… | |
… | |
18 | }; |
18 | }; |
19 | |
19 | |
20 | # version 2+ has request and group objects |
20 | # version 2+ has request and group objects |
21 | use IO::AIO 2; |
21 | use IO::AIO 2; |
22 | |
22 | |
|
|
23 | aioreq_pri 4; # give next request a very high priority |
23 | my $req = aio_unlink "/tmp/file", sub { }; |
24 | my $req = aio_unlink "/tmp/file", sub { }; |
24 | $req->cancel; # cancel request if still in queue |
25 | $req->cancel; # cancel request if still in queue |
25 | |
26 | |
26 | my $grp = aio_group sub { print "all stats done\n" }; |
27 | my $grp = aio_group sub { print "all stats done\n" }; |
27 | add $grp aio_stat "..." for ...; |
28 | add $grp aio_stat "..." for ...; |
… | |
… | |
50 | =head1 DESCRIPTION |
51 | =head1 DESCRIPTION |
51 | |
52 | |
52 | This module implements asynchronous I/O using whatever means your |
53 | This module implements asynchronous I/O using whatever means your |
53 | operating system supports. |
54 | operating system supports. |
54 | |
55 | |
55 | Currently, a number of threads are started that execute your read/writes |
56 | In this version, a number of threads are started that execute your |
56 | and signal their completion. You don't need thread support in your libc or |
57 | requests and signal their completion. You don't need thread support |
57 | perl, and the threads created by this module will not be visible to the |
58 | in perl, and the threads created by this module will not be visible |
58 | pthreads library. In the future, this module might make use of the native |
59 | to perl. In the future, this module might make use of the native aio |
59 | aio functions available on many operating systems. However, they are often |
60 | functions available on many operating systems. However, they are often |
60 | not well-supported (Linux doesn't allow them on normal files currently, |
61 | not well-supported or restricted (Linux doesn't allow them on normal |
61 | for example), and they would only support aio_read and aio_write, so the |
62 | files currently, for example), and they would only support aio_read and |
62 | remaining functionality would have to be implemented using threads anyway. |
63 | aio_write, so the remaining functionality would have to be implemented |
|
|
64 | using threads anyway. |
63 | |
65 | |
64 | Although the module will work with in the presence of other threads, it is |
66 | Although the module will work with in the presence of other (Perl-) |
65 | currently not reentrant, so use appropriate locking yourself, always call |
67 | threads, it is currently not reentrant in any way, so use appropriate |
66 | C<poll_cb> from within the same thread, or never call C<poll_cb> (or other |
68 | locking yourself, always call C<poll_cb> from within the same thread, or |
67 | C<aio_> functions) recursively. |
69 | never call C<poll_cb> (or other C<aio_> functions) recursively. |
|
|
70 | |
|
|
71 | =head1 REQUEST ANATOMY AND LIFETIME |
|
|
72 | |
|
|
73 | Every C<aio_*> function creates a request. which is a C data structure not |
|
|
74 | directly visible to Perl. |
|
|
75 | |
|
|
76 | If called in non-void context, every request function returns a Perl |
|
|
77 | object representing the request. In void context, nothing is returned, |
|
|
78 | which saves a bit of memory. |
|
|
79 | |
|
|
80 | The perl object is a fairly standard ref-to-hash object. The hash contents |
|
|
81 | are not used by IO::AIO so you are free to store anything you like in it. |
|
|
82 | |
|
|
83 | During their existance, aio requests travel through the following states, |
|
|
84 | in order: |
|
|
85 | |
|
|
86 | =over 4 |
|
|
87 | |
|
|
88 | =item ready |
|
|
89 | |
|
|
90 | Immediately after a request is created it is put into the ready state, |
|
|
91 | waiting for a thread to execute it. |
|
|
92 | |
|
|
93 | =item execute |
|
|
94 | |
|
|
95 | A thread has accepted the request for processing and is currently |
|
|
96 | executing it (e.g. blocking in read). |
|
|
97 | |
|
|
98 | =item pending |
|
|
99 | |
|
|
100 | The request has been executed and is waiting for result processing. |
|
|
101 | |
|
|
102 | While request submission and execution is fully asynchronous, result |
|
|
103 | processing is not and relies on the perl interpreter calling C<poll_cb> |
|
|
104 | (or another function with the same effect). |
|
|
105 | |
|
|
106 | =item result |
|
|
107 | |
|
|
108 | The request results are processed synchronously by C<poll_cb>. |
|
|
109 | |
|
|
110 | The C<poll_cb> function will process all outstanding aio requests by |
|
|
111 | calling their callbacks, freeing memory associated with them and managing |
|
|
112 | any groups they are contained in. |
|
|
113 | |
|
|
114 | =item done |
|
|
115 | |
|
|
116 | Request has reached the end of its lifetime and holds no resources anymore |
|
|
117 | (except possibly for the Perl object, but its connection to the actual |
|
|
118 | aio request is severed and calling its methods will either do nothing or |
|
|
119 | result in a runtime error). |
68 | |
120 | |
69 | =cut |
121 | =cut |
70 | |
122 | |
71 | package IO::AIO; |
123 | package IO::AIO; |
72 | |
124 | |
… | |
… | |
76 | use base 'Exporter'; |
128 | use base 'Exporter'; |
77 | |
129 | |
78 | BEGIN { |
130 | BEGIN { |
79 | our $VERSION = '2.0'; |
131 | our $VERSION = '2.0'; |
80 | |
132 | |
81 | our @EXPORT = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat |
133 | our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat |
82 | aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink |
