… | |
… | |
168 | use common::sense; |
168 | use common::sense; |
169 | |
169 | |
170 | use base 'Exporter'; |
170 | use base 'Exporter'; |
171 | |
171 | |
172 | BEGIN { |
172 | BEGIN { |
173 | our $VERSION = '3.8'; |
173 | our $VERSION = '4.15'; |
174 | |
174 | |
175 | our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close |
175 | our @AIO_REQ = qw(aio_sendfile aio_seek aio_read aio_write aio_open aio_close |
176 | aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx |
176 | aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx |
177 | aio_scandir aio_symlink aio_readlink aio_sync aio_fsync |
177 | aio_scandir aio_symlink aio_readlink aio_realpath aio_sync |
178 | aio_fdatasync aio_sync_file_range aio_pathsync aio_readahead |
178 | aio_fsync aio_syncfs aio_fdatasync aio_sync_file_range aio_fallocate |
|
|
179 | aio_pathsync aio_readahead aio_fiemap |
179 | aio_rename aio_link aio_move aio_copy aio_group |
180 | aio_rename aio_link aio_move aio_copy aio_group |
180 | aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown |
181 | aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown |
181 | aio_chmod aio_utime aio_truncate |
182 | aio_chmod aio_utime aio_truncate |
182 | aio_msync aio_mtouch aio_mlock aio_mlockall |
183 | aio_msync aio_mtouch aio_mlock aio_mlockall |
183 | aio_statvfs); |
184 | aio_statvfs |
|
|
185 | aio_wd); |
184 | |
186 | |
185 | our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice)); |
187 | our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice)); |
186 | our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush |
188 | our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush |
187 | min_parallel max_parallel max_idle idle_timeout |
189 | min_parallel max_parallel max_idle idle_timeout |
188 | nreqs nready npending nthreads |
190 | nreqs nready npending nthreads |
… | |
… | |
204 | |
206 | |
205 | This section simply lists the prototypes of the most important functions |
207 | This section simply lists the prototypes of the most important functions |
206 | for quick reference. See the following sections for function-by-function |
208 | for quick reference. See the following sections for function-by-function |
207 | documentation. |
209 | documentation. |
208 | |
210 | |
|
|
211 | aio_wd $pathname, $callback->($wd) |
209 | aio_open $pathname, $flags, $mode, $callback->($fh) |
212 | aio_open $pathname, $flags, $mode, $callback->($fh) |
210 | aio_close $fh, $callback->($status) |
213 | aio_close $fh, $callback->($status) |
|
|
214 | aio_seek $fh,$offset,$whence, $callback->($offs) |
211 | aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
215 | aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
212 | aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
216 | aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
213 | aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) |
217 | aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) |
214 | aio_readahead $fh,$offset,$length, $callback->($retval) |
218 | aio_readahead $fh,$offset,$length, $callback->($retval) |
215 | aio_stat $fh_or_path, $callback->($status) |
219 | aio_stat $fh_or_path, $callback->($status) |
216 | aio_lstat $fh, $callback->($status) |
220 | aio_lstat $fh, $callback->($status) |
217 | aio_statvfs $fh_or_path, $callback->($statvfs) |
221 | aio_statvfs $fh_or_path, $callback->($statvfs) |
218 | aio_utime $fh_or_path, $atime, $mtime, $callback->($status) |
222 | aio_utime $fh_or_path, $atime, $mtime, $callback->($status) |
219 | aio_chown $fh_or_path, $uid, $gid, $callback->($status) |
223 | aio_chown $fh_or_path, $uid, $gid, $callback->($status) |
|
|
224 | aio_chmod $fh_or_path, $mode, $callback->($status) |
220 | aio_truncate $fh_or_path, $offset, $callback->($status) |
225 | aio_truncate $fh_or_path, $offset, $callback->($status) |
221 | aio_chmod $fh_or_path, $mode, $callback->($status) |
|
|
222 | aio_unlink $pathname, $callback->($status) |
226 | aio_unlink $pathname, $callback->($status) |
223 | aio_mknod $path, $mode, $dev, $callback->($status) |
227 | aio_mknod $pathname, $mode, $dev, $callback->($status) |
224 | aio_link $srcpath, $dstpath, $callback->($status) |
228 | aio_link $srcpath, $dstpath, $callback->($status) |
225 | aio_symlink $srcpath, $dstpath, $callback->($status) |
229 | aio_symlink $srcpath, $dstpath, $callback->($status) |
226 | aio_readlink $path, $callback->($link) |
230 | aio_readlink $pathname, $callback->($link) |
|
|
231 | aio_realpath $pathname, $callback->($link) |
227 | aio_rename $srcpath, $dstpath, $callback->($status) |
232 | aio_rename $srcpath, $dstpath, $callback->($status) |
228 | aio_mkdir $pathname, $mode, $callback->($status) |
233 | aio_mkdir $pathname, $mode, $callback->($status) |
229 | aio_rmdir $pathname, $callback->($status) |
234 | aio_rmdir $pathname, $callback->($status) |
230 | aio_readdir $pathname, $callback->($entries) |
235 | aio_readdir $pathname, $callback->($entries) |
231 | aio_readdirx $pathname, $flags, $callback->($entries, $flags) |
236 | aio_readdirx $pathname, $flags, $callback->($entries, $flags) |
232 | IO::AIO::READDIR_DENTS IO::AIO::READDIR_DIRS_FIRST |
237 | IO::AIO::READDIR_DENTS IO::AIO::READDIR_DIRS_FIRST |
233 | IO::AIO::READDIR_STAT_ORDER IO::AIO::READDIR_FOUND_UNKNOWN |
238 | IO::AIO::READDIR_STAT_ORDER IO::AIO::READDIR_FOUND_UNKNOWN |
|
|
239 | aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs) |
234 | aio_load $path, $data, $callback->($status) |
240 | aio_load $pathname, $data, $callback->($status) |
235 | aio_copy $srcpath, $dstpath, $callback->($status) |
241 | aio_copy $srcpath, $dstpath, $callback->($status) |
236 | aio_move $srcpath, $dstpath, $callback->($status) |
242 | aio_move $srcpath, $dstpath, $callback->($status) |
237 | aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) |
|
|
238 | aio_rmtree $path, $callback->($status) |
243 | aio_rmtree $pathname, $callback->($status) |
239 | aio_sync $callback->($status) |
244 | aio_sync $callback->($status) |
|
|
245 | aio_syncfs $fh, $callback->($status) |
240 | aio_fsync $fh, $callback->($status) |
246 | aio_fsync $fh, $callback->($status) |
241 | aio_fdatasync $fh, $callback->($status) |
247 | aio_fdatasync $fh, $callback->($status) |
242 | aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status) |
248 | aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status) |
243 | aio_pathsync $path, $callback->($status) |
249 | aio_pathsync $pathname, $callback->($status) |
244 | aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status) |
250 | aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status) |
245 | aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status) |
251 | aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status) |
246 | aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status) |
252 | aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status) |
247 | aio_mlockall $flags, $callback->($status) |
253 | aio_mlockall $flags, $callback->($status) |
248 | aio_group $callback->(...) |
254 | aio_group $callback->(...) |
… | |
… | |
271 | IO::AIO::madvise $scalar, $offset, $length, $advice |
277 | IO::AIO::madvise $scalar, $offset, $length, $advice |
272 | IO::AIO::mprotect $scalar, $offset, $length, $protect |
278 | IO::AIO::mprotect $scalar, $offset, $length, $protect |
273 | IO::AIO::munlock $scalar, $offset = 0, $length = undef |
279 | IO::AIO::munlock $scalar, $offset = 0, $length = undef |
274 | IO::AIO::munlockall |
