ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/IO-AIO/AIO.pm

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.142 by root, Wed Oct 22 18:15:36 2008 UTC vs.
Revision 1.270 by root, Fri Jun 23 03:23:19 2017 UTC

1	=head1 NAME	1	=head1 NAME
2		2
3	IO::AIO - Asynchronous Input/Output	3	IO::AIO - Asynchronous/Advanced Input/Output
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
…		…
26	$req->cancel; # cancel request if still in queue	26	$req->cancel; # cancel request if still in queue
27		27
28	my $grp = aio_group sub { print "all stats done\n" };	28	my $grp = aio_group sub { print "all stats done\n" };
29	add $grp aio_stat "..." for ...;	29	add $grp aio_stat "..." for ...;
30		30
31	# AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...)
32	use AnyEvent::AIO;
33
34	# EV integration
35	my $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
54	=head1 DESCRIPTION	31	=head1 DESCRIPTION
55		32
56	This module implements asynchronous I/O using whatever means your	33	This module implements asynchronous I/O using whatever means your
57	operating system supports.	34	operating system supports. It is implemented as an interface to C<libeio>
		35	(L<http://software.schmorp.de/pkg/libeio.html>).
58		36
59	Asynchronous means that operations that can normally block your program	37	Asynchronous means that operations that can normally block your program
60	(e.g. reading from disk) will be done asynchronously: the operation	38	(e.g. reading from disk) will be done asynchronously: the operation
61	will still block, but you can do something else in the meantime. This	39	will still block, but you can do something else in the meantime. This
62	is extremely useful for programs that need to stay interactive even	40	is extremely useful for programs that need to stay interactive even
…		…
66	on a RAID volume or over NFS when you do a number of stat operations	44	on a RAID volume or over NFS when you do a number of stat operations
67	concurrently.	45	concurrently.
68		46
69	While most of this works on all types of file descriptors (for	47	While most of this works on all types of file descriptors (for
70	example sockets), using these functions on file descriptors that	48	example sockets), using these functions on file descriptors that
71	support nonblocking operation (again, sockets, pipes etc.) is very	49	support nonblocking operation (again, sockets, pipes etc.) is
72	inefficient. Use an event loop for that (such as the L<Event|Event>	50	very inefficient. Use an event loop for that (such as the L<EV>
73	module): IO::AIO will naturally fit into such an event loop itself.	51	module): IO::AIO will naturally fit into such an event loop itself.
74		52
75	In this version, a number of threads are started that execute your	53	In this version, a number of threads are started that execute your
76	requests and signal their completion. You don't need thread support	54	requests and signal their completion. You don't need thread support
77	in perl, and the threads created by this module will not be visible	55	in perl, and the threads created by this module will not be visible
…		…
80	not well-supported or restricted (GNU/Linux doesn't allow them on normal	58	not well-supported or restricted (GNU/Linux doesn't allow them on normal
81	files currently, for example), and they would only support aio_read and	59	files currently, for example), and they would only support aio_read and
82	aio_write, so the remaining functionality would have to be implemented	60	aio_write, so the remaining functionality would have to be implemented
83	using threads anyway.	61	using threads anyway.
84		62
		63	In addition to asynchronous I/O, this module also exports some rather
		64	arcane interfaces, such as C<madvise> or linux's C<splice> system call,
		65	which is why the C<A> in C<AIO> can also mean I<advanced>.
		66
85	Although the module will work in the presence of other (Perl-) threads,	67	Although the module will work in the presence of other (Perl-) threads,
86	it is currently not reentrant in any way, so use appropriate locking	68	it is currently not reentrant in any way, so use appropriate locking
87	yourself, always call C<poll_cb> from within the same thread, or never	69	yourself, always call C<poll_cb> from within the same thread, or never
88	call C<poll_cb> (or other C<aio_> functions) recursively.	70	call C<poll_cb> (or other C<aio_> functions) recursively.
89		71
90	=head2 EXAMPLE	72	=head2 EXAMPLE
91		73
92	This is a simple example that uses the Event module and loads	74	This is a simple example that uses the EV module and loads
93	F</etc/passwd> asynchronously:	75	F</etc/passwd> asynchronously:
94		76
95	use Fcntl;
96	use Event;	77	use EV;
97	use IO::AIO;	78	use IO::AIO;
98		79
99	# register the IO::AIO callback with Event	80	# register the IO::AIO callback with EV
100	Event->io (fd => IO::AIO::poll_fileno,	81	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
101	poll => 'r',
102	cb => \&IO::AIO::poll_cb);
103		82
104	# queue the request to open /etc/passwd	83	# queue the request to open /etc/passwd
105	aio_open "/etc/passwd", O_RDONLY, 0, sub {	84	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
106	my $fh = shift	85	my $fh = shift
107	or die "error while opening: $!";	86	or die "error while opening: $!";
108		87
109	# stat'ing filehandles is generally non-blocking	88	# stat'ing filehandles is generally non-blocking
110	my $size = -s $fh;	89	my $size = -s $fh;
…		…
119		98
120	# file contents now in $contents	99	# file contents now in $contents
121	print $contents;	100	print $contents;
122		101
123	# exit event loop and program	102	# exit event loop and program
124	Event::unloop;	103	EV::break;
125	};	104	};
126	};	105	};
127		106
128	# possibly queue up other requests, or open GUI windows,	107	# possibly queue up other requests, or open GUI windows,
129	# check for sockets etc. etc.	108	# check for sockets etc. etc.
130		109
131	# process events as long as there are some:	110	# process events as long as there are some:
132	Event::loop;	111	EV::run;
133		112
134	=head1 REQUEST ANATOMY AND LIFETIME	113	=head1 REQUEST ANATOMY AND LIFETIME
135		114
136	Every C<aio_*> function creates a request. which is a C data structure not	115	Every C<aio_*> function creates a request. which is a C data structure not
137	directly visible to Perl.	116	directly visible to Perl.
…		…
187		166
188	package IO::AIO;	167	package IO::AIO;
189		168
190	use Carp ();	169	use Carp ();
191		170
192	no warnings;	171	use common::sense;
193	use strict 'vars';
194		172
195	use base 'Exporter';	173	use base 'Exporter';
196		174
197	BEGIN {	175	BEGIN {
198	our $VERSION = '3.16';	176	our $VERSION = 4.35;
199		177
200	our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close	178	our @AIO_REQ = qw(aio_sendfile aio_seek aio_read aio_write aio_open aio_close
201	aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir	179	aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx
202	aio_scandir aio_symlink aio_readlink aio_sync aio_fsync	180	aio_scandir aio_symlink aio_readlink aio_realpath aio_fcntl aio_ioctl
203	aio_fdatasync aio_sync_file_range aio_pathsync aio_readahead	181	aio_sync aio_fsync aio_syncfs aio_fdatasync aio_sync_file_range
		182	aio_pathsync aio_readahead aio_fiemap aio_allocate
204	aio_rename aio_link aio_move aio_copy aio_group	183	aio_rename aio_rename2 aio_link aio_move aio_copy aio_group
205	aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown	184	aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown
206	aio_chmod aio_utime aio_truncate);	185	aio_chmod aio_utime aio_truncate
		186	aio_msync aio_mtouch aio_mlock aio_mlockall
		187	aio_statvfs
		188	aio_wd);
207		189
208	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice));	190	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice));
209	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush	191	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush
210	min_parallel max_parallel max_idle	192	min_parallel max_parallel max_idle idle_timeout
211	nreqs nready npending nthreads	193	nreqs nready npending nthreads
212	max_poll_time max_poll_reqs);	194	max_poll_time max_poll_reqs
		195	sendfile fadvise madvise
		196	mmap munmap munlock munlockall);
		197
		198	push @AIO_REQ, qw(aio_busy); # not exported
213		199
214	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';	200	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';
215		201
216	require XSLoader;	202	require XSLoader;
217	XSLoader::load ("IO::AIO", $VERSION);	203	XSLoader::load ("IO::AIO", $VERSION);
218	}	204	}
219		205
220	=head1 FUNCTIONS	206	=head1 FUNCTIONS
221		207
222	=head2 AIO REQUEST FUNCTIONS	208	=head2 QUICK OVERVIEW
		209
		210	This section simply lists the prototypes most of the functions for
		211	quick reference. See the following sections for function-by-function
		212	documentation.
		213
		214	aio_wd $pathname, $callback->($wd)
		215	aio_open $pathname, $flags, $mode, $callback->($fh)
		216	aio_close $fh, $callback->($status)
		217	aio_seek $fh,$offset,$whence, $callback->($offs)
		218	aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
		219	aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
		220	aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
		221	aio_readahead $fh,$offset,$length, $callback->($retval)
		222	aio_stat $fh_or_path, $callback->($status)
		223	aio_lstat $fh, $callback->($status)
		224	aio_statvfs $fh_or_path, $callback->($statvfs)
		225	aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
		226	aio_chown $fh_or_path, $uid, $gid, $callback->($status)
		227	aio_chmod $fh_or_path, $mode, $callback->($status)
		228	aio_truncate $fh_or_path, $offset, $callback->($status)
		229	aio_allocate $fh, $mode, $offset, $len, $callback->($status)
		230	aio_fiemap $fh, $start, $length, $flags, $count, $cb->(\@extents)
		231	aio_unlink $pathname, $callback->($status)
		232	aio_mknod $pathname, $mode, $dev, $callback->($status)
		233	aio_link $srcpath, $dstpath, $callback->($status)
		234	aio_symlink $srcpath, $dstpath, $callback->($status)
		235	aio_readlink $pathname, $callback->($link)
		236	aio_realpath $pathname, $callback->($path)
		237	aio_rename $srcpath, $dstpath, $callback->($status)
		238	aio_rename2 $srcpath, $dstpath, $flags, $callback->($status)
		239	aio_mkdir $pathname, $mode, $callback->($status)
		240	aio_rmdir $pathname, $callback->($status)
		241	aio_readdir $pathname, $callback->($entries)
		242	aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		243	IO::AIO::READDIR_DENTS IO::AIO::READDIR_DIRS_FIRST
		244	IO::AIO::READDIR_STAT_ORDER IO::AIO::READDIR_FOUND_UNKNOWN
		245	aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs)
		246	aio_load $pathname, $data, $callback->($status)
		247	aio_copy $srcpath, $dstpath, $callback->($status)
		248	aio_move $srcpath, $dstpath, $callback->($status)
		249	aio_rmtree $pathname, $callback->($status)
		250	aio_fcntl $fh, $cmd, $arg, $callback->($status)
		251	aio_ioctl $fh, $request, $buf, $callback->($status)
		252	aio_sync $callback->($status)
		253	aio_syncfs $fh, $callback->($status)
		254	aio_fsync $fh, $callback->($status)
		255	aio_fdatasync $fh, $callback->($status)
		256	aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		257	aio_pathsync $pathname, $callback->($status)
		258	aio_msync $scalar, $offset = 0, $length = undef, flags = MS_SYNC, $callback->($status)
		259	aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		260	aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
		261	aio_mlockall $flags, $callback->($status)
		262	aio_group $callback->(...)
		263	aio_nop $callback->()
		264
		265	$prev_pri = aioreq_pri [$pri]
		266	aioreq_nice $pri_adjust
		267
		268	IO::AIO::poll_wait
		269	IO::AIO::poll_cb
		270	IO::AIO::poll
		271	IO::AIO::flush
		272	IO::AIO::max_poll_reqs $nreqs
		273	IO::AIO::max_poll_time $seconds
		274	IO::AIO::min_parallel $nthreads
		275	IO::AIO::max_parallel $nthreads
		276	IO::AIO::max_idle $nthreads
		277	IO::AIO::idle_timeout $seconds
		278	IO::AIO::max_outstanding $maxreqs
		279	IO::AIO::nreqs
		280	IO::AIO::nready
		281	IO::AIO::npending
		282
		283	IO::AIO::sendfile $ofh, $ifh, $offset, $count
		284	IO::AIO::fadvise $fh, $offset, $len, $advice
		285	IO::AIO::mmap $scalar, $length, $prot, $flags[, $fh[, $offset]]
		286	IO::AIO::munmap $scalar
		287	IO::AIO::madvise $scalar, $offset, $length, $advice
		288	IO::AIO::mprotect $scalar, $offset, $length, $protect
		289	IO::AIO::munlock $scalar, $offset = 0, $length = undef
		290	IO::AIO::munlockall
		291
		292	=head2 API NOTES
223		293
224	All the C<aio_*> calls are more or less thin wrappers around the syscall	294	All the C<aio_*> calls are more or less thin wrappers around the syscall
225	with the same name (sans C<aio_>). The arguments are similar or identical,	295	with the same name (sans C<aio_>). The arguments are similar or identical,
226	and they all accept an additional (and optional) C<$callback> argument	296	and they all accept an additional (and optional) C<$callback> argument
227	which must be a code reference. This code reference will get called with	297	which must be a code reference. This code reference will be called after
228	the syscall return code (e.g. most syscalls return C<-1> on error, unlike	298	the syscall has been executed in an asynchronous fashion. The results
229	perl, which usually delivers "false") as its sole argument after the given	299	of the request will be passed as arguments to the callback (and, if an
230	syscall has been executed asynchronously.	300	error occured, in C<$!>) - for most requests the syscall return code (e.g.
