… | |
… | |
63 | use base 'Exporter'; |
63 | use base 'Exporter'; |
64 | |
64 | |
65 | use Fcntl (); |
65 | use Fcntl (); |
66 | |
66 | |
67 | BEGIN { |
67 | BEGIN { |
68 | $VERSION = 1.2; |
68 | $VERSION = 1.6; |
69 | |
69 | |
70 | @EXPORT = qw(aio_read aio_write aio_open aio_close aio_stat aio_lstat aio_unlink |
70 | @EXPORT = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat |
|
|
71 | aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink |
71 | aio_rmdir aio_symlink aio_fsync aio_fdatasync aio_readahead); |
72 | aio_fsync aio_fdatasync aio_readahead); |
72 | @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs); |
73 | @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel |
|
|
74 | max_outstanding nreqs); |
73 | |
75 | |
74 | require XSLoader; |
76 | require XSLoader; |
75 | XSLoader::load IO::AIO, $VERSION; |
77 | XSLoader::load IO::AIO, $VERSION; |
76 | } |
78 | } |
77 | |
79 | |
… | |
… | |
103 | environment, d) use Glib::filename_from_unicode on unicode filenames or e) |
105 | environment, d) use Glib::filename_from_unicode on unicode filenames or e) |
104 | use something else. |
106 | use something else. |
105 | |
107 | |
106 | =over 4 |
108 | =over 4 |
107 | |
109 | |
108 | =item aio_open $pathname, $flags, $mode, $callback |
110 | =item aio_open $pathname, $flags, $mode, $callback->($fh) |
109 | |
111 | |
110 | Asynchronously open or create a file and call the callback with a newly |
112 | Asynchronously open or create a file and call the callback with a newly |
111 | created filehandle for the file. |
113 | created filehandle for the file. |
112 | |
114 | |
113 | The pathname passed to C<aio_open> must be absolute. See API NOTES, above, |
115 | The pathname passed to C<aio_open> must be absolute. See API NOTES, above, |
… | |
… | |
130 | } else { |
132 | } else { |
131 | die "open failed: $!\n"; |
133 | die "open failed: $!\n"; |
132 | } |
134 | } |
133 | }; |
135 | }; |
134 | |
136 | |
135 | =item aio_close $fh, $callback |
137 | =item aio_close $fh, $callback->($status) |
136 | |
138 | |
137 | Asynchronously close a file and call the callback with the result |
139 | Asynchronously close a file and call the callback with the result |
138 | code. I<WARNING:> although accepted, you should not pass in a perl |
140 | code. I<WARNING:> although accepted, you should not pass in a perl |
139 | filehandle here, as perl will likely close the file descriptor another |
141 | filehandle here, as perl will likely close the file descriptor another |
140 | time when the filehandle is destroyed. Normally, you can safely call perls |
142 | time when the filehandle is destroyed. Normally, you can safely call perls |
141 | C<close> or just let filehandles go out of scope. |
143 | C<close> or just let filehandles go out of scope. |
142 | |
144 | |
143 | This is supposed to be a bug in the API, so that might change. It's |
145 | This is supposed to be a bug in the API, so that might change. It's |
144 | therefore best to avoid this function. |
146 | therefore best to avoid this function. |
145 | |
147 | |
146 | =item aio_read $fh,$offset,$length, $data,$dataoffset,$callback |
148 | =item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
147 | |
149 | |
148 | =item aio_write $fh,$offset,$length, $data,$dataoffset,$callback |
150 | =item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
149 | |
151 | |
150 | Reads or writes C<length> bytes from the specified C<fh> and C<offset> |
152 | Reads or writes C<length> bytes from the specified C<fh> and C<offset> |
151 | into the scalar given by C<data> and offset C<dataoffset> and calls the |
153 | into the scalar given by C<data> and offset C<dataoffset> and calls the |
152 | callback without the actual number of bytes read (or -1 on error, just |
154 | callback without the actual number of bytes read (or -1 on error, just |
153 | like the syscall). |
155 | like the syscall). |
154 | |
156 | |
|
|
157 | The C<$data> scalar I<MUST NOT> be modified in any way while the request |
|
|
158 | is outstanding. Modifying it can result in segfaults or WW3 (if the |
|
|
