
… | |
… | |
236 | |
609 | |
237 | You can still queue as many requests as you want. Therefore, |
610 | You can still queue as many requests as you want. Therefore, |
238 | C<max_oustsanding> is mainly useful in simple scripts (with low values) or |
611 | C<max_oustsanding> is mainly useful in simple scripts (with low values) or |
239 | as a stop gap to shield against fatal memory overflow (with large values). |
612 | as a stop gap to shield against fatal memory overflow (with large values). |
240 | |
613 | |
|
|
614 | =item BDB::set_sync_prepare $cb |
|
|
615 | |
|
|
616 | Sets a callback that is called whenever a request is created without an |
|
|
617 | explicit callback. It has to return two code references. The first is used |
|
|
618 | as the request callback (it should save the return status), and the second |
|
|
619 | is called to wait until the first callback has been called (it must set |
|
|
620 | C<$!> to the return status). |
|
|
621 | |
|
|
622 | This mechanism can be used to include BDB into other event mechanisms, |
|
|
623 | such as L<AnyEvent::BDB> or L<Coro::BDB>. |
|
|
624 | |
|
|
625 | The default implementation works like this: |
|
|
626 | |
|
|
627 | sub { |
|
|
628 | my $status; |
|
|
629 | ( |
|
|
630 | sub { $status = $! }, |
|
|
631 | sub { BDB::poll while !defined $status; $! = $status }, |
|
|
632 | ) |
|
|
633 | } |
|
|
634 | |
|
|
635 | It simply blocks the process till the request has finished and then sets |
|
|
636 | C<$!> to the return value. This means that if you don't use a callback, |
|
|
637 | BDB will simply fall back to synchronous operations. |
|
|
638 | |
|
|
639 | =back |
|
|
640 | |
241 | =head3 STATISTICAL INFORMATION |
641 | =head3 STATISTICAL INFORMATION |
242 | |
642 | |
|
|
643 | =over 4 |
|
|
644 | |
243 | =item BDB::AIO::nreqs |
645 | =item BDB::nreqs |
244 | |
646 | |
245 | Returns the number of requests currently in the ready, execute or pending |
647 | Returns the number of requests currently in the ready, execute or pending |
246 | states (i.e. for which their callback has not been invoked yet). |
648 | states (i.e. for which their callback has not been invoked yet). |
247 | |
649 | |
248 | Example: wait till there are no outstanding requests anymore: |
650 | Example: wait till there are no outstanding requests anymore: |
249 | |
651 | |
250 | BDB::AIO::poll_wait, BDB::AIO::poll_cb |
652 | BDB::poll_wait, BDB::poll_cb |
251 | while BDB::AIO::nreqs; |
653 | while BDB::nreqs; |
252 | |
654 | |
253 | =item BDB::AIO::nready |
655 | =item BDB::nready |
254 | |
656 | |
255 | Returns the number of requests currently in the ready state (not yet |
657 | Returns the number of requests currently in the ready state (not yet |
256 | executed). |
658 | executed). |
257 | |
659 | |
258 | =item BDB::AIO::npending |
660 | =item BDB::npending |
259 | |
661 | |
260 | Returns the number of requests currently in the pending state (executed, |
662 | Returns the number of requests currently in the pending state (executed, |
261 | but not yet processed by poll_cb). |
663 | but not yet processed by poll_cb). |
262 | |
664 | |
263 | =back |
665 | =back |
264 | |
666 | |
265 | =cut |
667 | =cut |
266 | |
668 | |
267 | # support function to convert a fd into a perl filehandle |
669 | set_sync_prepare { |
268 | sub _fd2fh { |
670 | my $status; |
269 | return undef if $_[0] < 0; |
671 | ( |
270 | |
672 | sub { |
271 | # try to generate nice filehandles |
673 | $status = $!; |
272 | my $sym = "BDB::AIO::fd#$_[0]"; |
674 | }, |
273 | local *$sym; |
675 | sub { |
274 | |
676 | BDB::poll while !defined $status; |
275 | open *$sym, "+<&=$_[0]" # usually works under any unix |
677 | $! = $status; |
276 | or open *$sym, "<&=$_[0]" # cygwin needs this |
678 | }, |
277 | or open *$sym, ">&=$_[0]" # or this |
679 | ) |
278 | or return undef; |
680 | }; |
279 | |
|
|
280 | *$sym |
|
|
281 | } |
|
|
282 | |
681 | |
283 | min_parallel 8; |
682 | min_parallel 8; |
284 | |
683 | |
285 | END { flush } |
684 | END { flush } |
286 | |
685 | |
… | |
… | |
288 | |
687 | |
289 | =head2 FORK BEHAVIOUR |
688 | =head2 FORK BEHAVIOUR |
290 | |
689 | |
291 | This module should do "the right thing" when the process using it forks: |