134 | aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink |
83 | aio_fsync aio_fdatasync aio_readahead aio_rename aio_link aio_move |
135 | aio_fsync aio_fdatasync aio_readahead aio_rename aio_link aio_move |
84 | aio_group aio_nop); |
136 | aio_copy aio_group aio_nop aio_mknod); |
85 | our @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs); |
137 | our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice)); |
|
|
138 | our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush |
|
|
139 | min_parallel max_parallel nreqs nready npending); |
86 | |
140 | |
87 | @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; |
141 | @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; |
88 | |
142 | |
89 | require XSLoader; |
143 | require XSLoader; |
90 | XSLoader::load ("IO::AIO", $VERSION); |
144 | XSLoader::load ("IO::AIO", $VERSION); |
… | |
… | |
121 | environment, d) use Glib::filename_from_unicode on unicode filenames or e) |
175 | environment, d) use Glib::filename_from_unicode on unicode filenames or e) |
122 | use something else. |
176 | use something else. |
123 | |
177 | |
124 | =over 4 |
178 | =over 4 |
125 | |
179 | |
|
|
180 | =item $prev_pri = aioreq_pri [$pri] |
|
|
181 | |
|
|
182 | Returns the priority value that would be used for the next request and, if |
|
|
183 | C<$pri> is given, sets the priority for the next aio request. |
|
|
184 | |
|
|
185 | The default priority is C<0>, the minimum and maximum priorities are C<-4> |
|
|
186 | and C<4>, respectively. Requests with higher priority will be serviced |
|
|
187 | first. |
|
|
188 | |
|
|
189 | The priority will be reset to C<0> after each call to one of the C<aio_*> |
|
|
190 | functions. |
|
|
191 | |
|
|
192 | Example: open a file with low priority, then read something from it with |
|
|
193 | higher priority so the read request is serviced before other low priority |
|
|
194 | open requests (potentially spamming the cache): |
|
|
195 | |
|
|
196 | aioreq_pri -3; |
|
|
197 | aio_open ..., sub { |
|
|
198 | return unless $_[0]; |
|
|
199 | |
|
|
200 | aioreq_pri -2; |
|
|
201 | aio_read $_[0], ..., sub { |
|
|
202 | ... |
|
|
203 | }; |
|
|
204 | }; |
|
|
205 | |
|
|
206 | =item aioreq_nice $pri_adjust |
|
|
207 | |
|
|
208 | Similar to C<aioreq_pri>, but subtracts the given value from the current |
|
|
209 | priority, so effects are cumulative. |
|
|
210 | |
126 | =item aio_open $pathname, $flags, $mode, $callback->($fh) |
211 | =item aio_open $pathname, $flags, $mode, $callback->($fh) |
127 | |
212 | |
128 | Asynchronously open or create a file and call the callback with a newly |
213 | Asynchronously open or create a file and call the callback with a newly |
129 | created filehandle for the file. |
214 | created filehandle for the file. |
130 | |
215 | |
… | |
… | |
179 | |
264 | |
180 | aio_read $fh, 7, 15, $buffer, 0, sub { |
265 | aio_read $fh, 7, 15, $buffer, 0, sub { |
181 | $_[0] > 0 or die "read error: $!"; |
266 | $_[0] > 0 or die "read error: $!"; |
182 | print "read $_[0] bytes: <$buffer>\n"; |
267 | print "read $_[0] bytes: <$buffer>\n"; |
183 | }; |
268 | }; |
184 | |
|
|
185 | =item aio_move $srcpath, $dstpath, $callback->($status) |
|
|
186 | |
|
|
187 | [EXPERIMENTAL due to internal aio_group use] |
|
|
188 | |
|
|
189 | Try to move the I<file> (directories not supported as either source or |
|
|
190 | destination) from C<$srcpath> to C<$dstpath> and call the callback with |
|
|
191 | the C<0> (error) or C<-1> ok. |
|
|
192 | |
|
|
193 | This is a composite request that tries to rename(2) the file first. If |
|
|
194 | rename files with C<EXDEV>, it creates the destination file with mode 0200 |
|
|
195 | and copies the contents of the source file into it using C<aio_sendfile>, |
|
|
196 | followed by restoring atime, mtime, access mode and uid/gid, in that |
|
|
197 | order, and unlinking the C<$srcpath>. |
|
|
198 | |
|
|
199 | If an error occurs, the partial destination file will be unlinked, if |
|
|
200 | possible, except when setting atime, mtime, access mode and uid/gid, where |
|
|
201 | errors are being ignored. |
|
|
202 | |
|
|
203 | =cut |
|
|
204 | |
|
|
205 | sub aio_move($$$) { |
|
|
206 | my ($src, $dst, $cb) = @_; |
|
|
207 | |
|
|
208 | my $grp = aio_group $cb; |
|
|
209 | |
|
|
210 | add $grp aio_rename $src, $dst, sub { |
|
|
211 | if ($_[0] && $! == EXDEV) { |
|
|
212 | add $grp aio_open $src, O_RDONLY, 0, sub { |
|
|
213 | if (my $src_fh = $_[0]) { |
|
|
214 | my @stat = stat $src_fh; |
|
|
215 | |
|
|
216 | add $grp aio_open $dst, O_WRONLY, 0200, sub { |
|
|
217 | if (my $dst_fh = $_[0]) { |
|
|
218 | add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub { |
|
|
219 | close $src_fh; |
|
|
220 | |
|
|
221 | if ($_[0] == $stat[7]) { |
|
|
222 | utime $stat[8], $stat[9], $dst; |
|
|
223 | chmod $stat[2] & 07777, $dst_fh; |
|
|
224 | chown $stat[4], $stat[5], $dst_fh; |
|
|
225 | close $dst_fh; |
|
|
226 | |
|
|
227 | add $grp aio_unlink $src, sub { |
|
|
228 | $grp->result ($_[0]); |
|
|
229 | }; |
|
|
230 | } else { |
|
|
231 | my $errno = $!; |
|
|
232 | add $grp aio_unlink $dst, sub { |
|
|
233 | $! = $errno; |
|
|
234 | $grp->result (-1); |
|
|
235 | }; |
|
|
236 | } |
|
|
237 | }; |
|
|
238 | } else { |
|
|
239 | $grp->result (-1); |
|
|
240 | } |
|
|
241 | }, |
|
|
242 | |
|
|
243 | } else { |
|
|
244 | $grp->result (-1); |
|
|
245 | } |
|
|
246 | }; |
|
|
247 | } else { |
|
|
248 | $grp->result ($_[0]); |
|
|
249 | } |
|
|
250 | }; |
|
|
251 | |
|
|
252 | $grp |
|
|
253 | } |
|
|
254 | |
269 | |
