… | |
… | |
26 | $req->cancel; # cancel request if still in queue |
26 | $req->cancel; # cancel request if still in queue |
27 | |
27 | |
28 | my $grp = aio_group sub { print "all stats done\n" }; |
28 | my $grp = aio_group sub { print "all stats done\n" }; |
29 | add $grp aio_stat "..." for ...; |
29 | add $grp aio_stat "..." for ...; |
30 | |
30 | |
|
|
31 | # AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...) |
|
|
32 | use AnyEvent::AIO; |
|
|
33 | |
31 | # AnyEvent integration |
34 | # EV integration |
32 | open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!"; |
35 | my $w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; |
33 | my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb }); |
|
|
34 | |
36 | |
35 | # Event integration |
37 | # Event integration |
36 | Event->io (fd => IO::AIO::poll_fileno, |
38 | Event->io (fd => IO::AIO::poll_fileno, |
37 | poll => 'r', |
39 | poll => 'r', |
38 | cb => \&IO::AIO::poll_cb); |
40 | cb => \&IO::AIO::poll_cb); |
… | |
… | |
62 | etc.), but can also be used to easily do operations in parallel that are |
64 | etc.), but can also be used to easily do operations in parallel that are |
63 | normally done sequentially, e.g. stat'ing many files, which is much faster |
65 | normally done sequentially, e.g. stat'ing many files, which is much faster |
64 | on a RAID volume or over NFS when you do a number of stat operations |
66 | on a RAID volume or over NFS when you do a number of stat operations |
65 | concurrently. |
67 | concurrently. |
66 | |
68 | |
67 | While most of this works on all types of file descriptors (for example |
69 | While most of this works on all types of file descriptors (for |
68 | sockets), using these functions on file descriptors that support |
70 | example sockets), using these functions on file descriptors that |
69 | nonblocking operation (again, sockets, pipes etc.) is very inefficient or |
71 | support nonblocking operation (again, sockets, pipes etc.) is very |
70 | might not work (aio_read fails on sockets/pipes/fifos). Use an event loop |
72 | inefficient. Use an event loop for that (such as the L<Event|Event> |
71 | for that (such as the L<Event|Event> module): IO::AIO will naturally fit |
73 | module): IO::AIO will naturally fit into such an event loop itself. |
72 | into such an event loop itself. |
|
|
73 | |
74 | |
74 | In this version, a number of threads are started that execute your |
75 | In this version, a number of threads are started that execute your |
75 | requests and signal their completion. You don't need thread support |
76 | requests and signal their completion. You don't need thread support |
76 | in perl, and the threads created by this module will not be visible |
77 | in perl, and the threads created by this module will not be visible |
77 | to perl. In the future, this module might make use of the native aio |
78 | to perl. In the future, this module might make use of the native aio |
… | |
… | |
79 | not well-supported or restricted (GNU/Linux doesn't allow them on normal |
80 | not well-supported or restricted (GNU/Linux doesn't allow them on normal |
80 | files currently, for example), and they would only support aio_read and |
81 | files currently, for example), and they would only support aio_read and |
81 | aio_write, so the remaining functionality would have to be implemented |
82 | aio_write, so the remaining functionality would have to be implemented |
82 | using threads anyway. |
83 | using threads anyway. |
83 | |
84 | |
84 | Although the module will work with in the presence of other (Perl-) |
85 | Although the module will work in the presence of other (Perl-) threads, |
85 | threads, it is currently not reentrant in any way, so use appropriate |
86 | it is currently not reentrant in any way, so use appropriate locking |
86 | locking yourself, always call C<poll_cb> from within the same thread, or |
87 | yourself, always call C<poll_cb> from within the same thread, or never |
87 | never call C<poll_cb> (or other C<aio_> functions) recursively. |
88 | call C<poll_cb> (or other C<aio_> functions) recursively. |
88 | |
89 | |
89 | =head2 EXAMPLE |
90 | =head2 EXAMPLE |
90 | |
91 | |
91 | This is a simple example that uses the Event module and loads |
92 | This is a simple example that uses the Event module and loads |
92 | F</etc/passwd> asynchronously: |
93 | F</etc/passwd> asynchronously: |
… | |
… | |
184 | |
185 | |
185 | =cut |
186 | =cut |
186 | |
187 | |
187 | package IO::AIO; |
188 | package IO::AIO; |
188 | |
189 | |
|
|
190 | use Carp (); |
|
|
191 | |
189 | no warnings; |
192 | no warnings; |
190 | use strict 'vars'; |
193 | use strict 'vars'; |
191 | |
194 | |
192 | use base 'Exporter'; |
195 | use base 'Exporter'; |
193 | |
196 | |
194 | BEGIN { |
197 | BEGIN { |
195 | our $VERSION = '2.21'; |
198 | our $VERSION = '3.22'; |
196 | |
199 | |
197 | our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat |
200 | our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close |
198 | aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink |
201 | aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx |
199 | aio_readlink aio_fsync aio_fdatasync aio_readahead aio_rename aio_link |
202 | aio_scandir aio_symlink aio_readlink aio_sync aio_fsync |
200 | aio_move aio_copy aio_group aio_nop aio_mknod); |
203 | aio_fdatasync aio_sync_file_range aio_pathsync aio_readahead |
|
|
204 | aio_rename aio_link aio_move aio_copy aio_group |
|
|
205 | aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown |
|
|
206 | aio_chmod aio_utime aio_truncate); |
|
|
207 | |
201 | our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice aio_block)); |
208 | our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice)); |
202 | our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush |
209 | our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush |
203 | min_parallel max_parallel max_idle |
210 | min_parallel max_parallel max_idle |
204 | nreqs nready npending nthreads |
211 | nreqs nready npending nthreads |
205 | max_poll_time max_poll_reqs); |
212 | max_poll_time max_poll_reqs); |
|
|
213 | |
|
|
214 | push @AIO_REQ, qw(aio_busy); # not exported |
206 | |
215 | |
207 | @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; |
216 | @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; |
208 | |
217 | |
209 | require XSLoader; |
218 | require XSLoader; |
210 | XSLoader::load ("IO::AIO", $VERSION); |
219 | XSLoader::load ("IO::AIO", $VERSION); |
… | |
… | |
217 | All the C<aio_*> calls are more or less thin wrappers around the syscall |
226 | All the C<aio_*> calls are more or less thin wrappers around the syscall |
218 | with the same name (sans C<aio_>). The arguments are similar or identical, |
227 | with the same name (sans C<aio_>). The arguments are similar or identical, |
219 | and they all accept an additional (and optional) C<$callback> argument |
228 | and they all accept an additional (and optional) C<$callback> argument |
220 | which must be a code reference. This code reference will get called with |
229 | which must be a code reference. This code reference will get called with |
221 | the syscall return code (e.g. most syscalls return C<-1> on error, unlike |
230 | the syscall return code (e.g. most syscalls return C<-1> on error, unlike |
222 | perl, which usually delivers "false") as it's sole argument when the given |
231 | perl, which usually delivers "false") as its sole argument after the given |
223 | syscall has been executed asynchronously. |
232 | syscall has been executed asynchronously. |
224 | |
233 | |
225 | All functions expecting a filehandle keep a copy of the filehandle |
234 | All functions expecting a filehandle keep a copy of the filehandle |