280 | IO::AIO::munlockall |
275 | |
281 | |
276 | =head2 AIO REQUEST FUNCTIONS |
282 | =head2 API NOTES |
277 | |
283 | |
278 | All the C<aio_*> calls are more or less thin wrappers around the syscall |
284 | All the C<aio_*> calls are more or less thin wrappers around the syscall |
279 | with the same name (sans C<aio_>). The arguments are similar or identical, |
285 | with the same name (sans C<aio_>). The arguments are similar or identical, |
280 | and they all accept an additional (and optional) C<$callback> argument |
286 | and they all accept an additional (and optional) C<$callback> argument |
281 | which must be a code reference. This code reference will get called with |
287 | which must be a code reference. This code reference will be called after |
282 | the syscall return code (e.g. most syscalls return C<-1> on error, unlike |
288 | the syscall has been executed in an asynchronous fashion. The results |
283 | perl, which usually delivers "false") as its sole argument after the given |
289 | of the request will be passed as arguments to the callback (and, if an |
284 | syscall has been executed asynchronously. |
290 | error occured, in C<$!>) - for most requests the syscall return code (e.g. |
|
|
291 | most syscalls return C<-1> on error, unlike perl, which usually delivers |
|
|
292 | "false"). |
|
|
293 | |
|
|
294 | Some requests (such as C<aio_readdir>) pass the actual results and |
|
|
295 | communicate failures by passing C<undef>. |
285 | |
296 | |
286 | All functions expecting a filehandle keep a copy of the filehandle |
297 | All functions expecting a filehandle keep a copy of the filehandle |
287 | internally until the request has finished. |
298 | internally until the request has finished. |
288 | |
299 | |
289 | All functions return request objects of type L<IO::AIO::REQ> that allow |
300 | All functions return request objects of type L<IO::AIO::REQ> that allow |
290 | further manipulation of those requests while they are in-flight. |
301 | further manipulation of those requests while they are in-flight. |
291 | |
302 | |
292 | The pathnames you pass to these routines I<must> be absolute and |
303 | The pathnames you pass to these routines I<should> be absolute. The |
293 | encoded as octets. The reason for the former is that at the time the |
304 | reason for this is that at the time the request is being executed, the |
294 | request is being executed, the current working directory could have |
305 | current working directory could have changed. Alternatively, you can |
295 | changed. Alternatively, you can make sure that you never change the |
306 | make sure that you never change the current working directory anywhere |
296 | current working directory anywhere in the program and then use relative |
307 | in the program and then use relative paths. You can also take advantage |
297 | paths. |
308 | of IO::AIOs working directory abstraction, that lets you specify paths |
|
|
309 | relative to some previously-opened "working directory object" - see the |
|
|
310 | description of the C<IO::AIO::WD> class later in this document. |
298 | |
311 | |
299 | To encode pathnames as octets, either make sure you either: a) always pass |
312 | To encode pathnames as octets, either make sure you either: a) always pass |
300 | in filenames you got from outside (command line, readdir etc.) without |
313 | in filenames you got from outside (command line, readdir etc.) without |
301 | tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module and encode |
314 | tinkering, b) are in your native filesystem encoding, c) use the Encode |
302 | your pathnames to the locale (or other) encoding in effect in the user |
315 | module and encode your pathnames to the locale (or other) encoding in |
303 | environment, d) use Glib::filename_from_unicode on unicode filenames or e) |
316 | effect in the user environment, d) use Glib::filename_from_unicode on |
304 | use something else to ensure your scalar has the correct contents. |
317 | unicode filenames or e) use something else to ensure your scalar has the |
|
|
318 | correct contents. |
305 | |
319 | |
306 | This works, btw. independent of the internal UTF-8 bit, which IO::AIO |
320 | This works, btw. independent of the internal UTF-8 bit, which IO::AIO |
307 | handles correctly whether it is set or not. |
321 | handles correctly whether it is set or not. |
|
|
322 | |
|
|
323 | =head2 AIO REQUEST FUNCTIONS |
308 | |
324 | |
309 | =over 4 |
325 | =over 4 |
310 | |
326 | |
311 | =item $prev_pri = aioreq_pri [$pri] |
327 | =item $prev_pri = aioreq_pri [$pri] |
312 | |
328 | |
… | |
… | |
368 | } else { |
384 | } else { |
369 | die "open failed: $!\n"; |
385 | die "open failed: $!\n"; |
370 | } |
386 | } |
371 | }; |
387 | }; |
372 | |
388 | |
|
|
389 | In addition to all the common open modes/flags (C<O_RDONLY>, C<O_WRONLY>, |
|
|
390 | C<O_RDWR>, C<O_CREAT>, C<O_TRUNC>, C<O_EXCL> and C<O_APPEND>), the |
|
|
391 | following POSIX and non-POSIX constants are available (missing ones on |
|
|
392 | your system are, as usual, C<0>): |
|
|
393 | |
|
|
394 | C<O_ASYNC>, C<O_DIRECT>, C<O_NOATIME>, C<O_CLOEXEC>, C<O_NOCTTY>, C<O_NOFOLLOW>, |
|
|
395 | C<O_NONBLOCK>, C<O_EXEC>, C<O_SEARCH>, C<O_DIRECTORY>, C<O_DSYNC>, |
|
|
396 | C<O_RSYNC>, C<O_SYNC> and C<O_TTY_INIT>. |
|
|
397 | |
373 | |
398 | |
374 | =item aio_close $fh, $callback->($status) |
399 | =item aio_close $fh, $callback->($status) |
375 | |
400 | |
376 | Asynchronously close a file and call the callback with the result |
401 | Asynchronously close a file and call the callback with the result |
377 | code. |
402 | code. |
… | |
… | |
385 | |
410 | |
386 | Or in other words: the file descriptor will be closed, but it will not be |
411 | Or in other words: the file descriptor will be closed, but it will not be |
387 | free for reuse until the perl filehandle is closed. |
412 | free for reuse until the perl filehandle is closed. |
388 | |
413 | |
389 | =cut |
414 | =cut |
|
|
415 | |
|
|
416 | =item aio_seek $fh, $offset, $whence, $callback->($offs) |
|
|
417 | |
|
|
418 | Seeks the filehandle to the new C<$offset>, similarly to perl's |
|
|
419 | C<sysseek>. The C<$whence> can use the traditional values (C<0> for |
|
|
420 | C<IO::AIO::SEEK_SET>, C<1> for C<IO::AIO::SEEK_CUR> or C<2> for |
|
|
421 | C<IO::AIO::SEEK_END>). |
|
|
422 | |
|
|
423 | The resulting absolute offset will be passed to the callback, or C<-1> in |
|
|
424 | case of an error. |
|
|
425 | |
|
|
426 | In theory, the C<$whence> constants could be different than the |
|
|
427 | corresponding values from L<Fcntl>, but perl guarantees they are the same, |
|
|
428 | so don't panic. |
|
|
429 | |
|
|
430 | As a GNU/Linux (and maybe Solaris) extension, also the constants |
|
|
431 | C<IO::AIO::SEEK_DATA> and C<IO::AIO::SEEK_HOLE> are available, if they |
|
|
432 | could be found. No guarantees about suitability for use in C<aio_seek> or |
|
|
433 | Perl's C<sysseek> can be made though, although I would naively assume they |
|
|
434 | "just work". |
390 | |
435 | |
391 | =item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
436 | =item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
392 | |
437 | |
393 | =item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
438 | =item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
394 | |
439 | |
… | |
… | |
427 | |
472 | |
428 | Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts |
