ViewVC Help
View File | Revision Log | Show Annotations | Download File
/cvs/IO-AIO/AIO.pm
(Generate patch)

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.171 by root, Sat Jan 2 14:24:32 2010 UTC vs.
Revision 1.224 by root, Sat Apr 7 00:50:33 2012 UTC

… …
4 4
5=head1 SYNOPSIS 5=head1 SYNOPSIS
6 6
7 use IO::AIO; 7 use IO::AIO;
8 8
9 aio_open "/etc/passwd", O_RDONLY, 0, sub { 9 aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
10 my $fh = shift 10 my $fh = shift
11 or die "/etc/passwd: $!"; 11 or die "/etc/passwd: $!";
12 ... 12 ...
13 }; 13 };
14 14
… …
25 my $req = aio_unlink "/tmp/file", sub { }; 25 my $req = aio_unlink "/tmp/file", sub { };
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
31 # AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...)
32 use AnyEvent::AIO;
33
34 # EV integration
35 my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
36
37 # Event integration
38 Event->io (fd => IO::AIO::poll_fileno,
39 poll => 'r',
40 cb => \&IO::AIO::poll_cb);
41
42 # Glib/Gtk2 integration
43 add_watch Glib::IO IO::AIO::poll_fileno,
44 in => sub { IO::AIO::poll_cb; 1 };
45
46 # Tk integration
47 Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
48 readable => \&IO::AIO::poll_cb);
49
50 # Danga::Socket integration
51 Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
52 \&IO::AIO::poll_cb);
53 30
54=head1 DESCRIPTION 31=head1 DESCRIPTION
55 32
56This module implements asynchronous I/O using whatever means your 33This module implements asynchronous I/O using whatever means your
57operating system supports. It is implemented as an interface to C<libeio> 34operating system supports. It is implemented as an interface to C<libeio>
… …
99 76
100 # register the IO::AIO callback with EV 77 # register the IO::AIO callback with EV
101 my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; 78 my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
102 79
103 # queue the request to open /etc/passwd 80 # queue the request to open /etc/passwd
104 aio_open "/etc/passwd", O_RDONLY, 0, sub { 81 aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
105 my $fh = shift 82 my $fh = shift
106 or die "error while opening: $!"; 83 or die "error while opening: $!";
107 84
108 # stat'ing filehandles is generally non-blocking 85 # stat'ing filehandles is generally non-blocking
109 my $size = -s $fh; 86 my $size = -s $fh;
… …
191use common::sense; 168use common::sense;
192 169
193use base 'Exporter'; 170use base 'Exporter';
194 171
195BEGIN { 172BEGIN {
196 our $VERSION = '3.4'; 173 our $VERSION = '4.14';
197 174
198 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
199 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
200 aio_scandir aio_symlink aio_readlink aio_sync aio_fsync 177 aio_scandir aio_symlink aio_readlink aio_realpath aio_sync
201 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
202 aio_rename aio_link aio_move aio_copy aio_group 180 aio_rename aio_link aio_move aio_copy aio_group
203 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
204 aio_chmod aio_utime aio_truncate 182 aio_chmod aio_utime aio_truncate
205 aio_msync aio_mtouch); 183 aio_msync aio_mtouch aio_mlock aio_mlockall
184 aio_statvfs
185 aio_wd);
206 186
207 our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice)); 187 our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice));
208 our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush 188 our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush
209 min_parallel max_parallel max_idle 189 min_parallel max_parallel max_idle idle_timeout
210 nreqs nready npending nthreads 190 nreqs nready npending nthreads
211 max_poll_time max_poll_reqs 191 max_poll_time max_poll_reqs
212 sendfile fadvise); 192 sendfile fadvise madvise
193 mmap munmap munlock munlockall);
213 194
214 push @AIO_REQ, qw(aio_busy); # not exported 195 push @AIO_REQ, qw(aio_busy); # not exported
215 196
216 @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; 197 @IO::AIO::GRP::ISA = 'IO::AIO::REQ';
217 198
… …
219 XSLoader::load ("IO::AIO", $VERSION); 200 XSLoader::load ("IO::AIO", $VERSION);
220} 201}
221 202
222=head1 FUNCTIONS 203=head1 FUNCTIONS
223 204
224=head2 AIO REQUEST FUNCTIONS 205=head2 QUICK OVERVIEW
206
207This section simply lists the prototypes of the most important functions
208for quick reference. See the following sections for function-by-function
209documentation.
210
211 aio_wd $pathname, $callback->($wd)
212 aio_open $pathname, $flags, $mode, $callback->($fh)
213 aio_close $fh, $callback->($status)
214 aio_seek $fh,$offset,$whence, $callback->($offs)
215 aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
216 aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
217 aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
218 aio_readahead $fh,$offset,$length, $callback->($retval)
219 aio_stat $fh_or_path, $callback->($status)
220 aio_lstat $fh, $callback->($status)
221 aio_statvfs $fh_or_path, $callback->($statvfs)
222 aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
223 aio_chown $fh_or_path, $uid, $gid, $callback->($status)
224 aio_chmod $fh_or_path, $mode, $callback->($status)
225 aio_truncate $fh_or_path, $offset, $callback->($status)
226 aio_unlink $pathname, $callback->($status)
227 aio_mknod $pathname, $mode, $dev, $callback->($status)
228 aio_link $srcpath, $dstpath, $callback->($status)
229 aio_symlink $srcpath, $dstpath, $callback->($status)
230 aio_readlink $pathname, $callback->($link)
231 aio_realpath $pathname, $callback->($link)
232 aio_rename $srcpath, $dstpath, $callback->($status)
233 aio_mkdir $pathname, $mode, $callback->($status)
234 aio_rmdir $pathname, $callback->($status)
235 aio_readdir $pathname, $callback->($entries)
236 aio_readdirx $pathname, $flags, $callback->($entries, $flags)
237 IO::AIO::READDIR_DENTS IO::AIO::READDIR_DIRS_FIRST
238 IO::AIO::READDIR_STAT_ORDER IO::AIO::READDIR_FOUND_UNKNOWN
239 aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs)
240 aio_load $pathname, $data, $callback->($status)
241 aio_copy $srcpath, $dstpath, $callback->($status)
242 aio_move $srcpath, $dstpath, $callback->($status)
243 aio_rmtree $pathname, $callback->($status)
244 aio_sync $callback->($status)
245 aio_syncfs $fh, $callback->($status)
246 aio_fsync $fh, $callback->($status)
247 aio_fdatasync $fh, $callback->($status)
248 aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
249 aio_pathsync $pathname, $callback->($status)
250 aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
251 aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
252 aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
253 aio_mlockall $flags, $callback->($status)
254 aio_group $callback->(...)
255 aio_nop $callback->()
256
257 $prev_pri = aioreq_pri [$pri]
258 aioreq_nice $pri_adjust
259
260 IO::AIO::poll_wait
261 IO::AIO::poll_cb
262 IO::AIO::poll
263 IO::AIO::flush
264 IO::AIO::max_poll_reqs $nreqs
265 IO::AIO::max_poll_time $seconds
266 IO::AIO::min_parallel $nthreads
267 IO::AIO::max_parallel $nthreads
268 IO::AIO::max_idle $nthreads
269 IO::AIO::idle_timeout $seconds
270 IO::AIO::max_outstanding $maxreqs
271 IO::AIO::nreqs
272 IO::AIO::nready
273 IO::AIO::npending
274
275 IO::AIO::sendfile $ofh, $ifh, $offset, $count
276 IO::AIO::fadvise $fh, $offset, $len, $advice
277 IO::AIO::madvise $scalar, $offset, $length, $advice
278 IO::AIO::mprotect $scalar, $offset, $length, $protect
279 IO::AIO::munlock $scalar, $offset = 0, $length = undef
280 IO::AIO::munlockall
281
282=head2 API NOTES
225 283
226All the C<aio_*> calls are more or less thin wrappers around the syscall 284All the C<aio_*> calls are more or less thin wrappers around the syscall
227with the same name (sans C<aio_>). The arguments are similar or identical, 285with the same name (sans C<aio_>). The arguments are similar or identical,
228and they all accept an additional (and optional) C<$callback> argument 286and they all accept an additional (and optional) C<$callback> argument
229which must be a code reference. This code reference will get called with 287which must be a code reference. This code reference will be called after
230the syscall return code (e.g. most syscalls return C<-1> on error, unlike 288the syscall has been executed in an asynchronous fashion. The results
231perl, which usually delivers "false") as its sole argument after the given 289of the request will be passed as arguments to the callback (and, if an
232syscall has been executed asynchronously. 290error occured, in C<$!>) - for most requests the syscall return code (e.g.