226 | internally until the request has finished. |
235 | internally until the request has finished. |
227 | |
236 | |
… | |
… | |
241 | your pathnames to the locale (or other) encoding in effect in the user |
250 | your pathnames to the locale (or other) encoding in effect in the user |
242 | environment, d) use Glib::filename_from_unicode on unicode filenames or e) |
251 | environment, d) use Glib::filename_from_unicode on unicode filenames or e) |
243 | use something else to ensure your scalar has the correct contents. |
252 | use something else to ensure your scalar has the correct contents. |
244 | |
253 | |
245 | This works, btw. independent of the internal UTF-8 bit, which IO::AIO |
254 | This works, btw. independent of the internal UTF-8 bit, which IO::AIO |
246 | handles correctly wether it is set or not. |
255 | handles correctly whether it is set or not. |
247 | |
256 | |
248 | =over 4 |
257 | =over 4 |
249 | |
258 | |
250 | =item $prev_pri = aioreq_pri [$pri] |
259 | =item $prev_pri = aioreq_pri [$pri] |
251 | |
260 | |
… | |
… | |
271 | aio_read $_[0], ..., sub { |
280 | aio_read $_[0], ..., sub { |
272 | ... |
281 | ... |
273 | }; |
282 | }; |
274 | }; |
283 | }; |
275 | |
284 | |
|
|
285 | |
276 | =item aioreq_nice $pri_adjust |
286 | =item aioreq_nice $pri_adjust |
277 | |
287 | |
278 | Similar to C<aioreq_pri>, but subtracts the given value from the current |
288 | Similar to C<aioreq_pri>, but subtracts the given value from the current |
279 | priority, so the effect is cumulative. |
289 | priority, so the effect is cumulative. |
|
|
290 | |
280 | |
291 | |
281 | =item aio_open $pathname, $flags, $mode, $callback->($fh) |
292 | =item aio_open $pathname, $flags, $mode, $callback->($fh) |
282 | |
293 | |
283 | Asynchronously open or create a file and call the callback with a newly |
294 | Asynchronously open or create a file and call the callback with a newly |
284 | created filehandle for the file. |
295 | created filehandle for the file. |
… | |
… | |
290 | list. They are the same as used by C<sysopen>. |
301 | list. They are the same as used by C<sysopen>. |
291 | |
302 | |
292 | Likewise, C<$mode> specifies the mode of the newly created file, if it |
303 | Likewise, C<$mode> specifies the mode of the newly created file, if it |
293 | didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>, |
304 | didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>, |
294 | except that it is mandatory (i.e. use C<0> if you don't create new files, |
305 | except that it is mandatory (i.e. use C<0> if you don't create new files, |
295 | and C<0666> or C<0777> if you do). |
306 | and C<0666> or C<0777> if you do). Note that the C<$mode> will be modified |
|
|
307 | by the umask in effect then the request is being executed, so better never |
|
|
308 | change the umask. |
296 | |
309 | |
297 | Example: |
310 | Example: |
298 | |
311 | |
299 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
312 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
300 | if ($_[0]) { |
313 | if ($_[0]) { |
… | |
… | |
303 | } else { |
316 | } else { |
304 | die "open failed: $!\n"; |
317 | die "open failed: $!\n"; |
305 | } |
318 | } |
306 | }; |
319 | }; |
307 | |
320 | |
|
|
321 | |
308 | =item aio_close $fh, $callback->($status) |
322 | =item aio_close $fh, $callback->($status) |
309 | |
323 | |
310 | Asynchronously close a file and call the callback with the result |
324 | Asynchronously close a file and call the callback with the result |
311 | code. I<WARNING:> although accepted, you should not pass in a perl |
325 | code. |
312 | filehandle here, as perl will likely close the file descriptor another |
|
|
313 | time when the filehandle is destroyed. Normally, you can safely call perls |
|
|
314 | C<close> or just let filehandles go out of scope. |
|
|
315 | |
326 | |
316 | This is supposed to be a bug in the API, so that might change. It's |
327 | Unfortunately, you can't do this to perl. Perl I<insists> very strongly on |
317 | therefore best to avoid this function. |
328 | closing the file descriptor associated with the filehandle itself. |
|
|
329 | |
|
|
330 | Therefore, C<aio_close> will not close the filehandle - instead it will |
|
|
331 | use dup2 to overwrite the file descriptor with the write-end of a pipe |
|
|
332 | (the pipe fd will be created on demand and will be cached). |
|
|
333 | |
|
|
334 | Or in other words: the file descriptor will be closed, but it will not be |
|
|
335 | free for reuse until the perl filehandle is closed. |
|
|
336 | |
|
|
337 | =cut |
318 | |
338 | |
319 | =item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
339 | =item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
320 | |
340 | |
321 | =item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
341 | =item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
322 | |
342 | |
323 | Reads or writes C<length> bytes from the specified C<fh> and C<offset> |
343 | Reads or writes C<$length> bytes from or to the specified C<$fh> and |
324 | into the scalar given by C<data> and offset C<dataoffset> and calls the |
344 | C<$offset> into the scalar given by C<$data> and offset C<$dataoffset> |
325 | callback without the actual number of bytes read (or -1 on error, just |
345 | and calls the callback without the actual number of bytes read (or -1 on |
326 | like the syscall). |
346 | error, just like the syscall). |
|
|
347 | |
|
|
348 | C<aio_read> will, like C<sysread>, shrink or grow the C<$data> scalar to |
|
|
349 | offset plus the actual number of bytes read. |
|
|
350 | |
|
|
351 | If C<$offset> is undefined, then the current file descriptor offset will |
|
|
352 | be used (and updated), otherwise the file descriptor offset will not be |
|
|
353 | changed by these calls. |
|
|
354 | |
|
|
355 | If C<$length> is undefined in C<aio_write>, use the remaining length of |
|
|
356 | C<$data>. |
|
|
357 | |
|
|
358 | If C<$dataoffset> is less than zero, it will be counted from the end of |
|
|
359 | C<$data>. |
327 | |
360 | |
328 | The C<$data> scalar I<MUST NOT> be modified in any way while the request |
361 | The C<$data> scalar I<MUST NOT> be modified in any way while the request |
329 | is outstanding. Modifying it can result in segfaults or WW3 (if the |
362 | is outstanding. Modifying it can result in segfaults or World War III (if |
330 | necessary/optional hardware is installed). |
363 | the necessary/optional hardware is installed). |
331 | |
364 | |
332 | Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at |
365 | Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at |
333 | offset C<0> within the scalar: |
366 | offset C<0> within the scalar: |
334 | |
367 | |
335 | aio_read $fh, 7, 15, $buffer, 0, sub { |
368 | aio_read $fh, 7, 15, $buffer, 0, sub { |
336 | $_[0] > 0 or die "read error: $!"; |
369 | $_[0] > 0 or die "read error: $!"; |
337 | print "read $_[0] bytes: <$buffer>\n"; |
370 | print "read $_[0] bytes: <$buffer>\n"; |
338 | }; |
371 | }; |
|
|
372 | |
339 | |
373 | |
340 | =item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) |
374 | =item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) |
341 | |
375 | |
342 | Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts |
376 | Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts |
343 | reading at byte offset C<$in_offset>, and starts writing at the current |
377 | reading at byte offset C<$in_offset>, and starts writing at the current |
… | |
… | |
357 | C<$in_fh> than are written, and there is no way to find out how many |
391 | C<$in_fh> than are written, and there is no way to find out how many |
358 | bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only |
392 | bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only |