473 | Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts |
429 | reading at byte offset C<$in_offset>, and starts writing at the current |
474 | reading at byte offset C<$in_offset>, and starts writing at the current |
430 | file offset of C<$out_fh>. Because of that, it is not safe to issue more |
475 | file offset of C<$out_fh>. Because of that, it is not safe to issue more |
431 | than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each |
476 | than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each |
432 | other. |
477 | other. The same C<$in_fh> works fine though, as this function does not |
|
|
478 | move or use the file offset of C<$in_fh>. |
433 | |
479 | |
434 | Please note that C<aio_sendfile> can read more bytes from C<$in_fh> than |
480 | Please note that C<aio_sendfile> can read more bytes from C<$in_fh> than |
435 | are written, and there is no way to find out how many bytes have been read |
481 | are written, and there is no way to find out how many more bytes have been |
436 | from C<aio_sendfile> alone, as C<aio_sendfile> only provides the number of |
482 | read from C<aio_sendfile> alone, as C<aio_sendfile> only provides the |
437 | bytes written to C<$out_fh>. Only if the result value equals C<$length> |
483 | number of bytes written to C<$out_fh>. Only if the result value equals |
438 | one can assume that C<$length> bytes have been read. |
484 | C<$length> one can assume that C<$length> bytes have been read. |
439 | |
485 | |
440 | Unlike with other C<aio_> functions, it makes a lot of sense to use |
486 | Unlike with other C<aio_> functions, it makes a lot of sense to use |
441 | C<aio_sendfile> on non-blocking sockets, as long as one end (typically |
487 | C<aio_sendfile> on non-blocking sockets, as long as one end (typically |
442 | the C<$in_fh>) is a file - the file I/O will then be asynchronous, while |
488 | the C<$in_fh>) is a file - the file I/O will then be asynchronous, while |
443 | the socket I/O will be non-blocking. Note, however, that you can run into |
489 | the socket I/O will be non-blocking. Note, however, that you can run |
444 | a trap where C<aio_sendfile> reads some data with readahead, then fails |
490 | into a trap where C<aio_sendfile> reads some data with readahead, then |
445 | to write all data, and when the socket is ready the next time, the data |
491 | fails to write all data, and when the socket is ready the next time, the |
446 | in the cache is already lost, forcing C<aio_sendfile> to again hit the |
492 | data in the cache is already lost, forcing C<aio_sendfile> to again hit |
447 | disk. Explicit C<aio_read> + C<aio_write> let's you control resource usage |
493 | the disk. Explicit C<aio_read> + C<aio_write> let's you better control |
448 | much better. |
494 | resource usage. |
449 | |
495 | |
450 | This call tries to make use of a native C<sendfile> syscall to provide |
496 | This call tries to make use of a native C<sendfile>-like syscall to |
451 | zero-copy operation. For this to work, C<$out_fh> should refer to a |
497 | provide zero-copy operation. For this to work, C<$out_fh> should refer to |
452 | socket, and C<$in_fh> should refer to an mmap'able file. |
498 | a socket, and C<$in_fh> should refer to an mmap'able file. |
453 | |
499 | |
454 | If a native sendfile cannot be found or it fails with C<ENOSYS>, |
500 | If a native sendfile cannot be found or it fails with C<ENOSYS>, |
455 | C<ENOTSUP>, C<EOPNOTSUPP>, C<EAFNOSUPPORT>, C<EPROTOTYPE> or C<ENOTSOCK>, |
501 | C<EINVAL>, C<ENOTSUP>, C<EOPNOTSUPP>, C<EAFNOSUPPORT>, C<EPROTOTYPE> or |
456 | it will be emulated, so you can call C<aio_sendfile> on any type of |
502 | C<ENOTSOCK>, it will be emulated, so you can call C<aio_sendfile> on any |
457 | filehandle regardless of the limitations of the operating system. |
503 | type of filehandle regardless of the limitations of the operating system. |
|
|
504 | |
|
|
505 | As native sendfile syscalls (as practically any non-POSIX interface hacked |
|
|
506 | together in a hurry to improve benchmark numbers) tend to be rather buggy |
|
|
507 | on many systems, this implementation tries to work around some known bugs |
|
|
508 | in Linux and FreeBSD kernels (probably others, too), but that might fail, |
|
|
509 | so you really really should check the return value of C<aio_sendfile> - |
|
|
510 | fewre bytes than expected might have been transferred. |
458 | |
511 | |
459 | |
512 | |
460 | =item aio_readahead $fh,$offset,$length, $callback->($retval) |
513 | =item aio_readahead $fh,$offset,$length, $callback->($retval) |
461 | |
514 | |
462 | C<aio_readahead> populates the page cache with data from a file so that |
515 | C<aio_readahead> populates the page cache with data from a file so that |
… | |
… | |
594 | |
647 | |
595 | Asynchronously unlink (delete) a file and call the callback with the |
648 | Asynchronously unlink (delete) a file and call the callback with the |
596 | result code. |
649 | result code. |
597 | |
650 | |
598 | |
651 | |
599 | =item aio_mknod $path, $mode, $dev, $callback->($status) |
652 | =item aio_mknod $pathname, $mode, $dev, $callback->($status) |
600 | |
653 | |
601 | [EXPERIMENTAL] |
654 | [EXPERIMENTAL] |
602 | |
655 | |
603 | Asynchronously create a device node (or fifo). See mknod(2). |
656 | Asynchronously create a device node (or fifo). See mknod(2). |
604 | |
657 | |
605 | The only (POSIX-) portable way of calling this function is: |
658 | The only (POSIX-) portable way of calling this function is: |
606 | |
659 | |
607 | aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ... |
660 | aio_mknod $pathname, IO::AIO::S_IFIFO | $mode, 0, sub { ... |
608 | |
661 | |
609 | See C<aio_stat> for info about some potentially helpful extra constants |
662 | See C<aio_stat> for info about some potentially helpful extra constants |
610 | and functions. |
663 | and functions. |
611 | |
664 | |
612 | =item aio_link $srcpath, $dstpath, $callback->($status) |
665 | =item aio_link $srcpath, $dstpath, $callback->($status) |
… | |
… | |
619 | |
672 | |
620 | Asynchronously create a new symbolic link to the existing object at C<$srcpath> at |
673 | Asynchronously create a new symbolic link to the existing object at C<$srcpath> at |
621 | the path C<$dstpath> and call the callback with the result code. |
674 | the path C<$dstpath> and call the callback with the result code. |
622 | |
675 | |
623 | |
676 | |
624 | =item aio_readlink $path, $callback->($link) |
677 | =item aio_readlink $pathname, $callback->($link) |
625 | |
678 | |
626 | Asynchronously read the symlink specified by C<$path> and pass it to |
679 | Asynchronously read the symlink specified by C<$path> and pass it to |
627 | the callback. If an error occurs, nothing or undef gets passed to the |
680 | the callback. If an error occurs, nothing or undef gets passed to the |
628 | callback. |
681 | callback. |
629 | |
682 | |
630 | |
683 | |
|
|
684 | =item aio_realpath $pathname, $callback->($path) |
|
|
685 | |
|
|
686 | Asynchronously make the path absolute and resolve any symlinks in |
|
|
687 | C<$path>. The resulting path only consists of directories (Same as |
|
|
688 | L<Cwd::realpath>). |
|
|
689 | |
|
|
690 | This request can be used to get the absolute path of the current working |
|
|
691 | directory by passing it a path of F<.> (a single dot). |
|
|
692 | |
|
|
693 | |
631 | =item aio_rename $srcpath, $dstpath, $callback->($status) |