		301	most syscalls return C<-1> on error, unlike perl, which usually delivers
		302	"false").
		303
		304	Some requests (such as C<aio_readdir>) pass the actual results and
		305	communicate failures by passing C<undef>.
231		306
232	All functions expecting a filehandle keep a copy of the filehandle	307	All functions expecting a filehandle keep a copy of the filehandle
233	internally until the request has finished.	308	internally until the request has finished.
234		309
235	All functions return request objects of type L<IO::AIO::REQ> that allow	310	All functions return request objects of type L<IO::AIO::REQ> that allow
236	further manipulation of those requests while they are in-flight.	311	further manipulation of those requests while they are in-flight.
237		312
238	The pathnames you pass to these routines I<must> be absolute and	313	The pathnames you pass to these routines I<should> be absolute. The
239	encoded as octets. The reason for the former is that at the time the	314	reason for this is that at the time the request is being executed, the
240	request is being executed, the current working directory could have	315	current working directory could have changed. Alternatively, you can
241	changed. Alternatively, you can make sure that you never change the	316	make sure that you never change the current working directory anywhere
242	current working directory anywhere in the program and then use relative	317	in the program and then use relative paths. You can also take advantage
243	paths.	318	of IO::AIOs working directory abstraction, that lets you specify paths
		319	relative to some previously-opened "working directory object" - see the
		320	description of the C<IO::AIO::WD> class later in this document.
244		321
245	To encode pathnames as octets, either make sure you either: a) always pass	322	To encode pathnames as octets, either make sure you either: a) always pass
246	in filenames you got from outside (command line, readdir etc.) without	323	in filenames you got from outside (command line, readdir etc.) without
247	tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module and encode	324	tinkering, b) are in your native filesystem encoding, c) use the Encode
248	your pathnames to the locale (or other) encoding in effect in the user	325	module and encode your pathnames to the locale (or other) encoding in
249	environment, d) use Glib::filename_from_unicode on unicode filenames or e)	326	effect in the user environment, d) use Glib::filename_from_unicode on
250	use something else to ensure your scalar has the correct contents.	327	unicode filenames or e) use something else to ensure your scalar has the
		328	correct contents.
251		329
252	This works, btw. independent of the internal UTF-8 bit, which IO::AIO	330	This works, btw. independent of the internal UTF-8 bit, which IO::AIO
253	handles correctly whether it is set or not.	331	handles correctly whether it is set or not.
		332
		333	=head2 AIO REQUEST FUNCTIONS
254		334
255	=over 4	335	=over 4
256		336
257	=item $prev_pri = aioreq_pri [$pri]	337	=item $prev_pri = aioreq_pri [$pri]
258		338
…		…
288		368
289		369
290	=item aio_open $pathname, $flags, $mode, $callback->($fh)	370	=item aio_open $pathname, $flags, $mode, $callback->($fh)
291		371
292	Asynchronously open or create a file and call the callback with a newly	372	Asynchronously open or create a file and call the callback with a newly
293	created filehandle for the file.	373	created filehandle for the file (or C<undef> in case of an error).
294		374
295	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,	375	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,
296	for an explanation.	376	for an explanation.
297		377
298	The C<$flags> argument is a bitmask. See the C<Fcntl> module for a	378	The C<$flags> argument is a bitmask. See the C<Fcntl> module for a
…		…
305	by the umask in effect then the request is being executed, so better never	385	by the umask in effect then the request is being executed, so better never
306	change the umask.	386	change the umask.
307		387
308	Example:	388	Example:
309		389
310	aio_open "/etc/passwd", O_RDONLY, 0, sub {	390	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
311	if ($_[0]) {	391	if ($_[0]) {
312	print "open successful, fh is $_[0]\n";	392	print "open successful, fh is $_[0]\n";
313	...	393	...
314	} else {	394	} else {
315	die "open failed: $!\n";	395	die "open failed: $!\n";
316	}	396	}
317	};	397	};
318		398
		399	In addition to all the common open modes/flags (C<O_RDONLY>, C<O_WRONLY>,
		400	C<O_RDWR>, C<O_CREAT>, C<O_TRUNC>, C<O_EXCL> and C<O_APPEND>), the
		401	following POSIX and non-POSIX constants are available (missing ones on
		402	your system are, as usual, C<0>):
		403
		404	C<O_ASYNC>, C<O_DIRECT>, C<O_NOATIME>, C<O_CLOEXEC>, C<O_NOCTTY>, C<O_NOFOLLOW>,
		405	C<O_NONBLOCK>, C<O_EXEC>, C<O_SEARCH>, C<O_DIRECTORY>, C<O_DSYNC>,
		406	C<O_RSYNC>, C<O_SYNC>, C<O_PATH>, C<O_TMPFILE>, and C<O_TTY_INIT>.
		407
319		408
320	=item aio_close $fh, $callback->($status)	409	=item aio_close $fh, $callback->($status)
321		410
322	Asynchronously close a file and call the callback with the result	411	Asynchronously close a file and call the callback with the result
323	code.	412	code.
…		…
332	Or in other words: the file descriptor will be closed, but it will not be	421	Or in other words: the file descriptor will be closed, but it will not be
333	free for reuse until the perl filehandle is closed.	422	free for reuse until the perl filehandle is closed.
334		423
335	=cut	424	=cut
336		425
		426	=item aio_seek $fh, $offset, $whence, $callback->($offs)
		427
		428	Seeks the filehandle to the new C<$offset>, similarly to perl's
		429	C<sysseek>. The C<$whence> can use the traditional values (C<0> for
		430	C<IO::AIO::SEEK_SET>, C<1> for C<IO::AIO::SEEK_CUR> or C<2> for
		431	C<IO::AIO::SEEK_END>).
		432
		433	The resulting absolute offset will be passed to the callback, or C<-1> in
		434	case of an error.
		435
		436	In theory, the C<$whence> constants could be different than the
		437	corresponding values from L<Fcntl>, but perl guarantees they are the same,
		438	so don't panic.
		439
		440	As a GNU/Linux (and maybe Solaris) extension, also the constants
		441	C<IO::AIO::SEEK_DATA> and C<IO::AIO::SEEK_HOLE> are available, if they
		442	could be found. No guarantees about suitability for use in C<aio_seek> or
		443	Perl's C<sysseek> can be made though, although I would naively assume they
		444	"just work".
		445
337	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	446	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
338		447
339	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	448	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
340		449
341	Reads or writes C<$length> bytes from the specified C<$fh> and C<$offset>	450	Reads or writes C<$length> bytes from or to the specified C<$fh> and
342	into the scalar given by C<$data> and offset C<$dataoffset> and calls the	451	C<$offset> into the scalar given by C<$data> and offset C<$dataoffset> and
343	callback without the actual number of bytes read (or -1 on error, just	452	calls the callback with the actual number of bytes transferred (or -1 on
344	like the syscall).	453	error, just like the syscall).
		454
		455	C<aio_read> will, like C<sysread>, shrink or grow the C<$data> scalar to
		456	offset plus the actual number of bytes read.
345		457
346	If C<$offset> is undefined, then the current file descriptor offset will	458	If C<$offset> is undefined, then the current file descriptor offset will
347	be used (and updated), otherwise the file descriptor offset will not be	459	be used (and updated), otherwise the file descriptor offset will not be
348	changed by these calls.	460	changed by these calls.
349		461
350	If C<$length> is undefined in C<aio_write>, use the remaining length of C<$data>.	462	If C<$length> is undefined in C<aio_write>, use the remaining length of
		463	C<$data>.
351		464
352	If C<$dataoffset> is less than zero, it will be counted from the end of	465	If C<$dataoffset> is less than zero, it will be counted from the end of
353	C<$data>.	466	C<$data>.
354		467
355	The C<$data> scalar I<MUST NOT> be modified in any way while the request	468	The C<$data> scalar I<MUST NOT> be modified in any way while the request
…		…
369		482
370	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts	483	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
371	reading at byte offset C<$in_offset>, and starts writing at the current	484	reading at byte offset C<$in_offset>, and starts writing at the current
372	file offset of C<$out_fh>. Because of that, it is not safe to issue more	485	file offset of C<$out_fh>. Because of that, it is not safe to issue more
373	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each	486	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each
374	other.	487	other. The same C<$in_fh> works fine though, as this function does not
		488	move or use the file offset of C<$in_fh>.
375		489
		490	Please note that C<aio_sendfile> can read more bytes from C<$in_fh> than
		491	are written, and there is no way to find out how many more bytes have been
		492	read from C<aio_sendfile> alone, as C<aio_sendfile> only provides the
		493	number of bytes written to C<$out_fh>. Only if the result value equals
		494	C<$length> one can assume that C<$length> bytes have been read.
		495
		496	Unlike with other C<aio_> functions, it makes a lot of sense to use
		497	C<aio_sendfile> on non-blocking sockets, as long as one end (typically
		498	the C<$in_fh>) is a file - the file I/O will then be asynchronous, while
		499	the socket I/O will be non-blocking. Note, however, that you can run
		500	into a trap where C<aio_sendfile> reads some data with readahead, then
		501	fails to write all data, and when the socket is ready the next time, the
		502	data in the cache is already lost, forcing C<aio_sendfile> to again hit
		503	the disk. Explicit C<aio_read> + C<aio_write> let's you better control
		504	resource usage.
		505
376	This call tries to make use of a native C<sendfile> syscall to provide	506	This call tries to make use of a native C<sendfile>-like syscall to
377	zero-copy operation. For this to work, C<$out_fh> should refer to a	507	provide zero-copy operation. For this to work, C<$out_fh> should refer to
378	socket, and C<$in_fh> should refer to mmap'able file.	508	a socket, and C<$in_fh> should refer to an mmap'able file.
379		509
380	If the native sendfile call fails or is not implemented, it will be	510	If a native sendfile cannot be found or it fails with C<ENOSYS>,
381	emulated, so you can call C<aio_sendfile> on any type of filehandle	511	C<EINVAL>, C<ENOTSUP>, C<EOPNOTSUPP>, C<EAFNOSUPPORT>, C<EPROTOTYPE> or
		512	C<ENOTSOCK>, it will be emulated, so you can call C<aio_sendfile> on any
382	regardless of the limitations of the operating system.	513	type of filehandle regardless of the limitations of the operating system.
383		514
384	Please note, however, that C<aio_sendfile> can read more bytes from	515	As native sendfile syscalls (as practically any non-POSIX interface hacked
385	C<$in_fh> than are written, and there is no way to find out how many	516	together in a hurry to improve benchmark numbers) tend to be rather buggy
386	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only	517	on many systems, this implementation tries to work around some known bugs
387	provides the number of bytes written to C<$out_fh>. Only if the result	518	in Linux and FreeBSD kernels (probably others, too), but that might fail,
388	value equals C<$length> one can assume that C<$length> bytes have been	519	so you really really should check the return value of C<aio_sendfile> -
389	read.	520	fewer bytes than expected might have been transferred.
390		521
391		522
392	=item aio_readahead $fh,$offset,$length, $callback->($retval)	523	=item aio_readahead $fh,$offset,$length, $callback->($retval)
393		524
394	C<aio_readahead> populates the page cache with data from a file so that	525	C<aio_readahead> populates the page cache with data from a file so that
…		…
398	whole pages, so that offset is effectively rounded down to a page boundary	529	whole pages, so that offset is effectively rounded down to a page boundary
399	and bytes are read up to the next page boundary greater than or equal to	530	and bytes are read up to the next page boundary greater than or equal to
400	(off-set+length). C<aio_readahead> does not read beyond the end of the	531	(off-set+length). C<aio_readahead> does not read beyond the end of the
401	file. The current file offset of the file is left unchanged.	532	file. The current file offset of the file is left unchanged.