291most syscalls return C<-1> on error, unlike perl, which usually delivers
292"false").
293
294Some requests (such as C<aio_readdir>) pass the actual results and
295communicate failures by passing C<undef>.
233 296
234All functions expecting a filehandle keep a copy of the filehandle 297All functions expecting a filehandle keep a copy of the filehandle
235internally until the request has finished. 298internally until the request has finished.
236 299
237All functions return request objects of type L<IO::AIO::REQ> that allow 300All functions return request objects of type L<IO::AIO::REQ> that allow
238further manipulation of those requests while they are in-flight. 301further manipulation of those requests while they are in-flight.
239 302
240The pathnames you pass to these routines I<must> be absolute and 303The pathnames you pass to these routines I<should> be absolute. The
241encoded as octets. The reason for the former is that at the time the 304reason for this is that at the time the request is being executed, the
242request is being executed, the current working directory could have 305current working directory could have changed. Alternatively, you can
243changed. Alternatively, you can make sure that you never change the 306make sure that you never change the current working directory anywhere
244current working directory anywhere in the program and then use relative 307in the program and then use relative paths. You can also take advantage
245paths. 308of IO::AIOs working directory abstraction, that lets you specify paths
309relative to some previously-opened "working directory object" - see the
310description of the C<IO::AIO::WD> class later in this document.
246 311
247To encode pathnames as octets, either make sure you either: a) always pass 312To encode pathnames as octets, either make sure you either: a) always pass
248in filenames you got from outside (command line, readdir etc.) without 313in filenames you got from outside (command line, readdir etc.) without
249tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module and encode 314tinkering, b) are in your native filesystem encoding, c) use the Encode
250your pathnames to the locale (or other) encoding in effect in the user 315module and encode your pathnames to the locale (or other) encoding in
251environment, d) use Glib::filename_from_unicode on unicode filenames or e) 316effect in the user environment, d) use Glib::filename_from_unicode on
252use something else to ensure your scalar has the correct contents. 317unicode filenames or e) use something else to ensure your scalar has the
318correct contents.
253 319
254This works, btw. independent of the internal UTF-8 bit, which IO::AIO 320This works, btw. independent of the internal UTF-8 bit, which IO::AIO
255handles correctly whether it is set or not. 321handles correctly whether it is set or not.
322
323=head2 AIO REQUEST FUNCTIONS
256 324
257=over 4 325=over 4
258 326
259=item $prev_pri = aioreq_pri [$pri] 327=item $prev_pri = aioreq_pri [$pri]
260 328
… …
307by the umask in effect then the request is being executed, so better never 375by the umask in effect then the request is being executed, so better never
308change the umask. 376change the umask.
309 377
310Example: 378Example:
311 379
312 aio_open "/etc/passwd", O_RDONLY, 0, sub { 380 aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
313 if ($_[0]) { 381 if ($_[0]) {
314 print "open successful, fh is $_[0]\n"; 382 print "open successful, fh is $_[0]\n";
315 ... 383 ...
316 } else { 384 } else {
317 die "open failed: $!\n"; 385 die "open failed: $!\n";
318 } 386 }
319 }; 387 };
320 388
389In addition to all the common open modes/flags (C<O_RDONLY>, C<O_WRONLY>,
390C<O_RDWR>, C<O_CREAT>, C<O_TRUNC>, C<O_EXCL> and C<O_APPEND>), the
391following POSIX and non-POSIX constants are available (missing ones on
392your system are, as usual, C<0>):
393
394C<O_ASYNC>, C<O_DIRECT>, C<O_NOATIME>, C<O_CLOEXEC>, C<O_NOCTTY>, C<O_NOFOLLOW>,
395C<O_NONBLOCK>, C<O_EXEC>, C<O_SEARCH>, C<O_DIRECTORY>, C<O_DSYNC>,
396C<O_RSYNC>, C<O_SYNC> and C<O_TTY_INIT>.
397
321 398
322=item aio_close $fh, $callback->($status) 399=item aio_close $fh, $callback->($status)
323 400
324Asynchronously close a file and call the callback with the result 401Asynchronously close a file and call the callback with the result
325code. 402code.
… …
333 410
334Or in other words: the file descriptor will be closed, but it will not be 411Or in other words: the file descriptor will be closed, but it will not be
335free for reuse until the perl filehandle is closed. 412free for reuse until the perl filehandle is closed.
336 413
337=cut 414=cut
415
416=item aio_seek $fh, $offset, $whence, $callback->($offs)
417
418Seeks the filehandle to the new C<$offset>, similarly to perl's
419C<sysseek>. The C<$whence> can use the traditional values (C<0> for
420C<IO::AIO::SEEK_SET>, C<1> for C<IO::AIO::SEEK_CUR> or C<2> for
421C<IO::AIO::SEEK_END>).
422
423The resulting absolute offset will be passed to the callback, or C<-1> in
424case of an error.
425
426In theory, the C<$whence> constants could be different than the
427corresponding values from L<Fcntl>, but perl guarantees they are the same,
428so don't panic.
338 429
339=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) 430=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
340 431
341=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) 432=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
342 433
… …
375 466
376Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts 467Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
377reading at byte offset C<$in_offset>, and starts writing at the current 468reading at byte offset C<$in_offset>, and starts writing at the current
378file offset of C<$out_fh>. Because of that, it is not safe to issue more 469file offset of C<$out_fh>. Because of that, it is not safe to issue more
379than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each 470than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each
380other. 471other. The same C<$in_fh> works fine though, as this function does not
472move or use the file offset of C<$in_fh>.
381 473
474Please note that C<aio_sendfile> can read more bytes from C<$in_fh> than
475are written, and there is no way to find out how many more bytes have been
476read from C<aio_sendfile> alone, as C<aio_sendfile> only provides the
477number of bytes written to C<$out_fh>. Only if the result value equals
478C<$length> one can assume that C<$length> bytes have been read.
479
480Unlike with other C<aio_> functions, it makes a lot of sense to use
481C<aio_sendfile> on non-blocking sockets, as long as one end (typically
482the C<$in_fh>) is a file - the file I/O will then be asynchronous, while
483the socket I/O will be non-blocking. Note, however, that you can run
484into a trap where C<aio_sendfile> reads some data with readahead, then
485fails to write all data, and when the socket is ready the next time, the
486data in the cache is already lost, forcing C<aio_sendfile> to again hit
487the disk. Explicit C<aio_read> + C<aio_write> let's you better control
488resource usage.
489
382This call tries to make use of a native C<sendfile> syscall to provide 490This call tries to make use of a native C<sendfile>-like syscall to
383zero-copy operation. For this to work, C<$out_fh> should refer to a 491provide zero-copy operation. For this to work, C<$out_fh> should refer to
384socket, and C<$in_fh> should refer to mmap'able file. 492a socket, and C<$in_fh> should refer to an mmap'able file.
385 493
386If a native sendfile cannot be found or it fails with C<ENOSYS>, 494If a native sendfile cannot be found or it fails with C<ENOSYS>,
387C<ENOTSUP>, C<EOPNOTSUPP>, C<EAFNOSUPPORT>, C<EPROTOTYPE> or C<ENOTSOCK>, 495C<EINVAL>, C<ENOTSUP>, C<EOPNOTSUPP>, C<EAFNOSUPPORT>, C<EPROTOTYPE> or
388it will be emulated, so you can call C<aio_sendfile> on any type of 496C<ENOTSOCK>, it will be emulated, so you can call C<aio_sendfile> on any
389filehandle regardless of the limitations of the operating system. 497type of filehandle regardless of the limitations of the operating system.
390 498
391Please note, however, that C<aio_sendfile> can read more bytes from 499As native sendfile syscalls (as practically any non-POSIX interface hacked
392C<$in_fh> than are written, and there is no way to find out how many 500together in a hurry to improve benchmark numbers) tend to be rather buggy
393bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only 501on many systems, this implementation tries to work around some known bugs
394provides the number of bytes written to C<$out_fh>. Only if the result 502in Linux and FreeBSD kernels (probably others, too), but that might fail,
395value equals C<$length> one can assume that C<$length> bytes have been 503so you really really should check the return value of C<aio_sendfile> -
396read. 504fewre bytes than expected might have been transferred.