694 | =item aio_rename $srcpath, $dstpath, $callback->($status) |
632 | |
695 | |
633 | Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as |
696 | Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as |
634 | rename(2) and call the callback with the result code. |
697 | rename(2) and call the callback with the result code. |
635 | |
698 | |
… | |
… | |
657 | array-ref with the filenames. |
720 | array-ref with the filenames. |
658 | |
721 | |
659 | |
722 | |
660 | =item aio_readdirx $pathname, $flags, $callback->($entries, $flags) |
723 | =item aio_readdirx $pathname, $flags, $callback->($entries, $flags) |
661 | |
724 | |
662 | Quite similar to C<aio_readdir>, but the C<$flags> argument allows to tune |
725 | Quite similar to C<aio_readdir>, but the C<$flags> argument allows one to |
663 | behaviour and output format. In case of an error, C<$entries> will be |
726 | tune behaviour and output format. In case of an error, C<$entries> will be |
664 | C<undef>. |
727 | C<undef>. |
665 | |
728 | |
666 | The flags are a combination of the following constants, ORed together (the |
729 | The flags are a combination of the following constants, ORed together (the |
667 | flags will also be passed to the callback, possibly modified): |
730 | flags will also be passed to the callback, possibly modified): |
668 | |
731 | |
… | |
… | |
692 | systems that do not deliver the inode information. |
755 | systems that do not deliver the inode information. |
693 | |
756 | |
694 | =item IO::AIO::READDIR_DIRS_FIRST |
757 | =item IO::AIO::READDIR_DIRS_FIRST |
695 | |
758 | |
696 | When this flag is set, then the names will be returned in an order where |
759 | When this flag is set, then the names will be returned in an order where |
697 | likely directories come first. This is useful when you need to quickly |
760 | likely directories come first, in optimal stat order. This is useful when |
698 | find directories, or you want to find all directories while avoiding to |
761 | you need to quickly find directories, or you want to find all directories |
699 | stat() each entry. |
762 | while avoiding to stat() each entry. |
700 | |
763 | |
701 | If the system returns type information in readdir, then this is used |
764 | If the system returns type information in readdir, then this is used |
702 | to find directories directly. Otherwise, likely directories are files |
765 | to find directories directly. Otherwise, likely directories are names |
703 | beginning with ".", or otherwise files with no dots, of which files with |
766 | beginning with ".", or otherwise names with no dots, of which names with |
704 | short names are tried first. |
767 | short names are tried first. |
705 | |
768 | |
706 | =item IO::AIO::READDIR_STAT_ORDER |
769 | =item IO::AIO::READDIR_STAT_ORDER |
707 | |
770 | |
708 | When this flag is set, then the names will be returned in an order |
771 | When this flag is set, then the names will be returned in an order |
… | |
… | |
715 | |
778 | |
716 | =item IO::AIO::READDIR_FOUND_UNKNOWN |
779 | =item IO::AIO::READDIR_FOUND_UNKNOWN |
717 | |
780 | |
718 | This flag should not be set when calling C<aio_readdirx>. Instead, it |
781 | This flag should not be set when calling C<aio_readdirx>. Instead, it |
719 | is being set by C<aio_readdirx>, when any of the C<$type>'s found were |
782 | is being set by C<aio_readdirx>, when any of the C<$type>'s found were |
720 | C<IO::AIO::DT_UNKNOWN>. The absense of this flag therefore indicates that all |
783 | C<IO::AIO::DT_UNKNOWN>. The absence of this flag therefore indicates that all |
721 | C<$type>'s are known, which can be used to speed up some algorithms. |
784 | C<$type>'s are known, which can be used to speed up some algorithms. |
722 | |
785 | |
723 | =back |
786 | =back |
724 | |
787 | |
725 | |
788 | |
726 | =item aio_load $path, $data, $callback->($status) |
789 | =item aio_load $pathname, $data, $callback->($status) |
727 | |
790 | |
728 | This is a composite request that tries to fully load the given file into |
791 | This is a composite request that tries to fully load the given file into |
729 | memory. Status is the same as with aio_read. |
792 | memory. Status is the same as with aio_read. |
730 | |
793 | |
731 | =cut |
794 | =cut |
… | |
… | |
853 | if ($_[0] && $! == EXDEV) { |
916 | if ($_[0] && $! == EXDEV) { |
854 | aioreq_pri $pri; |
917 | aioreq_pri $pri; |
855 | add $grp aio_copy $src, $dst, sub { |
918 | add $grp aio_copy $src, $dst, sub { |
856 | $grp->result ($_[0]); |
919 | $grp->result ($_[0]); |
857 | |
920 | |
858 | if (!$_[0]) { |
921 | unless ($_[0]) { |
859 | aioreq_pri $pri; |
922 | aioreq_pri $pri; |
860 | add $grp aio_unlink $src; |
923 | add $grp aio_unlink $src; |
861 | } |
924 | } |
862 | }; |
925 | }; |
863 | } else { |
926 | } else { |
… | |
… | |
866 | }; |
929 | }; |
867 | |
930 | |
868 | $grp |
931 | $grp |
869 | } |
932 | } |
870 | |
933 | |
871 | =item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) |
934 | =item aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs) |
872 | |
935 | |
873 | Scans a directory (similar to C<aio_readdir>) but additionally tries to |
936 | Scans a directory (similar to C<aio_readdir>) but additionally tries to |
874 | efficiently separate the entries of directory C<$path> into two sets of |
937 | efficiently separate the entries of directory C<$path> into two sets of |
875 | names, directories you can recurse into (directories), and ones you cannot |
938 | names, directories you can recurse into (directories), and ones you cannot |
876 | recurse into (everything else, including symlinks to directories). |
939 | recurse into (everything else, including symlinks to directories). |
… | |
… | |
907 | Then entries will be sorted into likely directories a non-initial dot |
970 | Then entries will be sorted into likely directories a non-initial dot |
908 | currently) and likely non-directories (see C<aio_readdirx>). Then every |
971 | currently) and likely non-directories (see C<aio_readdirx>). Then every |
909 | entry plus an appended C</.> will be C<stat>'ed, likely directories first, |
972 | entry plus an appended C</.> will be C<stat>'ed, likely directories first, |
910 | in order of their inode numbers. If that succeeds, it assumes that the |
973 | in order of their inode numbers. If that succeeds, it assumes that the |
911 | entry is a directory or a symlink to directory (which will be checked |
974 | entry is a directory or a symlink to directory (which will be checked |
912 | seperately). This is often faster than stat'ing the entry itself because |
975 | separately). This is often faster than stat'ing the entry itself because |
913 | filesystems might detect the type of the entry without reading the inode |
976 | filesystems might detect the type of the entry without reading the inode |
914 | data (e.g. ext2fs filetype feature), even on systems that cannot return |
977 | data (e.g. ext2fs filetype feature), even on systems that cannot return |
915 | the filetype information on readdir. |
978 | the filetype information on readdir. |
916 | |
979 | |
917 | If the known number of directories (link count - 2) has been reached, the |
980 | If the known number of directories (link count - 2) has been reached, the |
… | |
… | |
933 | |
996 | |
934 | my $grp = aio_group $cb; |
997 | my $grp = aio_group $cb; |
935 | |
998 | |
936 | $maxreq = 4 if $maxreq <= 0; |
999 | $maxreq = 4 if $maxreq <= 0; |
937 | |
1000 | |
938 | # stat once |