402		533
403	If that syscall doesn't exist (likely if your OS isn't Linux) it will be	534	If that syscall doesn't exist (likely if your kernel isn't Linux) it will
404	emulated by simply reading the data, which would have a similar effect.	535	be emulated by simply reading the data, which would have a similar effect.
405		536
406		537
407	=item aio_stat $fh_or_path, $callback->($status)	538	=item aio_stat $fh_or_path, $callback->($status)
408		539
409	=item aio_lstat $fh, $callback->($status)	540	=item aio_lstat $fh, $callback->($status)
…		…
416	for an explanation.	547	for an explanation.
417		548
418	Currently, the stats are always 64-bit-stats, i.e. instead of returning an	549	Currently, the stats are always 64-bit-stats, i.e. instead of returning an
419	error when stat'ing a large file, the results will be silently truncated	550	error when stat'ing a large file, the results will be silently truncated
420	unless perl itself is compiled with large file support.	551	unless perl itself is compiled with large file support.
		552
		553	To help interpret the mode and dev/rdev stat values, IO::AIO offers the
		554	following constants and functions (if not implemented, the constants will
		555	be C<0> and the functions will either C<croak> or fall back on traditional
		556	behaviour).
		557
		558	C<S_IFMT>, C<S_IFIFO>, C<S_IFCHR>, C<S_IFBLK>, C<S_IFLNK>, C<S_IFREG>,
		559	C<S_IFDIR>, C<S_IFWHT>, C<S_IFSOCK>, C<IO::AIO::major $dev_t>,
		560	C<IO::AIO::minor $dev_t>, C<IO::AIO::makedev $major, $minor>.
421		561
422	Example: Print the length of F</etc/passwd>:	562	Example: Print the length of F</etc/passwd>:
423		563
424	aio_stat "/etc/passwd", sub {	564	aio_stat "/etc/passwd", sub {
425	$_[0] and die "stat failed: $!";	565	$_[0] and die "stat failed: $!";
426	print "size is ", -s _, "\n";	566	print "size is ", -s _, "\n";
427	};	567	};
428		568
429		569
		570	=item aio_statvfs $fh_or_path, $callback->($statvfs)
		571
		572	Works like the POSIX C<statvfs> or C<fstatvfs> syscalls, depending on
		573	whether a file handle or path was passed.
		574
		575	On success, the callback is passed a hash reference with the following
		576	members: C<bsize>, C<frsize>, C<blocks>, C<bfree>, C<bavail>, C<files>,
		577	C<ffree>, C<favail>, C<fsid>, C<flag> and C<namemax>. On failure, C<undef>
		578	is passed.
		579
		580	The following POSIX IO::AIO::ST_* constants are defined: C<ST_RDONLY> and
		581	C<ST_NOSUID>.
		582
		583	The following non-POSIX IO::AIO::ST_* flag masks are defined to
		584	their correct value when available, or to C<0> on systems that do
		585	not support them: C<ST_NODEV>, C<ST_NOEXEC>, C<ST_SYNCHRONOUS>,
		586	C<ST_MANDLOCK>, C<ST_WRITE>, C<ST_APPEND>, C<ST_IMMUTABLE>, C<ST_NOATIME>,
		587	C<ST_NODIRATIME> and C<ST_RELATIME>.
		588
		589	Example: stat C</wd> and dump out the data if successful.
		590
		591	aio_statvfs "/wd", sub {
		592	my $f = $_[0]
		593	or die "statvfs: $!";
		594
		595	use Data::Dumper;
		596	say Dumper $f;
		597	};
		598
		599	# result:
		600	{
		601	bsize => 1024,
		602	bfree => 4333064312,
		603	blocks => 10253828096,
		604	files => 2050765568,
		605	flag => 4096,
		606	favail => 2042092649,
		607	bavail => 4333064312,
		608	ffree => 2042092649,
		609	namemax => 255,
		610	frsize => 1024,
		611	fsid => 1810
		612	}
		613
		614	Here is a (likely partial - send me updates!) list of fsid values used by
		615	Linux - it is safe to hardcode these when C<$^O> is C<linux>:
		616
		617	0x0000adf5 adfs
		618	0x0000adff affs
		619	0x5346414f afs
		620	0x09041934 anon-inode filesystem
		621	0x00000187 autofs
		622	0x42465331 befs
		623	0x1badface bfs
		624	0x42494e4d binfmt_misc
		625	0x9123683e btrfs
		626	0x0027e0eb cgroupfs
		627	0xff534d42 cifs
		628	0x73757245 coda
		629	0x012ff7b7 coh
		630	0x28cd3d45 cramfs
		631	0x453dcd28 cramfs-wend (wrong endianness)
		632	0x64626720 debugfs
		633	0x00001373 devfs
		634	0x00001cd1 devpts
		635	0x0000f15f ecryptfs
		636	0x00414a53 efs
		637	0x0000137d ext
		638	0x0000ef53 ext2/ext3/ext4
		639	0x0000ef51 ext2
		640	0xf2f52010 f2fs
		641	0x00004006 fat
		642	0x65735546 fuseblk
		643	0x65735543 fusectl
		644	0x0bad1dea futexfs
		645	0x01161970 gfs2
		646	0x47504653 gpfs
		647	0x00004244 hfs
		648	0xf995e849 hpfs
		649	0x00c0ffee hostfs
		650	0x958458f6 hugetlbfs
		651	0x2bad1dea inotifyfs
		652	0x00009660 isofs
		653	0x000072b6 jffs2
		654	0x3153464a jfs
		655	0x6b414653 k-afs
		656	0x0bd00bd0 lustre
		657	0x0000137f minix
		658	0x0000138f minix 30 char names
		659	0x00002468 minix v2
		660	0x00002478 minix v2 30 char names
		661	0x00004d5a minix v3
		662	0x19800202 mqueue
		663	0x00004d44 msdos
		664	0x0000564c novell
		665	0x00006969 nfs
		666	0x6e667364 nfsd
		667	0x00003434 nilfs
		668	0x5346544e ntfs
		669	0x00009fa1 openprom
		670	0x7461636F ocfs2
		671	0x00009fa0 proc
		672	0x6165676c pstorefs
		673	0x0000002f qnx4
		674	0x68191122 qnx6
		675	0x858458f6 ramfs
		676	0x52654973 reiserfs
		677	0x00007275 romfs
		678	0x67596969 rpc_pipefs
		679	0x73636673 securityfs
		680	0xf97cff8c selinux
		681	0x0000517b smb
		682	0x534f434b sockfs
		683	0x73717368 squashfs
		684	0x62656572 sysfs
		685	0x012ff7b6 sysv2
		686	0x012ff7b5 sysv4
		687	0x01021994 tmpfs
		688	0x15013346 udf
		689	0x00011954 ufs
		690	0x54190100 ufs byteswapped
		691	0x00009fa2 usbdevfs
		692	0x01021997 v9fs
		693	0xa501fcf5 vxfs
		694	0xabba1974 xenfs
		695	0x012ff7b4 xenix
		696	0x58465342 xfs
		697	0x012fd16d xia
		698
430	=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)	699	=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
431		700
432	Works like perl's C<utime> function (including the special case of $atime	701	Works like perl's C<utime> function (including the special case of $atime
433	and $mtime being undef). Fractional times are supported if the underlying	702	and $mtime being undef). Fractional times are supported if the underlying
434	syscalls support them.	703	syscalls support them.
…		…
461	=item aio_truncate $fh_or_path, $offset, $callback->($status)	730	=item aio_truncate $fh_or_path, $offset, $callback->($status)
462		731
463	Works like truncate(2) or ftruncate(2).	732	Works like truncate(2) or ftruncate(2).
464		733
465		734
		735	=item aio_allocate $fh, $mode, $offset, $len, $callback->($status)
		736
		737	Allocates or frees disk space according to the C<$mode> argument. See the
		738	linux C<fallocate> documentation for details.
		739
		740	C<$mode> is usually C<0> or C<IO::AIO::FALLOC_FL_KEEP_SIZE> to allocate
		741	space, or C<IO::AIO::FALLOC_FL_PUNCH_HOLE | IO::AIO::FALLOC_FL_KEEP_SIZE>,
		742	to deallocate a file range.
		743
		744	IO::AIO also supports C<FALLOC_FL_COLLAPSE_RANGE>, to remove a range
		745	(without leaving a hole) and C<FALLOC_FL_ZERO_RANGE>, to zero a range (see
		746	your L<fallocate(2)> manpage).
		747
		748	The file system block size used by C<fallocate> is presumably the
		749	C<f_bsize> returned by C<statvfs>.
		750
		751	If C<fallocate> isn't available or cannot be emulated (currently no
		752	emulation will be attempted), passes C<-1> and sets C<$!> to C<ENOSYS>.
		753
		754
466	=item aio_chmod $fh_or_path, $mode, $callback->($status)	755	=item aio_chmod $fh_or_path, $mode, $callback->($status)
467		756
468	Works like perl's C<chmod> function.	757	Works like perl's C<chmod> function.
469		758
470		759
…		…
472		761
473	Asynchronously unlink (delete) a file and call the callback with the	762	Asynchronously unlink (delete) a file and call the callback with the
474	result code.	763	result code.
475		764
476		765
477	=item aio_mknod $path, $mode, $dev, $callback->($status)	766	=item aio_mknod $pathname, $mode, $dev, $callback->($status)
478		767
479	[EXPERIMENTAL]	768	[EXPERIMENTAL]
480		769
481	Asynchronously create a device node (or fifo). See mknod(2).	770	Asynchronously create a device node (or fifo). See mknod(2).
482		771
483	The only (POSIX-) portable way of calling this function is:	772	The only (POSIX-) portable way of calling this function is:
484		773
485	aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ...	774	aio_mknod $pathname, IO::AIO::S_IFIFO | $mode, 0, sub { ...
486		775
		776	See C<aio_stat> for info about some potentially helpful extra constants
		777	and functions.
487		778
488	=item aio_link $srcpath, $dstpath, $callback->($status)	779	=item aio_link $srcpath, $dstpath, $callback->($status)
489		780
490	Asynchronously create a new link to the existing object at C<$srcpath> at	781	Asynchronously create a new link to the existing object at C<$srcpath> at
491	the path C<$dstpath> and call the callback with the result code.	782	the path C<$dstpath> and call the callback with the result code.
…		…
495		786
496	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at	787	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at
497	the path C<$dstpath> and call the callback with the result code.	788	the path C<$dstpath> and call the callback with the result code.
498		789
499		790
500	=item aio_readlink $path, $callback->($link)	791	=item aio_readlink $pathname, $callback->($link)
501		792
502	Asynchronously read the symlink specified by C<$path> and pass it to	793	Asynchronously read the symlink specified by C<$path> and pass it to
503	the callback. If an error occurs, nothing or undef gets passed to the	794	the callback. If an error occurs, nothing or undef gets passed to the
504	callback.	795	callback.
505		796
506		797
		798	=item aio_realpath $pathname, $callback->($path)
		799
		800	Asynchronously make the path absolute and resolve any symlinks in
		801	C<$path>. The resulting path only consists of directories (same as
		802	L<Cwd::realpath>).
		803
		804	This request can be used to get the absolute path of the current working
		805	directory by passing it a path of F<.> (a single dot).
		806
		807
507	=item aio_rename $srcpath, $dstpath, $callback->($status)	808	=item aio_rename $srcpath, $dstpath, $callback->($status)
508		809
509	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as	810	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as
510	rename(2) and call the callback with the result code.	811	rename(2) and call the callback with the result code.
		812
		813	On systems that support the AIO::WD working directory abstraction
		814	natively, the case C<[$wd, "."]> as C<$srcpath> is specialcased - instead
		815	of failing, C<rename> is called on the absolute path of C<$wd>.
		816
		817
		818	=item aio_rename2 $srcpath, $dstpath, $flags, $callback->($status)
		819
		820	Basically a version of C<aio_rename> with an additional C<$flags>
		821	argument. Calling this with C<$flags=0> is the same as calling
		822	C<aio_rename>.
		823
		824	Non-zero flags are currently only supported on GNU/Linux systems that
		825	support renameat2. Other systems fail with C<ENOSYS> in this case.
		826
		827	The following constants are available (missing ones are, as usual C<0>),
		828	see renameat2(2) for details:
		829
		830	C<IO::AIO::RENAME_NOREPLACE>, C<IO::AIO::RENAME_EXCHANGE>
		831	and C<IO::AIO::RENAME_WHITEOUT>.