255 | =item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) |
270 | =item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) |
256 | |
271 | |
257 | Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts |
272 | Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts |
258 | reading at byte offset C<$in_offset>, and starts writing at the current |
273 | reading at byte offset C<$in_offset>, and starts writing at the current |
… | |
… | |
314 | =item aio_unlink $pathname, $callback->($status) |
329 | =item aio_unlink $pathname, $callback->($status) |
315 | |
330 | |
316 | Asynchronously unlink (delete) a file and call the callback with the |
331 | Asynchronously unlink (delete) a file and call the callback with the |
317 | result code. |
332 | result code. |
318 | |
333 | |
|
|
334 | =item aio_mknod $path, $mode, $dev, $callback->($status) |
|
|
335 | |
|
|
336 | Asynchronously create a device node (or fifo). See mknod(2): the only |
|
|
337 | portable value for C<$mode> is C<S_IFIFO> ored with permissions, and C<0> |
|
|
338 | for C<$dev>. |
|
|
339 | |
319 | =item aio_link $srcpath, $dstpath, $callback->($status) |
340 | =item aio_link $srcpath, $dstpath, $callback->($status) |
320 | |
341 | |
321 | Asynchronously create a new link to the existing object at C<$srcpath> at |
342 | Asynchronously create a new link to the existing object at C<$srcpath> at |
322 | the path C<$dstpath> and call the callback with the result code. |
343 | the path C<$dstpath> and call the callback with the result code. |
323 | |
344 | |
… | |
… | |
343 | sorted, and will B<NOT> include the C<.> and C<..> entries. |
364 | sorted, and will B<NOT> include the C<.> and C<..> entries. |
344 | |
365 | |
345 | The callback a single argument which is either C<undef> or an array-ref |
366 | The callback a single argument which is either C<undef> or an array-ref |
346 | with the filenames. |
367 | with the filenames. |
347 | |
368 | |
|
|
369 | =item aio_copy $srcpath, $dstpath, $callback->($status) |
|
|
370 | |
|
|
371 | Try to copy the I<file> (directories not supported as either source or |
|
|
372 | destination) from C<$srcpath> to C<$dstpath> and call the callback with |
|
|
373 | the C<0> (error) or C<-1> ok. |
|
|
374 | |
|
|
375 | This is a composite request that it creates the destination file with |
|
|
376 | mode 0200 and copies the contents of the source file into it using |
|
|
377 | C<aio_sendfile>, followed by restoring atime, mtime, access mode and |
|
|
378 | uid/gid, in that order. |
|
|
379 | |
|
|
380 | If an error occurs, the partial destination file will be unlinked, if |
|
|
381 | possible, except when setting atime, mtime, access mode and uid/gid, where |
|
|
382 | errors are being ignored. |
|
|
383 | |
|
|
384 | =cut |
|
|
385 | |
|
|
386 | sub aio_copy($$;$) { |
|
|
387 | my ($src, $dst, $cb) = @_; |
|
|
388 | |
|
|
389 | my $pri = aioreq_pri; |
|
|
390 | my $grp = aio_group $cb; |
|
|
391 | |
|
|
392 | aioreq_pri $pri; |
|
|
393 | add $grp aio_open $src, O_RDONLY, 0, sub { |
|
|
394 | if (my $src_fh = $_[0]) { |
|
|
395 | my @stat = stat $src_fh; |
|
|
396 | |
|
|
397 | aioreq_pri $pri; |
|
|
398 | add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub { |
|
|
399 | if (my $dst_fh = $_[0]) { |
|
|
400 | aioreq_pri $pri; |
|
|
401 | add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub { |
|
|
402 | if ($_[0] == $stat[7]) { |
|
|
403 | $grp->result (0); |
|
|
404 | close $src_fh; |
|
|
405 | |
|
|
406 | # those should not normally block. should. should. |
|
|
407 | utime $stat[8], $stat[9], $dst; |
|
|
408 | chmod $stat[2] & 07777, $dst_fh; |
|
|
409 | chown $stat[4], $stat[5], $dst_fh; |
|
|
410 | close $dst_fh; |
|
|
411 | } else { |
|
|
412 | $grp->result (-1); |
|
|
413 | close $src_fh; |
|
|
414 | close $dst_fh; |
|
|
415 | |
|
|
416 | aioreq $pri; |
|
|
417 | add $grp aio_unlink $dst; |
|
|
418 | } |
|
|
419 | }; |
|
|
420 | } else { |
|
|
421 | $grp->result (-1); |
|
|
422 | } |
|
|
423 | }, |
|
|
424 | |
|
|
425 | } else { |
|
|
426 | $grp->result (-1); |
|
|
427 | } |
|
|
428 | }; |
|
|
429 | |
|
|
430 | $grp |
|
|
431 | } |
|
|
432 | |
|
|
433 | =item aio_move $srcpath, $dstpath, $callback->($status) |
|
|
434 | |
|
|
435 | Try to move the I<file> (directories not supported as either source or |
|
|
436 | destination) from C<$srcpath> to C<$dstpath> and call the callback with |
|
|
437 | the C<0> (error) or C<-1> ok. |
|
|
438 | |
|
|
439 | This is a composite request that tries to rename(2) the file first. If |
|
|
440 | rename files with C<EXDEV>, it copies the file with C<aio_copy> and, if |
|
|
441 | that is successful, unlinking the C<$srcpath>. |
|
|
442 | |
|
|
443 | =cut |
|
|
444 | |
|
|
445 | sub aio_move($$;$) { |
|
|
446 | my ($src, $dst, $cb) = @_; |
|
|
447 | |
|
|
448 | my $pri = aioreq_pri; |
|
|
449 | my $grp = aio_group $cb; |
|
|
450 | |
|
|
451 | aioreq_pri $pri; |
|
|
452 | add $grp aio_rename $src, $dst, sub { |
|
|
453 | if ($_[0] && $! == EXDEV) { |
|
|
454 | aioreq_pri $pri; |
|
|
455 | add $grp aio_copy $src, $dst, sub { |
|
|
456 | $grp->result ($_[0]); |
|
|
457 | |
|
|
458 | if (!$_[0]) { |
|
|
459 | aioreq_pri $pri; |
|
|
460 | add $grp aio_unlink $src; |
|
|
461 | } |
|
|
462 | }; |
|
|
463 | } else { |
|
|
464 | $grp->result ($_[0]); |
|
|
465 | } |
|
|
466 | }; |
|
|
467 | |
|
|
468 | $grp |
|
|
469 | } |
|
|
470 | |
348 | =item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) |
471 | =item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) |
349 | |
472 | |
350 | [EXPERIMENTAL due to internal aio_group use] |