397 505
398 506
399=item aio_readahead $fh,$offset,$length, $callback->($retval) 507=item aio_readahead $fh,$offset,$length, $callback->($retval)
400 508
401C<aio_readahead> populates the page cache with data from a file so that 509C<aio_readahead> populates the page cache with data from a file so that
… …
424 532
425Currently, the stats are always 64-bit-stats, i.e. instead of returning an 533Currently, the stats are always 64-bit-stats, i.e. instead of returning an
426error when stat'ing a large file, the results will be silently truncated 534error when stat'ing a large file, the results will be silently truncated
427unless perl itself is compiled with large file support. 535unless perl itself is compiled with large file support.
428 536
537To help interpret the mode and dev/rdev stat values, IO::AIO offers the
538following constants and functions (if not implemented, the constants will
539be C<0> and the functions will either C<croak> or fall back on traditional
540behaviour).
541
542C<S_IFMT>, C<S_IFIFO>, C<S_IFCHR>, C<S_IFBLK>, C<S_IFLNK>, C<S_IFREG>,
543C<S_IFDIR>, C<S_IFWHT>, C<S_IFSOCK>, C<IO::AIO::major $dev_t>,
544C<IO::AIO::minor $dev_t>, C<IO::AIO::makedev $major, $minor>.
545
429Example: Print the length of F</etc/passwd>: 546Example: Print the length of F</etc/passwd>:
430 547
431 aio_stat "/etc/passwd", sub { 548 aio_stat "/etc/passwd", sub {
432 $_[0] and die "stat failed: $!"; 549 $_[0] and die "stat failed: $!";
433 print "size is ", -s _, "\n"; 550 print "size is ", -s _, "\n";
434 }; 551 };
435 552
436 553
554=item aio_statvfs $fh_or_path, $callback->($statvfs)
555
556Works like the POSIX C<statvfs> or C<fstatvfs> syscalls, depending on
557whether a file handle or path was passed.
558
559On success, the callback is passed a hash reference with the following
560members: C<bsize>, C<frsize>, C<blocks>, C<bfree>, C<bavail>, C<files>,
561C<ffree>, C<favail>, C<fsid>, C<flag> and C<namemax>. On failure, C<undef>
562is passed.
563
564The following POSIX IO::AIO::ST_* constants are defined: C<ST_RDONLY> and
565C<ST_NOSUID>.
566
567The following non-POSIX IO::AIO::ST_* flag masks are defined to
568their correct value when available, or to C<0> on systems that do
569not support them: C<ST_NODEV>, C<ST_NOEXEC>, C<ST_SYNCHRONOUS>,
570C<ST_MANDLOCK>, C<ST_WRITE>, C<ST_APPEND>, C<ST_IMMUTABLE>, C<ST_NOATIME>,
571C<ST_NODIRATIME> and C<ST_RELATIME>.
572
573Example: stat C</wd> and dump out the data if successful.
574
575 aio_statvfs "/wd", sub {
576 my $f = $_[0]
577 or die "statvfs: $!";
578
579 use Data::Dumper;
580 say Dumper $f;
581 };
582
583 # result:
584 {
585 bsize => 1024,
586 bfree => 4333064312,
587 blocks => 10253828096,
588 files => 2050765568,
589 flag => 4096,
590 favail => 2042092649,
591 bavail => 4333064312,
592 ffree => 2042092649,
593 namemax => 255,
594 frsize => 1024,
595 fsid => 1810
596 }
597
598
437=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status) 599=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
438 600
439Works like perl's C<utime> function (including the special case of $atime 601Works like perl's C<utime> function (including the special case of $atime
440and $mtime being undef). Fractional times are supported if the underlying 602and $mtime being undef). Fractional times are supported if the underlying
441syscalls support them. 603syscalls support them.
… …
479 641
480Asynchronously unlink (delete) a file and call the callback with the 642Asynchronously unlink (delete) a file and call the callback with the
481result code. 643result code.
482 644
483 645
484=item aio_mknod $path, $mode, $dev, $callback->($status) 646=item aio_mknod $pathname, $mode, $dev, $callback->($status)
485 647
486[EXPERIMENTAL] 648[EXPERIMENTAL]
487 649
488Asynchronously create a device node (or fifo). See mknod(2). 650Asynchronously create a device node (or fifo). See mknod(2).
489 651
490The only (POSIX-) portable way of calling this function is: 652The only (POSIX-) portable way of calling this function is:
491 653
492 aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ... 654 aio_mknod $pathname, IO::AIO::S_IFIFO | $mode, 0, sub { ...
493 655
656See C<aio_stat> for info about some potentially helpful extra constants
657and functions.
494 658
495=item aio_link $srcpath, $dstpath, $callback->($status) 659=item aio_link $srcpath, $dstpath, $callback->($status)
496 660
497Asynchronously create a new link to the existing object at C<$srcpath> at 661Asynchronously create a new link to the existing object at C<$srcpath> at
498the path C<$dstpath> and call the callback with the result code. 662the path C<$dstpath> and call the callback with the result code.
… …
502 666
503Asynchronously create a new symbolic link to the existing object at C<$srcpath> at 667Asynchronously create a new symbolic link to the existing object at C<$srcpath> at
504the path C<$dstpath> and call the callback with the result code. 668the path C<$dstpath> and call the callback with the result code.
505 669
506 670
507=item aio_readlink $path, $callback->($link) 671=item aio_readlink $pathname, $callback->($link)
508 672
509Asynchronously read the symlink specified by C<$path> and pass it to 673Asynchronously read the symlink specified by C<$path> and pass it to
510the callback. If an error occurs, nothing or undef gets passed to the 674the callback. If an error occurs, nothing or undef gets passed to the
511callback. 675callback.
512 676
513 677
678=item aio_realpath $pathname, $callback->($path)
679
680Asynchronously make the path absolute and resolve any symlinks in
681C<$path>. The resulting path only consists of directories (Same as
682L<Cwd::realpath>).
683
684This request can be used to get the absolute path of the current working
685directory by passing it a path of F<.> (a single dot).
686
687
514=item aio_rename $srcpath, $dstpath, $callback->($status) 688=item aio_rename $srcpath, $dstpath, $callback->($status)
515 689
516Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as 690Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as
517rename(2) and call the callback with the result code. 691rename(2) and call the callback with the result code.
518 692
… …
540array-ref with the filenames. 714array-ref with the filenames.
541 715
542 716
543=item aio_readdirx $pathname, $flags, $callback->($entries, $flags) 717=item aio_readdirx $pathname, $flags, $callback->($entries, $flags)
544 718
545Quite similar to C<aio_readdir>, but the C<$flags> argument allows to tune 719Quite similar to C<aio_readdir>, but the C<$flags> argument allows one to
546behaviour and output format. In case of an error, C<$entries> will be 720tune behaviour and output format. In case of an error, C<$entries> will be
547C<undef>. 721C<undef>.
548 722
549The flags are a combination of the following constants, ORed together (the 723The flags are a combination of the following constants, ORed together (the
550flags will also be passed to the callback, possibly modified): 724flags will also be passed to the callback, possibly modified):
551 725
552=over 4 726=over 4
553 727
554=item IO::AIO::READDIR_DENTS 728=item IO::AIO::READDIR_DENTS
555 729
556When this flag is off, then the callback gets an arrayref with of names 730When this flag is off, then the callback gets an arrayref consisting of
557only (as with C<aio_readdir>), otherwise it gets an arrayref with 731names only (as with C<aio_readdir>), otherwise it gets an arrayref with
558C<[$name, $type, $inode]> arrayrefs, each describing a single directory 732C<[$name, $type, $inode]> arrayrefs, each describing a single directory
559entry in more detail. 733entry in more detail.
560 734
561C<$name> is the name of the entry. 735C<$name> is the name of the entry.
562 736
… …
575systems that do not deliver the inode information. 749systems that do not deliver the inode information.
576 750
577=item IO::AIO::READDIR_DIRS_FIRST 751=item IO::AIO::READDIR_DIRS_FIRST
578 752
579When this flag is set, then the names will be returned in an order where 753When this flag is set, then the names will be returned in an order where
580likely directories come first. This is useful when you need to quickly 754likely directories come first, in optimal stat order. This is useful when
581find directories, or you want to find all directories while avoiding to 755you need to quickly find directories, or you want to find all directories
582stat() each entry. 756while avoiding to stat() each entry.