1001 | # get a wd object |
939 | aioreq_pri $pri; |
1002 | aioreq_pri $pri; |
940 | add $grp aio_stat $path, sub { |
1003 | add $grp aio_wd $path, sub { |
|
|
1004 | $_[0] |
941 | return $grp->result () if $_[0]; |
1005 | or return $grp->result (); |
942 | my $now = time; |
|
|
943 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
|
|
944 | |
1006 | |
945 | # read the directory entries |
1007 | my $wd = [shift, "."]; |
|
|
1008 | |
|
|
1009 | # stat once |
946 | aioreq_pri $pri; |
1010 | aioreq_pri $pri; |
947 | add $grp aio_readdirx $path, READDIR_DIRS_FIRST, sub { |
1011 | add $grp aio_stat $wd, sub { |
948 | my $entries = shift |
|
|
949 | or return $grp->result (); |
1012 | return $grp->result () if $_[0]; |
|
|
1013 | my $now = time; |
|
|
1014 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
950 | |
1015 | |
951 | # stat the dir another time |
1016 | # read the directory entries |
952 | aioreq_pri $pri; |
1017 | aioreq_pri $pri; |
|
|
1018 | add $grp aio_readdirx $wd, READDIR_DIRS_FIRST, sub { |
|
|
1019 | my $entries = shift |
|
|
1020 | or return $grp->result (); |
|
|
1021 | |
|
|
1022 | # stat the dir another time |
|
|
1023 | aioreq_pri $pri; |
953 | add $grp aio_stat $path, sub { |
1024 | add $grp aio_stat $wd, sub { |
954 | my $hash2 = join ":", (stat _)[0,1,3,7,9]; |
1025 | my $hash2 = join ":", (stat _)[0,1,3,7,9]; |
955 | |
1026 | |
956 | my $ndirs; |
1027 | my $ndirs; |
957 | |
1028 | |
958 | # take the slow route if anything looks fishy |
1029 | # take the slow route if anything looks fishy |
959 | if ($hash1 ne $hash2 or (stat _)[9] == $now) { |
1030 | if ($hash1 ne $hash2 or (stat _)[9] == $now) { |
960 | $ndirs = -1; |
1031 | $ndirs = -1; |
961 | } else { |
1032 | } else { |
962 | # if nlink == 2, we are finished |
1033 | # if nlink == 2, we are finished |
963 | # for non-posix-fs's, we rely on nlink < 2 |
1034 | # for non-posix-fs's, we rely on nlink < 2 |
964 | $ndirs = (stat _)[3] - 2 |
1035 | $ndirs = (stat _)[3] - 2 |
965 | or return $grp->result ([], $entries); |
1036 | or return $grp->result ([], $entries); |
966 | } |
1037 | } |
967 | |
1038 | |
968 | my (@dirs, @nondirs); |
1039 | my (@dirs, @nondirs); |
969 | |
1040 | |
970 | my $statgrp = add $grp aio_group sub { |
1041 | my $statgrp = add $grp aio_group sub { |
971 | $grp->result (\@dirs, \@nondirs); |
1042 | $grp->result (\@dirs, \@nondirs); |
972 | }; |
1043 | }; |
973 | |
1044 | |
974 | limit $statgrp $maxreq; |
1045 | limit $statgrp $maxreq; |
975 | feed $statgrp sub { |
1046 | feed $statgrp sub { |
976 | return unless @$entries; |
1047 | return unless @$entries; |
977 | my $entry = shift @$entries; |
1048 | my $entry = shift @$entries; |
978 | |
1049 | |
979 | aioreq_pri $pri; |
1050 | aioreq_pri $pri; |
|
|
1051 | $wd->[1] = "$entry/."; |
980 | add $statgrp aio_stat "$path/$entry/.", sub { |
1052 | add $statgrp aio_stat $wd, sub { |
981 | if ($_[0] < 0) { |
1053 | if ($_[0] < 0) { |
982 | push @nondirs, $entry; |
1054 | push @nondirs, $entry; |
983 | } else { |
1055 | } else { |
984 | # need to check for real directory |
1056 | # need to check for real directory |
985 | aioreq_pri $pri; |
1057 | aioreq_pri $pri; |
|
|
1058 | $wd->[1] = $entry; |
986 | add $statgrp aio_lstat "$path/$entry", sub { |
1059 | add $statgrp aio_lstat $wd, sub { |
987 | if (-d _) { |
1060 | if (-d _) { |
988 | push @dirs, $entry; |
1061 | push @dirs, $entry; |
989 | |
1062 | |
990 | unless (--$ndirs) { |
1063 | unless (--$ndirs) { |
991 | push @nondirs, @$entries; |
1064 | push @nondirs, @$entries; |
992 | feed $statgrp; |
1065 | feed $statgrp; |
|
|
1066 | } |
|
|
1067 | } else { |
|
|
1068 | push @nondirs, $entry; |
993 | } |
1069 | } |
994 | } else { |
|
|
995 | push @nondirs, $entry; |
|
|
996 | } |
1070 | } |
997 | } |
1071 | } |
998 | } |
1072 | }; |
999 | }; |
1073 | }; |
1000 | }; |
1074 | }; |
1001 | }; |
1075 | }; |
1002 | }; |
1076 | }; |
1003 | }; |
1077 | }; |
1004 | |
1078 | |
1005 | $grp |
1079 | $grp |
1006 | } |
1080 | } |
1007 | |
1081 | |
1008 | =item aio_rmtree $path, $callback->($status) |
1082 | =item aio_rmtree $pathname, $callback->($status) |
1009 | |
1083 | |
1010 | Delete a directory tree starting (and including) C<$path>, return the |
1084 | Delete a directory tree starting (and including) C<$path>, return the |
1011 | status of the final C<rmdir> only. This is a composite request that |
1085 | status of the final C<rmdir> only. This is a composite request that |
1012 | uses C<aio_scandir> to recurse into and rmdir directories, and unlink |
1086 | uses C<aio_scandir> to recurse into and rmdir directories, and unlink |
1013 | everything else. |
1087 | everything else. |
… | |
… | |
1055 | callback with the fdatasync result code. |
1129 | callback with the fdatasync result code. |
1056 | |
1130 | |
1057 | If this call isn't available because your OS lacks it or it couldn't be |
1131 | If this call isn't available because your OS lacks it or it couldn't be |
1058 | detected, it will be emulated by calling C<fsync> instead. |
1132 | detected, it will be emulated by calling C<fsync> instead. |
1059 | |
1133 | |
|
|
1134 | =item aio_syncfs $fh, $callback->($status) |
|
|
1135 | |
|
|
1136 | Asynchronously call the syncfs syscall to sync the filesystem associated |
|
|
1137 | to the given filehandle and call the callback with the syncfs result |
|
|
1138 | code. If syncfs is not available, calls sync(), but returns C<-1> and sets |
|
|
1139 | errno to C<ENOSYS> nevertheless. |
|
|
1140 | |
1060 | =item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status) |
1141 | =item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status) |
1061 | |
1142 | |
1062 | Sync the data portion of the file specified by C<$offset> and C<$length> |
1143 | Sync the data portion of the file specified by C<$offset> and C<$length> |
1063 | to disk (but NOT the metadata), by calling the Linux-specific |
1144 | to disk (but NOT the metadata), by calling the Linux-specific |
1064 | sync_file_range call. If sync_file_range is not available or it returns |
1145 | sync_file_range call. If sync_file_range is not available or it returns |
… | |
… | |
1067 | C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>, |
1148 | C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>, |
1068 | C<IO::AIO::SYNC_FILE_RANGE_WRITE> and |
1149 | C<IO::AIO::SYNC_FILE_RANGE_WRITE> and |
1069 | C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range |
1150 | C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range |
1070 | manpage for details. |
1151 | manpage for details. |
1071 | |
1152 | |
1072 | =item aio_pathsync $path, $callback->($status) |
1153 | =item aio_pathsync $pathname, $callback->($status) |
1073 | |
1154 | |
1074 | This request tries to open, fsync and close the given path. This is a |
1155 | This request tries to open, fsync and close the given path. This is a |
1075 | composite request intended to sync directories after directory operations |
1156 | composite request intended to sync directories after directory operations |
1076 | (E.g. rename). This might not work on all operating systems or have any |
1157 | (E.g. rename). This might not work on all operating systems or have any |
1077 | specific effect, but usually it makes sure that directory changes get |
1158 | specific effect, but usually it makes sure that directory changes get |
… | |
… | |
1174 | |
1255 | |
1175 | Example: asynchronously lock all current and future pages into memory. |