159 | necessary/optional hardware is installed). |
|
|
160 | |
155 | Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at |
161 | Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at |
156 | offset C<0> within the scalar: |
162 | offset C<0> within the scalar: |
157 | |
163 | |
158 | aio_read $fh, 7, 15, $buffer, 0, sub { |
164 | aio_read $fh, 7, 15, $buffer, 0, sub { |
159 | $_[0] > 0 or die "read error: $!"; |
165 | $_[0] > 0 or die "read error: $!"; |
160 | print "read $_[0] bytes: <$buffer>\n"; |
166 | print "read $_[0] bytes: <$buffer>\n"; |
161 | }; |
167 | }; |
162 | |
168 | |
|
|
169 | =item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) |
|
|
170 | |
|
|
171 | Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts |
|
|
172 | reading at byte offset C<$in_offset>, and starts writing at the current |
|
|
173 | file offset of C<$out_fh>. Because of that, it is not safe to issue more |
|
|
174 | than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each |
|
|
175 | other. |
|
|
176 | |
|
|
177 | This call tries to make use of a native C<sendfile> syscall to provide |
|
|
178 | zero-copy operation. For this to work, C<$out_fh> should refer to a |
|
|
179 | socket, and C<$in_fh> should refer to mmap'able file. |
|
|
180 | |
|
|
181 | If the native sendfile call fails or is not implemented, it will be |
|
|
182 | emulated, so you can call C<aio_sendfile> on any type of filehandle |
|
|
183 | regardless of the limitations of the operating system. |
|
|
184 | |
|
|
185 | Please note, however, that C<aio_sendfile> can read more bytes from |
|
|
186 | C<$in_fh> than are written, and there is no way to find out how many |
|
|
187 | bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only |
|
|
188 | provides the number of bytes written to C<$out_fh>. Only if the result |
|
|
189 | value equals C<$length> one can assume that C<$length> bytes have been |
|
|
190 | read. |
|
|
191 | |
163 | =item aio_readahead $fh,$offset,$length, $callback |
192 | =item aio_readahead $fh,$offset,$length, $callback->($retval) |
164 | |
193 | |
165 | C<aio_readahead> populates the page cache with data from a file so that |
194 | C<aio_readahead> populates the page cache with data from a file so that |
166 | subsequent reads from that file will not block on disk I/O. The C<$offset> |
195 | subsequent reads from that file will not block on disk I/O. The C<$offset> |
167 | argument specifies the starting point from which data is to be read and |
196 | argument specifies the starting point from which data is to be read and |
168 | C<$length> specifies the number of bytes to be read. I/O is performed in |
197 | C<$length> specifies the number of bytes to be read. I/O is performed in |
… | |
… | |
172 | file. The current file offset of the file is left unchanged. |
201 | file. The current file offset of the file is left unchanged. |
173 | |
202 | |
174 | If that syscall doesn't exist (likely if your OS isn't Linux) it will be |
203 | If that syscall doesn't exist (likely if your OS isn't Linux) it will be |
175 | emulated by simply reading the data, which would have a similar effect. |
204 | emulated by simply reading the data, which would have a similar effect. |
176 | |
205 | |
177 | =item aio_stat $fh_or_path, $callback |
206 | =item aio_stat $fh_or_path, $callback->($status) |
178 | |
207 | |
179 | =item aio_lstat $fh, $callback |
208 | =item aio_lstat $fh, $callback->($status) |
180 | |
209 | |
181 | Works like perl's C<stat> or C<lstat> in void context. The callback will |
210 | Works like perl's C<stat> or C<lstat> in void context. The callback will |
182 | be called after the stat and the results will be available using C<stat _> |
211 | be called after the stat and the results will be available using C<stat _> |
183 | or C<-s _> etc... |
212 | or C<-s _> etc... |
184 | |
213 | |
… | |
… | |
194 | aio_stat "/etc/passwd", sub { |
223 | aio_stat "/etc/passwd", sub { |
195 | $_[0] and die "stat failed: $!"; |
224 | $_[0] and die "stat failed: $!"; |
196 | print "size is ", -s _, "\n"; |
225 | print "size is ", -s _, "\n"; |
197 | }; |
226 | }; |
198 | |
227 | |