583 757
584If the system returns type information in readdir, then this is used 758If the system returns type information in readdir, then this is used
585to find directories directly. Otherwise, likely directories are files 759to find directories directly. Otherwise, likely directories are names
586beginning with ".", or otherwise files with no dots, of which files with 760beginning with ".", or otherwise names with no dots, of which names with
587short names are tried first. 761short names are tried first.
588 762
589=item IO::AIO::READDIR_STAT_ORDER 763=item IO::AIO::READDIR_STAT_ORDER
590 764
591When this flag is set, then the names will be returned in an order 765When this flag is set, then the names will be returned in an order
… …
598 772
599=item IO::AIO::READDIR_FOUND_UNKNOWN 773=item IO::AIO::READDIR_FOUND_UNKNOWN
600 774
601This flag should not be set when calling C<aio_readdirx>. Instead, it 775This flag should not be set when calling C<aio_readdirx>. Instead, it
602is being set by C<aio_readdirx>, when any of the C<$type>'s found were 776is being set by C<aio_readdirx>, when any of the C<$type>'s found were
603C<IO::AIO::DT_UNKNOWN>. The absense of this flag therefore indicates that all 777C<IO::AIO::DT_UNKNOWN>. The absence of this flag therefore indicates that all
604C<$type>'s are known, which can be used to speed up some algorithms. 778C<$type>'s are known, which can be used to speed up some algorithms.
605 779
606=back 780=back
607 781
608 782
609=item aio_load $path, $data, $callback->($status) 783=item aio_load $pathname, $data, $callback->($status)
610 784
611This is a composite request that tries to fully load the given file into 785This is a composite request that tries to fully load the given file into
612memory. Status is the same as with aio_read. 786memory. Status is the same as with aio_read.
613 787
614=cut 788=cut
… …
736 if ($_[0] && $! == EXDEV) { 910 if ($_[0] && $! == EXDEV) {
737 aioreq_pri $pri; 911 aioreq_pri $pri;
738 add $grp aio_copy $src, $dst, sub { 912 add $grp aio_copy $src, $dst, sub {
739 $grp->result ($_[0]); 913 $grp->result ($_[0]);
740 914
741 if (!$_[0]) { 915 unless ($_[0]) {
742 aioreq_pri $pri; 916 aioreq_pri $pri;
743 add $grp aio_unlink $src; 917 add $grp aio_unlink $src;
744 } 918 }
745 }; 919 };
746 } else { 920 } else {
… …
749 }; 923 };
750 924
751 $grp 925 $grp
752} 926}
753 927
754=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) 928=item aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs)
755 929
756Scans a directory (similar to C<aio_readdir>) but additionally tries to 930Scans a directory (similar to C<aio_readdir>) but additionally tries to
757efficiently separate the entries of directory C<$path> into two sets of 931efficiently separate the entries of directory C<$path> into two sets of
758names, directories you can recurse into (directories), and ones you cannot 932names, directories you can recurse into (directories), and ones you cannot
759recurse into (everything else, including symlinks to directories). 933recurse into (everything else, including symlinks to directories).
… …
790Then entries will be sorted into likely directories a non-initial dot 964Then entries will be sorted into likely directories a non-initial dot
791currently) and likely non-directories (see C<aio_readdirx>). Then every 965currently) and likely non-directories (see C<aio_readdirx>). Then every
792entry plus an appended C</.> will be C<stat>'ed, likely directories first, 966entry plus an appended C</.> will be C<stat>'ed, likely directories first,
793in order of their inode numbers. If that succeeds, it assumes that the 967in order of their inode numbers. If that succeeds, it assumes that the
794entry is a directory or a symlink to directory (which will be checked 968entry is a directory or a symlink to directory (which will be checked
795seperately). This is often faster than stat'ing the entry itself because 969separately). This is often faster than stat'ing the entry itself because
796filesystems might detect the type of the entry without reading the inode 970filesystems might detect the type of the entry without reading the inode
797data (e.g. ext2fs filetype feature), even on systems that cannot return 971data (e.g. ext2fs filetype feature), even on systems that cannot return
798the filetype information on readdir. 972the filetype information on readdir.
799 973
800If the known number of directories (link count - 2) has been reached, the 974If the known number of directories (link count - 2) has been reached, the
… …
816 990
817 my $grp = aio_group $cb; 991 my $grp = aio_group $cb;
818 992
819 $maxreq = 4 if $maxreq <= 0; 993 $maxreq = 4 if $maxreq <= 0;
820 994
821 # stat once 995 # get a wd object
822 aioreq_pri $pri; 996 aioreq_pri $pri;
823 add $grp aio_stat $path, sub { 997 add $grp aio_wd $path, sub {
998 $_[0]
824 return $grp->result () if $_[0]; 999 or return $grp->result ();
825 my $now = time;
826 my $hash1 = join ":", (stat _)[0,1,3,7,9];
827 1000
828 # read the directory entries 1001 my $wd = [shift, "."];
1002
1003 # stat once
829 aioreq_pri $pri; 1004 aioreq_pri $pri;
830 add $grp aio_readdirx $path, READDIR_DIRS_FIRST, sub { 1005 add $grp aio_stat $wd, sub {
831 my $entries = shift
832 or return $grp->result (); 1006 return $grp->result () if $_[0];
1007 my $now = time;
1008 my $hash1 = join ":", (stat _)[0,1,3,7,9];
833 1009
834 # stat the dir another time 1010 # read the directory entries
835 aioreq_pri $pri; 1011 aioreq_pri $pri;
1012 add $grp aio_readdirx $wd, READDIR_DIRS_FIRST, sub {
1013 my $entries = shift
1014 or return $grp->result ();
1015
1016 # stat the dir another time
1017 aioreq_pri $pri;
836 add $grp aio_stat $path, sub { 1018 add $grp aio_stat $wd, sub {
837 my $hash2 = join ":", (stat _)[0,1,3,7,9]; 1019 my $hash2 = join ":", (stat _)[0,1,3,7,9];
838 1020
839 my $ndirs; 1021 my $ndirs;
840 1022
841 # take the slow route if anything looks fishy 1023 # take the slow route if anything looks fishy
842 if ($hash1 ne $hash2 or (stat _)[9] == $now) { 1024 if ($hash1 ne $hash2 or (stat _)[9] == $now) {
843 $ndirs = -1; 1025 $ndirs = -1;
844 } else { 1026 } else {
845 # if nlink == 2, we are finished 1027 # if nlink == 2, we are finished
846 # for non-posix-fs's, we rely on nlink < 2 1028 # for non-posix-fs's, we rely on nlink < 2
847 $ndirs = (stat _)[3] - 2 1029 $ndirs = (stat _)[3] - 2
848 or return $grp->result ([], $entries); 1030 or return $grp->result ([], $entries);
849 } 1031 }
850 1032
851 my (@dirs, @nondirs); 1033 my (@dirs, @nondirs);
852 1034
853 my $statgrp = add $grp aio_group sub { 1035 my $statgrp = add $grp aio_group sub {
854 $grp->result (\@dirs, \@nondirs); 1036 $grp->result (\@dirs, \@nondirs);
855 }; 1037 };
856 1038
857 limit $statgrp $maxreq; 1039 limit $statgrp $maxreq;
858 feed $statgrp sub { 1040 feed $statgrp sub {
859 return unless @$entries; 1041 return unless @$entries;
860 my $entry = shift @$entries; 1042 my $entry = shift @$entries;
861 1043
862 aioreq_pri $pri; 1044 aioreq_pri $pri;
1045 $wd->[1] = "$entry/.";
863 add $statgrp aio_stat "$path/$entry/.", sub { 1046 add $statgrp aio_stat $wd, sub {
864 if ($_[0] < 0) { 1047 if ($_[0] < 0) {
865 push @nondirs, $entry; 1048 push @nondirs, $entry;
866 } else { 1049 } else {
867 # need to check for real directory 1050 # need to check for real directory
868 aioreq_pri $pri; 1051 aioreq_pri $pri;
1052 $wd->[1] = $entry;
869 add $statgrp aio_lstat "$path/$entry", sub { 1053 add $statgrp aio_lstat $wd, sub {
870 if (-d _) { 1054 if (-d _) {
871 push @dirs, $entry; 1055 push @dirs, $entry;
872 1056
873 unless (--$ndirs) { 1057 unless (--$ndirs) {
874 push @nondirs, @$entries; 1058 push @nondirs, @$entries;
875 feed $statgrp; 1059 feed $statgrp;
1060 }
1061 } else {
1062 push @nondirs, $entry;
876 } 1063 }
877 } else {
878 push @nondirs, $entry;
879 } 1064 }
880 } 1065 }
881 } 1066 };
882 }; 1067 };
883 }; 1068 };
884 }; 1069 };
885 }; 1070 };
886 }; 1071 };
887 1072
888 $grp 1073 $grp
889} 1074}
890 1075
891=item aio_rmtree $path, $callback->($status) 1076=item aio_rmtree $pathname, $callback->($status)
892 1077
893Delete a directory tree starting (and including) C<$path>, return the 1078Delete a directory tree starting (and including) C<$path>, return the
894status of the final C<rmdir> only. This is a composite request that 1079status of the final C<rmdir> only. This is a composite request that
895uses C<aio_scandir> to recurse into and rmdir directories, and unlink 1080uses C<aio_scandir> to recurse into and rmdir directories, and unlink
896everything else. 1081everything else.