|
|
351 | |
|
|
352 | Scans a directory (similar to C<aio_readdir>) but additionally tries to |
473 | Scans a directory (similar to C<aio_readdir>) but additionally tries to |
353 | separate the entries of directory C<$path> into two sets of names, ones |
474 | efficiently separate the entries of directory C<$path> into two sets of |
354 | you can recurse into (directories or links to them), and ones you cannot |
475 | names, directories you can recurse into (directories), and ones you cannot |
355 | recurse into (everything else). |
476 | recurse into (everything else, including symlinks to directories). |
356 | |
477 | |
357 | C<aio_scandir> is a composite request that creates of many sub requests_ |
478 | C<aio_scandir> is a composite request that creates of many sub requests_ |
358 | C<$maxreq> specifies the maximum number of outstanding aio requests that |
479 | C<$maxreq> specifies the maximum number of outstanding aio requests that |
359 | this function generates. If it is C<< <= 0 >>, then a suitable default |
480 | this function generates. If it is C<< <= 0 >>, then a suitable default |
360 | will be chosen (currently 6). |
481 | will be chosen (currently 4). |
361 | |
482 | |
362 | On error, the callback is called without arguments, otherwise it receives |
483 | On error, the callback is called without arguments, otherwise it receives |
363 | two array-refs with path-relative entry names. |
484 | two array-refs with path-relative entry names. |
364 | |
485 | |
365 | Example: |
486 | Example: |
… | |
… | |
402 | =cut |
523 | =cut |
403 | |
524 | |
404 | sub aio_scandir($$$) { |
525 | sub aio_scandir($$$) { |
405 | my ($path, $maxreq, $cb) = @_; |
526 | my ($path, $maxreq, $cb) = @_; |
406 | |
527 | |
|
|
528 | my $pri = aioreq_pri; |
|
|
529 | |
407 | my $grp = aio_group $cb; |
530 | my $grp = aio_group $cb; |
408 | |
531 | |
409 | $maxreq = 6 if $maxreq <= 0; |
532 | $maxreq = 4 if $maxreq <= 0; |
410 | |
533 | |
411 | # stat once |
534 | # stat once |
|
|
535 | aioreq_pri $pri; |
412 | add $grp aio_stat $path, sub { |
536 | add $grp aio_stat $path, sub { |
413 | return $grp->result () if $_[0]; |
537 | return $grp->result () if $_[0]; |
414 | my $now = time; |
538 | my $now = time; |
415 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
539 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
416 | |
540 | |
417 | # read the directory entries |
541 | # read the directory entries |
|
|
542 | aioreq_pri $pri; |
418 | add $grp aio_readdir $path, sub { |
543 | add $grp aio_readdir $path, sub { |
419 | my $entries = shift |
544 | my $entries = shift |
420 | or return $grp->result (); |
545 | or return $grp->result (); |
421 | |
546 | |
422 | # stat the dir another time |
547 | # stat the dir another time |
|
|
548 | aioreq_pri $pri; |
423 | add $grp aio_stat $path, sub { |
549 | add $grp aio_stat $path, sub { |
424 | my $hash2 = join ":", (stat _)[0,1,3,7,9]; |
550 | my $hash2 = join ":", (stat _)[0,1,3,7,9]; |
425 | |
551 | |
426 | my $ndirs; |
552 | my $ndirs; |
427 | |
553 | |
… | |
… | |
442 | map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length], |
568 | map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length], |
443 | @$entries]; |
569 | @$entries]; |
444 | |
570 | |
445 | my (@dirs, @nondirs); |
571 | my (@dirs, @nondirs); |
446 | |
572 | |
447 | my ($statcb, $schedcb); |
|
|
448 | my $nreq = 0; |
|
|
449 | |
|
|
450 | my $statgrp = add $grp aio_group; |
573 | my $statgrp = add $grp aio_group sub { |
|
|
574 | $grp->result (\@dirs, \@nondirs); |
|
|
575 | }; |
451 | |
576 | |
452 | $schedcb = sub { |
577 | limit $statgrp $maxreq; |
453 | if (@$entries) { |
578 | feed $statgrp sub { |
454 | if ($nreq < $maxreq) { |
579 | return unless @$entries; |
455 | my $ent = pop @$entries; |
580 | my $entry = pop @$entries; |
|
|
581 | |
|
|
582 | aioreq_pri $pri; |
|
|
583 | add $statgrp aio_stat "$path/$entry/.", sub { |
|
|
584 | if ($_[0] < 0) { |
|
|
585 | push @nondirs, $entry; |
|
|
586 | } else { |
|
|
587 | # need to check for real directory |
|
|
588 | aioreq_pri $pri; |
|
|
589 | add $statgrp aio_lstat "$path/$entry", sub { |
|
|
590 | if (-d _) { |
|
|
591 | push @dirs, $entry; |
|
|
592 | |
|
|
593 | unless (--$ndirs) { |
|
|
594 | push @nondirs, @$entries; |
|
|
595 | feed $statgrp; |
|
|
596 | } |
|
|
597 | } else { |
|
|
598 | push @nondirs, $entry; |
|
|
599 | } |
456 | $nreq++; |
600 | } |
457 | add $statgrp aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) }; |
|
|
458 | } |
601 | } |
459 | } elsif (!$nreq) { |
|
|
460 | # finished |
|
|
461 | $statgrp->cancel; |
|
|
462 | undef $statcb; |
|
|
463 | undef $schedcb; |
|
|
464 | $grp->result (\@dirs, \@nondirs); |
|
|
465 | } |
602 | }; |
466 | }; |
603 | }; |
467 | $statcb = sub { |
|
|
468 | my ($status, $entry) = @_; |
|
|
469 | |
|
|
470 | if ($status < 0) { |
|
|
471 | $nreq--; |
|
|
472 | push @nondirs, $entry; |
|
|
473 | &$schedcb; |
|
|
474 | } else { |
|
|
475 | # need to check for real directory |
|
|
476 | add $grp aio_lstat "$path/$entry", sub { |
|
|
477 | $nreq--; |
|
|
478 | |
|
|
479 | if (-d _) { |
|
|
480 | push @dirs, $entry; |
|
|
481 | |
|
|
482 | if (!--$ndirs) { |
|
|
483 | push @nondirs, @$entries; |
|
|
484 | $entries = []; |
|
|
485 | } |
|
|
486 | } else { |
|
|
487 | push @nondirs, $entry; |
|
|
488 | } |
|
|
489 | |
|
|
490 | &$schedcb; |
|
|
491 | } |
|
|
492 | } |
|
|
493 | }; |
|
|
494 | |
|
|
495 | &$schedcb while @$entries && $nreq < $maxreq; |
|
|
496 | }; |
604 | }; |
497 | }; |
605 | }; |
498 | }; |
606 | }; |