359 | provides the number of bytes written to C<$out_fh>. Only if the result |
393 | provides the number of bytes written to C<$out_fh>. Only if the result |
360 | value equals C<$length> one can assume that C<$length> bytes have been |
394 | value equals C<$length> one can assume that C<$length> bytes have been |
361 | read. |
395 | read. |
|
|
396 | |
362 | |
397 | |
363 | =item aio_readahead $fh,$offset,$length, $callback->($retval) |
398 | =item aio_readahead $fh,$offset,$length, $callback->($retval) |
364 | |
399 | |
365 | C<aio_readahead> populates the page cache with data from a file so that |
400 | C<aio_readahead> populates the page cache with data from a file so that |
366 | subsequent reads from that file will not block on disk I/O. The C<$offset> |
401 | subsequent reads from that file will not block on disk I/O. The C<$offset> |
… | |
… | |
372 | file. The current file offset of the file is left unchanged. |
407 | file. The current file offset of the file is left unchanged. |
373 | |
408 | |
374 | If that syscall doesn't exist (likely if your OS isn't Linux) it will be |
409 | If that syscall doesn't exist (likely if your OS isn't Linux) it will be |
375 | emulated by simply reading the data, which would have a similar effect. |
410 | emulated by simply reading the data, which would have a similar effect. |
376 | |
411 | |
|
|
412 | |
377 | =item aio_stat $fh_or_path, $callback->($status) |
413 | =item aio_stat $fh_or_path, $callback->($status) |
378 | |
414 | |
379 | =item aio_lstat $fh, $callback->($status) |
415 | =item aio_lstat $fh, $callback->($status) |
380 | |
416 | |
381 | Works like perl's C<stat> or C<lstat> in void context. The callback will |
417 | Works like perl's C<stat> or C<lstat> in void context. The callback will |
… | |
… | |
394 | aio_stat "/etc/passwd", sub { |
430 | aio_stat "/etc/passwd", sub { |
395 | $_[0] and die "stat failed: $!"; |
431 | $_[0] and die "stat failed: $!"; |
396 | print "size is ", -s _, "\n"; |
432 | print "size is ", -s _, "\n"; |
397 | }; |
433 | }; |
398 | |
434 | |
|
|
435 | |
|
|
436 | =item aio_utime $fh_or_path, $atime, $mtime, $callback->($status) |
|
|
437 | |
|
|
438 | Works like perl's C<utime> function (including the special case of $atime |
|
|
439 | and $mtime being undef). Fractional times are supported if the underlying |
|
|
440 | syscalls support them. |
|
|
441 | |
|
|
442 | When called with a pathname, uses utimes(2) if available, otherwise |
|
|
443 | utime(2). If called on a file descriptor, uses futimes(2) if available, |
|
|
444 | otherwise returns ENOSYS, so this is not portable. |
|
|
445 | |
|
|
446 | Examples: |
|
|
447 | |
|
|
448 | # set atime and mtime to current time (basically touch(1)): |
|
|
449 | aio_utime "path", undef, undef; |
|
|
450 | # set atime to current time and mtime to beginning of the epoch: |
|
|
451 | aio_utime "path", time, undef; # undef==0 |
|
|
452 | |
|
|
453 | |
|
|
454 | =item aio_chown $fh_or_path, $uid, $gid, $callback->($status) |
|
|
455 | |
|
|
456 | Works like perl's C<chown> function, except that C<undef> for either $uid |
|
|
457 | or $gid is being interpreted as "do not change" (but -1 can also be used). |
|
|
458 | |
|
|
459 | Examples: |
|
|
460 | |
|
|
461 | # same as "chown root path" in the shell: |
|
|
462 | aio_chown "path", 0, -1; |
|
|
463 | # same as above: |
|
|
464 | aio_chown "path", 0, undef; |
|
|
465 | |
|
|
466 | |
|
|
467 | =item aio_truncate $fh_or_path, $offset, $callback->($status) |
|
|
468 | |
|
|
469 | Works like truncate(2) or ftruncate(2). |
|
|
470 | |
|
|
471 | |
|
|
472 | =item aio_chmod $fh_or_path, $mode, $callback->($status) |
|
|
473 | |
|
|
474 | Works like perl's C<chmod> function. |
|
|
475 | |
|
|
476 | |
399 | =item aio_unlink $pathname, $callback->($status) |
477 | =item aio_unlink $pathname, $callback->($status) |
400 | |
478 | |
401 | Asynchronously unlink (delete) a file and call the callback with the |
479 | Asynchronously unlink (delete) a file and call the callback with the |
402 | result code. |
480 | result code. |
403 | |
481 | |
|
|
482 | |
404 | =item aio_mknod $path, $mode, $dev, $callback->($status) |
483 | =item aio_mknod $path, $mode, $dev, $callback->($status) |
405 | |
484 | |
406 | [EXPERIMENTAL] |
485 | [EXPERIMENTAL] |
407 | |
486 | |
408 | Asynchronously create a device node (or fifo). See mknod(2). |
487 | Asynchronously create a device node (or fifo). See mknod(2). |
409 | |
488 | |
410 | The only (POSIX-) portable way of calling this function is: |
489 | The only (POSIX-) portable way of calling this function is: |
411 | |
490 | |
412 | aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ... |
491 | aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ... |
|
|
492 | |
413 | |
493 | |
414 | =item aio_link $srcpath, $dstpath, $callback->($status) |
494 | =item aio_link $srcpath, $dstpath, $callback->($status) |
415 | |
495 | |
416 | Asynchronously create a new link to the existing object at C<$srcpath> at |
496 | Asynchronously create a new link to the existing object at C<$srcpath> at |
417 | the path C<$dstpath> and call the callback with the result code. |
497 | the path C<$dstpath> and call the callback with the result code. |
418 | |
498 | |
|
|
499 | |
419 | =item aio_symlink $srcpath, $dstpath, $callback->($status) |
500 | =item aio_symlink $srcpath, $dstpath, $callback->($status) |
420 | |
501 | |
421 | Asynchronously create a new symbolic link to the existing object at C<$srcpath> at |
502 | Asynchronously create a new symbolic link to the existing object at C<$srcpath> at |
422 | the path C<$dstpath> and call the callback with the result code. |
503 | the path C<$dstpath> and call the callback with the result code. |
|
|
504 | |
423 | |
505 | |
424 | =item aio_readlink $path, $callback->($link) |
506 | =item aio_readlink $path, $callback->($link) |
425 | |
507 | |
426 | Asynchronously read the symlink specified by C<$path> and pass it to |
508 | Asynchronously read the symlink specified by C<$path> and pass it to |
427 | the callback. If an error occurs, nothing or undef gets passed to the |
509 | the callback. If an error occurs, nothing or undef gets passed to the |
428 | callback. |
510 | callback. |
429 | |
511 | |
|
|
512 | |
430 | =item aio_rename $srcpath, $dstpath, $callback->($status) |
513 | =item aio_rename $srcpath, $dstpath, $callback->($status) |
431 | |
514 | |
432 | Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as |
515 | Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as |
433 | rename(2) and call the callback with the result code. |
516 | rename(2) and call the callback with the result code. |
434 | |
517 | |
|
|
518 | |
|
|
519 | =item aio_mkdir $pathname, $mode, $callback->($status) |
|
|
520 | |
|
|
521 | Asynchronously mkdir (create) a directory and call the callback with |
|
|
522 | the result code. C<$mode> will be modified by the umask at the time the |
|
|
523 | request is executed, so do not change your umask. |
|
|
524 | |
|
|
525 | |
435 | =item aio_rmdir $pathname, $callback->($status) |
526 | =item aio_rmdir $pathname, $callback->($status) |
436 | |
527 | |
437 | Asynchronously rmdir (delete) a directory and call the callback with the |
528 | Asynchronously rmdir (delete) a directory and call the callback with the |
438 | result code. |
529 | result code. |
|
|
530 | |
439 | |
531 | |
440 | =item aio_readdir $pathname, $callback->($entries) |
532 | =item aio_readdir $pathname, $callback->($entries) |
441 | |
533 | |
442 | Unlike the POSIX call of the same name, C<aio_readdir> reads an entire |
534 | Unlike the POSIX call of the same name, C<aio_readdir> reads an entire |
443 | directory (i.e. opendir + readdir + closedir). The entries will not be |