1256 | Example: asynchronously lock all current and future pages into memory. |
1176 | |
1257 | |
1177 | aio_mlockall IO::AIO::MCL_FUTURE; |
1258 | aio_mlockall IO::AIO::MCL_FUTURE; |
1178 | |
1259 | |
|
|
1260 | =item aio_fiemap $fh, $start, $length, $flags, $count, $cb->(\@extents) |
|
|
1261 | |
|
|
1262 | Queries the extents of the given file (by calling the Linux FIEMAP ioctl, |
|
|
1263 | see L<http://cvs.schmorp.de/IO-AIO/doc/fiemap.txt> for details). If the |
|
|
1264 | C<ioctl> is not available on your OS, then this rquiest will fail with |
|
|
1265 | C<ENOSYS>. |
|
|
1266 | |
|
|
1267 | C<$start> is the starting offset to query extents for, C<$length> is the |
|
|
1268 | size of the range to query - if it is C<undef>, then the whole file will |
|
|
1269 | be queried. |
|
|
1270 | |
|
|
1271 | C<$flags> is a combination of flags (C<IO::AIO::FIEMAP_FLAG_SYNC> or |
|
|
1272 | C<IO::AIO::FIEMAP_FLAG_XATTR> - C<IO::AIO::FIEMAP_FLAGS_COMPAT> is also |
|
|
1273 | exported), and is normally C<0> or C<IO::AIO::FIEMAP_FLAG_SYNC> to query |
|
|
1274 | the data portion. |
|
|
1275 | |
|
|
1276 | C<$count> is the maximum number of extent records to return. If it is |
|
|
1277 | C<undef>, then IO::AIO queries all extents of the file. As a very special |
|
|
1278 | case, if it is C<0>, then the callback receives the number of extents |
|
|
1279 | instead of the extents themselves. |
|
|
1280 | |
|
|
1281 | If an error occurs, the callback receives no arguments. The special |
|
|
1282 | C<errno> value C<IO::AIO::EBADR> is available to test for flag errors. |
|
|
1283 | |
|
|
1284 | Otherwise, the callback receives an array reference with extent |
|
|
1285 | structures. Each extent structure is an array reference itself, with the |
|
|
1286 | following members: |
|
|
1287 | |
|
|
1288 | [$logical, $physical, $length, $flags] |
|
|
1289 | |
|
|
1290 | Flags is any combination of the following flag values (typically either C<0> |
|
|
1291 | or C<IO::AIO::FIEMAP_EXTENT_LAST>): |
|
|
1292 | |
|
|
1293 | C<IO::AIO::FIEMAP_EXTENT_LAST>, C<IO::AIO::FIEMAP_EXTENT_UNKNOWN>, |
|
|
1294 | C<IO::AIO::FIEMAP_EXTENT_DELALLOC>, C<IO::AIO::FIEMAP_EXTENT_ENCODED>, |
|
|
1295 | C<IO::AIO::FIEMAP_EXTENT_DATA_ENCRYPTED>, C<IO::AIO::FIEMAP_EXTENT_NOT_ALIGNED>, |
|
|
1296 | C<IO::AIO::FIEMAP_EXTENT_DATA_INLINE>, C<IO::AIO::FIEMAP_EXTENT_DATA_TAIL>, |
|
|
1297 | C<IO::AIO::FIEMAP_EXTENT_UNWRITTEN>, C<IO::AIO::FIEMAP_EXTENT_MERGED> or |
|
|
1298 | C<IO::AIO::FIEMAP_EXTENT_SHARED>. |
|
|
1299 | |
1179 | =item aio_group $callback->(...) |
1300 | =item aio_group $callback->(...) |
1180 | |
1301 | |
1181 | This is a very special aio request: Instead of doing something, it is a |
1302 | This is a very special aio request: Instead of doing something, it is a |
1182 | container for other aio requests, which is useful if you want to bundle |
1303 | container for other aio requests, which is useful if you want to bundle |
1183 | many requests into a single, composite, request with a definite callback |
1304 | many requests into a single, composite, request with a definite callback |
… | |
… | |
1219 | like sleep and file handle readable/writable, the overhead this creates is |
1340 | like sleep and file handle readable/writable, the overhead this creates is |
1220 | immense (it blocks a thread for a long time) so do not use this function |
1341 | immense (it blocks a thread for a long time) so do not use this function |
1221 | except to put your application under artificial I/O pressure. |
1342 | except to put your application under artificial I/O pressure. |
1222 | |
1343 | |
1223 | =back |
1344 | =back |
|
|
1345 | |
|
|
1346 | |
|
|
1347 | =head2 IO::AIO::WD - multiple working directories |
|
|
1348 | |
|
|
1349 | Your process only has one current working directory, which is used by all |
|
|
1350 | threads. This makes it hard to use relative paths (some other component |
|
|
1351 | could call C<chdir> at any time, and it is hard to control when the path |
|
|
1352 | will be used by IO::AIO). |
|
|
1353 | |
|
|
1354 | One solution for this is to always use absolute paths. This usually works, |
|
|
1355 | but can be quite slow (the kernel has to walk the whole path on every |
|
|
1356 | access), and can also be a hassle to implement. |
|
|
1357 | |
|
|
1358 | Newer POSIX systems have a number of functions (openat, fdopendir, |
|
|
1359 | futimensat and so on) that make it possible to specify working directories |
|
|
1360 | per operation. |
|
|
1361 | |
|
|
1362 | For portability, and because the clowns who "designed", or shall I write, |
|
|
1363 | perpetrated this new interface were obviously half-drunk, this abstraction |
|
|
1364 | cannot be perfect, though. |
|
|
1365 | |
|
|
1366 | IO::AIO allows you to convert directory paths into a so-called IO::AIO::WD |
|
|
1367 | object. This object stores the canonicalised, absolute version of the |
|
|
1368 | path, and on systems that allow it, also a directory file descriptor. |
|
|
1369 | |
|
|
1370 | Everywhere where a pathname is accepted by IO::AIO (e.g. in C<aio_stat> |
|
|
1371 | or C<aio_unlink>), one can specify an array reference with an IO::AIO::WD |
|
|
1372 | object and a pathname instead (or the IO::AIO::WD object alone, which |
|
|
1373 | gets interpreted as C<[$wd, "."]>). If the pathname is absolute, the |
|
|
1374 | IO::AIO::WD object is ignored, otherwise the pathname is resolved relative |
|
|
1375 | to that IO::AIO::WD object. |
|
|
1376 | |
|
|
1377 | For example, to get a wd object for F</etc> and then stat F<passwd> |
|
|
1378 | inside, you would write: |
|
|
1379 | |
|
|
1380 | aio_wd "/etc", sub { |
|
|
1381 | my $etcdir = shift; |
|
|
1382 | |
|
|
1383 | # although $etcdir can be undef on error, there is generally no reason |
|
|
1384 | # to check for errors here, as aio_stat will fail with ENOENT |
|
|
1385 | # when $etcdir is undef. |
|
|
1386 | |
|
|
1387 | aio_stat [$etcdir, "passwd"], sub { |
|
|
1388 | # yay |
|
|
1389 | }; |
|
|
1390 | }; |
|
|
1391 | |
|
|
1392 | That C<aio_wd> is a request and not a normal function shows that creating |
|
|
1393 | an IO::AIO::WD object is itself a potentially blocking operation, which is |
|
|
1394 | why it is done asynchronously. |
|
|
1395 | |
|
|
1396 | To stat the directory obtained with C<aio_wd> above, one could write |
|
|
1397 | either of the following three request calls: |
|
|
1398 | |
|
|
1399 | aio_lstat "/etc" , sub { ... # pathname as normal string |
|
|
1400 | aio_lstat [$wd, "."], sub { ... # "." relative to $wd (i.e. $wd itself) |
|
|
1401 | aio_lstat $wd , sub { ... # shorthand for the previous |
|
|
1402 | |
|
|
1403 | As with normal pathnames, IO::AIO keeps a copy of the working directory |
|
|
1404 | object and the pathname string, so you could write the following without |
|
|
1405 | causing any issues due to C<$path> getting reused: |
|
|
1406 | |
|
|
1407 | my $path = [$wd, undef]; |
|
|
1408 | |
|
|
1409 | for my $name (qw(abc def ghi)) { |
|
|
1410 | $path->[1] = $name; |
|
|
1411 | aio_stat $path, sub { |
|
|
1412 | # ... |
|
|
1413 | }; |
|
|
1414 | } |
|
|
1415 | |
|
|
1416 | There are some caveats: when directories get renamed (or deleted), the |
|
|
1417 | pathname string doesn't change, so will point to the new directory (or |
|
|
1418 | nowhere at all), while the directory fd, if available on the system, |
|
|
1419 | will still point to the original directory. Most functions accepting a |
|
|