511		832
512		833
513	=item aio_mkdir $pathname, $mode, $callback->($status)	834	=item aio_mkdir $pathname, $mode, $callback->($status)
514		835
515	Asynchronously mkdir (create) a directory and call the callback with	836	Asynchronously mkdir (create) a directory and call the callback with
…		…
520	=item aio_rmdir $pathname, $callback->($status)	841	=item aio_rmdir $pathname, $callback->($status)
521		842
522	Asynchronously rmdir (delete) a directory and call the callback with the	843	Asynchronously rmdir (delete) a directory and call the callback with the
523	result code.	844	result code.
524		845
		846	On systems that support the AIO::WD working directory abstraction
		847	natively, the case C<[$wd, "."]> is specialcased - instead of failing,
		848	C<rmdir> is called on the absolute path of C<$wd>.
		849
525		850
526	=item aio_readdir $pathname, $callback->($entries)	851	=item aio_readdir $pathname, $callback->($entries)
527		852
528	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire	853	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
529	directory (i.e. opendir + readdir + closedir). The entries will not be	854	directory (i.e. opendir + readdir + closedir). The entries will not be
530	sorted, and will B<NOT> include the C<.> and C<..> entries.	855	sorted, and will B<NOT> include the C<.> and C<..> entries.
531		856
532	The callback a single argument which is either C<undef> or an array-ref	857	The callback is passed a single argument which is either C<undef> or an
533	with the filenames.	858	array-ref with the filenames.
534		859
535		860
		861	=item aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		862
		863	Quite similar to C<aio_readdir>, but the C<$flags> argument allows one to
		864	tune behaviour and output format. In case of an error, C<$entries> will be
		865	C<undef>.
		866
		867	The flags are a combination of the following constants, ORed together (the
		868	flags will also be passed to the callback, possibly modified):
		869
		870	=over 4
		871
		872	=item IO::AIO::READDIR_DENTS
		873
		874	When this flag is off, then the callback gets an arrayref consisting of
		875	names only (as with C<aio_readdir>), otherwise it gets an arrayref with
		876	C<[$name, $type, $inode]> arrayrefs, each describing a single directory
		877	entry in more detail.
		878
		879	C<$name> is the name of the entry.
		880
		881	C<$type> is one of the C<IO::AIO::DT_xxx> constants:
		882
		883	C<IO::AIO::DT_UNKNOWN>, C<IO::AIO::DT_FIFO>, C<IO::AIO::DT_CHR>, C<IO::AIO::DT_DIR>,
		884	C<IO::AIO::DT_BLK>, C<IO::AIO::DT_REG>, C<IO::AIO::DT_LNK>, C<IO::AIO::DT_SOCK>,
		885	C<IO::AIO::DT_WHT>.
		886
		887	C<IO::AIO::DT_UNKNOWN> means just that: readdir does not know. If you need to
		888	know, you have to run stat yourself. Also, for speed reasons, the C<$type>
		889	scalars are read-only: you can not modify them.
		890
		891	C<$inode> is the inode number (which might not be exact on systems with 64
		892	bit inode numbers and 32 bit perls). This field has unspecified content on
		893	systems that do not deliver the inode information.
		894
		895	=item IO::AIO::READDIR_DIRS_FIRST
		896
		897	When this flag is set, then the names will be returned in an order where
		898	likely directories come first, in optimal stat order. This is useful when
		899	you need to quickly find directories, or you want to find all directories
		900	while avoiding to stat() each entry.
		901
		902	If the system returns type information in readdir, then this is used
		903	to find directories directly. Otherwise, likely directories are names
		904	beginning with ".", or otherwise names with no dots, of which names with
		905	short names are tried first.
		906
		907	=item IO::AIO::READDIR_STAT_ORDER
		908
		909	When this flag is set, then the names will be returned in an order
		910	suitable for stat()'ing each one. That is, when you plan to stat()
		911	all files in the given directory, then the returned order will likely
		912	be fastest.
		913
		914	If both this flag and C<IO::AIO::READDIR_DIRS_FIRST> are specified, then
		915	the likely dirs come first, resulting in a less optimal stat order.
		916
		917	=item IO::AIO::READDIR_FOUND_UNKNOWN
		918
		919	This flag should not be set when calling C<aio_readdirx>. Instead, it
		920	is being set by C<aio_readdirx>, when any of the C<$type>'s found were
		921	C<IO::AIO::DT_UNKNOWN>. The absence of this flag therefore indicates that all
		922	C<$type>'s are known, which can be used to speed up some algorithms.
		923
		924	=back
		925
		926
536	=item aio_load $path, $data, $callback->($status)	927	=item aio_load $pathname, $data, $callback->($status)
537		928
538	This is a composite request that tries to fully load the given file into	929	This is a composite request that tries to fully load the given file into
539	memory. Status is the same as with aio_read.	930	memory. Status is the same as with aio_read.
540		931
541	=cut	932	=cut
…		…
563		954
564	=item aio_copy $srcpath, $dstpath, $callback->($status)	955	=item aio_copy $srcpath, $dstpath, $callback->($status)
565		956
566	Try to copy the I<file> (directories not supported as either source or	957	Try to copy the I<file> (directories not supported as either source or
567	destination) from C<$srcpath> to C<$dstpath> and call the callback with	958	destination) from C<$srcpath> to C<$dstpath> and call the callback with
568	the C<0> (error) or C<-1> ok.	959	a status of C<0> (ok) or C<-1> (error, see C<$!>).
569		960
570	This is a composite request that creates the destination file with	961	This is a composite request that creates the destination file with
571	mode 0200 and copies the contents of the source file into it using	962	mode 0200 and copies the contents of the source file into it using
572	C<aio_sendfile>, followed by restoring atime, mtime, access mode and	963	C<aio_sendfile>, followed by restoring atime, mtime, access mode and
573	uid/gid, in that order.	964	uid/gid, in that order.
…		…
585	my $grp = aio_group $cb;	976	my $grp = aio_group $cb;
586		977
587	aioreq_pri $pri;	978	aioreq_pri $pri;
588	add $grp aio_open $src, O_RDONLY, 0, sub {	979	add $grp aio_open $src, O_RDONLY, 0, sub {
589	if (my $src_fh = $_[0]) {	980	if (my $src_fh = $_[0]) {
590	my @stat = stat $src_fh;	981	my @stat = stat $src_fh; # hmm, might block over nfs?
591		982
592	aioreq_pri $pri;	983	aioreq_pri $pri;
593	add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {	984	add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {
594	if (my $dst_fh = $_[0]) {	985	if (my $dst_fh = $_[0]) {
595	aioreq_pri $pri;	986	aioreq_pri $pri;
596	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {	987	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
597	if ($_[0] == $stat[7]) {	988	if ($_[0] == $stat[7]) {
598	$grp->result (0);	989	$grp->result (0);
599	close $src_fh;	990	close $src_fh;
600		991
601	# those should not normally block. should. should.	992	my $ch = sub {
602	utime $stat[8], $stat[9], $dst;	993	aioreq_pri $pri;
603	chmod $stat[2] & 07777, $dst_fh;	994	add $grp aio_chmod $dst_fh, $stat[2] & 07777, sub {
604	chown $stat[4], $stat[5], $dst_fh;	995	aioreq_pri $pri;
		996	add $grp aio_chown $dst_fh, $stat[4], $stat[5], sub {
		997	aioreq_pri $pri;
		998	add $grp aio_close $dst_fh;
		999	}
		1000	};
		1001	};
605		1002
606	aioreq_pri $pri;	1003	aioreq_pri $pri;
607	add $grp aio_close $dst_fh;	1004	add $grp aio_utime $dst_fh, $stat[8], $stat[9], sub {
		1005	if ($_[0] < 0 && $! == ENOSYS) {
		1006	aioreq_pri $pri;
		1007	add $grp aio_utime $dst, $stat[8], $stat[9], $ch;
		1008	} else {
		1009	$ch->();
		1010	}
		1011	};
608	} else {	1012	} else {
609	$grp->result (-1);	1013	$grp->result (-1);
610	close $src_fh;	1014	close $src_fh;
611	close $dst_fh;	1015	close $dst_fh;
612		1016
…		…
629		1033
630	=item aio_move $srcpath, $dstpath, $callback->($status)	1034	=item aio_move $srcpath, $dstpath, $callback->($status)
631		1035
632	Try to move the I<file> (directories not supported as either source or	1036	Try to move the I<file> (directories not supported as either source or
633	destination) from C<$srcpath> to C<$dstpath> and call the callback with	1037	destination) from C<$srcpath> to C<$dstpath> and call the callback with
634	the C<0> (error) or C<-1> ok.	1038	a status of C<0> (ok) or C<-1> (error, see C<$!>).
635		1039
636	This is a composite request that tries to rename(2) the file first; if	1040	This is a composite request that tries to rename(2) the file first; if
637	rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if	1041	rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if
638	that is successful, unlinks the C<$srcpath>.	1042	that is successful, unlinks the C<$srcpath>.
639		1043
…		…
650	if ($_[0] && $! == EXDEV) {	1054	if ($_[0] && $! == EXDEV) {
651	aioreq_pri $pri;	1055	aioreq_pri $pri;
652	add $grp aio_copy $src, $dst, sub {	1056	add $grp aio_copy $src, $dst, sub {
653	$grp->result ($_[0]);	1057	$grp->result ($_[0]);
654		1058
655	if (!$_[0]) {	1059	unless ($_[0]) {
656	aioreq_pri $pri;	1060	aioreq_pri $pri;
657	add $grp aio_unlink $src;	1061	add $grp aio_unlink $src;
658	}	1062	}
659	};	1063	};
660	} else {	1064	} else {
…		…
663	};	1067	};
664		1068
665	$grp	1069	$grp
666	}	1070	}
667		1071
668	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)	1072	=item aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs)
669		1073
670	Scans a directory (similar to C<aio_readdir>) but additionally tries to	1074	Scans a directory (similar to C<aio_readdir>) but additionally tries to
671	efficiently separate the entries of directory C<$path> into two sets of	1075	efficiently separate the entries of directory C<$path> into two sets of
672	names, directories you can recurse into (directories), and ones you cannot	1076	names, directories you can recurse into (directories), and ones you cannot
673	recurse into (everything else, including symlinks to directories).	1077	recurse into (everything else, including symlinks to directories).
…		…
690		1094
691	Implementation notes.	1095	Implementation notes.
692		1096
693	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.	1097	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.
694		1098
		1099	If readdir returns file type information, then this is used directly to
		1100	find directories.
		1101
695	After reading the directory, the modification time, size etc. of the	1102	Otherwise, after reading the directory, the modification time, size etc.
696	directory before and after the readdir is checked, and if they match (and	1103	of the directory before and after the readdir is checked, and if they
697	isn't the current time), the link count will be used to decide how many	1104	match (and isn't the current time), the link count will be used to decide
698	entries are directories (if >= 2). Otherwise, no knowledge of the number	1105	how many entries are directories (if >= 2). Otherwise, no knowledge of the
699	of subdirectories will be assumed.	1106	number of subdirectories will be assumed.
700		1107
701	Then entries will be sorted into likely directories (everything without	1108	Then entries will be sorted into likely directories a non-initial dot
702	a non-initial dot currently) and likely non-directories (everything	1109	currently) and likely non-directories (see C<aio_readdirx>). Then every
703	else). Then every entry plus an appended C</.> will be C<stat>'ed,	1110	entry plus an appended C</.> will be C<stat>'ed, likely directories first,
704	likely directories first. If that succeeds, it assumes that the entry	1111	in order of their inode numbers. If that succeeds, it assumes that the
705	is a directory or a symlink to directory (which will be checked	1112	entry is a directory or a symlink to directory (which will be checked
706	seperately). This is often faster than stat'ing the entry itself because	1113	separately). This is often faster than stat'ing the entry itself because
707	filesystems might detect the type of the entry without reading the inode	1114	filesystems might detect the type of the entry without reading the inode
708	data (e.g. ext2fs filetype feature).	1115	data (e.g. ext2fs filetype feature), even on systems that cannot return
		1116	the filetype information on readdir.
709		1117
710	If the known number of directories (link count - 2) has been reached, the	1118	If the known number of directories (link count - 2) has been reached, the
711	rest of the entries is assumed to be non-directories.	1119	rest of the entries is assumed to be non-directories.