499 | |
607 | |
500 | $grp |
608 | $grp |
… | |
… | |
513 | If this call isn't available because your OS lacks it or it couldn't be |
621 | If this call isn't available because your OS lacks it or it couldn't be |
514 | detected, it will be emulated by calling C<fsync> instead. |
622 | detected, it will be emulated by calling C<fsync> instead. |
515 | |
623 | |
516 | =item aio_group $callback->(...) |
624 | =item aio_group $callback->(...) |
517 | |
625 | |
518 | [EXPERIMENTAL] |
|
|
519 | |
|
|
520 | This is a very special aio request: Instead of doing something, it is a |
626 | This is a very special aio request: Instead of doing something, it is a |
521 | container for other aio requests, which is useful if you want to bundle |
627 | container for other aio requests, which is useful if you want to bundle |
522 | many requests into a single, composite, request. |
628 | many requests into a single, composite, request with a definite callback |
|
|
629 | and the ability to cancel the whole request with its subrequests. |
523 | |
630 | |
524 | Returns an object of class L<IO::AIO::GRP>. See its documentation below |
631 | Returns an object of class L<IO::AIO::GRP>. See its documentation below |
525 | for more info. |
632 | for more info. |
526 | |
633 | |
527 | Example: |
634 | Example: |
… | |
… | |
546 | phase and still requires a worker thread. Thus, the callback will not |
653 | phase and still requires a worker thread. Thus, the callback will not |
547 | be executed immediately but only after other requests in the queue have |
654 | be executed immediately but only after other requests in the queue have |
548 | entered their execution phase. This can be used to measure request |
655 | entered their execution phase. This can be used to measure request |
549 | latency. |
656 | latency. |
550 | |
657 | |
551 | =item IO::AIO::aio_sleep $fractional_seconds, $callback->() *NOT EXPORTED* |
658 | =item IO::AIO::aio_busy $fractional_seconds, $callback->() *NOT EXPORTED* |
552 | |
659 | |
553 | Mainly used for debugging and benchmarking, this aio request puts one of |
660 | Mainly used for debugging and benchmarking, this aio request puts one of |
554 | the request workers to sleep for the given time. |
661 | the request workers to sleep for the given time. |
555 | |
662 | |
556 | While it is theoretically handy to have simple I/O scheduling requests |
663 | While it is theoretically handy to have simple I/O scheduling requests |
557 | like sleep and file handle readable/writable, the overhead this creates |
664 | like sleep and file handle readable/writable, the overhead this creates is |
558 | is immense, so do not use this function except to put your application |
665 | immense (it blocks a thread for a long time) so do not use this function |
559 | under artificial I/O pressure. |
666 | except to put your application under artificial I/O pressure. |
560 | |
667 | |
561 | =back |
668 | =back |
562 | |
669 | |
563 | =head2 IO::AIO::REQ CLASS |
670 | =head2 IO::AIO::REQ CLASS |
564 | |
671 | |
565 | All non-aggregate C<aio_*> functions return an object of this class when |
672 | All non-aggregate C<aio_*> functions return an object of this class when |
566 | called in non-void context. |
673 | called in non-void context. |
567 | |
674 | |
568 | A request always moves through the following five states in its lifetime, |
|
|
569 | in order: B<ready> (request has been created, but has not been executed |
|
|
570 | yet), B<execute> (request is currently being executed), B<pending> |
|
|
571 | (request has been executed but callback has not been called yet), |
|
|
572 | B<result> (results are being processed synchronously, includes calling the |
|
|
573 | callback) and B<done> (request has reached the end of its lifetime and |
|
|
574 | holds no resources anymore). |
|
|
575 | |
|
|
576 | =over 4 |
675 | =over 4 |
577 | |
676 | |
578 | =item $req->cancel |
677 | =item cancel $req |
579 | |
678 | |
580 | Cancels the request, if possible. Has the effect of skipping execution |
679 | Cancels the request, if possible. Has the effect of skipping execution |
581 | when entering the B<execute> state and skipping calling the callback when |
680 | when entering the B<execute> state and skipping calling the callback when |
582 | entering the the B<result> state, but will leave the request otherwise |
681 | entering the the B<result> state, but will leave the request otherwise |
583 | untouched. That means that requests that currently execute will not be |
682 | untouched. That means that requests that currently execute will not be |
584 | stopped and resources held by the request will not be freed prematurely. |
683 | stopped and resources held by the request will not be freed prematurely. |
585 | |
684 | |
|
|
685 | =item cb $req $callback->(...) |
|
|
686 | |
|
|
687 | Replace (or simply set) the callback registered to the request. |
|
|
688 | |
586 | =back |
689 | =back |
587 | |
690 | |
588 | =head2 IO::AIO::GRP CLASS |
691 | =head2 IO::AIO::GRP CLASS |
589 | |
692 | |
590 | This class is a subclass of L<IO::AIO::REQ>, so all its methods apply to |
693 | This class is a subclass of L<IO::AIO::REQ>, so all its methods apply to |
… | |
… | |
629 | =item * They can also can also be added to other IO::AIO::GRP objects. |
732 | =item * They can also can also be added to other IO::AIO::GRP objects. |
630 | |
733 | |
631 | =item * You must not add requests to a group from within the group callback (or |
734 | =item * You must not add requests to a group from within the group callback (or |