1420 | pathname will use the directory fd on newer systems, and the string on |
|
|
1421 | older systems. Some functions (such as realpath) will always rely on the |
|
|
1422 | string form of the pathname. |
|
|
1423 | |
|
|
1424 | So this fucntionality is mainly useful to get some protection against |
|
|
1425 | C<chdir>, to easily get an absolute path out of a relative path for future |
|
|
1426 | reference, and to speed up doing many operations in the same directory |
|
|
1427 | (e.g. when stat'ing all files in a directory). |
|
|
1428 | |
|
|
1429 | The following functions implement this working directory abstraction: |
|
|
1430 | |
|
|
1431 | =over 4 |
|
|
1432 | |
|
|
1433 | =item aio_wd $pathname, $callback->($wd) |
|
|
1434 | |
|
|
1435 | Asynchonously canonicalise the given pathname and convert it to an |
|
|
1436 | IO::AIO::WD object representing it. If possible and supported on the |
|
|
1437 | system, also open a directory fd to speed up pathname resolution relative |
|
|
1438 | to this working directory. |
|
|
1439 | |
|
|
1440 | If something goes wrong, then C<undef> is passwd to the callback instead |
|
|
1441 | of a working directory object and C<$!> is set appropriately. Since |
|
|
1442 | passing C<undef> as working directory component of a pathname fails the |
|
|
1443 | request with C<ENOENT>, there is often no need for error checking in the |
|
|
1444 | C<aio_wd> callback, as future requests using the value will fail in the |
|
|
1445 | expected way. |
|
|
1446 | |
|
|
1447 | If this call isn't available because your OS lacks it or it couldn't be |
|
|
1448 | detected, it will be emulated by calling C<fsync> instead. |
|
|
1449 | |
|
|
1450 | =item IO::AIO::CWD |
|
|
1451 | |
|
|
1452 | This is a compiletime constant (object) that represents the process |
|
|
1453 | current working directory. |
|
|
1454 | |
|
|
1455 | Specifying this object as working directory object for a pathname is as |
|
|
1456 | if the pathname would be specified directly, without a directory object, |
|
|
1457 | e.g., these calls are functionally identical: |
|
|
1458 | |
|
|
1459 | aio_stat "somefile", sub { ... }; |
|
|
1460 | aio_stat [IO::AIO::CWD, "somefile"], sub { ... }; |
|
|
1461 | |
|
|
1462 | =back |
|
|
1463 | |
1224 | |
1464 | |
1225 | =head2 IO::AIO::REQ CLASS |
1465 | =head2 IO::AIO::REQ CLASS |
1226 | |
1466 | |
1227 | All non-aggregate C<aio_*> functions return an object of this class when |
1467 | All non-aggregate C<aio_*> functions return an object of this class when |
1228 | called in non-void context. |
1468 | called in non-void context. |
… | |
… | |
1346 | |
1586 | |
1347 | Sets a feeder/generator on this group: every group can have an attached |
1587 | Sets a feeder/generator on this group: every group can have an attached |
1348 | generator that generates requests if idle. The idea behind this is that, |
1588 | generator that generates requests if idle. The idea behind this is that, |
1349 | although you could just queue as many requests as you want in a group, |
1589 | although you could just queue as many requests as you want in a group, |
1350 | this might starve other requests for a potentially long time. For example, |
1590 | this might starve other requests for a potentially long time. For example, |
1351 | C<aio_scandir> might generate hundreds of thousands C<aio_stat> requests, |
1591 | C<aio_scandir> might generate hundreds of thousands of C<aio_stat> |
1352 | delaying any later requests for a long time. |
1592 | requests, delaying any later requests for a long time. |
1353 | |
1593 | |
1354 | To avoid this, and allow incremental generation of requests, you can |
1594 | To avoid this, and allow incremental generation of requests, you can |
1355 | instead a group and set a feeder on it that generates those requests. The |
1595 | instead a group and set a feeder on it that generates those requests. The |
1356 | feed callback will be called whenever there are few enough (see C<limit>, |
1596 | feed callback will be called whenever there are few enough (see C<limit>, |
1357 | below) requests active in the group itself and is expected to queue more |
1597 | below) requests active in the group itself and is expected to queue more |
… | |
… | |
1555 | Sets the minimum idle timeout (default 10) after which worker threads are |
1795 | Sets the minimum idle timeout (default 10) after which worker threads are |
1556 | allowed to exit. SEe C<IO::AIO::max_idle>. |
1796 | allowed to exit. SEe C<IO::AIO::max_idle>. |
1557 | |
1797 | |
1558 | =item IO::AIO::max_outstanding $maxreqs |
1798 | =item IO::AIO::max_outstanding $maxreqs |
1559 | |
1799 | |
|
|
1800 | Sets the maximum number of outstanding requests to C<$nreqs>. If |
|
|
1801 | you do queue up more than this number of requests, the next call to |
|
|
1802 | C<IO::AIO::poll_cb> (and other functions calling C<poll_cb>, such as |
|
|
1803 | C<IO::AIO::flush> or C<IO::AIO::poll>) will block until the limit is no |
|
|
1804 | longer exceeded. |
|
|
1805 | |
|
|
1806 | In other words, this setting does not enforce a queue limit, but can be |
|
|
1807 | used to make poll functions block if the limit is exceeded. |
|
|
1808 | |
1560 | This is a very bad function to use in interactive programs because it |
1809 | This is a very bad function to use in interactive programs because it |
1561 | blocks, and a bad way to reduce concurrency because it is inexact: Better |
1810 | blocks, and a bad way to reduce concurrency because it is inexact: Better |
1562 | use an C<aio_group> together with a feed callback. |
1811 | use an C<aio_group> together with a feed callback. |
1563 | |
1812 | |
1564 | Sets the maximum number of outstanding requests to C<$nreqs>. If you |
1813 | It's main use is in scripts without an event loop - when you want to stat |
1565 | do queue up more than this number of requests, the next call to the |
1814 | a lot of files, you can write somehting like this: |
1566 | C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>) |
|
|
1567 | function will block until the limit is no longer exceeded. |
|
|
1568 | |
1815 | |
1569 | The default value is very large, so there is no practical limit on the |
1816 | IO::AIO::max_outstanding 32; |
1570 | number of outstanding requests. |
|
|
1571 | |
1817 | |
1572 | You can still queue as many requests as you want. Therefore, |
1818 | for my $path (...) { |
1573 | C<max_outstanding> is mainly useful in simple scripts (with low values) or |
1819 | aio_stat $path , ...; |
1574 | as a stop gap to shield against fatal memory overflow (with large values). |
1820 | IO::AIO::poll_cb; |
|
|
1821 | } |
|
|
1822 | |
|
|
1823 | IO::AIO::flush; |
|
|
1824 | |
|
|
1825 | The call to C<poll_cb> inside the loop will normally return instantly, but |
|
|
1826 | as soon as more thna C<32> reqeusts are in-flight, it will block until |
|
|
1827 | some requests have been handled. This keeps the loop from pushing a large |
|
|
1828 | number of C<aio_stat> requests onto the queue. |
|
|
1829 | |
|
|
1830 | The default value for C<max_outstanding> is very large, so there is no |
|
|
1831 | practical limit on the number of outstanding requests. |
1575 | |
1832 | |
1576 | =back |
1833 | =back |
1577 | |
1834 | |
1578 | =head3 STATISTICAL INFORMATION |
1835 | =head3 STATISTICAL INFORMATION |
1579 | |
1836 | |
… | |
… | |
1619 | |
1876 | |
1620 | =item IO::AIO::fadvise $fh, $offset, $len, $advice |
1877 | =item IO::AIO::fadvise $fh, $offset, $len, $advice |