199 | =item aio_unlink $pathname, $callback |
228 | =item aio_unlink $pathname, $callback->($status) |
200 | |
229 | |
201 | Asynchronously unlink (delete) a file and call the callback with the |
230 | Asynchronously unlink (delete) a file and call the callback with the |
202 | result code. |
231 | result code. |
203 | |
232 | |
204 | =item aio_rmdir $pathname, $callback |
233 | =item aio_rmdir $pathname, $callback->($status) |
205 | |
234 | |
206 | Asynchronously rmdir (delete) a directory and call the callback with the |
235 | Asynchronously rmdir (delete) a directory and call the callback with the |
207 | result code. |
236 | result code. |
208 | |
237 | |
|
|
238 | =item aio_readdir $pathname $callback->($entries) |
|
|
239 | |
|
|
240 | Unlike the POSIX call of the same name, C<aio_readdir> reads an entire |
|
|
241 | directory (i.e. opendir + readdir + closedir). The entries will not be |
|
|
242 | sorted, and will B<NOT> include the C<.> and C<..> entries. |
|
|
243 | |
|
|
244 | The callback a single argument which is either C<undef> or an array-ref |
|
|
245 | with the filenames. |
|
|
246 | |
|
|
247 | =item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) |
|
|
248 | |
|
|
249 | Scans a directory (similar to C<aio_readdir>) and tries to separate the |
|
|
250 | entries of directory C<$path> into two sets of names, ones you can recurse |
|
|
251 | into (directories), and ones you cannot recurse into (everything else). |
|
|
252 | |
|
|
253 | C<aio_scandir> is a composite request that consists of many |
|
|
254 | aio-primitives. C<$maxreq> specifies the maximum number of outstanding |
|
|
255 | aio requests that this function generates. If it is C<< <= 0 >>, then a |
|
|
256 | suitable default will be chosen (currently 8). |
|
|
257 | |
|
|
258 | On error, the callback is called without arguments, otherwise it receives |
|
|
259 | two array-refs with path-relative entry names. |
|
|
260 | |
|
|
261 | Example: |
|
|
262 | |
|
|
263 | aio_scandir $dir, 0, sub { |
|
|
264 | my ($dirs, $nondirs) = @_; |
|
|
265 | print "real directories: @$dirs\n"; |
|
|
266 | print "everything else: @$nondirs\n"; |
|
|
267 | }; |
|
|
268 | |
|
|
269 | Implementation notes. |
|
|
270 | |
|
|
271 | The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can. |
|
|
272 | |
|
|
273 | After reading the directory, the modification time, size etc. of the |
|
|
274 | directory before and after the readdir is checked, and if they match, the |
|
|
275 | link count will be used to decide how many entries are directories (if |
|
|
276 | >= 2). Otherwise, no knowledge of the number of subdirectories will be |
|
|
277 | assumed. |
|
|
278 | |
|
|
279 | Then entires will be sorted into likely directories (everything without a |
|
|
280 | non-initial dot) and likely non-directories (everything else). Then every |
|
|
281 | entry + C</.> will be C<stat>'ed, likely directories first. This is often |
|
|
282 | faster because filesystems might detect the type of the entry without |
|
|
283 | reading the inode data (e.g. ext2s filetype feature). If that succeeds, |
|
|
284 | it assumes that the entry is a directory or a symlink to directory (which |
|
|
285 | will be checked seperately). |
|
|
286 | |
|
|
287 | If the known number of directories has been reached, the rest of the |
|
|
288 | entries is assumed to be non-directories. |
|
|
289 | |
|
|
290 | =cut |
|
|
291 | |
|
|
292 | sub aio_scandir($$$) { |
|
|
293 | my ($path, $maxreq, $cb) = @_; |
|
|
294 | |
|
|
295 | $maxreq = 8 if $maxreq <= 0; |
|
|
296 | |
|
|
297 | # stat once |
|
|
298 | aio_stat $path, sub { |
|
|
299 | $cb->() if $_[0]; |
|
|
300 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
|
|
301 | |
|
|
302 | # read the directory entries |
|
|
303 | aio_readdir $path, sub { |
|
|
304 | my $entries = shift |
|
|
305 | or return $cb->(); |
|
|
306 | |
|
|
307 | # stat the dir another time |
|
|
308 | aio_stat $path, sub { |
|
|
309 | my $hash2 = join ":", (stat _)[0,1,3,7,9]; |
|
|
310 | |
|
|
311 | my $ndirs; |
|
|
312 | |
|
|
313 | # take the slow route if anything looks fishy |
|
|