632 | any later time). |
735 | any later time). |
633 | |
736 | |
634 | =item * This does not harmonise well with C<max_outstanding>, so best do |
|
|
635 | not combine C<aio_group> with it. Groups and feeders are recommended for |
|
|
636 | this kind of concurrency-limiting. |
|
|
637 | |
|
|
638 | =back |
737 | =back |
639 | |
738 | |
640 | Their lifetime, simplified, looks like this: when they are empty, they |
739 | Their lifetime, simplified, looks like this: when they are empty, they |
641 | will finish very quickly. If they contain only requests that are in the |
740 | will finish very quickly. If they contain only requests that are in the |
642 | C<done> state, they will also finish. Otherwise they will continue to |
741 | C<done> state, they will also finish. Otherwise they will continue to |
… | |
… | |
647 | group. And only when all those requests have finished will the the group |
746 | group. And only when all those requests have finished will the the group |
648 | itself finish. |
747 | itself finish. |
649 | |
748 | |
650 | =over 4 |
749 | =over 4 |
651 | |
750 | |
|
|
751 | =item add $grp ... |
|
|
752 | |
652 | =item $grp->add (...) |
753 | =item $grp->add (...) |
653 | |
|
|
654 | =item add $grp ... |
|
|
655 | |
754 | |
656 | Add one or more requests to the group. Any type of L<IO::AIO::REQ> can |
755 | Add one or more requests to the group. Any type of L<IO::AIO::REQ> can |
657 | be added, including other groups, as long as you do not create circular |
756 | be added, including other groups, as long as you do not create circular |
658 | dependencies. |
757 | dependencies. |
659 | |
758 | |
660 | Returns all its arguments. |
759 | Returns all its arguments. |
661 | |
760 | |
|
|
761 | =item $grp->cancel_subs |
|
|
762 | |
|
|
763 | Cancel all subrequests and clears any feeder, but not the group request |
|
|
764 | itself. Useful when you queued a lot of events but got a result early. |
|
|
765 | |
662 | =item $grp->result (...) |
766 | =item $grp->result (...) |
663 | |
767 | |
664 | Set the result value(s) that will be passed to the group callback when all |
768 | Set the result value(s) that will be passed to the group callback when all |
665 | subrequests have finished. By default, no argument will be passed. |
769 | subrequests have finished and set thre groups errno to the current value |
|
|
770 | of errno (just like calling C<errno> without an error number). By default, |
|
|
771 | no argument will be passed and errno is zero. |
666 | |
772 | |
667 | =item $grp->set_feeder ($callback->($grp)) |
773 | =item $grp->errno ([$errno]) |
668 | |
774 | |
669 | [VERY EXPERIMENTAL] |
775 | Sets the group errno value to C<$errno>, or the current value of errno |
|
|
776 | when the argument is missing. |
|
|
777 | |
|
|
778 | Every aio request has an associated errno value that is restored when |
|
|
779 | the callback is invoked. This method lets you change this value from its |
|
|
780 | default (0). |
|
|
781 | |
|
|
782 | Calling C<result> will also set errno, so make sure you either set C<$!> |
|
|
783 | before the call to C<result>, or call c<errno> after it. |
|
|
784 | |
|
|
785 | =item feed $grp $callback->($grp) |
670 | |
786 | |
671 | Sets a feeder/generator on this group: every group can have an attached |
787 | Sets a feeder/generator on this group: every group can have an attached |
672 | generator that generates requests if idle. The idea behind this is that, |
788 | generator that generates requests if idle. The idea behind this is that, |
673 | although you could just queue as many requests as you want in a group, |
789 | although you could just queue as many requests as you want in a group, |
674 | this might starve other requests for a potentially long time. For |
790 | this might starve other requests for a potentially long time. For |
675 | example, C<aio_scandir> might generate hundreds of thousands C<aio_stat> |
791 | example, C<aio_scandir> might generate hundreds of thousands C<aio_stat> |
676 | requests, delaying any later requests for a long time. |
792 | requests, delaying any later requests for a long time. |
677 | |
793 | |
678 | To avoid this, and allow incremental generation of requests, you can |
794 | To avoid this, and allow incremental generation of requests, you can |
679 | instead a group and set a feeder on it that generates those requests. The |
795 | instead a group and set a feeder on it that generates those requests. The |
680 | feeder will be called whenever there are few enough (see C<feeder_limit>, |
796 | feed callback will be called whenever there are few enough (see C<limit>, |
681 | below) requests active in the group itself and is expected to queue more |
797 | below) requests active in the group itself and is expected to queue more |
682 | requests. |
798 | requests. |
683 | |
799 | |
684 | The feeder can queue as many requests as it likes (i.e. C<add> does not |
800 | The feed callback can queue as many requests as it likes (i.e. C<add> does |
685 | impose any limits). |
801 | not impose any limits). |
686 | |
802 | |
687 | If the feeder does not queue more requests when called, it will be |
803 | If the feed does not queue more requests when called, it will be |
688 | automatically removed from the group. |
804 | automatically removed from the group. |
689 | |
805 | |
690 | If the feeder limit is C<0>, it will be set to C<2> automatically. |
806 | If the feed limit is C<0>, it will be set to C<2> automatically. |
691 | |
807 | |
692 | Example: |