1621 | |
1878 | |
1622 | Simply calls the C<posix_fadvise> function (see its |
1879 | Simply calls the C<posix_fadvise> function (see its |
1623 | manpage for details). The following advice constants are |
1880 | manpage for details). The following advice constants are |
1624 | avaiable: C<IO::AIO::FADV_NORMAL>, C<IO::AIO::FADV_SEQUENTIAL>, |
1881 | available: C<IO::AIO::FADV_NORMAL>, C<IO::AIO::FADV_SEQUENTIAL>, |
1625 | C<IO::AIO::FADV_RANDOM>, C<IO::AIO::FADV_NOREUSE>, |
1882 | C<IO::AIO::FADV_RANDOM>, C<IO::AIO::FADV_NOREUSE>, |
1626 | C<IO::AIO::FADV_WILLNEED>, C<IO::AIO::FADV_DONTNEED>. |
1883 | C<IO::AIO::FADV_WILLNEED>, C<IO::AIO::FADV_DONTNEED>. |
1627 | |
1884 | |
1628 | On systems that do not implement C<posix_fadvise>, this function returns |
1885 | On systems that do not implement C<posix_fadvise>, this function returns |
1629 | ENOSYS, otherwise the return value of C<posix_fadvise>. |
1886 | ENOSYS, otherwise the return value of C<posix_fadvise>. |
1630 | |
1887 | |
1631 | =item IO::AIO::madvise $scalar, $offset, $len, $advice |
1888 | =item IO::AIO::madvise $scalar, $offset, $len, $advice |
1632 | |
1889 | |
1633 | Simply calls the C<posix_madvise> function (see its |
1890 | Simply calls the C<posix_madvise> function (see its |
1634 | manpage for details). The following advice constants are |
1891 | manpage for details). The following advice constants are |
1635 | avaiable: C<IO::AIO::MADV_NORMAL>, C<IO::AIO::MADV_SEQUENTIAL>, |
1892 | available: C<IO::AIO::MADV_NORMAL>, C<IO::AIO::MADV_SEQUENTIAL>, |
1636 | C<IO::AIO::MADV_RANDOM>, C<IO::AIO::MADV_WILLNEED>, C<IO::AIO::MADV_DONTNEED>. |
1893 | C<IO::AIO::MADV_RANDOM>, C<IO::AIO::MADV_WILLNEED>, C<IO::AIO::MADV_DONTNEED>. |
1637 | |
1894 | |
1638 | On systems that do not implement C<posix_madvise>, this function returns |
1895 | On systems that do not implement C<posix_madvise>, this function returns |
1639 | ENOSYS, otherwise the return value of C<posix_madvise>. |
1896 | ENOSYS, otherwise the return value of C<posix_madvise>. |
1640 | |
1897 | |
1641 | =item IO::AIO::mprotect $scalar, $offset, $len, $protect |
1898 | =item IO::AIO::mprotect $scalar, $offset, $len, $protect |
1642 | |
1899 | |
1643 | Simply calls the C<mprotect> function on the preferably AIO::mmap'ed |
1900 | Simply calls the C<mprotect> function on the preferably AIO::mmap'ed |
1644 | $scalar (see its manpage for details). The following protect |
1901 | $scalar (see its manpage for details). The following protect |
1645 | constants are avaiable: C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_READ>, |
1902 | constants are available: C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_READ>, |
1646 | C<IO::AIO::PROT_WRITE>, C<IO::AIO::PROT_EXEC>. |
1903 | C<IO::AIO::PROT_WRITE>, C<IO::AIO::PROT_EXEC>. |
1647 | |
1904 | |
1648 | On systems that do not implement C<mprotect>, this function returns |
1905 | On systems that do not implement C<mprotect>, this function returns |
1649 | ENOSYS, otherwise the return value of C<mprotect>. |
1906 | ENOSYS, otherwise the return value of C<mprotect>. |
1650 | |
1907 | |
… | |
… | |
1712 | Calls the C<munlockall> function. |
1969 | Calls the C<munlockall> function. |
1713 | |
1970 | |
1714 | On systems that do not implement C<munlockall>, this function returns |
1971 | On systems that do not implement C<munlockall>, this function returns |
1715 | ENOSYS, otherwise the return value of C<munlockall>. |
1972 | ENOSYS, otherwise the return value of C<munlockall>. |
1716 | |
1973 | |
|
|
1974 | =item IO::AIO::splice $r_fh, $r_off, $w_fh, $w_off, $length, $flags |
|
|
1975 | |
|
|
1976 | Calls the GNU/Linux C<splice(2)> syscall, if available. If C<$r_off> or |
|
|
1977 | C<$w_off> are C<undef>, then C<NULL> is passed for these, otherwise they |
|
|
1978 | should be the file offset. |
|
|
1979 | |
|
|
1980 | The following symbol flag values are available: C<IO::AIO::SPLICE_F_MOVE>, |
|
|
1981 | C<IO::AIO::SPLICE_F_NONBLOCK>, C<IO::AIO::SPLICE_F_MORE> and |
|
|
1982 | C<IO::AIO::SPLICE_F_GIFT>. |
|
|
1983 | |
|
|
1984 | See the C<splice(2)> manpage for details. |
|
|
1985 | |
|
|
1986 | =item IO::AIO::tee $r_fh, $w_fh, $length, $flags |
|
|
1987 | |
|
|
1988 | Calls the GNU/Linux C<tee(2)> syscall, see it's manpage and the |
|
|
1989 | description for C<IO::AIO::splice> above for details. |
|
|
1990 | |
1717 | =back |
1991 | =back |
1718 | |
1992 | |
1719 | =cut |
1993 | =cut |
1720 | |
1994 | |
1721 | min_parallel 8; |
1995 | min_parallel 8; |
… | |
… | |
1755 | Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => |
2029 | Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => |
1756 | \&IO::AIO::poll_cb); |
2030 | \&IO::AIO::poll_cb); |
1757 | |
2031 | |
1758 | =head2 FORK BEHAVIOUR |
2032 | =head2 FORK BEHAVIOUR |
1759 | |
2033 | |
1760 | This module should do "the right thing" when the process using it forks: |
2034 | Usage of pthreads in a program changes the semantics of fork |
|
|
2035 | considerably. Specifically, only async-safe functions can be called after |
|
|
2036 | fork. Perl doesn't know about this, so in general, you cannot call fork |
|
|
2037 | with defined behaviour in perl if pthreads are involved. IO::AIO uses |
|
|
2038 | pthreads, so this applies, but many other extensions and (for inexplicable |
|
|
2039 | reasons) perl itself often is linked against pthreads, so this limitation |
|
|
2040 | applies to quite a lot of perls. |
1761 | |
2041 | |
1762 | Before the fork, IO::AIO enters a quiescent state where no requests |
2042 | This module no longer tries to fight your OS, or POSIX. That means IO::AIO |
1763 | can be added in other threads and no results will be processed. After |
2043 | only works in the process that loaded it. Forking is fully supported, but |
1764 | the fork the parent simply leaves the quiescent state and continues |
2044 | using IO::AIO in the child is not. |
1765 | request/result processing, while the child frees the request/result queue |
|
|
1766 | (so that the requests started before the fork will only be handled in the |
|
|
1767 | parent). Threads will be started on demand until the limit set in the |
|
|
1768 | parent process has been reached again. |
|
|
1769 | |
2045 | |
1770 | In short: the parent will, after a short pause, continue as if fork had |
2046 | You might get around by not I<using> IO::AIO before (or after) |
1771 | not been called, while the child will act as if IO::AIO has not been used |
2047 | forking. You could also try to call the L<IO::AIO::reinit> function in the |
1772 | yet. |
2048 | child: |
|
|
2049 | |
|
|
2050 | =over 4 |
|
|
2051 | |
|
|
2052 | =item IO::AIO::reinit |
|
|
2053 | |
|
|
2054 | Abandons all current requests and I/O threads and simply reinitialises all |
|
|
2055 | data structures. This is not an operation supported by any standards, but |
|
|
2056 | happens to work on GNU/Linux and some newer BSD systems. |
|
|
2057 | |
|
|
2058 | The only reasonable use for this function is to call it after forking, if |
|
|
2059 | C<IO::AIO> was used in the parent. Calling it while IO::AIO is active in |
|
|
2060 | the process will result in undefined behaviour. Calling it at any time |
|
|
2061 | will also result in any undefined (by POSIX) behaviour. |
|
|
2062 | |
|
|
2063 | =back |
1773 | |
2064 | |
1774 | =head2 MEMORY USAGE |
2065 | =head2 MEMORY USAGE |
1775 | |
2066 | |
1776 | Per-request usage: |
2067 | Per-request usage: |
1777 | |
2068 | |