690 | This module should do "the right thing" when the process using it forks: |
292 | |
691 | |
293 | Before the fork, IO::AIO enters a quiescent state where no requests |
692 | Before the fork, BDB enters a quiescent state where no requests |
294 | can be added in other threads and no results will be processed. After |
693 | can be added in other threads and no results will be processed. After |
295 | the fork the parent simply leaves the quiescent state and continues |
694 | the fork the parent simply leaves the quiescent state and continues |
296 | request/result processing, while the child frees the request/result queue |
695 | request/result processing, while the child frees the request/result queue |
297 | (so that the requests started before the fork will only be handled in the |
696 | (so that the requests started before the fork will only be handled in the |
298 | parent). Threads will be started on demand until the limit set in the |
697 | parent). Threads will be started on demand until the limit set in the |
299 | parent process has been reached again. |
698 | parent process has been reached again. |
300 | |
699 | |
301 | In short: the parent will, after a short pause, continue as if fork had |
700 | In short: the parent will, after a short pause, continue as if fork had |
302 | not been called, while the child will act as if IO::AIO has not been used |
701 | not been called, while the child will act as if BDB has not been used |
303 | yet. |
702 | yet. |
|
|
703 | |
|
|
704 | Win32 note: there is no fork on win32, and perls emulation of it is too |
|
|
705 | broken to be supported, so do not use BDB in a windows pseudo-fork, better |
|
|
706 | yet, switch to a more capable platform. |
304 | |
707 | |
305 | =head2 MEMORY USAGE |
708 | =head2 MEMORY USAGE |
306 | |
709 | |
307 | Per-request usage: |
710 | Per-request usage: |
308 | |
711 | |
… | |
… | |
310 | bytes of memory. In addition, stat requests need a stat buffer (possibly |
713 | bytes of memory. In addition, stat requests need a stat buffer (possibly |
311 | a few hundred bytes), readdir requires a result buffer and so on. Perl |
714 | a few hundred bytes), readdir requires a result buffer and so on. Perl |
312 | scalars and other data passed into aio requests will also be locked and |
715 | scalars and other data passed into aio requests will also be locked and |
313 | will consume memory till the request has entered the done state. |
716 | will consume memory till the request has entered the done state. |
314 | |
717 | |
315 | This is now awfully much, so queuing lots of requests is not usually a |
718 | This is not awfully much, so queuing lots of requests is not usually a |
316 | problem. |
719 | problem. |
317 | |
720 | |
318 | Per-thread usage: |
721 | Per-thread usage: |
319 | |
722 | |
320 | In the execution phase, some aio requests require more memory for |
723 | In the execution phase, some aio requests require more memory for |
321 | temporary buffers, and each thread requires a stack and other data |
724 | temporary buffers, and each thread requires a stack and other data |
322 | structures (usually around 16k-128k, depending on the OS). |
725 | structures (usually around 16k-128k, depending on the OS). |
323 | |
726 | |
324 | =head1 KNOWN BUGS |
727 | =head1 KNOWN BUGS |
325 | |
728 | |
326 | Known bugs will be fixed in the next release. |
729 | Known bugs will be fixed in the next release, except: |
|
|
730 | |
|
|
731 | If you use a transaction in any request, and the request returns |
|
|
732 | with an operating system error or DB_LOCK_NOTGRANTED, the internal |
|
|
733 | TXN_DEADLOCK flag will be set on the transaction. See C<db_txn_finish>, |
|
|
734 | above. |
327 | |
735 | |
328 | =head1 SEE ALSO |
736 | =head1 SEE ALSO |
329 | |
737 | |
330 | L<Coro::AIO>. |
738 | L<AnyEvent::BDB> (event loop integration), L<Coro::BDB> (more natural |
|
|
739 | syntax), L<IO::AIO> (nice to have). |
331 | |
740 | |
332 | =head1 AUTHOR |
741 | =head1 AUTHOR |
333 | |
742 | |
334 | Marc Lehmann <schmorp@schmorp.de> |
743 | Marc Lehmann <schmorp@schmorp.de> |
335 | http://home.schmorp.de/ |
744 | http://home.schmorp.de/ |