535 | directory (i.e. opendir + readdir + closedir). The entries will not be |
444 | sorted, and will B<NOT> include the C<.> and C<..> entries. |
536 | sorted, and will B<NOT> include the C<.> and C<..> entries. |
445 | |
537 | |
446 | The callback a single argument which is either C<undef> or an array-ref |
538 | The callback is passed a single argument which is either C<undef> or an |
447 | with the filenames. |
539 | array-ref with the filenames. |
|
|
540 | |
|
|
541 | |
|
|
542 | =item aio_readdirx $pathname, $flags, $callback->($entries, $flags) |
|
|
543 | |
|
|
544 | Quite similar to C<aio_readdir>, but the C<$flags> argument allows to tune |
|
|
545 | behaviour and output format. In case of an error, C<$entries> will be |
|
|
546 | C<undef>. |
|
|
547 | |
|
|
548 | The flags are a combination of the following constants, ORed together (the |
|
|
549 | flags will also be passed to the callback, possibly modified): |
|
|
550 | |
|
|
551 | =over 4 |
|
|
552 | |
|
|
553 | =item IO::AIO::READDIR_DENTS |
|
|
554 | |
|
|
555 | When this flag is off, then the callback gets an arrayref with of names |
|
|
556 | only (as with C<aio_readdir>), otherwise it gets an arrayref with |
|
|
557 | C<[$name, $type, $inode]> arrayrefs, each describing a single directory |
|
|
558 | entry in more detail. |
|
|
559 | |
|
|
560 | C<$name> is the name of the entry. |
|
|
561 | |
|
|
562 | C<$type> is one of the C<IO::AIO::DT_xxx> constants: |
|
|
563 | |
|
|
564 | C<IO::AIO::DT_UNKNOWN>, C<IO::AIO::DT_FIFO>, C<IO::AIO::DT_CHR>, C<IO::AIO::DT_DIR>, |
|
|
565 | C<IO::AIO::DT_BLK>, C<IO::AIO::DT_REG>, C<IO::AIO::DT_LNK>, C<IO::AIO::DT_SOCK>, |
|
|
566 | C<IO::AIO::DT_WHT>. |
|
|
567 | |
|
|
568 | C<IO::AIO::DT_UNKNOWN> means just that: readdir does not know. If you need to |
|
|
569 | know, you have to run stat yourself. Also, for speed reasons, the C<$type> |
|
|
570 | scalars are read-only: you can not modify them. |
|
|
571 | |
|
|
572 | C<$inode> is the inode number (which might not be exact on systems with 64 |
|
|
573 | bit inode numbers and 32 bit perls). On systems that do not deliver the |
|
|
574 | inode information, this will always be zero. |
|
|
575 | |
|
|
576 | =item IO::AIO::READDIR_DIRS_FIRST |
|
|
577 | |
|
|
578 | When this flag is set, then the names will be returned in an order where |
|
|
579 | likely directories come first. This is useful when you need to quickly |
|
|
580 | find directories, or you want to find all directories while avoiding to |
|
|
581 | stat() each entry. |
|
|
582 | |
|
|
583 | If the system returns type information in readdir, then this is used |
|
|
584 | to find directories directly. Otherwise, likely directories are files |
|
|
585 | beginning with ".", or otherwise files with no dots, of which files with |
|
|
586 | short names are tried first. |
|
|
587 | |
|
|
588 | =item IO::AIO::READDIR_STAT_ORDER |
|
|
589 | |
|
|
590 | When this flag is set, then the names will be returned in an order |
|
|
591 | suitable for stat()'ing each one. That is, when you plan to stat() |
|
|
592 | all files in the given directory, then the returned order will likely |
|
|
593 | be fastest. |
|
|
594 | |
|
|
595 | If both this flag and C<IO::AIO::READDIR_DIRS_FIRST> are specified, then |
|
|
596 | the likely dirs come first, resulting in a less optimal stat order. |
|
|
597 | |
|
|
598 | =item IO::AIO::READDIR_FOUND_UNKNOWN |
|
|
599 | |
|
|
600 | This flag should not be set when calling C<aio_readdirx>. Instead, it |
|
|
601 | is being set by C<aio_readdirx>, when any of the C<$type>'s found were |
|
|
602 | C<IO::AIO::DT_UNKNOWN>. The absense of this flag therefore indicates that all |
|
|
603 | C<$type>'s are known, which can be used to speed up some algorithms. |
|
|
604 | |
|
|
605 | =back |
|
|
606 | |
|
|
607 | |
|
|
608 | =item aio_load $path, $data, $callback->($status) |
|
|
609 | |
|
|
610 | This is a composite request that tries to fully load the given file into |
|
|
611 | memory. Status is the same as with aio_read. |
|
|
612 | |
|
|
613 | =cut |
|
|
614 | |
|
|
615 | sub aio_load($$;$) { |
|
|
616 | my ($path, undef, $cb) = @_; |
|
|
617 | my $data = \$_[1]; |
|
|
618 | |
|
|
619 | my $pri = aioreq_pri; |
|
|
620 | my $grp = aio_group $cb; |
|
|
621 | |
|
|
622 | aioreq_pri $pri; |
|
|
623 | add $grp aio_open $path, O_RDONLY, 0, sub { |
|
|
624 | my $fh = shift |
|
|
625 | or return $grp->result (-1); |
|
|
626 | |
|
|
627 | aioreq_pri $pri; |
|
|
628 | add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub { |
|
|
629 | $grp->result ($_[0]); |
|
|
630 | }; |
|
|
631 | }; |
|
|
632 | |
|
|
633 | $grp |
|
|
634 | } |
448 | |
635 | |
449 | =item aio_copy $srcpath, $dstpath, $callback->($status) |
636 | =item aio_copy $srcpath, $dstpath, $callback->($status) |
450 | |
637 | |
451 | Try to copy the I<file> (directories not supported as either source or |
638 | Try to copy the I<file> (directories not supported as either source or |
452 | destination) from C<$srcpath> to C<$dstpath> and call the callback with |
639 | destination) from C<$srcpath> to C<$dstpath> and call the callback with |
453 | the C<0> (error) or C<-1> ok. |
640 | the C<0> (error) or C<-1> ok. |
454 | |
641 | |
455 | This is a composite request that it creates the destination file with |
642 | This is a composite request that creates the destination file with |
456 | mode 0200 and copies the contents of the source file into it using |
643 | mode 0200 and copies the contents of the source file into it using |
457 | C<aio_sendfile>, followed by restoring atime, mtime, access mode and |
644 | C<aio_sendfile>, followed by restoring atime, mtime, access mode and |
458 | uid/gid, in that order. |
645 | uid/gid, in that order. |
459 | |
646 | |
460 | If an error occurs, the partial destination file will be unlinked, if |
647 | If an error occurs, the partial destination file will be unlinked, if |
… | |
… | |
462 | errors are being ignored. |
649 | errors are being ignored. |
463 | |
650 | |
464 | =cut |
651 | =cut |
465 | |
652 | |
466 | sub aio_copy($$;$) { |
653 | sub aio_copy($$;$) { |
467 | aio_block { |
|
|
468 | my ($src, $dst, $cb) = @_; |
654 | my ($src, $dst, $cb) = @_; |
469 | |
655 | |
470 | my $pri = aioreq_pri; |
656 | my $pri = aioreq_pri; |
471 | my $grp = aio_group $cb; |
657 | my $grp = aio_group $cb; |
472 | |
658 | |
473 | aioreq_pri $pri; |
659 | aioreq_pri $pri; |
474 | add $grp aio_open $src, O_RDONLY, 0, sub { |
660 | add $grp aio_open $src, O_RDONLY, 0, sub { |
475 | if (my $src_fh = $_[0]) { |
661 | if (my $src_fh = $_[0]) { |
476 | my @stat = stat $src_fh; |
662 | my @stat = stat $src_fh; # hmm, might bock over nfs? |
477 | |
663 | |
478 | aioreq_pri $pri; |
664 | aioreq_pri $pri; |
479 | add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub { |
665 | add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub { |
480 | if (my $dst_fh = $_[0]) { |
666 | if (my $dst_fh = $_[0]) { |
481 | aioreq_pri $pri; |
667 | aioreq_pri $pri; |
482 | add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub { |
668 | add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub { |
483 | if ($_[0] == $stat[7]) { |
669 | if ($_[0] == $stat[7]) { |
484 | $grp->result (0); |
670 | $grp->result (0); |
485 | close $src_fh; |
671 | close $src_fh; |
486 | |
672 | |
487 | # those should not normally block. should. should. |
|
|
488 | utime $stat[8], $stat[9], $dst; |
|
|
489 | chmod $stat[2] & 07777, $dst_fh; |
|
|
490 | chown $stat[4], $stat[5], $dst_fh; |
|
|
491 | close $dst_fh; |
|
|
492 | } else { |
673 | my $ch = sub { |
493 | $grp->result (-1); |
|
|
494 | close $src_fh; |
|
|
495 | close $dst_fh; |
|
|
496 | |
|
|
497 | aioreq $pri; |
674 | aioreq_pri $pri; |