… …
938callback with the fdatasync result code. 1123callback with the fdatasync result code.
939 1124
940If this call isn't available because your OS lacks it or it couldn't be 1125If this call isn't available because your OS lacks it or it couldn't be
941detected, it will be emulated by calling C<fsync> instead. 1126detected, it will be emulated by calling C<fsync> instead.
942 1127
1128=item aio_syncfs $fh, $callback->($status)
1129
1130Asynchronously call the syncfs syscall to sync the filesystem associated
1131to the given filehandle and call the callback with the syncfs result
1132code. If syncfs is not available, calls sync(), but returns C<-1> and sets
1133errno to C<ENOSYS> nevertheless.
1134
943=item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status) 1135=item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
944 1136
945Sync the data portion of the file specified by C<$offset> and C<$length> 1137Sync the data portion of the file specified by C<$offset> and C<$length>
946to disk (but NOT the metadata), by calling the Linux-specific 1138to disk (but NOT the metadata), by calling the Linux-specific
947sync_file_range call. If sync_file_range is not available or it returns 1139sync_file_range call. If sync_file_range is not available or it returns
… …
950C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>, 1142C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>,
951C<IO::AIO::SYNC_FILE_RANGE_WRITE> and 1143C<IO::AIO::SYNC_FILE_RANGE_WRITE> and
952C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range 1144C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range
953manpage for details. 1145manpage for details.
954 1146
955=item aio_pathsync $path, $callback->($status) 1147=item aio_pathsync $pathname, $callback->($status)
956 1148
957This request tries to open, fsync and close the given path. This is a 1149This request tries to open, fsync and close the given path. This is a
958composite request intended to sync directories after directory operations 1150composite request intended to sync directories after directory operations
959(E.g. rename). This might not work on all operating systems or have any 1151(E.g. rename). This might not work on all operating systems or have any
960specific effect, but usually it makes sure that directory changes get 1152specific effect, but usually it makes sure that directory changes get
… …
994} 1186}
995 1187
996=item aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status) 1188=item aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
997 1189
998This is a rather advanced IO::AIO call, which only works on mmap(2)ed 1190This is a rather advanced IO::AIO call, which only works on mmap(2)ed
999scalars (see the L<Sys::Mmap> or L<Mmap> modules for details on this, note 1191scalars (see the C<IO::AIO::mmap> function, although it also works on data
1192scalars managed by the L<Sys::Mmap> or L<Mmap> modules, note that the
1000that the scalar must only be modified in-place while an aio operation is 1193scalar must only be modified in-place while an aio operation is pending on
1001pending on it). 1194it).
1002 1195
1003It calls the C<msync> function of your OS, if available, with the memory 1196It calls the C<msync> function of your OS, if available, with the memory
1004area starting at C<$offset> in the string and ending C<$length> bytes 1197area starting at C<$offset> in the string and ending C<$length> bytes
1005later. If C<$length> is negative, counts from the end, and if C<$length> 1198later. If C<$length> is negative, counts from the end, and if C<$length>
1006is C<undef>, then it goes till the end of the string. The flags can be 1199is C<undef>, then it goes till the end of the string. The flags can be
… …
1017as for C<aio_msync>, above, except for flags, which must be either 1210as for C<aio_msync>, above, except for flags, which must be either
1018C<0> (which reads all pages and ensures they are instantiated) or 1211C<0> (which reads all pages and ensures they are instantiated) or
1019C<IO::AIO::MT_MODIFY>, which modifies the memory page s(by reading and 1212C<IO::AIO::MT_MODIFY>, which modifies the memory page s(by reading and
1020writing an octet from it, which dirties the page). 1213writing an octet from it, which dirties the page).
1021 1214
1215=item aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
1216
1217This is a rather advanced IO::AIO call, which works best on mmap(2)ed
1218scalars.
1219
1220It reads in all the pages of the underlying storage into memory (if any)
1221and locks them, so they are not getting swapped/paged out or removed.
1222
1223If C<$length> is undefined, then the scalar will be locked till the end.
1224
1225On systems that do not implement C<mlock>, this function returns C<-1>
1226and sets errno to C<ENOSYS>.
1227
1228Note that the corresponding C<munlock> is synchronous and is
1229documented under L<MISCELLANEOUS FUNCTIONS>.
1230
1231Example: open a file, mmap and mlock it - both will be undone when
1232C<$data> gets destroyed.
1233
1234 open my $fh, "<", $path or die "$path: $!";
1235 my $data;
1236 IO::AIO::mmap $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh;
1237 aio_mlock $data; # mlock in background
1238
1239=item aio_mlockall $flags, $callback->($status)
1240
1241Calls the C<mlockall> function with the given C<$flags> (a combination of
1242C<IO::AIO::MCL_CURRENT> and C<IO::AIO::MCL_FUTURE>).
1243
1244On systems that do not implement C<mlockall>, this function returns C<-1>
1245and sets errno to C<ENOSYS>.
1246
1247Note that the corresponding C<munlockall> is synchronous and is
1248documented under L<MISCELLANEOUS FUNCTIONS>.
1249
1250Example: asynchronously lock all current and future pages into memory.
1251
1252 aio_mlockall IO::AIO::MCL_FUTURE;
1253
1254=item aio_fiemap $fh, $start, $length, $flags, $count, $cb->(\@extents)
1255
1256Queries the extents of the given file (by calling the Linux FIEMAP ioctl,
1257see L<http://cvs.schmorp.de/IO-AIO/doc/fiemap.txt> for details). If the
1258C<ioctl> is not available on your OS, then this rquiest will fail with
1259C<ENOSYS>.
1260
1261C<$start> is the starting offset to query extents for, C<$length> is the
1262size of the range to query - if it is C<undef>, then the whole file will
1263be queried.
1264
1265C<$flags> is a combination of flags (C<IO::AIO::FIEMAP_FLAG_SYNC> or
1266C<IO::AIO::FIEMAP_FLAG_XATTR> - C<IO::AIO::FIEMAP_FLAGS_COMPAT> is also
1267exported), and is normally C<0> or C<IO::AIO::FIEMAP_FLAG_SYNC> to query
1268the data portion.
1269
1270C<$count> is the maximum number of extent records to return. If it is
1271C<undef>, then IO::AIO queries all extents of the file. As a very special
1272case, if it is C<0>, then the callback receives the number of extents
1273instead of the extents themselves.
1274
1275If an error occurs, the callback receives no arguments. The special
1276C<errno> value C<IO::AIO::EBADR> is available to test for flag errors.
1277
1278Otherwise, the callback receives an array reference with extent
1279structures. Each extent structure is an array reference itself, with the
1280following members:
1281
1282 [$logical, $physical, $length, $flags]
1283
1284Flags is any combination of the following flag values (typically either C<0>
1285or C<IO::AIO::FIEMAP_EXTENT_LAST>):
1286
1287C<IO::AIO::FIEMAP_EXTENT_LAST>, C<IO::AIO::FIEMAP_EXTENT_UNKNOWN>,
1288C<IO::AIO::FIEMAP_EXTENT_DELALLOC>, C<IO::AIO::FIEMAP_EXTENT_ENCODED>,
1289C<IO::AIO::FIEMAP_EXTENT_DATA_ENCRYPTED>, C<IO::AIO::FIEMAP_EXTENT_NOT_ALIGNED>,
1290C<IO::AIO::FIEMAP_EXTENT_DATA_INLINE>, C<IO::AIO::FIEMAP_EXTENT_DATA_TAIL>,
1291C<IO::AIO::FIEMAP_EXTENT_UNWRITTEN>, C<IO::AIO::FIEMAP_EXTENT_MERGED> or
1292C<IO::AIO::FIEMAP_EXTENT_SHARED>.