314 | if ($hash1 ne $hash2) { |
|
|
315 | $ndirs = -1; |
|
|
316 | } else { |
|
|
317 | # if nlink == 2, we are finished |
|
|
318 | # on non-posix-fs's, we rely on nlink < 2 |
|
|
319 | $ndirs = (stat _)[3] - 2 |
|
|
320 | or $cb->([], $entries); |
|
|
321 | } |
|
|
322 | |
|
|
323 | # sort into likely dirs and likely nondirs |
|
|
324 | # dirs == files without ".", short entries first |
|
|
325 | $entries = [map $_->[0], |
|
|
326 | sort { $b->[1] cmp $a->[1] } |
|
|
327 | map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length], |
|
|
328 | @$entries]; |
|
|
329 | |
|
|
330 | my (@dirs, @nondirs); |
|
|
331 | |
|
|
332 | my ($statcb, $schedcb); |
|
|
333 | my $nreq = 0; |
|
|
334 | |
|
|
335 | $schedcb = sub { |
|
|
336 | if (@$entries) { |
|
|
337 | if ($nreq < $maxreq) { |
|
|
338 | my $ent = pop @$entries; |
|
|
339 | $nreq++; |
|
|
340 | aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) }; |
|
|
341 | } |
|
|
342 | } elsif (!$nreq) { |
|
|
343 | # finished |
|
|
344 | undef $statcb; |
|
|
345 | undef $schedcb; |
|
|
346 | $cb->(\@dirs, \@nondirs); |
|
|
347 | undef $cb; |
|
|
348 | } |
|
|
349 | }; |
|
|
350 | $statcb = sub { |
|
|
351 | my ($status, $entry) = @_; |
|
|
352 | |
|
|
353 | if ($status < 0) { |
|
|
354 | $nreq--; |
|
|
355 | push @nondirs, $entry; |
|
|
356 | &$schedcb; |
|
|
357 | } else { |
|
|
358 | # need to check for real directory |
|
|
359 | aio_lstat "$path/$entry", sub { |
|
|
360 | $nreq--; |
|
|
361 | |
|
|
362 | if (-d _) { |
|
|
363 | push @dirs, $entry; |
|
|
364 | |
|
|
365 | if (!--$ndirs) { |
|
|
366 | push @nondirs, @$entries; |
|
|
367 | $entries = []; |
|
|
368 | } |
|
|
369 | } else { |
|
|
370 | push @nondirs, $entry; |
|
|
371 | } |
|
|
372 | |
|
|
373 | &$schedcb; |
|
|
374 | } |
|
|
375 | } |
|
|
376 | }; |
|
|
377 | |
|
|
378 | &$schedcb while @$entries && $nreq < $maxreq; |
|
|
379 | }; |
|
|
380 | }; |
|
|
381 | }; |
|
|
382 | } |
|
|
383 | |
209 | =item aio_fsync $fh, $callback |
384 | =item aio_fsync $fh, $callback->($status) |
210 | |
385 | |
211 | Asynchronously call fsync on the given filehandle and call the callback |
386 | Asynchronously call fsync on the given filehandle and call the callback |
212 | with the fsync result code. |
387 | with the fsync result code. |
213 | |
388 | |
214 | =item aio_fdatasync $fh, $callback |
389 | =item aio_fdatasync $fh, $callback->($status) |
215 | |
390 | |
216 | Asynchronously call fdatasync on the given filehandle and call the |
391 | Asynchronously call fdatasync on the given filehandle and call the |
217 | callback with the fdatasync result code. |
392 | callback with the fdatasync result code. |
218 | |
393 | |
219 | If this call isn't available because your OS lacks it or it couldn't be |
394 | If this call isn't available because your OS lacks it or it couldn't be |
… | |
… | |
283 | IO::AIO::poll_wait, IO::AIO::poll_cb |
458 | IO::AIO::poll_wait, IO::AIO::poll_cb |
284 | if IO::AIO::nreqs; |
459 | if IO::AIO::nreqs; |
285 | |
460 | |
286 | =item IO::AIO::min_parallel $nthreads |
461 | =item IO::AIO::min_parallel $nthreads |
287 | |
462 | |
288 | Set the minimum number of AIO threads to C<$nthreads>. The default is |
463 | Set the minimum number of AIO threads to C<$nthreads>. The current default |
289 | C<1>, which means a single asynchronous operation can be done at one time |
464 | is C<4>, which means four asynchronous operations can be done at one time |
290 | (the number of outstanding operations, however, is unlimited). |
465 | (the number of outstanding operations, however, is unlimited). |
|
|
466 | |
|
|
467 | IO::AIO starts threads only on demand, when an AIO request is queued and |
|
|
468 | no free thread exists. |
291 | |
469 | |
292 | It is recommended to keep the number of threads low, as some Linux |
470 | It is recommended to keep the number of threads low, as some Linux |
293 | kernel versions will scale negatively with the number of threads (higher |
471 | kernel versions will scale negatively with the number of threads (higher |
294 | parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32 |