712		1120
713	This only works with certainty on POSIX (= UNIX) filesystems, which	1121	This only works with certainty on POSIX (= UNIX) filesystems, which
…		…
726		1134
727	my $grp = aio_group $cb;	1135	my $grp = aio_group $cb;
728		1136
729	$maxreq = 4 if $maxreq <= 0;	1137	$maxreq = 4 if $maxreq <= 0;
730		1138
731	# stat once	1139	# get a wd object
732	aioreq_pri $pri;	1140	aioreq_pri $pri;
733	add $grp aio_stat $path, sub {	1141	add $grp aio_wd $path, sub {
		1142	$_[0]
734	return $grp->result () if $_[0];	1143	or return $grp->result ();
735	my $now = time;
736	my $hash1 = join ":", (stat _)[0,1,3,7,9];
737		1144
738	# read the directory entries	1145	my $wd = [shift, "."];
		1146
		1147	# stat once
739	aioreq_pri $pri;	1148	aioreq_pri $pri;
740	add $grp aio_readdir $path, sub {	1149	add $grp aio_stat $wd, sub {
741	my $entries = shift
742	or return $grp->result ();	1150	return $grp->result () if $_[0];
		1151	my $now = time;
		1152	my $hash1 = join ":", (stat _)[0,1,3,7,9];
743		1153
744	# stat the dir another time	1154	# read the directory entries
745	aioreq_pri $pri;	1155	aioreq_pri $pri;
		1156	add $grp aio_readdirx $wd, READDIR_DIRS_FIRST, sub {
		1157	my $entries = shift
		1158	or return $grp->result ();
		1159
		1160	# stat the dir another time
		1161	aioreq_pri $pri;
746	add $grp aio_stat $path, sub {	1162	add $grp aio_stat $wd, sub {
747	my $hash2 = join ":", (stat _)[0,1,3,7,9];	1163	my $hash2 = join ":", (stat _)[0,1,3,7,9];
748		1164
749	my $ndirs;	1165	my $ndirs;
750		1166
751	# take the slow route if anything looks fishy	1167	# take the slow route if anything looks fishy
752	if ($hash1 ne $hash2 or (stat _)[9] == $now) {	1168	if ($hash1 ne $hash2 or (stat _)[9] == $now) {
753	$ndirs = -1;	1169	$ndirs = -1;
754	} else {	1170	} else {
755	# if nlink == 2, we are finished	1171	# if nlink == 2, we are finished
756	# on non-posix-fs's, we rely on nlink < 2	1172	# for non-posix-fs's, we rely on nlink < 2
757	$ndirs = (stat _)[3] - 2	1173	$ndirs = (stat _)[3] - 2
758	or return $grp->result ([], $entries);	1174	or return $grp->result ([], $entries);
759	}	1175	}
760		1176
761	# sort into likely dirs and likely nondirs
762	# dirs == files without ".", short entries first
763	$entries = [map $_->[0],
764	sort { $b->[1] cmp $a->[1] }
765	map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],
766	@$entries];
767
768	my (@dirs, @nondirs);	1177	my (@dirs, @nondirs);
769		1178
770	my $statgrp = add $grp aio_group sub {	1179	my $statgrp = add $grp aio_group sub {
771	$grp->result (\@dirs, \@nondirs);	1180	$grp->result (\@dirs, \@nondirs);
772	};	1181	};
773		1182
774	limit $statgrp $maxreq;	1183	limit $statgrp $maxreq;
775	feed $statgrp sub {	1184	feed $statgrp sub {
776	return unless @$entries;	1185	return unless @$entries;
777	my $entry = pop @$entries;	1186	my $entry = shift @$entries;
778		1187
779	aioreq_pri $pri;	1188	aioreq_pri $pri;
		1189	$wd->[1] = "$entry/.";
780	add $statgrp aio_stat "$path/$entry/.", sub {	1190	add $statgrp aio_stat $wd, sub {
781	if ($_[0] < 0) {	1191	if ($_[0] < 0) {
782	push @nondirs, $entry;	1192	push @nondirs, $entry;
783	} else {	1193	} else {
784	# need to check for real directory	1194	# need to check for real directory
785	aioreq_pri $pri;	1195	aioreq_pri $pri;
		1196	$wd->[1] = $entry;
786	add $statgrp aio_lstat "$path/$entry", sub {	1197	add $statgrp aio_lstat $wd, sub {
787	if (-d _) {	1198	if (-d _) {
788	push @dirs, $entry;	1199	push @dirs, $entry;
789		1200
790	unless (--$ndirs) {	1201	unless (--$ndirs) {
791	push @nondirs, @$entries;	1202	push @nondirs, @$entries;
792	feed $statgrp;	1203	feed $statgrp;
		1204	}
		1205	} else {
		1206	push @nondirs, $entry;
793	}	1207	}
794	} else {
795	push @nondirs, $entry;
796	}	1208	}
797	}	1209	}
798	}	1210	};
799	};	1211	};
800	};	1212	};
801	};	1213	};
802	};	1214	};
803	};	1215	};
804		1216
805	$grp	1217	$grp
806	}	1218	}
807		1219
808	=item aio_rmtree $path, $callback->($status)	1220	=item aio_rmtree $pathname, $callback->($status)
809		1221
810	Delete a directory tree starting (and including) C<$path>, return the	1222	Delete a directory tree starting (and including) C<$path>, return the
811	status of the final C<rmdir> only. This is a composite request that	1223	status of the final C<rmdir> only. This is a composite request that
812	uses C<aio_scandir> to recurse into and rmdir directories, and unlink	1224	uses C<aio_scandir> to recurse into and rmdir directories, and unlink
813	everything else.	1225	everything else.
814		1226
815	=cut	1227	=cut
816		1228
…		…
838	};	1250	};
839		1251
840	$grp	1252	$grp
841	}	1253	}
842		1254
		1255	=item aio_fcntl $fh, $cmd, $arg, $callback->($status)
		1256
		1257	=item aio_ioctl $fh, $request, $buf, $callback->($status)
		1258
		1259	These work just like the C<fcntl> and C<ioctl> built-in functions, except
		1260	they execute asynchronously and pass the return value to the callback.
		1261
		1262	Both calls can be used for a lot of things, some of which make more sense
		1263	to run asynchronously in their own thread, while some others make less
		1264	sense. For example, calls that block waiting for external events, such
		1265	as locking, will also lock down an I/O thread while it is waiting, which
		1266	can deadlock the whole I/O system. At the same time, there might be no
		1267	alternative to using a thread to wait.
		1268
		1269	So in general, you should only use these calls for things that do
		1270	(filesystem) I/O, not for things that wait for other events (network,
		1271	other processes), although if you are careful and know what you are doing,
		1272	you still can.
		1273
		1274	The following constants are available (missing ones are, as usual C<0>):
		1275
		1276	C<FIFREEZE>, C<FITHAW>, C<FITRIM>, C<FICLONE>, C<FICLONERANGE>, C<FIDEDUPERANGE>.
		1277
		1278	C<FS_IOC_GETFLAGS>, C<FS_IOC_SETFLAGS>, C<FS_IOC_GETVERSION>, C<FS_IOC_SETVERSION>,
		1279	C<FS_IOC_FIEMAP>.
		1280
		1281	C<FS_IOC_FSGETXATTR>, C<FS_IOC_FSSETXATTR>, C<FS_IOC_SET_ENCRYPTION_POLICY>,
		1282	C<FS_IOC_GET_ENCRYPTION_PWSALT>, C<FS_IOC_GET_ENCRYPTION_POLICY>, C<FS_KEY_DESCRIPTOR_SIZE>.
		1283
		1284	C<FS_SECRM_FL>, C<FS_UNRM_FL>, C<FS_COMPR_FL>, C<FS_SYNC_FL>, C<FS_IMMUTABLE_FL>,
		1285	C<FS_APPEND_FL>, C<FS_NODUMP_FL>, C<FS_NOATIME_FL>, C<FS_DIRTY_FL>,
		1286	C<FS_COMPRBLK_FL>, C<FS_NOCOMP_FL>, C<FS_ENCRYPT_FL>, C<FS_BTREE_FL>,
		1287	C<FS_INDEX_FL>, C<FS_JOURNAL_DATA_FL>, C<FS_NOTAIL_FL>, C<FS_DIRSYNC_FL>, C<FS_TOPDIR_FL>,
		1288	C<FS_FL_USER_MODIFIABLE>.
		1289
		1290	C<FS_XFLAG_REALTIME>, C<FS_XFLAG_PREALLOC>, C<FS_XFLAG_IMMUTABLE>, C<FS_XFLAG_APPEND>,
		1291	C<FS_XFLAG_SYNC>, C<FS_XFLAG_NOATIME>, C<FS_XFLAG_NODUMP>, C<FS_XFLAG_RTINHERIT>,
		1292	C<FS_XFLAG_PROJINHERIT>, C<FS_XFLAG_NOSYMLINKS>, C<FS_XFLAG_EXTSIZE>, C<FS_XFLAG_EXTSZINHERIT>,
		1293	C<FS_XFLAG_NODEFRAG>, C<FS_XFLAG_FILESTREAM>, C<FS_XFLAG_DAX>, C<FS_XFLAG_HASATTR>,
		1294
843	=item aio_sync $callback->($status)	1295	=item aio_sync $callback->($status)
844		1296
845	Asynchronously call sync and call the callback when finished.	1297	Asynchronously call sync and call the callback when finished.
846		1298
847	=item aio_fsync $fh, $callback->($status)	1299	=item aio_fsync $fh, $callback->($status)
…		…
854	Asynchronously call fdatasync on the given filehandle and call the	1306	Asynchronously call fdatasync on the given filehandle and call the
855	callback with the fdatasync result code.	1307	callback with the fdatasync result code.
856		1308
857	If this call isn't available because your OS lacks it or it couldn't be	1309	If this call isn't available because your OS lacks it or it couldn't be
858	detected, it will be emulated by calling C<fsync> instead.	1310	detected, it will be emulated by calling C<fsync> instead.
		1311
		1312	=item aio_syncfs $fh, $callback->($status)
		1313
		1314	Asynchronously call the syncfs syscall to sync the filesystem associated
		1315	to the given filehandle and call the callback with the syncfs result
		1316	code. If syncfs is not available, calls sync(), but returns C<-1> and sets
		1317	errno to C<ENOSYS> nevertheless.
859		1318
860	=item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)	1319	=item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
861		1320
862	Sync the data portion of the file specified by C<$offset> and C<$length>	1321	Sync the data portion of the file specified by C<$offset> and C<$length>
863	to disk (but NOT the metadata), by calling the Linux-specific	1322	to disk (but NOT the metadata), by calling the Linux-specific
…		…
867	C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>,	1326	C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>,
868	C<IO::AIO::SYNC_FILE_RANGE_WRITE> and	1327	C<IO::AIO::SYNC_FILE_RANGE_WRITE> and
869	C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range	1328	C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range
870	manpage for details.	1329	manpage for details.
871		1330
872	=item aio_pathsync $path, $callback->($status)	1331	=item aio_pathsync $pathname, $callback->($status)
873		1332
874	This request tries to open, fsync and close the given path. This is a	1333	This request tries to open, fsync and close the given path. This is a
875	composite request intended to sync directories after directory operations	1334	composite request intended to sync directories after directory operations
876	(E.g. rename). This might not work on all operating systems or have any	1335	(E.g. rename). This might not work on all operating systems or have any
877	specific effect, but usually it makes sure that directory changes get	1336	specific effect, but usually it makes sure that directory changes get
878	written to disc. It works for anything that can be opened for read-only,	1337	written to disc. It works for anything that can be opened for read-only,
879	not just directories.	1338	not just directories.
		1339
		1340	Future versions of this function might fall back to other methods when
		1341	C<fsync> on the directory fails (such as calling C<sync>).
880		1342
881	Passes C<0> when everything went ok, and C<-1> on error.	1343	Passes C<0> when everything went ok, and C<-1> on error.
882		1344
883	=cut	1345	=cut
884		1346
…		…
905	};	1367	};
906		1368
907	$grp	1369	$grp
908	}	1370	}
909		1371
		1372	=item aio_msync $scalar, $offset = 0, $length = undef, flags = MS_SYNC, $callback->($status)
		1373
		1374	This is a rather advanced IO::AIO call, which only works on mmap(2)ed
		1375	scalars (see the C<IO::AIO::mmap> function, although it also works on data
		1376	scalars managed by the L<Sys::Mmap> or L<Mmap> modules, note that the
		1377	scalar must only be modified in-place while an aio operation is pending on
		1378	it).