|
|
675 | add $grp aio_chmod $dst_fh, $stat[2] & 07777, sub { |
|
|
676 | aioreq_pri $pri; |
|
|
677 | add $grp aio_chown $dst_fh, $stat[4], $stat[5], sub { |
|
|
678 | aioreq_pri $pri; |
498 | add $grp aio_unlink $dst; |
679 | add $grp aio_close $dst_fh; |
|
|
680 | } |
|
|
681 | }; |
499 | } |
682 | }; |
|
|
683 | |
|
|
684 | aioreq_pri $pri; |
|
|
685 | add $grp aio_utime $dst_fh, $stat[8], $stat[9], sub { |
|
|
686 | if ($_[0] < 0 && $! == ENOSYS) { |
|
|
687 | aioreq_pri $pri; |
|
|
688 | add $grp aio_utime $dst, $stat[8], $stat[9], $ch; |
|
|
689 | } else { |
|
|
690 | $ch->(); |
|
|
691 | } |
|
|
692 | }; |
|
|
693 | } else { |
|
|
694 | $grp->result (-1); |
|
|
695 | close $src_fh; |
|
|
696 | close $dst_fh; |
|
|
697 | |
|
|
698 | aioreq $pri; |
|
|
699 | add $grp aio_unlink $dst; |
500 | }; |
700 | } |
501 | } else { |
|
|
502 | $grp->result (-1); |
|
|
503 | } |
701 | }; |
|
|
702 | } else { |
|
|
703 | $grp->result (-1); |
504 | }, |
704 | } |
505 | |
|
|
506 | } else { |
|
|
507 | $grp->result (-1); |
|
|
508 | } |
705 | }, |
|
|
706 | |
|
|
707 | } else { |
|
|
708 | $grp->result (-1); |
509 | }; |
709 | } |
510 | |
|
|
511 | $grp |
|
|
512 | } |
710 | }; |
|
|
711 | |
|
|
712 | $grp |
513 | } |
713 | } |
514 | |
714 | |
515 | =item aio_move $srcpath, $dstpath, $callback->($status) |
715 | =item aio_move $srcpath, $dstpath, $callback->($status) |
516 | |
716 | |
517 | Try to move the I<file> (directories not supported as either source or |
717 | Try to move the I<file> (directories not supported as either source or |
518 | destination) from C<$srcpath> to C<$dstpath> and call the callback with |
718 | destination) from C<$srcpath> to C<$dstpath> and call the callback with |
519 | the C<0> (error) or C<-1> ok. |
719 | the C<0> (error) or C<-1> ok. |
520 | |
720 | |
521 | This is a composite request that tries to rename(2) the file first. If |
721 | This is a composite request that tries to rename(2) the file first; if |
522 | rename files with C<EXDEV>, it copies the file with C<aio_copy> and, if |
722 | rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if |
523 | that is successful, unlinking the C<$srcpath>. |
723 | that is successful, unlinks the C<$srcpath>. |
524 | |
724 | |
525 | =cut |
725 | =cut |
526 | |
726 | |
527 | sub aio_move($$;$) { |
727 | sub aio_move($$;$) { |
528 | aio_block { |
|
|
529 | my ($src, $dst, $cb) = @_; |
728 | my ($src, $dst, $cb) = @_; |
530 | |
729 | |
531 | my $pri = aioreq_pri; |
730 | my $pri = aioreq_pri; |
532 | my $grp = aio_group $cb; |
731 | my $grp = aio_group $cb; |
533 | |
732 | |
534 | aioreq_pri $pri; |
733 | aioreq_pri $pri; |
535 | add $grp aio_rename $src, $dst, sub { |
734 | add $grp aio_rename $src, $dst, sub { |
536 | if ($_[0] && $! == EXDEV) { |
735 | if ($_[0] && $! == EXDEV) { |
537 | aioreq_pri $pri; |
736 | aioreq_pri $pri; |
538 | add $grp aio_copy $src, $dst, sub { |
737 | add $grp aio_copy $src, $dst, sub { |
539 | $grp->result ($_[0]); |
|
|
540 | |
|
|
541 | if (!$_[0]) { |
|
|
542 | aioreq_pri $pri; |
|
|
543 | add $grp aio_unlink $src; |
|
|
544 | } |
|
|
545 | }; |
|
|
546 | } else { |
|
|
547 | $grp->result ($_[0]); |
738 | $grp->result ($_[0]); |
|
|
739 | |
|
|
740 | if (!$_[0]) { |
|
|
741 | aioreq_pri $pri; |
|
|
742 | add $grp aio_unlink $src; |
|
|
743 | } |
548 | } |
744 | }; |
|
|
745 | } else { |
|
|
746 | $grp->result ($_[0]); |
549 | }; |
747 | } |
550 | |
|
|
551 | $grp |
|
|
552 | } |
748 | }; |
|
|
749 | |
|
|
750 | $grp |
553 | } |
751 | } |
554 | |
752 | |
555 | =item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) |
753 | =item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) |
556 | |
754 | |
557 | Scans a directory (similar to C<aio_readdir>) but additionally tries to |
755 | Scans a directory (similar to C<aio_readdir>) but additionally tries to |
… | |
… | |
577 | |
775 | |
578 | Implementation notes. |
776 | Implementation notes. |
579 | |
777 | |
580 | The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can. |
778 | The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can. |
581 | |
779 | |
|
|
780 | If readdir returns file type information, then this is used directly to |
|
|
781 | find directories. |
|
|
782 | |
582 | After reading the directory, the modification time, size etc. of the |
783 | Otherwise, after reading the directory, the modification time, size etc. |
583 | directory before and after the readdir is checked, and if they match (and |
784 | of the directory before and after the readdir is checked, and if they |
584 | isn't the current time), the link count will be used to decide how many |
785 | match (and isn't the current time), the link count will be used to decide |
585 | entries are directories (if >= 2). Otherwise, no knowledge of the number |
786 | how many entries are directories (if >= 2). Otherwise, no knowledge of the |
586 | of subdirectories will be assumed. |
787 | number of subdirectories will be assumed. |
587 | |
788 | |
588 | Then entries will be sorted into likely directories (everything without |
789 | Then entries will be sorted into likely directories a non-initial dot |
589 | a non-initial dot currently) and likely non-directories (everything |
790 | currently) and likely non-directories (see C<aio_readdirx>). Then every |
590 | else). Then every entry plus an appended C</.> will be C<stat>'ed, |
791 | entry plus an appended C</.> will be C<stat>'ed, likely directories first, |
591 | likely directories first. If that succeeds, it assumes that the entry |
792 | in order of their inode numbers. If that succeeds, it assumes that the |
592 | is a directory or a symlink to directory (which will be checked |
793 | entry is a directory or a symlink to directory (which will be checked |
593 | seperately). This is often faster than stat'ing the entry itself because |
794 | seperately). This is often faster than stat'ing the entry itself because |
594 | filesystems might detect the type of the entry without reading the inode |
795 | filesystems might detect the type of the entry without reading the inode |
595 | data (e.g. ext2fs filetype feature). |
796 | data (e.g. ext2fs filetype feature), even on systems that cannot return |
|
|
797 | the filetype information on readdir. |
596 | |
798 | |
597 | If the known number of directories (link count - 2) has been reached, the |
799 | If the known number of directories (link count - 2) has been reached, the |
598 | rest of the entries is assumed to be non-directories. |
800 | rest of the entries is assumed to be non-directories. |
599 | |
801 | |
600 | This only works with certainty on POSIX (= UNIX) filesystems, which |
802 | This only works with certainty on POSIX (= UNIX) filesystems, which |
… | |
… | |
604 | as those tend to return 0 or 1 as link counts, which disables the |
806 | as those tend to return 0 or 1 as link counts, which disables the |
605 | directory counting heuristic. |
807 | directory counting heuristic. |
606 | |
808 | |
607 | =cut |
809 | =cut |
608 | |
810 | |
609 | sub aio_scandir($$$) { |
811 | sub aio_scandir($$;$) { |
610 | aio_block { |
|
|
611 | my ($path, $maxreq, $cb) = @_; |
812 | my ($path, $maxreq, $cb) = @_; |
612 | |
813 | |
613 | my $pri = aioreq_pri; |
814 | my $pri = aioreq_pri; |
614 | |
815 | |
615 | my $grp = aio_group $cb; |
816 | my $grp = aio_group $cb; |
616 | |
817 | |
617 | $maxreq = 4 if $maxreq <= 0; |
818 | $maxreq = 4 if $maxreq <= 0; |
618 | |
819 | |
619 | # stat once |
820 | # stat once |
|
|
821 | aioreq_pri $pri; |
|
|
822 | add $grp aio_stat $path, sub { |
|
|
823 | return $grp->result () if $_[0]; |
|
|
824 | my $now = time; |
|
|
825 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
|
|
826 | |
|
|
827 | # read the directory entries |