1293
1022=item aio_group $callback->(...) 1294=item aio_group $callback->(...)
1023 1295
1024This is a very special aio request: Instead of doing something, it is a 1296This is a very special aio request: Instead of doing something, it is a
1025container for other aio requests, which is useful if you want to bundle 1297container for other aio requests, which is useful if you want to bundle
1026many requests into a single, composite, request with a definite callback 1298many requests into a single, composite, request with a definite callback
… …
1062like sleep and file handle readable/writable, the overhead this creates is 1334like sleep and file handle readable/writable, the overhead this creates is
1063immense (it blocks a thread for a long time) so do not use this function 1335immense (it blocks a thread for a long time) so do not use this function
1064except to put your application under artificial I/O pressure. 1336except to put your application under artificial I/O pressure.
1065 1337
1066=back 1338=back
1339
1340
1341=head2 IO::AIO::WD - multiple working directories
1342
1343Your process only has one current working directory, which is used by all
1344threads. This makes it hard to use relative paths (some other component
1345could call C<chdir> at any time, and it is hard to control when the path
1346will be used by IO::AIO).
1347
1348One solution for this is to always use absolute paths. This usually works,
1349but can be quite slow (the kernel has to walk the whole path on every
1350access), and can also be a hassle to implement.
1351
1352Newer POSIX systems have a number of functions (openat, fdopendir,
1353futimensat and so on) that make it possible to specify working directories
1354per operation.
1355
1356For portability, and because the clowns who "designed", or shall I write,
1357perpetrated this new interface were obviously half-drunk, this abstraction
1358cannot be perfect, though.
1359
1360IO::AIO allows you to convert directory paths into a so-called IO::AIO::WD
1361object. This object stores the canonicalised, absolute version of the
1362path, and on systems that allow it, also a directory file descriptor.
1363
1364Everywhere where a pathname is accepted by IO::AIO (e.g. in C<aio_stat>
1365or C<aio_unlink>), one can specify an array reference with an IO::AIO::WD
1366object and a pathname instead (or the IO::AIO::WD object alone, which
1367gets interpreted as C<[$wd, "."]>). If the pathname is absolute, the
1368IO::AIO::WD object is ignored, otherwise the pathname is resolved relative
1369to that IO::AIO::WD object.
1370
1371For example, to get a wd object for F</etc> and then stat F<passwd>
1372inside, you would write:
1373
1374 aio_wd "/etc", sub {
1375 my $etcdir = shift;
1376
1377 # although $etcdir can be undef on error, there is generally no reason
1378 # to check for errors here, as aio_stat will fail with ENOENT
1379 # when $etcdir is undef.
1380
1381 aio_stat [$etcdir, "passwd"], sub {
1382 # yay
1383 };
1384 };
1385
1386That C<aio_wd> is a request and not a normal function shows that creating
1387an IO::AIO::WD object is itself a potentially blocking operation, which is
1388why it is done asynchronously.
1389
1390To stat the directory obtained with C<aio_wd> above, one could write
1391either of the following three request calls:
1392
1393 aio_lstat "/etc" , sub { ... # pathname as normal string
1394 aio_lstat [$wd, "."], sub { ... # "." relative to $wd (i.e. $wd itself)
1395 aio_lstat $wd , sub { ... # shorthand for the previous
1396
1397As with normal pathnames, IO::AIO keeps a copy of the working directory
1398object and the pathname string, so you could write the following without
1399causing any issues due to C<$path> getting reused:
1400
1401 my $path = [$wd, undef];
1402
1403 for my $name (qw(abc def ghi)) {
1404 $path->[1] = $name;
1405 aio_stat $path, sub {
1406 # ...
1407 };
1408 }
1409
1410There are some caveats: when directories get renamed (or deleted), the
1411pathname string doesn't change, so will point to the new directory (or
1412nowhere at all), while the directory fd, if available on the system,
1413will still point to the original directory. Most functions accepting a
1414pathname will use the directory fd on newer systems, and the string on
1415older systems. Some functions (such as realpath) will always rely on the
1416string form of the pathname.
1417
1418So this fucntionality is mainly useful to get some protection against
1419C<chdir>, to easily get an absolute path out of a relative path for future
1420reference, and to speed up doing many operations in the same directory
1421(e.g. when stat'ing all files in a directory).
1422
1423The following functions implement this working directory abstraction:
1424
1425=over 4
1426
1427=item aio_wd $pathname, $callback->($wd)
1428
1429Asynchonously canonicalise the given pathname and convert it to an
1430IO::AIO::WD object representing it. If possible and supported on the
1431system, also open a directory fd to speed up pathname resolution relative
1432to this working directory.
1433
1434If something goes wrong, then C<undef> is passwd to the callback instead
1435of a working directory object and C<$!> is set appropriately. Since
1436passing C<undef> as working directory component of a pathname fails the
1437request with C<ENOENT>, there is often no need for error checking in the
1438C<aio_wd> callback, as future requests using the value will fail in the
1439expected way.
1440
1441If this call isn't available because your OS lacks it or it couldn't be
1442detected, it will be emulated by calling C<fsync> instead.
1443
1444=item IO::AIO::CWD
1445
1446This is a compiletime constant (object) that represents the process
1447current working directory.
1448
1449Specifying this object as working directory object for a pathname is as
1450if the pathname would be specified directly, without a directory object,
1451e.g., these calls are functionally identical:
1452
1453 aio_stat "somefile", sub { ... };
1454 aio_stat [IO::AIO::CWD, "somefile"], sub { ... };
1455
1456=back
1457
1067 1458
1068=head2 IO::AIO::REQ CLASS 1459=head2 IO::AIO::REQ CLASS
1069 1460
1070All non-aggregate C<aio_*> functions return an object of this class when 1461All non-aggregate C<aio_*> functions return an object of this class when
1071called in non-void context. 1462called in non-void context.
… …
1189 1580
1190Sets a feeder/generator on this group: every group can have an attached 1581Sets a feeder/generator on this group: every group can have an attached
1191generator that generates requests if idle. The idea behind this is that, 1582generator that generates requests if idle. The idea behind this is that,
1192although you could just queue as many requests as you want in a group, 1583although you could just queue as many requests as you want in a group,
1193this might starve other requests for a potentially long time. For example, 1584this might starve other requests for a potentially long time. For example,
1194C<aio_scandir> might generate hundreds of thousands C<aio_stat> requests, 1585C<aio_scandir> might generate hundreds of thousands of C<aio_stat>
1195delaying any later requests for a long time. 1586requests, delaying any later requests for a long time.
1196 1587
1197To avoid this, and allow incremental generation of requests, you can 1588To avoid this, and allow incremental generation of requests, you can
1198instead a group and set a feeder on it that generates those requests. The 1589instead a group and set a feeder on it that generates those requests. The
1199feed callback will be called whenever there are few enough (see C<limit>, 1590feed callback will be called whenever there are few enough (see C<limit>,
1200below) requests active in the group itself and is expected to queue more 1591below) requests active in the group itself and is expected to queue more
… …
1249 1640
1250See C<poll_cb> for an example. 1641See C<poll_cb> for an example.
1251 1642
1252=item IO::AIO::poll_cb 1643=item IO::AIO::poll_cb
1253 1644
1254Process some outstanding events on the result pipe. You have to call this 1645Process some outstanding events on the result pipe. You have to call
1255regularly. Returns C<0> if all events could be processed, or C<-1> if it 1646this regularly. Returns C<0> if all events could be processed (or there
1256returned earlier for whatever reason. Returns immediately when no events 1647were no events to process), or C<-1> if it returned earlier for whatever
1257are outstanding. The amount of events processed depends on the settings of 1648reason. Returns immediately when no events are outstanding. The amount of
1258C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>. 1649events processed depends on the settings of C<IO::AIO::max_poll_req> and
1650C<IO::AIO::max_poll_time>.