		1379
		1380	It calls the C<msync> function of your OS, if available, with the memory
		1381	area starting at C<$offset> in the string and ending C<$length> bytes
		1382	later. If C<$length> is negative, counts from the end, and if C<$length>
		1383	is C<undef>, then it goes till the end of the string. The flags can be
		1384	either C<IO::AIO::MS_ASYNC> or C<IO::AIO::MS_SYNC>, plus an optional
		1385	C<IO::AIO::MS_INVALIDATE>.
		1386
		1387	=item aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		1388
		1389	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1390	scalars.
		1391
		1392	It touches (reads or writes) all memory pages in the specified
		1393	range inside the scalar. All caveats and parameters are the same
		1394	as for C<aio_msync>, above, except for flags, which must be either
		1395	C<0> (which reads all pages and ensures they are instantiated) or
		1396	C<IO::AIO::MT_MODIFY>, which modifies the memory pages (by reading and
		1397	writing an octet from it, which dirties the page).
		1398
		1399	=item aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
		1400
		1401	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1402	scalars.
		1403
		1404	It reads in all the pages of the underlying storage into memory (if any)
		1405	and locks them, so they are not getting swapped/paged out or removed.
		1406
		1407	If C<$length> is undefined, then the scalar will be locked till the end.
		1408
		1409	On systems that do not implement C<mlock>, this function returns C<-1>
		1410	and sets errno to C<ENOSYS>.
		1411
		1412	Note that the corresponding C<munlock> is synchronous and is
		1413	documented under L<MISCELLANEOUS FUNCTIONS>.
		1414
		1415	Example: open a file, mmap and mlock it - both will be undone when
		1416	C<$data> gets destroyed.
		1417
		1418	open my $fh, "<", $path or die "$path: $!";
		1419	my $data;
		1420	IO::AIO::mmap $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh;
		1421	aio_mlock $data; # mlock in background
		1422
		1423	=item aio_mlockall $flags, $callback->($status)
		1424
		1425	Calls the C<mlockall> function with the given C<$flags> (a combination of
		1426	C<IO::AIO::MCL_CURRENT> and C<IO::AIO::MCL_FUTURE>).
		1427
		1428	On systems that do not implement C<mlockall>, this function returns C<-1>
		1429	and sets errno to C<ENOSYS>.
		1430
		1431	Note that the corresponding C<munlockall> is synchronous and is
		1432	documented under L<MISCELLANEOUS FUNCTIONS>.
		1433
		1434	Example: asynchronously lock all current and future pages into memory.
		1435
		1436	aio_mlockall IO::AIO::MCL_FUTURE;
		1437
		1438	=item aio_fiemap $fh, $start, $length, $flags, $count, $cb->(\@extents)
		1439
		1440	Queries the extents of the given file (by calling the Linux C<FIEMAP>
		1441	ioctl, see L<http://cvs.schmorp.de/IO-AIO/doc/fiemap.txt> for details). If
		1442	the ioctl is not available on your OS, then this request will fail with
		1443	C<ENOSYS>.
		1444
		1445	C<$start> is the starting offset to query extents for, C<$length> is the
		1446	size of the range to query - if it is C<undef>, then the whole file will
		1447	be queried.
		1448
		1449	C<$flags> is a combination of flags (C<IO::AIO::FIEMAP_FLAG_SYNC> or
		1450	C<IO::AIO::FIEMAP_FLAG_XATTR> - C<IO::AIO::FIEMAP_FLAGS_COMPAT> is also
		1451	exported), and is normally C<0> or C<IO::AIO::FIEMAP_FLAG_SYNC> to query
		1452	the data portion.
		1453
		1454	C<$count> is the maximum number of extent records to return. If it is
		1455	C<undef>, then IO::AIO queries all extents of the range. As a very special
		1456	case, if it is C<0>, then the callback receives the number of extents
		1457	instead of the extents themselves (which is unreliable, see below).
		1458
		1459	If an error occurs, the callback receives no arguments. The special
		1460	C<errno> value C<IO::AIO::EBADR> is available to test for flag errors.
		1461
		1462	Otherwise, the callback receives an array reference with extent
		1463	structures. Each extent structure is an array reference itself, with the
		1464	following members:
		1465
		1466	[$logical, $physical, $length, $flags]
		1467
		1468	Flags is any combination of the following flag values (typically either C<0>
		1469	or C<IO::AIO::FIEMAP_EXTENT_LAST> (1)):
		1470
		1471	C<IO::AIO::FIEMAP_EXTENT_LAST>, C<IO::AIO::FIEMAP_EXTENT_UNKNOWN>,
		1472	C<IO::AIO::FIEMAP_EXTENT_DELALLOC>, C<IO::AIO::FIEMAP_EXTENT_ENCODED>,
		1473	C<IO::AIO::FIEMAP_EXTENT_DATA_ENCRYPTED>, C<IO::AIO::FIEMAP_EXTENT_NOT_ALIGNED>,
		1474	C<IO::AIO::FIEMAP_EXTENT_DATA_INLINE>, C<IO::AIO::FIEMAP_EXTENT_DATA_TAIL>,
		1475	C<IO::AIO::FIEMAP_EXTENT_UNWRITTEN>, C<IO::AIO::FIEMAP_EXTENT_MERGED> or
		1476	C<IO::AIO::FIEMAP_EXTENT_SHARED>.
		1477
		1478	At the time of this writing (Linux 3.2), this requets is unreliable unless
		1479	C<$count> is C<undef>, as the kernel has all sorts of bugs preventing
		1480	it to return all extents of a range for files with large number of
		1481	extents. The code works around all these issues if C<$count> is undef.
		1482
910	=item aio_group $callback->(...)	1483	=item aio_group $callback->(...)
911		1484
912	This is a very special aio request: Instead of doing something, it is a	1485	This is a very special aio request: Instead of doing something, it is a
913	container for other aio requests, which is useful if you want to bundle	1486	container for other aio requests, which is useful if you want to bundle
914	many requests into a single, composite, request with a definite callback	1487	many requests into a single, composite, request with a definite callback
…		…
951	immense (it blocks a thread for a long time) so do not use this function	1524	immense (it blocks a thread for a long time) so do not use this function
952	except to put your application under artificial I/O pressure.	1525	except to put your application under artificial I/O pressure.
953		1526
954	=back	1527	=back
955		1528
		1529
		1530	=head2 IO::AIO::WD - multiple working directories
		1531
		1532	Your process only has one current working directory, which is used by all
		1533	threads. This makes it hard to use relative paths (some other component
		1534	could call C<chdir> at any time, and it is hard to control when the path
		1535	will be used by IO::AIO).
		1536
		1537	One solution for this is to always use absolute paths. This usually works,
		1538	but can be quite slow (the kernel has to walk the whole path on every
		1539	access), and can also be a hassle to implement.
		1540
		1541	Newer POSIX systems have a number of functions (openat, fdopendir,
		1542	futimensat and so on) that make it possible to specify working directories
		1543	per operation.
		1544
		1545	For portability, and because the clowns who "designed", or shall I write,
		1546	perpetrated this new interface were obviously half-drunk, this abstraction
		1547	cannot be perfect, though.
		1548
		1549	IO::AIO allows you to convert directory paths into a so-called IO::AIO::WD
		1550	object. This object stores the canonicalised, absolute version of the
		1551	path, and on systems that allow it, also a directory file descriptor.
		1552
		1553	Everywhere where a pathname is accepted by IO::AIO (e.g. in C<aio_stat>
		1554	or C<aio_unlink>), one can specify an array reference with an IO::AIO::WD
		1555	object and a pathname instead (or the IO::AIO::WD object alone, which
		1556	gets interpreted as C<[$wd, "."]>). If the pathname is absolute, the
		1557	IO::AIO::WD object is ignored, otherwise the pathname is resolved relative
		1558	to that IO::AIO::WD object.
		1559
		1560	For example, to get a wd object for F</etc> and then stat F<passwd>
		1561	inside, you would write:
		1562
		1563	aio_wd "/etc", sub {
		1564	my $etcdir = shift;
		1565
		1566	# although $etcdir can be undef on error, there is generally no reason
		1567	# to check for errors here, as aio_stat will fail with ENOENT
		1568	# when $etcdir is undef.
		1569
		1570	aio_stat [$etcdir, "passwd"], sub {
		1571	# yay
		1572	};
		1573	};
		1574
		1575	The fact that C<aio_wd> is a request and not a normal function shows that
		1576	creating an IO::AIO::WD object is itself a potentially blocking operation,
		1577	which is why it is done asynchronously.
		1578
		1579	To stat the directory obtained with C<aio_wd> above, one could write
		1580	either of the following three request calls:
		1581
		1582	aio_lstat "/etc" , sub { ... # pathname as normal string
		1583	aio_lstat [$wd, "."], sub { ... # "." relative to $wd (i.e. $wd itself)
		1584	aio_lstat $wd , sub { ... # shorthand for the previous
		1585
		1586	As with normal pathnames, IO::AIO keeps a copy of the working directory
		1587	object and the pathname string, so you could write the following without
		1588	causing any issues due to C<$path> getting reused:
		1589
		1590	my $path = [$wd, undef];
		1591
		1592	for my $name (qw(abc def ghi)) {
		1593	$path->[1] = $name;
		1594	aio_stat $path, sub {
		1595	# ...
		1596	};
		1597	}
		1598
		1599	There are some caveats: when directories get renamed (or deleted), the
		1600	pathname string doesn't change, so will point to the new directory (or
		1601	nowhere at all), while the directory fd, if available on the system,
		1602	will still point to the original directory. Most functions accepting a
		1603	pathname will use the directory fd on newer systems, and the string on
		1604	older systems. Some functions (such as realpath) will always rely on the
		1605	string form of the pathname.
		1606
		1607	So this functionality is mainly useful to get some protection against
		1608	C<chdir>, to easily get an absolute path out of a relative path for future
		1609	reference, and to speed up doing many operations in the same directory
		1610	(e.g. when stat'ing all files in a directory).
		1611
		1612	The following functions implement this working directory abstraction:
		1613
		1614	=over 4
		1615
		1616	=item aio_wd $pathname, $callback->($wd)
		1617
		1618	Asynchonously canonicalise the given pathname and convert it to an
		1619	IO::AIO::WD object representing it. If possible and supported on the
		1620	system, also open a directory fd to speed up pathname resolution relative
		1621	to this working directory.
		1622
		1623	If something goes wrong, then C<undef> is passwd to the callback instead
		1624	of a working directory object and C<$!> is set appropriately. Since
		1625	passing C<undef> as working directory component of a pathname fails the
		1626	request with C<ENOENT>, there is often no need for error checking in the
		1627	C<aio_wd> callback, as future requests using the value will fail in the
		1628	expected way.
		1629
		1630	=item IO::AIO::CWD
		1631
		1632	This is a compiletime constant (object) that represents the process
		1633	current working directory.
		1634
		1635	Specifying this object as working directory object for a pathname is as if
		1636	the pathname would be specified directly, without a directory object. For
		1637	example, these calls are functionally identical:
		1638
		1639	aio_stat "somefile", sub { ... };
		1640	aio_stat [IO::AIO::CWD, "somefile"], sub { ... };
		1641
		1642	=back
		1643
		1644	To recover the path associated with an IO::AIO::WD object, you can use
		1645	C<aio_realpath>:
		1646
		1647	aio_realpath $wd, sub {
		1648	warn "path is $_[0]\n";
		1649	};
		1650
		1651	Currently, C<aio_statvfs> always, and C<aio_rename> and C<aio_rmdir>
		1652	sometimes, fall back to using an absolue path.
		1653
956	=head2 IO::AIO::REQ CLASS	1654	=head2 IO::AIO::REQ CLASS
957		1655
958	All non-aggregate C<aio_*> functions return an object of this class when	1656	All non-aggregate C<aio_*> functions return an object of this class when
959	called in non-void context.	1657	called in non-void context.
960		1658
…		…
963	=item cancel $req	1661	=item cancel $req
964		1662
965	Cancels the request, if possible. Has the effect of skipping execution	1663	Cancels the request, if possible. Has the effect of skipping execution
966	when entering the B<execute> state and skipping calling the callback when	1664	when entering the B<execute> state and skipping calling the callback when
967	entering the the B<result> state, but will leave the request otherwise	1665	entering the the B<result> state, but will leave the request otherwise
968	untouched. That means that requests that currently execute will not be	1666	untouched (with the exception of readdir). That means that requests that
969	stopped and resources held by the request will not be freed prematurely.	1667	currently execute will not be stopped and resources held by the request
		1668	will not be freed prematurely.