620 | aioreq_pri $pri; |
828 | aioreq_pri $pri; |
621 | add $grp aio_stat $path, sub { |
829 | add $grp aio_readdirx $path, READDIR_DIRS_FIRST, sub { |
|
|
830 | my $entries = shift |
622 | return $grp->result () if $_[0]; |
831 | or return $grp->result (); |
623 | my $now = time; |
|
|
624 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
|
|
625 | |
832 | |
626 | # read the directory entries |
833 | # stat the dir another time |
627 | aioreq_pri $pri; |
834 | aioreq_pri $pri; |
628 | add $grp aio_readdir $path, sub { |
|
|
629 | my $entries = shift |
|
|
630 | or return $grp->result (); |
|
|
631 | |
|
|
632 | # stat the dir another time |
|
|
633 | aioreq_pri $pri; |
|
|
634 | add $grp aio_stat $path, sub { |
835 | add $grp aio_stat $path, sub { |
635 | my $hash2 = join ":", (stat _)[0,1,3,7,9]; |
836 | my $hash2 = join ":", (stat _)[0,1,3,7,9]; |
636 | |
837 | |
637 | my $ndirs; |
838 | my $ndirs; |
638 | |
839 | |
639 | # take the slow route if anything looks fishy |
840 | # take the slow route if anything looks fishy |
640 | if ($hash1 ne $hash2 or (stat _)[9] == $now) { |
841 | if ($hash1 ne $hash2 or (stat _)[9] == $now) { |
641 | $ndirs = -1; |
842 | $ndirs = -1; |
642 | } else { |
843 | } else { |
643 | # if nlink == 2, we are finished |
844 | # if nlink == 2, we are finished |
644 | # on non-posix-fs's, we rely on nlink < 2 |
845 | # for non-posix-fs's, we rely on nlink < 2 |
645 | $ndirs = (stat _)[3] - 2 |
846 | $ndirs = (stat _)[3] - 2 |
646 | or return $grp->result ([], $entries); |
847 | or return $grp->result ([], $entries); |
647 | } |
848 | } |
648 | |
849 | |
649 | # sort into likely dirs and likely nondirs |
|
|
650 | # dirs == files without ".", short entries first |
|
|
651 | $entries = [map $_->[0], |
|
|
652 | sort { $b->[1] cmp $a->[1] } |
|
|
653 | map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length], |
|
|
654 | @$entries]; |
|
|
655 | |
|
|
656 | my (@dirs, @nondirs); |
850 | my (@dirs, @nondirs); |
657 | |
851 | |
658 | my $statgrp = add $grp aio_group sub { |
852 | my $statgrp = add $grp aio_group sub { |
659 | $grp->result (\@dirs, \@nondirs); |
853 | $grp->result (\@dirs, \@nondirs); |
660 | }; |
854 | }; |
661 | |
855 | |
662 | limit $statgrp $maxreq; |
856 | limit $statgrp $maxreq; |
663 | feed $statgrp sub { |
857 | feed $statgrp sub { |
664 | return unless @$entries; |
858 | return unless @$entries; |
665 | my $entry = pop @$entries; |
859 | my $entry = shift @$entries; |
666 | |
860 | |
667 | aioreq_pri $pri; |
861 | aioreq_pri $pri; |
668 | add $statgrp aio_stat "$path/$entry/.", sub { |
862 | add $statgrp aio_stat "$path/$entry/.", sub { |
669 | if ($_[0] < 0) { |
863 | if ($_[0] < 0) { |
670 | push @nondirs, $entry; |
864 | push @nondirs, $entry; |
671 | } else { |
865 | } else { |
672 | # need to check for real directory |
866 | # need to check for real directory |
673 | aioreq_pri $pri; |
867 | aioreq_pri $pri; |
674 | add $statgrp aio_lstat "$path/$entry", sub { |
868 | add $statgrp aio_lstat "$path/$entry", sub { |
675 | if (-d _) { |
869 | if (-d _) { |
676 | push @dirs, $entry; |
870 | push @dirs, $entry; |
677 | |
871 | |
678 | unless (--$ndirs) { |
872 | unless (--$ndirs) { |
679 | push @nondirs, @$entries; |
873 | push @nondirs, @$entries; |
680 | feed $statgrp; |
874 | feed $statgrp; |
681 | } |
|
|
682 | } else { |
|
|
683 | push @nondirs, $entry; |
|
|
684 | } |
875 | } |
|
|
876 | } else { |
|
|
877 | push @nondirs, $entry; |
685 | } |
878 | } |
686 | } |
879 | } |
687 | }; |
880 | } |
688 | }; |
881 | }; |
689 | }; |
882 | }; |
690 | }; |
883 | }; |
691 | }; |
884 | }; |
692 | |
|
|
693 | $grp |
|
|
694 | } |
885 | }; |
|
|
886 | |
|
|
887 | $grp |
695 | } |
888 | } |
|
|
889 | |
|
|
890 | =item aio_rmtree $path, $callback->($status) |
|
|
891 | |
|
|
892 | Delete a directory tree starting (and including) C<$path>, return the |
|
|
893 | status of the final C<rmdir> only. This is a composite request that |
|
|
894 | uses C<aio_scandir> to recurse into and rmdir directories, and unlink |
|
|
895 | everything else. |
|
|
896 | |
|
|
897 | =cut |
|
|
898 | |
|
|
899 | sub aio_rmtree; |
|
|
900 | sub aio_rmtree($;$) { |
|
|
901 | my ($path, $cb) = @_; |
|
|
902 | |
|
|
903 | my $pri = aioreq_pri; |
|
|
904 | my $grp = aio_group $cb; |
|
|
905 | |
|
|
906 | aioreq_pri $pri; |
|
|
907 | add $grp aio_scandir $path, 0, sub { |
|
|
908 | my ($dirs, $nondirs) = @_; |
|
|
909 | |
|
|
910 | my $dirgrp = aio_group sub { |
|
|
911 | add $grp aio_rmdir $path, sub { |
|
|
912 | $grp->result ($_[0]); |
|
|
913 | }; |
|
|
914 | }; |
|
|
915 | |
|
|
916 | (aioreq_pri $pri), add $dirgrp aio_rmtree "$path/$_" for @$dirs; |
|
|
917 | (aioreq_pri $pri), add $dirgrp aio_unlink "$path/$_" for @$nondirs; |
|
|
918 | |
|
|
919 | add $grp $dirgrp; |
|
|
920 | }; |
|
|
921 | |
|
|
922 | $grp |
|
|
923 | } |
|
|
924 | |
|
|
925 | =item aio_sync $callback->($status) |
|
|
926 | |
|
|
927 | Asynchronously call sync and call the callback when finished. |
696 | |
928 | |
697 | =item aio_fsync $fh, $callback->($status) |
929 | =item aio_fsync $fh, $callback->($status) |
698 | |
930 | |
699 | Asynchronously call fsync on the given filehandle and call the callback |
931 | Asynchronously call fsync on the given filehandle and call the callback |
700 | with the fsync result code. |
932 | with the fsync result code. |
… | |
… | |
704 | Asynchronously call fdatasync on the given filehandle and call the |
936 | Asynchronously call fdatasync on the given filehandle and call the |
705 | callback with the fdatasync result code. |
937 | callback with the fdatasync result code. |
706 | |
938 | |
707 | If this call isn't available because your OS lacks it or it couldn't be |
939 | If this call isn't available because your OS lacks it or it couldn't be |
708 | detected, it will be emulated by calling C<fsync> instead. |
940 | detected, it will be emulated by calling C<fsync> instead. |
|
|
941 | |
|
|
942 | =item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status) |
|
|
943 | |
|
|
944 | Sync the data portion of the file specified by C<$offset> and C<$length> |
|
|
945 | to disk (but NOT the metadata), by calling the Linux-specific |
|
|
946 | sync_file_range call. If sync_file_range is not available or it returns |
|
|
947 | ENOSYS, then fdatasync or fsync is being substituted. |
|
|
948 | |
|
|
949 | C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>, |
|
|
950 | C<IO::AIO::SYNC_FILE_RANGE_WRITE> and |
|
|
951 | C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range |
|
|
952 | manpage for details. |
|
|
953 | |
|
|
954 | =item aio_pathsync $path, $callback->($status) |
|
|
955 | |
|
|
956 | This request tries to open, fsync and close the given path. This is a |
|
|
957 | composite request intended to sync directories after directory operations |
|
|
958 | (E.g. rename). This might not work on all operating systems or have any |
|
|
959 | specific effect, but usually it makes sure that directory changes get |
|
|
960 | written to disc. It works for anything that can be opened for read-only, |
|
|
961 | not just directories. |
|
|
962 | |
|
|
963 | Passes C<0> when everything went ok, and C<-1> on error. |
|
|
964 | |
|
|
965 | =cut |
|
|
966 | |
|
|
967 | sub aio_pathsync($;$) { |
|
|
968 | my ($path, $cb) = @_; |
|
|
969 | |
|
|
970 | my $pri = aioreq_pri; |
|
|
971 | my $grp = aio_group $cb; |
|
|
972 | |
|
|
973 | aioreq_pri $pri; |
|
|
974 | add $grp aio_open $path, O_RDONLY, 0, sub { |
|
|
975 | my ($fh) = @_; |
|
|
976 | if ($fh) { |
|
|
977 | aioreq_pri $pri; |
|
|
978 | add $grp aio_fsync $fh, sub { |
|
|
979 | $grp->result ($_[0]); |
|
|
980 | |
|
|
981 | aioreq_pri $pri; |
|
|
982 | add $grp aio_close $fh; |
|
|
983 | }; |
|
|