1259 1651
1260If not all requests were processed for whatever reason, the filehandle 1652If not all requests were processed for whatever reason, the filehandle
1261will still be ready when C<poll_cb> returns, so normally you don't have to 1653will still be ready when C<poll_cb> returns, so normally you don't have to
1262do anything special to have it called later. 1654do anything special to have it called later.
1263 1655
1656Apart from calling C<IO::AIO::poll_cb> when the event filehandle becomes
1657ready, it can be beneficial to call this function from loops which submit
1658a lot of requests, to make sure the results get processed when they become
1659available and not just when the loop is finished and the event loop takes
1660over again. This function returns very fast when there are no outstanding
1661requests.
1662
1264Example: Install an Event watcher that automatically calls 1663Example: Install an Event watcher that automatically calls
1265IO::AIO::poll_cb with high priority (more examples can be found in the 1664IO::AIO::poll_cb with high priority (more examples can be found in the
1266SYNOPSIS section, at the top of this document): 1665SYNOPSIS section, at the top of this document):
1267 1666
1268 Event->io (fd => IO::AIO::poll_fileno, 1667 Event->io (fd => IO::AIO::poll_fileno,
1269 poll => 'r', async => 1, 1668 poll => 'r', async => 1,
1270 cb => \&IO::AIO::poll_cb); 1669 cb => \&IO::AIO::poll_cb);
1670
1671=item IO::AIO::poll_wait
1672
1673If there are any outstanding requests and none of them in the result
1674phase, wait till the result filehandle becomes ready for reading (simply
1675does a C<select> on the filehandle. This is useful if you want to
1676synchronously wait for some requests to finish).
1677
1678See C<nreqs> for an example.
1679
1680=item IO::AIO::poll
1681
1682Waits until some requests have been handled.
1683
1684Returns the number of requests processed, but is otherwise strictly
1685equivalent to:
1686
1687 IO::AIO::poll_wait, IO::AIO::poll_cb
1688
1689=item IO::AIO::flush
1690
1691Wait till all outstanding AIO requests have been handled.
1692
1693Strictly equivalent to:
1694
1695 IO::AIO::poll_wait, IO::AIO::poll_cb
1696 while IO::AIO::nreqs;
1271 1697
1272=item IO::AIO::max_poll_reqs $nreqs 1698=item IO::AIO::max_poll_reqs $nreqs
1273 1699
1274=item IO::AIO::max_poll_time $seconds 1700=item IO::AIO::max_poll_time $seconds
1275 1701
… …
1300 # use a low priority so other tasks have priority 1726 # use a low priority so other tasks have priority
1301 Event->io (fd => IO::AIO::poll_fileno, 1727 Event->io (fd => IO::AIO::poll_fileno,
1302 poll => 'r', nice => 1, 1728 poll => 'r', nice => 1,
1303 cb => &IO::AIO::poll_cb); 1729 cb => &IO::AIO::poll_cb);
1304 1730
1305=item IO::AIO::poll_wait
1306
1307If there are any outstanding requests and none of them in the result
1308phase, wait till the result filehandle becomes ready for reading (simply
1309does a C<select> on the filehandle. This is useful if you want to
1310synchronously wait for some requests to finish).
1311
1312See C<nreqs> for an example.
1313
1314=item IO::AIO::poll
1315
1316Waits until some requests have been handled.
1317
1318Returns the number of requests processed, but is otherwise strictly
1319equivalent to:
1320
1321 IO::AIO::poll_wait, IO::AIO::poll_cb
1322
1323=item IO::AIO::flush
1324
1325Wait till all outstanding AIO requests have been handled.
1326
1327Strictly equivalent to:
1328
1329 IO::AIO::poll_wait, IO::AIO::poll_cb
1330 while IO::AIO::nreqs;
1331
1332=back 1731=back
1333 1732
1334=head3 CONTROLLING THE NUMBER OF THREADS 1733=head3 CONTROLLING THE NUMBER OF THREADS
1335 1734
1336=over 1735=over
… …
1369 1768
1370Under normal circumstances you don't need to call this function. 1769Under normal circumstances you don't need to call this function.
1371 1770
1372=item IO::AIO::max_idle $nthreads 1771=item IO::AIO::max_idle $nthreads
1373 1772
1374Limit the number of threads (default: 4) that are allowed to idle (i.e., 1773Limit the number of threads (default: 4) that are allowed to idle
1375threads that did not get a request to process within 10 seconds). That 1774(i.e., threads that did not get a request to process within the idle
1376means if a thread becomes idle while C<$nthreads> other threads are also 1775timeout (default: 10 seconds). That means if a thread becomes idle while
1377idle, it will free its resources and exit. 1776C<$nthreads> other threads are also idle, it will free its resources and
1777exit.
1378 1778
1379This is useful when you allow a large number of threads (e.g. 100 or 1000) 1779This is useful when you allow a large number of threads (e.g. 100 or 1000)
1380to allow for extremely high load situations, but want to free resources 1780to allow for extremely high load situations, but want to free resources
1381under normal circumstances (1000 threads can easily consume 30MB of RAM). 1781under normal circumstances (1000 threads can easily consume 30MB of RAM).
1382 1782
1383The default is probably ok in most situations, especially if thread 1783The default is probably ok in most situations, especially if thread
1384creation is fast. If thread creation is very slow on your system you might 1784creation is fast. If thread creation is very slow on your system you might
1385want to use larger values. 1785want to use larger values.
1386 1786
1787=item IO::AIO::idle_timeout $seconds
1788
1789Sets the minimum idle timeout (default 10) after which worker threads are
1790allowed to exit. SEe C<IO::AIO::max_idle>.
1791
1387=item IO::AIO::max_outstanding $maxreqs 1792=item IO::AIO::max_outstanding $maxreqs
1793
1794Sets the maximum number of outstanding requests to C<$nreqs>. If
1795you do queue up more than this number of requests, the next call to
1796C<IO::AIO::poll_cb> (and other functions calling C<poll_cb>, such as
1797C<IO::AIO::flush> or C<IO::AIO::poll>) will block until the limit is no
1798longer exceeded.
1799
1800In other words, this setting does not enforce a queue limit, but can be
1801used to make poll functions block if the limit is exceeded.
1388 1802
1389This is a very bad function to use in interactive programs because it 1803This is a very bad function to use in interactive programs because it
1390blocks, and a bad way to reduce concurrency because it is inexact: Better 1804blocks, and a bad way to reduce concurrency because it is inexact: Better
1391use an C<aio_group> together with a feed callback. 1805use an C<aio_group> together with a feed callback.
1392 1806
1393Sets the maximum number of outstanding requests to C<$nreqs>. If you 1807It's main use is in scripts without an event loop - when you want to stat
1394do queue up more than this number of requests, the next call to the 1808a lot of files, you can write somehting like this:
1395C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>)
1396function will block until the limit is no longer exceeded.
1397 1809
1398The default value is very large, so there is no practical limit on the 1810 IO::AIO::max_outstanding 32;
1399number of outstanding requests.
1400 1811
1401You can still queue as many requests as you want. Therefore, 1812 for my $path (...) {
1402C<max_outstanding> is mainly useful in simple scripts (with low values) or 1813 aio_stat $path , ...;
1403as a stop gap to shield against fatal memory overflow (with large values). 1814 IO::AIO::poll_cb;
1815 }
1816
1817 IO::AIO::flush;
1818
1819The call to C<poll_cb> inside the loop will normally return instantly, but
1820as soon as more thna C<32> reqeusts are in-flight, it will block until
1821some requests have been handled. This keeps the loop from pushing a large
1822number of C<aio_stat> requests onto the queue.
1823
1824The default value for C<max_outstanding> is very large, so there is no
1825practical limit on the number of outstanding requests.
1404 1826
1405=back 1827=back
1406 1828
1407=head3 STATISTICAL INFORMATION 1829=head3 STATISTICAL INFORMATION
1408 1830
… …
1446 1868
1447Returns the number of bytes copied, or C<-1> on error. 1869Returns the number of bytes copied, or C<-1> on error.