808 | Example: |
693 | |
809 | |
694 | # stat all files in @files, but only ever use four aio requests concurrently: |
810 | # stat all files in @files, but only ever use four aio requests concurrently: |
695 | |
811 | |
696 | my $grp = aio_group sub { print "finished\n" }; |
812 | my $grp = aio_group sub { print "finished\n" }; |
697 | $grp->feeder_limit (4); |
813 | limit $grp 4; |
698 | $grp->set_feeder (sub { |
814 | feed $grp sub { |
699 | my $file = pop @files |
815 | my $file = pop @files |
700 | or return; |
816 | or return; |
701 | |
817 | |
702 | add $grp aio_stat $file, sub { ... }; |
818 | add $grp aio_stat $file, sub { ... }; |
703 | }); |
819 | }; |
704 | |
820 | |
705 | =item $grp->feeder_limit ($num) |
821 | =item limit $grp $num |
706 | |
822 | |
707 | Sets the feeder limit for the group: The feeder will be called whenever |
823 | Sets the feeder limit for the group: The feeder will be called whenever |
708 | the group contains less than this many requests. |
824 | the group contains less than this many requests. |
709 | |
825 | |
710 | Setting the limit to C<0> will pause the feeding process. |
826 | Setting the limit to C<0> will pause the feeding process. |
… | |
… | |
728 | |
844 | |
729 | Process all outstanding events on the result pipe. You have to call this |
845 | Process all outstanding events on the result pipe. You have to call this |
730 | regularly. Returns the number of events processed. Returns immediately |
846 | regularly. Returns the number of events processed. Returns immediately |
731 | when no events are outstanding. |
847 | when no events are outstanding. |
732 | |
848 | |
|
|
849 | If not all requests were processed for whatever reason, the filehandle |
|
|
850 | will still be ready when C<poll_cb> returns. |
|
|
851 | |
733 | Example: Install an Event watcher that automatically calls |
852 | Example: Install an Event watcher that automatically calls |
734 | IO::AIO::poll_cb with high priority: |
853 | IO::AIO::poll_cb with high priority: |
735 | |
854 | |
736 | Event->io (fd => IO::AIO::poll_fileno, |
855 | Event->io (fd => IO::AIO::poll_fileno, |
737 | poll => 'r', async => 1, |
856 | poll => 'r', async => 1, |
738 | cb => \&IO::AIO::poll_cb); |
857 | cb => \&IO::AIO::poll_cb); |
739 | |
858 | |
|
|
859 | =item IO::AIO::poll_some $max_requests |
|
|
860 | |
|
|
861 | Similar to C<poll_cb>, but only processes up to C<$max_requests> requests |
|
|
862 | at a time. |
|
|
863 | |
|
|
864 | Useful if you want to ensure some level of interactiveness when perl is |
|
|
865 | not fast enough to process all requests in time. |
|
|
866 | |
|
|
867 | Example: Install an Event watcher that automatically calls |
|
|
868 | IO::AIO::poll_some with low priority, to ensure that other parts of the |
|
|
869 | program get the CPU sometimes even under high AIO load. |
|
|
870 | |
|
|
871 | Event->io (fd => IO::AIO::poll_fileno, |
|
|
872 | poll => 'r', nice => 1, |
|
|
873 | cb => sub { IO::AIO::poll_some 256 }); |
|
|
874 | |
740 | =item IO::AIO::poll_wait |
875 | =item IO::AIO::poll_wait |
741 | |
876 | |
742 | Wait till the result filehandle becomes ready for reading (simply does a |
877 | Wait till the result filehandle becomes ready for reading (simply does a |
743 | C<select> on the filehandle. This is useful if you want to synchronously wait |
878 | C<select> on the filehandle. This is useful if you want to synchronously wait |
744 | for some requests to finish). |
879 | for some requests to finish). |
745 | |
880 | |
746 | See C<nreqs> for an example. |
881 | See C<nreqs> for an example. |
747 | |
882 | |
748 | =item IO::AIO::nreqs |
883 | =item IO::AIO::nreqs |
749 | |
884 | |
750 | Returns the number of requests currently outstanding (i.e. for which their |
885 | Returns the number of requests currently in the ready, execute or pending |
751 | callback has not been invoked yet). |
886 | states (i.e. for which their callback has not been invoked yet). |
752 | |
887 | |
753 | Example: wait till there are no outstanding requests anymore: |
888 | Example: wait till there are no outstanding requests anymore: |
754 | |
889 | |
755 | IO::AIO::poll_wait, IO::AIO::poll_cb |
890 | IO::AIO::poll_wait, IO::AIO::poll_cb |
756 | while IO::AIO::nreqs; |
891 | while IO::AIO::nreqs; |
|
|
892 | |
|
|
893 | =item IO::AIO::nready |
|
|
894 | |
|
|
895 | Returns the number of requests currently in the ready state (not yet |
|
|
896 | executed). |
|
|
897 | |
|
|
898 | =item IO::AIO::npending |
|
|
899 | |
|
|
900 | Returns the number of requests currently in the pending state (executed, |
|
|
901 | but not yet processed by poll_cb). |
757 | |
902 | |
758 | =item IO::AIO::flush |
903 | =item IO::AIO::flush |
759 | |
904 | |
760 | Wait till all outstanding AIO requests have been handled. |
905 | Wait till all outstanding AIO requests have been handled. |
761 | |
906 | |
… | |
… | |
803 | This module automatically runs C<max_parallel 0> at program end, to ensure |
948 | This module automatically runs C<max_parallel 0> at program end, to ensure |
804 | that all threads are killed and that there are no outstanding requests. |
949 | that all threads are killed and that there are no outstanding requests. |
805 | |
950 | |
806 | Under normal circumstances you don't need to call this function. |
951 | Under normal circumstances you don't need to call this function. |
807 | |
952 | |
808 | =item $oldnreqs = IO::AIO::max_outstanding $nreqs |
953 | =item $oldmaxreqs = IO::AIO::max_outstanding $maxreqs |
809 | |
954 | |
810 | [DEPRECATED] |