984 | } else { |
|
|
985 | $grp->result (-1); |
|
|
986 | } |
|
|
987 | }; |
|
|
988 | |
|
|
989 | $grp |
|
|
990 | } |
709 | |
991 | |
710 | =item aio_group $callback->(...) |
992 | =item aio_group $callback->(...) |
711 | |
993 | |
712 | This is a very special aio request: Instead of doing something, it is a |
994 | This is a very special aio request: Instead of doing something, it is a |
713 | container for other aio requests, which is useful if you want to bundle |
995 | container for other aio requests, which is useful if you want to bundle |
… | |
… | |
763 | =item cancel $req |
1045 | =item cancel $req |
764 | |
1046 | |
765 | Cancels the request, if possible. Has the effect of skipping execution |
1047 | Cancels the request, if possible. Has the effect of skipping execution |
766 | when entering the B<execute> state and skipping calling the callback when |
1048 | when entering the B<execute> state and skipping calling the callback when |
767 | entering the the B<result> state, but will leave the request otherwise |
1049 | entering the the B<result> state, but will leave the request otherwise |
768 | untouched. That means that requests that currently execute will not be |
1050 | untouched (with the exception of readdir). That means that requests that |
769 | stopped and resources held by the request will not be freed prematurely. |
1051 | currently execute will not be stopped and resources held by the request |
|
|
1052 | will not be freed prematurely. |
770 | |
1053 | |
771 | =item cb $req $callback->(...) |
1054 | =item cb $req $callback->(...) |
772 | |
1055 | |
773 | Replace (or simply set) the callback registered to the request. |
1056 | Replace (or simply set) the callback registered to the request. |
774 | |
1057 | |
… | |
… | |
825 | Their lifetime, simplified, looks like this: when they are empty, they |
1108 | Their lifetime, simplified, looks like this: when they are empty, they |
826 | will finish very quickly. If they contain only requests that are in the |
1109 | will finish very quickly. If they contain only requests that are in the |
827 | C<done> state, they will also finish. Otherwise they will continue to |
1110 | C<done> state, they will also finish. Otherwise they will continue to |
828 | exist. |
1111 | exist. |
829 | |
1112 | |
830 | That means after creating a group you have some time to add requests. And |
1113 | That means after creating a group you have some time to add requests |
831 | in the callbacks of those requests, you can add further requests to the |
1114 | (precisely before the callback has been invoked, which is only done within |
832 | group. And only when all those requests have finished will the the group |
1115 | the C<poll_cb>). And in the callbacks of those requests, you can add |
833 | itself finish. |
1116 | further requests to the group. And only when all those requests have |
|
|
1117 | finished will the the group itself finish. |
834 | |
1118 | |
835 | =over 4 |
1119 | =over 4 |
836 | |
1120 | |
837 | =item add $grp ... |
1121 | =item add $grp ... |
838 | |
1122 | |
… | |
… | |
850 | itself. Useful when you queued a lot of events but got a result early. |
1134 | itself. Useful when you queued a lot of events but got a result early. |
851 | |
1135 | |
852 | =item $grp->result (...) |
1136 | =item $grp->result (...) |
853 | |
1137 | |
854 | Set the result value(s) that will be passed to the group callback when all |
1138 | Set the result value(s) that will be passed to the group callback when all |
855 | subrequests have finished and set thre groups errno to the current value |
1139 | subrequests have finished and set the groups errno to the current value |
856 | of errno (just like calling C<errno> without an error number). By default, |
1140 | of errno (just like calling C<errno> without an error number). By default, |
857 | no argument will be passed and errno is zero. |
1141 | no argument will be passed and errno is zero. |
858 | |
1142 | |
859 | =item $grp->errno ([$errno]) |
1143 | =item $grp->errno ([$errno]) |
860 | |
1144 | |
… | |
… | |
871 | =item feed $grp $callback->($grp) |
1155 | =item feed $grp $callback->($grp) |
872 | |
1156 | |
873 | Sets a feeder/generator on this group: every group can have an attached |
1157 | Sets a feeder/generator on this group: every group can have an attached |
874 | generator that generates requests if idle. The idea behind this is that, |
1158 | generator that generates requests if idle. The idea behind this is that, |
875 | although you could just queue as many requests as you want in a group, |
1159 | although you could just queue as many requests as you want in a group, |
876 | this might starve other requests for a potentially long time. For |
1160 | this might starve other requests for a potentially long time. For example, |
877 | example, C<aio_scandir> might generate hundreds of thousands C<aio_stat> |
1161 | C<aio_scandir> might generate hundreds of thousands C<aio_stat> requests, |
878 | requests, delaying any later requests for a long time. |
1162 | delaying any later requests for a long time. |
879 | |
1163 | |
880 | To avoid this, and allow incremental generation of requests, you can |
1164 | To avoid this, and allow incremental generation of requests, you can |
881 | instead a group and set a feeder on it that generates those requests. The |
1165 | instead a group and set a feeder on it that generates those requests. The |
882 | feed callback will be called whenever there are few enough (see C<limit>, |
1166 | feed callback will be called whenever there are few enough (see C<limit>, |
883 | below) requests active in the group itself and is expected to queue more |
1167 | below) requests active in the group itself and is expected to queue more |
… | |
… | |
887 | not impose any limits). |
1171 | not impose any limits). |
888 | |
1172 | |
889 | If the feed does not queue more requests when called, it will be |
1173 | If the feed does not queue more requests when called, it will be |
890 | automatically removed from the group. |
1174 | automatically removed from the group. |
891 | |
1175 | |
892 | If the feed limit is C<0>, it will be set to C<2> automatically. |
1176 | If the feed limit is C<0> when this method is called, it will be set to |
|
|
1177 | C<2> automatically. |
893 | |
1178 | |
894 | Example: |
1179 | Example: |
895 | |
1180 | |
896 | # stat all files in @files, but only ever use four aio requests concurrently: |
1181 | # stat all files in @files, but only ever use four aio requests concurrently: |
897 | |
1182 | |
… | |
… | |
909 | Sets the feeder limit for the group: The feeder will be called whenever |
1194 | Sets the feeder limit for the group: The feeder will be called whenever |
910 | the group contains less than this many requests. |
1195 | the group contains less than this many requests. |
911 | |
1196 | |
912 | Setting the limit to C<0> will pause the feeding process. |
1197 | Setting the limit to C<0> will pause the feeding process. |
913 | |
1198 | |
|
|
1199 | The default value for the limit is C<0>, but note that setting a feeder |
|
|
1200 | automatically bumps it up to C<2>. |
|
|
1201 | |
914 | =back |
1202 | =back |
915 | |
1203 | |
916 | =head2 SUPPORT FUNCTIONS |
1204 | =head2 SUPPORT FUNCTIONS |
917 | |
1205 | |
918 | =head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION |
1206 | =head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION |
… | |
… | |
929 | See C<poll_cb> for an example. |
1217 | See C<poll_cb> for an example. |
930 | |
1218 | |
931 | =item IO::AIO::poll_cb |
1219 | =item IO::AIO::poll_cb |
932 | |
1220 | |
933 | Process some outstanding events on the result pipe. You have to call this |