970		1669
971	=item cb $req $callback->(...)	1670	=item cb $req $callback->(...)
972		1671
973	Replace (or simply set) the callback registered to the request.	1672	Replace (or simply set) the callback registered to the request.
974		1673
…		…
1048	=item $grp->cancel_subs	1747	=item $grp->cancel_subs
1049		1748
1050	Cancel all subrequests and clears any feeder, but not the group request	1749	Cancel all subrequests and clears any feeder, but not the group request
1051	itself. Useful when you queued a lot of events but got a result early.	1750	itself. Useful when you queued a lot of events but got a result early.
1052		1751
		1752	The group request will finish normally (you cannot add requests to the
		1753	group).
		1754
1053	=item $grp->result (...)	1755	=item $grp->result (...)
1054		1756
1055	Set the result value(s) that will be passed to the group callback when all	1757	Set the result value(s) that will be passed to the group callback when all
1056	subrequests have finished and set the groups errno to the current value	1758	subrequests have finished and set the groups errno to the current value
1057	of errno (just like calling C<errno> without an error number). By default,	1759	of errno (just like calling C<errno> without an error number). By default,
…		…
1073		1775
1074	Sets a feeder/generator on this group: every group can have an attached	1776	Sets a feeder/generator on this group: every group can have an attached
1075	generator that generates requests if idle. The idea behind this is that,	1777	generator that generates requests if idle. The idea behind this is that,
1076	although you could just queue as many requests as you want in a group,	1778	although you could just queue as many requests as you want in a group,
1077	this might starve other requests for a potentially long time. For example,	1779	this might starve other requests for a potentially long time. For example,
1078	C<aio_scandir> might generate hundreds of thousands C<aio_stat> requests,	1780	C<aio_scandir> might generate hundreds of thousands of C<aio_stat>
1079	delaying any later requests for a long time.	1781	requests, delaying any later requests for a long time.
1080		1782
1081	To avoid this, and allow incremental generation of requests, you can	1783	To avoid this, and allow incremental generation of requests, you can
1082	instead a group and set a feeder on it that generates those requests. The	1784	instead a group and set a feeder on it that generates those requests. The
1083	feed callback will be called whenever there are few enough (see C<limit>,	1785	feed callback will be called whenever there are few enough (see C<limit>,
1084	below) requests active in the group itself and is expected to queue more	1786	below) requests active in the group itself and is expected to queue more
…		…
1125	=over 4	1827	=over 4
1126		1828
1127	=item $fileno = IO::AIO::poll_fileno	1829	=item $fileno = IO::AIO::poll_fileno
1128		1830
1129	Return the I<request result pipe file descriptor>. This filehandle must be	1831	Return the I<request result pipe file descriptor>. This filehandle must be
1130	polled for reading by some mechanism outside this module (e.g. Event or	1832	polled for reading by some mechanism outside this module (e.g. EV, Glib,
1131	select, see below or the SYNOPSIS). If the pipe becomes readable you have	1833	select and so on, see below or the SYNOPSIS). If the pipe becomes readable
1132	to call C<poll_cb> to check the results.	1834	you have to call C<poll_cb> to check the results.
1133		1835
1134	See C<poll_cb> for an example.	1836	See C<poll_cb> for an example.
1135		1837
1136	=item IO::AIO::poll_cb	1838	=item IO::AIO::poll_cb
1137		1839
1138	Process some outstanding events on the result pipe. You have to call this	1840	Process some requests that have reached the result phase (i.e. they have
1139	regularly. Returns C<0> if all events could be processed, or C<-1> if it	1841	been executed but the results are not yet reported). You have to call
1140	returned earlier for whatever reason. Returns immediately when no events	1842	this "regularly" to finish outstanding requests.
1141	are outstanding. The amount of events processed depends on the settings of
1142	C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>.
1143		1843
		1844	Returns C<0> if all events could be processed (or there were no
		1845	events to process), or C<-1> if it returned earlier for whatever
		1846	reason. Returns immediately when no events are outstanding. The amount
		1847	of events processed depends on the settings of C<IO::AIO::max_poll_req>,
		1848	C<IO::AIO::max_poll_time> and C<IO::AIO::max_outstanding>.
		1849
1144	If not all requests were processed for whatever reason, the filehandle	1850	If not all requests were processed for whatever reason, the poll file
1145	will still be ready when C<poll_cb> returns, so normally you don't have to	1851	descriptor will still be ready when C<poll_cb> returns, so normally you
1146	do anything special to have it called later.	1852	don't have to do anything special to have it called later.
		1853
		1854	Apart from calling C<IO::AIO::poll_cb> when the event filehandle becomes
		1855	ready, it can be beneficial to call this function from loops which submit
		1856	a lot of requests, to make sure the results get processed when they become
		1857	available and not just when the loop is finished and the event loop takes
		1858	over again. This function returns very fast when there are no outstanding
		1859	requests.
1147		1860
1148	Example: Install an Event watcher that automatically calls	1861	Example: Install an Event watcher that automatically calls
1149	IO::AIO::poll_cb with high priority:	1862	IO::AIO::poll_cb with high priority (more examples can be found in the
		1863	SYNOPSIS section, at the top of this document):
1150		1864
1151	Event->io (fd => IO::AIO::poll_fileno,	1865	Event->io (fd => IO::AIO::poll_fileno,
1152	poll => 'r', async => 1,	1866	poll => 'r', async => 1,
1153	cb => \&IO::AIO::poll_cb);	1867	cb => \&IO::AIO::poll_cb);
		1868
		1869	=item IO::AIO::poll_wait
		1870
		1871	Wait until either at least one request is in the result phase or no
		1872	requests are outstanding anymore.
		1873
		1874	This is useful if you want to synchronously wait for some requests to
		1875	become ready, without actually handling them.
		1876
		1877	See C<nreqs> for an example.
		1878
		1879	=item IO::AIO::poll
		1880
		1881	Waits until some requests have been handled.
		1882
		1883	Returns the number of requests processed, but is otherwise strictly
		1884	equivalent to:
		1885
		1886	IO::AIO::poll_wait, IO::AIO::poll_cb
		1887
		1888	=item IO::AIO::flush
		1889
		1890	Wait till all outstanding AIO requests have been handled.
		1891
		1892	Strictly equivalent to:
		1893
		1894	IO::AIO::poll_wait, IO::AIO::poll_cb
		1895	while IO::AIO::nreqs;
1154		1896
1155	=item IO::AIO::max_poll_reqs $nreqs	1897	=item IO::AIO::max_poll_reqs $nreqs
1156		1898
1157	=item IO::AIO::max_poll_time $seconds	1899	=item IO::AIO::max_poll_time $seconds
1158		1900
…		…
1183	# use a low priority so other tasks have priority	1925	# use a low priority so other tasks have priority
1184	Event->io (fd => IO::AIO::poll_fileno,	1926	Event->io (fd => IO::AIO::poll_fileno,
1185	poll => 'r', nice => 1,	1927	poll => 'r', nice => 1,
1186	cb => &IO::AIO::poll_cb);	1928	cb => &IO::AIO::poll_cb);
1187		1929
1188	=item IO::AIO::poll_wait
1189
1190	If there are any outstanding requests and none of them in the result
1191	phase, wait till the result filehandle becomes ready for reading (simply
1192	does a C<select> on the filehandle. This is useful if you want to
1193	synchronously wait for some requests to finish).
1194
1195	See C<nreqs> for an example.
1196
1197	=item IO::AIO::poll
1198
1199	Waits until some requests have been handled.
1200
1201	Returns the number of requests processed, but is otherwise strictly
1202	equivalent to:
1203
1204	IO::AIO::poll_wait, IO::AIO::poll_cb
1205
1206	=item IO::AIO::flush
1207
1208	Wait till all outstanding AIO requests have been handled.
1209
1210	Strictly equivalent to:
1211
1212	IO::AIO::poll_wait, IO::AIO::poll_cb
1213	while IO::AIO::nreqs;
1214
1215	=back	1930	=back
1216		1931
1217	=head3 CONTROLLING THE NUMBER OF THREADS	1932	=head3 CONTROLLING THE NUMBER OF THREADS
1218		1933
1219	=over	1934	=over
…		…
1252		1967
1253	Under normal circumstances you don't need to call this function.	1968	Under normal circumstances you don't need to call this function.
1254		1969
1255	=item IO::AIO::max_idle $nthreads	1970	=item IO::AIO::max_idle $nthreads
1256		1971
1257	Limit the number of threads (default: 4) that are allowed to idle (i.e.,	1972	Limit the number of threads (default: 4) that are allowed to idle
1258	threads that did not get a request to process within 10 seconds). That	1973	(i.e., threads that did not get a request to process within the idle
1259	means if a thread becomes idle while C<$nthreads> other threads are also	1974	timeout (default: 10 seconds). That means if a thread becomes idle while
1260	idle, it will free its resources and exit.	1975	C<$nthreads> other threads are also idle, it will free its resources and
		1976	exit.
1261		1977
1262	This is useful when you allow a large number of threads (e.g. 100 or 1000)	1978	This is useful when you allow a large number of threads (e.g. 100 or 1000)
1263	to allow for extremely high load situations, but want to free resources	1979	to allow for extremely high load situations, but want to free resources
1264	under normal circumstances (1000 threads can easily consume 30MB of RAM).	1980	under normal circumstances (1000 threads can easily consume 30MB of RAM).
1265		1981
1266	The default is probably ok in most situations, especially if thread	1982	The default is probably ok in most situations, especially if thread
1267	creation is fast. If thread creation is very slow on your system you might	1983	creation is fast. If thread creation is very slow on your system you might
1268	want to use larger values.	1984	want to use larger values.
1269		1985
		1986	=item IO::AIO::idle_timeout $seconds
		1987
		1988	Sets the minimum idle timeout (default 10) after which worker threads are
		1989	allowed to exit. SEe C<IO::AIO::max_idle>.
		1990
1270	=item IO::AIO::max_outstanding $maxreqs	1991	=item IO::AIO::max_outstanding $maxreqs
		1992
		1993	Sets the maximum number of outstanding requests to C<$nreqs>. If
		1994	you do queue up more than this number of requests, the next call to
		1995	C<IO::AIO::poll_cb> (and other functions calling C<poll_cb>, such as
		1996	C<IO::AIO::flush> or C<IO::AIO::poll>) will block until the limit is no
		1997	longer exceeded.
		1998
		1999	In other words, this setting does not enforce a queue limit, but can be
		2000	used to make poll functions block if the limit is exceeded.
1271		2001
1272	This is a very bad function to use in interactive programs because it	2002	This is a very bad function to use in interactive programs because it
1273	blocks, and a bad way to reduce concurrency because it is inexact: Better	2003	blocks, and a bad way to reduce concurrency because it is inexact: Better
1274	use an C<aio_group> together with a feed callback.	2004	use an C<aio_group> together with a feed callback.
1275		2005
1276	Sets the maximum number of outstanding requests to C<$nreqs>. If you	2006	Its main use is in scripts without an event loop - when you want to stat
1277	do queue up more than this number of requests, the next call to the	2007	a lot of files, you can write somehting like this:
1278	C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>)
1279	function will block until the limit is no longer exceeded.
1280		2008
1281	The default value is very large, so there is no practical limit on the	2009	IO::AIO::max_outstanding 32;
1282	number of outstanding requests.
1283		2010
1284	You can still queue as many requests as you want. Therefore,	2011	for my $path (...) {
1285	C<max_outstanding> is mainly useful in simple scripts (with low values) or	2012	aio_stat $path , ...;
1286	as a stop gap to shield against fatal memory overflow (with large values).	2013	IO::AIO::poll_cb;
		2014	}
		2015
		2016	IO::AIO::flush;
		2017
		2018	The call to C<poll_cb> inside the loop will normally return instantly, but
		2019	as soon as more thna C<32> reqeusts are in-flight, it will block until
		2020	some requests have been handled. This keeps the loop from pushing a large
		2021	number of C<aio_stat> requests onto the queue.
		2022
		2023	The default value for C<max_outstanding> is very large, so there is no
		2024	practical limit on the number of outstanding requests.