955 | This is a very bad function to use in interactive programs because it |
|
|
956 | blocks, and a bad way to reduce concurrency because it is inexact: Better |
|
|
957 | use an C<aio_group> together with a feed callback. |
811 | |
958 | |
812 | Sets the maximum number of outstanding requests to C<$nreqs>. If you |
959 | Sets the maximum number of outstanding requests to C<$nreqs>. If you |
813 | try to queue up more than this number of requests, the caller will block until |
960 | to queue up more than this number of requests, the next call to the |
814 | some requests have been handled. |
961 | C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>) |
|
|
962 | function will block until the limit is no longer exceeded. |
815 | |
963 | |
816 | The default is very large, so normally there is no practical limit. If you |
964 | The default value is very large, so there is no practical limit on the |
817 | queue up many requests in a loop it often improves speed if you set |
965 | number of outstanding requests. |
818 | this to a relatively low number, such as C<100>. |
|
|
819 | |
966 | |
820 | This function does not work well together with C<aio_group>'s, and their |
967 | You can still queue as many requests as you want. Therefore, |
821 | feeder interface is better suited to limiting concurrency, so do not use |
968 | C<max_oustsanding> is mainly useful in simple scripts (with low values) or |
822 | this function. |
969 | as a stop gap to shield against fatal memory overflow (with large values). |
823 | |
|
|
824 | Under normal circumstances you don't need to call this function. |
|
|
825 | |
970 | |
826 | =back |
971 | =back |
827 | |
972 | |
828 | =cut |
973 | =cut |
829 | |
974 | |
… | |
… | |
844 | } |
989 | } |
845 | |
990 | |
846 | min_parallel 8; |
991 | min_parallel 8; |
847 | |
992 | |
848 | END { |
993 | END { |
849 | max_parallel 0; |
994 | flush; |
850 | } |
995 | }; |
851 | |
996 | |
852 | 1; |
997 | 1; |
853 | |
998 | |
854 | =head2 FORK BEHAVIOUR |
999 | =head2 FORK BEHAVIOUR |
855 | |
1000 | |
856 | This module should do "the right thing" when the process using it forks: |
1001 | This module should do "the right thing" when the process using it forks: |
857 | |
1002 | |
858 | Before the fork, IO::AIO enters a quiescent state where no requests |
1003 | Before the fork, IO::AIO enters a quiescent state where no requests |
859 | can be added in other threads and no results will be processed. After |
1004 | can be added in other threads and no results will be processed. After |
860 | the fork the parent simply leaves the quiescent state and continues |
1005 | the fork the parent simply leaves the quiescent state and continues |
861 | request/result processing, while the child clears the request/result |
1006 | request/result processing, while the child frees the request/result queue |
862 | queue (so the requests started before the fork will only be handled in |
1007 | (so that the requests started before the fork will only be handled in the |
863 | the parent). Threads will be started on demand until the limit ste in the |
1008 | parent). Threads will be started on demand until the limit set in the |
864 | parent process has been reached again. |
1009 | parent process has been reached again. |
865 | |
1010 | |
866 | In short: the parent will, after a short pause, continue as if fork had |
1011 | In short: the parent will, after a short pause, continue as if fork had |
867 | not been called, while the child will act as if IO::AIO has not been used |
1012 | not been called, while the child will act as if IO::AIO has not been used |
868 | yet. |
1013 | yet. |
869 | |
1014 | |
870 | =head2 MEMORY USAGE |
1015 | =head2 MEMORY USAGE |
871 | |
1016 | |
|
|
1017 | Per-request usage: |
|
|
1018 | |
872 | Each aio request uses - depending on your architecture - around 128 bytes |
1019 | Each aio request uses - depending on your architecture - around 100-200 |
873 | of memory. In addition, stat requests need a stat buffer (possibly a few |
1020 | bytes of memory. In addition, stat requests need a stat buffer (possibly |
874 | hundred bytes). Perl scalars and other data passed into aio requests will |
1021 | a few hundred bytes), readdir requires a result buffer and so on. Perl |
875 | also be locked. |
1022 | scalars and other data passed into aio requests will also be locked and |
|
|
1023 | will consume memory till the request has entered the done state. |
876 | |
1024 | |
877 | This is now awfully much, so queuing lots of requests is not usually a |
1025 | This is now awfully much, so queuing lots of requests is not usually a |
878 | problem. |
1026 | problem. |
879 | |
1027 | |
880 | Each thread needs a stack area which is usually around 16k, sometimes much |
1028 | Per-thread usage: |
881 | larger, depending on the OS. |
1029 | |
|
|
1030 | In the execution phase, some aio requests require more memory for |
|
|
1031 | temporary buffers, and each thread requires a stack and other data |
|
|
1032 | structures (usually around 16k-128k, depending on the OS). |
|
|
1033 | |
|
|
1034 | =head1 KNOWN BUGS |
|
|
1035 | |
|
|
1036 | Known bugs will be fixed in the next release. |
882 | |
1037 | |
883 | =head1 SEE ALSO |
1038 | =head1 SEE ALSO |
884 | |
1039 | |
885 | L<Coro>, L<Linux::AIO> (obsolete). |
1040 | L<Coro::AIO>. |
886 | |
1041 | |
887 | =head1 AUTHOR |
1042 | =head1 AUTHOR |
888 | |
1043 | |
889 | Marc Lehmann <schmorp@schmorp.de> |
1044 | Marc Lehmann <schmorp@schmorp.de> |
890 | http://home.schmorp.de/ |
1045 | http://home.schmorp.de/ |