1221 | Process some outstanding events on the result pipe. You have to call this |
934 | regularly. Returns the number of events processed. Returns immediately |
1222 | regularly. Returns C<0> if all events could be processed, or C<-1> if it |
|
|
1223 | returned earlier for whatever reason. Returns immediately when no events |
935 | when no events are outstanding. The amount of events processed depends on |
1224 | are outstanding. The amount of events processed depends on the settings of |
936 | the settings of C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>. |
1225 | C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>. |
937 | |
1226 | |
938 | If not all requests were processed for whatever reason, the filehandle |
1227 | If not all requests were processed for whatever reason, the filehandle |
939 | will still be ready when C<poll_cb> returns. |
1228 | will still be ready when C<poll_cb> returns, so normally you don't have to |
|
|
1229 | do anything special to have it called later. |
940 | |
1230 | |
941 | Example: Install an Event watcher that automatically calls |
1231 | Example: Install an Event watcher that automatically calls |
942 | IO::AIO::poll_cb with high priority: |
1232 | IO::AIO::poll_cb with high priority: |
943 | |
1233 | |
944 | Event->io (fd => IO::AIO::poll_fileno, |
1234 | Event->io (fd => IO::AIO::poll_fileno, |
… | |
… | |
1003 | Strictly equivalent to: |
1293 | Strictly equivalent to: |
1004 | |
1294 | |
1005 | IO::AIO::poll_wait, IO::AIO::poll_cb |
1295 | IO::AIO::poll_wait, IO::AIO::poll_cb |
1006 | while IO::AIO::nreqs; |
1296 | while IO::AIO::nreqs; |
1007 | |
1297 | |
|
|
1298 | =back |
|
|
1299 | |
1008 | =head3 CONTROLLING THE NUMBER OF THREADS |
1300 | =head3 CONTROLLING THE NUMBER OF THREADS |
|
|
1301 | |
|
|
1302 | =over |
1009 | |
1303 | |
1010 | =item IO::AIO::min_parallel $nthreads |
1304 | =item IO::AIO::min_parallel $nthreads |
1011 | |
1305 | |
1012 | Set the minimum number of AIO threads to C<$nthreads>. The current |
1306 | Set the minimum number of AIO threads to C<$nthreads>. The current |
1013 | default is C<8>, which means eight asynchronous operations can execute |
1307 | default is C<8>, which means eight asynchronous operations can execute |
… | |
… | |
1054 | |
1348 | |
1055 | The default is probably ok in most situations, especially if thread |
1349 | The default is probably ok in most situations, especially if thread |
1056 | creation is fast. If thread creation is very slow on your system you might |
1350 | creation is fast. If thread creation is very slow on your system you might |
1057 | want to use larger values. |
1351 | want to use larger values. |
1058 | |
1352 | |
1059 | =item $oldmaxreqs = IO::AIO::max_outstanding $maxreqs |
1353 | =item IO::AIO::max_outstanding $maxreqs |
1060 | |
1354 | |
1061 | This is a very bad function to use in interactive programs because it |
1355 | This is a very bad function to use in interactive programs because it |
1062 | blocks, and a bad way to reduce concurrency because it is inexact: Better |
1356 | blocks, and a bad way to reduce concurrency because it is inexact: Better |
1063 | use an C<aio_group> together with a feed callback. |
1357 | use an C<aio_group> together with a feed callback. |
1064 | |
1358 | |
1065 | Sets the maximum number of outstanding requests to C<$nreqs>. If you |
1359 | Sets the maximum number of outstanding requests to C<$nreqs>. If you |
1066 | to queue up more than this number of requests, the next call to the |
1360 | do queue up more than this number of requests, the next call to the |
1067 | C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>) |
1361 | C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>) |
1068 | function will block until the limit is no longer exceeded. |
1362 | function will block until the limit is no longer exceeded. |
1069 | |
1363 | |
1070 | The default value is very large, so there is no practical limit on the |
1364 | The default value is very large, so there is no practical limit on the |
1071 | number of outstanding requests. |
1365 | number of outstanding requests. |
1072 | |
1366 | |
1073 | You can still queue as many requests as you want. Therefore, |
1367 | You can still queue as many requests as you want. Therefore, |
1074 | C<max_oustsanding> is mainly useful in simple scripts (with low values) or |
1368 | C<max_outstanding> is mainly useful in simple scripts (with low values) or |
1075 | as a stop gap to shield against fatal memory overflow (with large values). |
1369 | as a stop gap to shield against fatal memory overflow (with large values). |
1076 | |
1370 | |
|
|
1371 | =back |
|
|
1372 | |
1077 | =head3 STATISTICAL INFORMATION |
1373 | =head3 STATISTICAL INFORMATION |
|
|
1374 | |
|
|
1375 | =over |
1078 | |
1376 | |
1079 | =item IO::AIO::nreqs |
1377 | =item IO::AIO::nreqs |
1080 | |
1378 | |
1081 | Returns the number of requests currently in the ready, execute or pending |
1379 | Returns the number of requests currently in the ready, execute or pending |
1082 | states (i.e. for which their callback has not been invoked yet). |
1380 | states (i.e. for which their callback has not been invoked yet). |
… | |
… | |
1097 | but not yet processed by poll_cb). |
1395 | but not yet processed by poll_cb). |
1098 | |
1396 | |
1099 | =back |
1397 | =back |
1100 | |
1398 | |
1101 | =cut |
1399 | =cut |
1102 | |
|
|
1103 | # support function to convert a fd into a perl filehandle |
|
|
1104 | sub _fd2fh { |
|
|
1105 | return undef if $_[0] < 0; |
|
|
1106 | |
|
|
1107 | # try to generate nice filehandles |
|
|
1108 | my $sym = "IO::AIO::fd#$_[0]"; |
|
|
1109 | local *$sym; |
|
|
1110 | |
|
|
1111 | open *$sym, "+<&=$_[0]" # usually works under any unix |
|
|
1112 | or open *$sym, "<&=$_[0]" # cygwin needs this |
|
|
1113 | or open *$sym, ">&=$_[0]" # or this |
|
|
1114 | or return undef; |
|
|
1115 | |
|
|
1116 | *$sym |
|
|
1117 | } |
|
|
1118 | |
1400 | |
1119 | min_parallel 8; |
1401 | min_parallel 8; |
1120 | |
1402 | |
1121 | END { flush } |
1403 | END { flush } |
1122 | |
1404 | |
… | |
… | |
1146 | bytes of memory. In addition, stat requests need a stat buffer (possibly |
1428 | bytes of memory. In addition, stat requests need a stat buffer (possibly |
1147 | a few hundred bytes), readdir requires a result buffer and so on. Perl |
1429 | a few hundred bytes), readdir requires a result buffer and so on. Perl |
1148 | scalars and other data passed into aio requests will also be locked and |
1430 | scalars and other data passed into aio requests will also be locked and |
1149 | will consume memory till the request has entered the done state. |
1431 | will consume memory till the request has entered the done state. |
1150 | |
1432 | |
1151 | This is now awfully much, so queuing lots of requests is not usually a |
1433 | This is not awfully much, so queuing lots of requests is not usually a |
1152 | problem. |
1434 | problem. |
1153 | |
1435 | |
1154 | Per-thread usage: |
1436 | Per-thread usage: |
1155 | |
1437 | |
1156 | In the execution phase, some aio requests require more memory for |
1438 | In the execution phase, some aio requests require more memory for |
… | |
… | |
1161 | |
1443 | |
1162 | Known bugs will be fixed in the next release. |
1444 | Known bugs will be fixed in the next release. |
1163 | |
1445 | |
1164 | =head1 SEE ALSO |
1446 | =head1 SEE ALSO |
1165 | |
1447 | |
1166 | L<Coro::AIO>. |
1448 | L<AnyEvent::AIO> for easy integration into event loops, L<Coro::AIO> for a |
|
|
1449 | more natural syntax. |
1167 | |
1450 | |
1168 | =head1 AUTHOR |
1451 | =head1 AUTHOR |
1169 | |
1452 | |
1170 | Marc Lehmann <schmorp@schmorp.de> |
1453 | Marc Lehmann <schmorp@schmorp.de> |
1171 | http://home.schmorp.de/ |
1454 | http://home.schmorp.de/ |