1448 1870
1449=item IO::AIO::fadvise $fh, $offset, $len, $advice 1871=item IO::AIO::fadvise $fh, $offset, $len, $advice
1450 1872
1451Simply calls the C<posix_fadvise> function (see it's 1873Simply calls the C<posix_fadvise> function (see its
1452manpage for details). The following advice constants are 1874manpage for details). The following advice constants are
1453avaiable: C<IO::AIO::FADV_NORMAL>, C<IO::AIO::FADV_SEQUENTIAL>, 1875available: C<IO::AIO::FADV_NORMAL>, C<IO::AIO::FADV_SEQUENTIAL>,
1454C<IO::AIO::FADV_RANDOM>, C<IO::AIO::FADV_NOREUSE>, 1876C<IO::AIO::FADV_RANDOM>, C<IO::AIO::FADV_NOREUSE>,
1455C<IO::AIO::FADV_WILLNEED>, C<IO::AIO::FADV_DONTNEED>. 1877C<IO::AIO::FADV_WILLNEED>, C<IO::AIO::FADV_DONTNEED>.
1456 1878
1457On systems that do not implement C<posix_fadvise>, this function returns 1879On systems that do not implement C<posix_fadvise>, this function returns
1458ENOSYS, otherwise the return value of C<posix_fadvise>. 1880ENOSYS, otherwise the return value of C<posix_fadvise>.
1459 1881
1882=item IO::AIO::madvise $scalar, $offset, $len, $advice
1883
1884Simply calls the C<posix_madvise> function (see its
1885manpage for details). The following advice constants are
1886available: C<IO::AIO::MADV_NORMAL>, C<IO::AIO::MADV_SEQUENTIAL>,
1887C<IO::AIO::MADV_RANDOM>, C<IO::AIO::MADV_WILLNEED>, C<IO::AIO::MADV_DONTNEED>.
1888
1889On systems that do not implement C<posix_madvise>, this function returns
1890ENOSYS, otherwise the return value of C<posix_madvise>.
1891
1892=item IO::AIO::mprotect $scalar, $offset, $len, $protect
1893
1894Simply calls the C<mprotect> function on the preferably AIO::mmap'ed
1895$scalar (see its manpage for details). The following protect
1896constants are available: C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_READ>,
1897C<IO::AIO::PROT_WRITE>, C<IO::AIO::PROT_EXEC>.
1898
1899On systems that do not implement C<mprotect>, this function returns
1900ENOSYS, otherwise the return value of C<mprotect>.
1901
1902=item IO::AIO::mmap $scalar, $length, $prot, $flags, $fh[, $offset]
1903
1904Memory-maps a file (or anonymous memory range) and attaches it to the
1905given C<$scalar>, which will act like a string scalar.
1906
1907The only operations allowed on the scalar are C<substr>/C<vec> that don't
1908change the string length, and most read-only operations such as copying it
1909or searching it with regexes and so on.
1910
1911Anything else is unsafe and will, at best, result in memory leaks.
1912
1913The memory map associated with the C<$scalar> is automatically removed
1914when the C<$scalar> is destroyed, or when the C<IO::AIO::mmap> or
1915C<IO::AIO::munmap> functions are called.
1916
1917This calls the C<mmap>(2) function internally. See your system's manual
1918page for details on the C<$length>, C<$prot> and C<$flags> parameters.
1919
1920The C<$length> must be larger than zero and smaller than the actual
1921filesize.
1922
1923C<$prot> is a combination of C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_EXEC>,
1924C<IO::AIO::PROT_READ> and/or C<IO::AIO::PROT_WRITE>,
1925
1926C<$flags> can be a combination of C<IO::AIO::MAP_SHARED> or
1927C<IO::AIO::MAP_PRIVATE>, or a number of system-specific flags (when
1928not available, the are defined as 0): C<IO::AIO::MAP_ANONYMOUS>
1929(which is set to C<MAP_ANON> if your system only provides this
1930constant), C<IO::AIO::MAP_HUGETLB>, C<IO::AIO::MAP_LOCKED>,
1931C<IO::AIO::MAP_NORESERVE>, C<IO::AIO::MAP_POPULATE> or
1932C<IO::AIO::MAP_NONBLOCK>
1933
1934If C<$fh> is C<undef>, then a file descriptor of C<-1> is passed.
1935
1936C<$offset> is the offset from the start of the file - it generally must be
1937a multiple of C<IO::AIO::PAGESIZE> and defaults to C<0>.
1938
1939Example:
1940
1941 use Digest::MD5;
1942 use IO::AIO;
1943
1944 open my $fh, "<verybigfile"
1945 or die "$!";
1946
1947 IO::AIO::mmap my $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh
1948 or die "verybigfile: $!";
1949
1950 my $fast_md5 = md5 $data;
1951
1952=item IO::AIO::munmap $scalar
1953
1954Removes a previous mmap and undefines the C<$scalar>.
1955
1956=item IO::AIO::munlock $scalar, $offset = 0, $length = undef
1957
1958Calls the C<munlock> function, undoing the effects of a previous
1959C<aio_mlock> call (see its description for details).
1960
1961=item IO::AIO::munlockall
1962
1963Calls the C<munlockall> function.
1964
1965On systems that do not implement C<munlockall>, this function returns
1966ENOSYS, otherwise the return value of C<munlockall>.
1967
1460=back 1968=back
1461 1969
1462=cut 1970=cut
1463 1971
1464min_parallel 8; 1972min_parallel 8;
1465 1973
1466END { flush } 1974END { flush }
1467 1975
14681; 19761;
1469 1977
1978=head1 EVENT LOOP INTEGRATION
1979
1980It is recommended to use L<AnyEvent::AIO> to integrate IO::AIO
1981automatically into many event loops:
1982
1983 # AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...)
1984 use AnyEvent::AIO;
1985
1986You can also integrate IO::AIO manually into many event loops, here are
1987some examples of how to do this:
1988
1989 # EV integration
1990 my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
1991
1992 # Event integration
1993 Event->io (fd => IO::AIO::poll_fileno,
1994 poll => 'r',
1995 cb => \&IO::AIO::poll_cb);
1996
1997 # Glib/Gtk2 integration
1998 add_watch Glib::IO IO::AIO::poll_fileno,
1999 in => sub { IO::AIO::poll_cb; 1 };
2000
2001 # Tk integration
2002 Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
2003 readable => \&IO::AIO::poll_cb);
2004
2005 # Danga::Socket integration
2006 Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
2007 \&IO::AIO::poll_cb);
2008
1470=head2 FORK BEHAVIOUR 2009=head2 FORK BEHAVIOUR
1471 2010
1472This module should do "the right thing" when the process using it forks: 2011Usage of pthreads in a program changes the semantics of fork
2012considerably. Specifically, only async-safe functions can be called after
2013fork. Perl doesn't know about this, so in general, you cannot call fork
2014with defined behaviour in perl if pthreads are involved. IO::AIO uses
2015pthreads, so this applies, but many other extensions and (for inexplicable
2016reasons) perl itself often is linked against pthreads, so this limitation
2017applies to quite a lot of perls.
1473 2018
1474Before the fork, IO::AIO enters a quiescent state where no requests 2019This module no longer tries to fight your OS, or POSIX. That means IO::AIO
1475can be added in other threads and no results will be processed. After 2020only works in the process that loaded it. Forking is fully supported, but
1476the fork the parent simply leaves the quiescent state and continues 2021using IO::AIO in the child is not.
1477request/result processing, while the child frees the request/result queue
1478(so that the requests started before the fork will only be handled in the
1479parent). Threads will be started on demand until the limit set in the
1480parent process has been reached again.
1481 2022
1482In short: the parent will, after a short pause, continue as if fork had 2023You might get around by not I<using> IO::AIO before (or after)
1483not been called, while the child will act as if IO::AIO has not been used 2024forking. You could also try to call the L<IO::AIO::reinit> function in the
1484yet. 2025child:
2026
2027=over 4
2028
2029=item IO::AIO::reinit
2030
2031Abandons all current requests and I/O threads and simply reinitialises all
2032data structures. This is not an operation supported by any standards, but
2033happens to work on GNU/Linux and some newer BSD systems.
2034
2035The only reasonable use for this function is to call it after forking, if
2036C<IO::AIO> was used in the parent. Calling it while IO::AIO is active in
2037the process will result in undefined behaviour. Calling it at any time
2038will also result in any undefined (by POSIX) behaviour.
2039
2040=back
1485 2041
1486=head2 MEMORY USAGE 2042=head2 MEMORY USAGE
1487 2043
1488Per-request usage: 2044Per-request usage:
1489 2045

Diff Legend

– Removed lines
+ Added lines
< Changed lines
> Changed lines