472 | parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32 |
295 | threads should be fine. |
473 | threads should be fine. |
296 | |
474 | |
297 | Under normal circumstances you don't need to call this function, as this |
475 | Under most circumstances you don't need to call this function, as the |
298 | module automatically starts some threads (the exact number might change, |
476 | module selects a default that is suitable for low to moderate load. |
299 | and is currently 4). |
|
|
300 | |
477 | |
301 | =item IO::AIO::max_parallel $nthreads |
478 | =item IO::AIO::max_parallel $nthreads |
302 | |
479 | |
303 | Sets the maximum number of AIO threads to C<$nthreads>. If more than |
480 | Sets the maximum number of AIO threads to C<$nthreads>. If more than the |
304 | the specified number of threads are currently running, kill them. This |
481 | specified number of threads are currently running, this function kills |
305 | function blocks until the limit is reached. |
482 | them. This function blocks until the limit is reached. |
|
|
483 | |
|
|
484 | While C<$nthreads> are zero, aio requests get queued but not executed |
|
|
485 | until the number of threads has been increased again. |
306 | |
486 | |
307 | This module automatically runs C<max_parallel 0> at program end, to ensure |
487 | This module automatically runs C<max_parallel 0> at program end, to ensure |
308 | that all threads are killed and that there are no outstanding requests. |
488 | that all threads are killed and that there are no outstanding requests. |
309 | |
489 | |
310 | Under normal circumstances you don't need to call this function. |
490 | Under normal circumstances you don't need to call this function. |
… | |
… | |
314 | Sets the maximum number of outstanding requests to C<$nreqs>. If you |
494 | Sets the maximum number of outstanding requests to C<$nreqs>. If you |
315 | try to queue up more than this number of requests, the caller will block until |
495 | try to queue up more than this number of requests, the caller will block until |
316 | some requests have been handled. |
496 | some requests have been handled. |
317 | |
497 | |
318 | The default is very large, so normally there is no practical limit. If you |
498 | The default is very large, so normally there is no practical limit. If you |
319 | queue up many requests in a loop it it often improves speed if you set |
499 | queue up many requests in a loop it often improves speed if you set |
320 | this to a relatively low number, such as C<100>. |
500 | this to a relatively low number, such as C<100>. |
321 | |
501 | |
322 | Under normal circumstances you don't need to call this function. |
502 | Under normal circumstances you don't need to call this function. |
323 | |
503 | |
324 | =back |
504 | =back |
… | |
… | |
349 | |
529 | |
350 | 1; |
530 | 1; |
351 | |
531 | |
352 | =head2 FORK BEHAVIOUR |
532 | =head2 FORK BEHAVIOUR |
353 | |
533 | |
354 | Before the fork IO::AIO first handles all outstanding requests - if other |
534 | Before the fork, IO::AIO enters a quiescent state where no requests |
355 | threads add requests during this period, this time is prolonged. It then |
535 | can be added in other threads and no results will be processed. After |
356 | enters a quiescent state where no requests can be added in other threads |
536 | the fork the parent simply leaves the quiescent state and continues |
357 | and no results will be processed. After the fork the parent simply leaves |
537 | request/result processing, while the child clears the request/result |
358 | the quiescent state and continues request processing, while the child will |
538 | queue (so the requests started before the fork will only be handled in |
359 | free the request and result queue and start the same number of threads as |
539 | the parent). Threats will be started on demand until the limit ste in the |
360 | were in use by the parent. |
540 | parent process has been reached again. |
361 | |
541 | |
362 | =head1 SEE ALSO |
542 | =head1 SEE ALSO |
363 | |
543 | |
364 | L<Coro>, L<Linux::AIO>. |
544 | L<Coro>, L<Linux::AIO>. |
365 | |
545 | |