1287		2025
1288	=back	2026	=back
1289		2027
1290	=head3 STATISTICAL INFORMATION	2028	=head3 STATISTICAL INFORMATION
1291		2029
…		…
1311	Returns the number of requests currently in the pending state (executed,	2049	Returns the number of requests currently in the pending state (executed,
1312	but not yet processed by poll_cb).	2050	but not yet processed by poll_cb).
1313		2051
1314	=back	2052	=back
1315		2053
		2054	=head3 MISCELLANEOUS FUNCTIONS
		2055
		2056	IO::AIO implements some functions that are useful when you want to use
		2057	some "Advanced I/O" function not available to in Perl, without going the
		2058	"Asynchronous I/O" route. Many of these have an asynchronous C<aio_*>
		2059	counterpart.
		2060
		2061	=over 4
		2062
		2063	=item IO::AIO::sendfile $ofh, $ifh, $offset, $count
		2064
		2065	Calls the C<eio_sendfile_sync> function, which is like C<aio_sendfile>,
		2066	but is blocking (this makes most sense if you know the input data is
		2067	likely cached already and the output filehandle is set to non-blocking
		2068	operations).
		2069
		2070	Returns the number of bytes copied, or C<-1> on error.
		2071
		2072	=item IO::AIO::fadvise $fh, $offset, $len, $advice
		2073
		2074	Simply calls the C<posix_fadvise> function (see its
		2075	manpage for details). The following advice constants are
		2076	available: C<IO::AIO::FADV_NORMAL>, C<IO::AIO::FADV_SEQUENTIAL>,
		2077	C<IO::AIO::FADV_RANDOM>, C<IO::AIO::FADV_NOREUSE>,
		2078	C<IO::AIO::FADV_WILLNEED>, C<IO::AIO::FADV_DONTNEED>.
		2079
		2080	On systems that do not implement C<posix_fadvise>, this function returns
		2081	ENOSYS, otherwise the return value of C<posix_fadvise>.
		2082
		2083	=item IO::AIO::madvise $scalar, $offset, $len, $advice
		2084
		2085	Simply calls the C<posix_madvise> function (see its
		2086	manpage for details). The following advice constants are
		2087	available: C<IO::AIO::MADV_NORMAL>, C<IO::AIO::MADV_SEQUENTIAL>,
		2088	C<IO::AIO::MADV_RANDOM>, C<IO::AIO::MADV_WILLNEED>, C<IO::AIO::MADV_DONTNEED>,
		2089	C<IO::AIO::MADV_FREE>.
		2090
		2091	If C<$offset> is negative, counts from the end. If C<$length> is negative,
		2092	the remaining length of the C<$scalar> is used. If possible, C<$length>
		2093	will be reduced to fit into the C<$scalar>.
		2094
		2095	On systems that do not implement C<posix_madvise>, this function returns
		2096	ENOSYS, otherwise the return value of C<posix_madvise>.
		2097
		2098	=item IO::AIO::mprotect $scalar, $offset, $len, $protect
		2099
		2100	Simply calls the C<mprotect> function on the preferably AIO::mmap'ed
		2101	$scalar (see its manpage for details). The following protect
		2102	constants are available: C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_READ>,
		2103	C<IO::AIO::PROT_WRITE>, C<IO::AIO::PROT_EXEC>.
		2104
		2105	If C<$offset> is negative, counts from the end. If C<$length> is negative,
		2106	the remaining length of the C<$scalar> is used. If possible, C<$length>
		2107	will be reduced to fit into the C<$scalar>.
		2108
		2109	On systems that do not implement C<mprotect>, this function returns
		2110	ENOSYS, otherwise the return value of C<mprotect>.
		2111
		2112	=item IO::AIO::mmap $scalar, $length, $prot, $flags, $fh[, $offset]
		2113
		2114	Memory-maps a file (or anonymous memory range) and attaches it to the
		2115	given C<$scalar>, which will act like a string scalar. Returns true on
		2116	success, and false otherwise.
		2117
		2118	The scalar must exist, but its contents do not matter - this means you
		2119	cannot use a nonexistant array or hash element. When in doubt, C<undef>
		2120	the scalar first.
		2121
		2122	The only operations allowed on the mmapped scalar are C<substr>/C<vec>,
		2123	which don't change the string length, and most read-only operations such
		2124	as copying it or searching it with regexes and so on.
		2125
		2126	Anything else is unsafe and will, at best, result in memory leaks.
		2127
		2128	The memory map associated with the C<$scalar> is automatically removed
		2129	when the C<$scalar> is undef'd or destroyed, or when the C<IO::AIO::mmap>
		2130	or C<IO::AIO::munmap> functions are called on it.
		2131
		2132	This calls the C<mmap>(2) function internally. See your system's manual
		2133	page for details on the C<$length>, C<$prot> and C<$flags> parameters.
		2134
		2135	The C<$length> must be larger than zero and smaller than the actual
		2136	filesize.
		2137
		2138	C<$prot> is a combination of C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_EXEC>,
		2139	C<IO::AIO::PROT_READ> and/or C<IO::AIO::PROT_WRITE>,
		2140
		2141	C<$flags> can be a combination of
		2142	C<IO::AIO::MAP_SHARED> or
		2143	C<IO::AIO::MAP_PRIVATE>,
		2144	or a number of system-specific flags (when not available, the are C<0>):
		2145	C<IO::AIO::MAP_ANONYMOUS> (which is set to C<MAP_ANON> if your system only provides this constant),
		2146	C<IO::AIO::MAP_LOCKED>,
		2147	C<IO::AIO::MAP_NORESERVE>,
		2148	C<IO::AIO::MAP_POPULATE>,
		2149	C<IO::AIO::MAP_NONBLOCK>,
		2150	C<IO::AIO::MAP_FIXED>,
		2151	C<IO::AIO::MAP_GROWSDOWN>,
		2152	C<IO::AIO::MAP_32BIT>,
		2153	C<IO::AIO::MAP_HUGETLB> or
		2154	C<IO::AIO::MAP_STACK>.
		2155
		2156	If C<$fh> is C<undef>, then a file descriptor of C<-1> is passed.
		2157
		2158	C<$offset> is the offset from the start of the file - it generally must be
		2159	a multiple of C<IO::AIO::PAGESIZE> and defaults to C<0>.
		2160
		2161	Example:
		2162
		2163	use Digest::MD5;
		2164	use IO::AIO;
		2165
		2166	open my $fh, "<verybigfile"
		2167	or die "$!";
		2168
		2169	IO::AIO::mmap my $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh
		2170	or die "verybigfile: $!";
		2171
		2172	my $fast_md5 = md5 $data;
		2173
		2174	=item IO::AIO::munmap $scalar
		2175
		2176	Removes a previous mmap and undefines the C<$scalar>.
		2177
		2178	=item IO::AIO::munlock $scalar, $offset = 0, $length = undef
		2179
		2180	Calls the C<munlock> function, undoing the effects of a previous
		2181	C<aio_mlock> call (see its description for details).
		2182
		2183	=item IO::AIO::munlockall
		2184
		2185	Calls the C<munlockall> function.
		2186
		2187	On systems that do not implement C<munlockall>, this function returns
		2188	ENOSYS, otherwise the return value of C<munlockall>.
		2189
		2190	=item IO::AIO::splice $r_fh, $r_off, $w_fh, $w_off, $length, $flags
		2191
		2192	Calls the GNU/Linux C<splice(2)> syscall, if available. If C<$r_off> or
		2193	C<$w_off> are C<undef>, then C<NULL> is passed for these, otherwise they
		2194	should be the file offset.
		2195
		2196	C<$r_fh> and C<$w_fh> should not refer to the same file, as splice might
		2197	silently corrupt the data in this case.
		2198
		2199	The following symbol flag values are available: C<IO::AIO::SPLICE_F_MOVE>,
		2200	C<IO::AIO::SPLICE_F_NONBLOCK>, C<IO::AIO::SPLICE_F_MORE> and
		2201	C<IO::AIO::SPLICE_F_GIFT>.
		2202
		2203	See the C<splice(2)> manpage for details.
		2204
		2205	=item IO::AIO::tee $r_fh, $w_fh, $length, $flags
		2206
		2207	Calls the GNU/Linux C<tee(2)> syscall, see its manpage and the
		2208	description for C<IO::AIO::splice> above for details.
		2209
		2210	=item $actual_size = IO::AIO::pipesize $r_fh[, $new_size]
		2211
		2212	Attempts to query or change the pipe buffer size. Obviously works only
		2213	on pipes, and currently works only on GNU/Linux systems, and fails with
		2214	C<-1>/C<ENOSYS> everywhere else. If anybody knows how to influence pipe buffer
		2215	size on other systems, drop me a note.
		2216
		2217	=item ($rfh, $wfh) = IO::AIO::pipe2 [$flags]
		2218
		2219	This is a direct interface to the Linux L<pipe2(2)> system call. If
		2220	C<$flags> is missing or C<0>, then this should be the same as a call to
		2221	perl's built-in C<pipe> function and create a new pipe, and works on
		2222	systems that lack the pipe2 syscall. On win32, this case invokes C<_pipe
		2223	(..., 4096, O_BINARY)>.
		2224
		2225	If C<$flags> is non-zero, it tries to invoke the pipe2 system call with
		2226	the given flags (Linux 2.6.27, glibc 2.9).
		2227
		2228	On success, the read and write file handles are returned.
		2229
		2230	On error, nothing will be returned. If the pipe2 syscall is missing and
		2231	C<$flags> is non-zero, fails with C<ENOSYS>.
		2232
		2233	Please refer to L<pipe2(2)> for more info on the C<$flags>, but at the
		2234	time of this writing, C<IO::AIO::O_CLOEXEC>, C<IO::AIO::O_NONBLOCK> and
		2235	C<IO::AIO::O_DIRECT> (Linux 3.4, for packet-based pipes) were supported.
		2236
		2237	=back
		2238
1316	=cut	2239	=cut
1317		2240
1318	min_parallel 8;	2241	min_parallel 8;
1319		2242
1320	END { flush }	2243	END { flush }
1321		2244
1322	1;	2245	1;
1323		2246
		2247	=head1 EVENT LOOP INTEGRATION
		2248
		2249	It is recommended to use L<AnyEvent::AIO> to integrate IO::AIO
		2250	automatically into many event loops:
		2251
		2252	# AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...)
		2253	use AnyEvent::AIO;
		2254
		2255	You can also integrate IO::AIO manually into many event loops, here are
		2256	some examples of how to do this:
		2257
		2258	# EV integration
		2259	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
		2260
		2261	# Event integration
		2262	Event->io (fd => IO::AIO::poll_fileno,
		2263	poll => 'r',
		2264	cb => \&IO::AIO::poll_cb);
		2265
		2266	# Glib/Gtk2 integration
		2267	add_watch Glib::IO IO::AIO::poll_fileno,
		2268	in => sub { IO::AIO::poll_cb; 1 };
		2269
		2270	# Tk integration
		2271	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
		2272	readable => \&IO::AIO::poll_cb);
		2273
		2274	# Danga::Socket integration
		2275	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
		2276	\&IO::AIO::poll_cb);
		2277
1324	=head2 FORK BEHAVIOUR	2278	=head2 FORK BEHAVIOUR
1325		2279
1326	This module should do "the right thing" when the process using it forks:	2280	Usage of pthreads in a program changes the semantics of fork
		2281	considerably. Specifically, only async-safe functions can be called after
		2282	fork. Perl doesn't know about this, so in general, you cannot call fork
		2283	with defined behaviour in perl if pthreads are involved. IO::AIO uses
		2284	pthreads, so this applies, but many other extensions and (for inexplicable
		2285	reasons) perl itself often is linked against pthreads, so this limitation
		2286	applies to quite a lot of perls.
1327		2287
1328	Before the fork, IO::AIO enters a quiescent state where no requests	2288	This module no longer tries to fight your OS, or POSIX. That means IO::AIO
1329	can be added in other threads and no results will be processed. After	2289	only works in the process that loaded it. Forking is fully supported, but
1330	the fork the parent simply leaves the quiescent state and continues	2290	using IO::AIO in the child is not.
1331	request/result processing, while the child frees the request/result queue
1332	(so that the requests started before the fork will only be handled in the
1333	parent). Threads will be started on demand until the limit set in the
1334	parent process has been reached again.
1335		2291
1336	In short: the parent will, after a short pause, continue as if fork had	2292	You might get around by not I<using> IO::AIO before (or after)
1337	not been called, while the child will act as if IO::AIO has not been used	2293	forking. You could also try to call the L<IO::AIO::reinit> function in the
1338	yet.	2294	child:
		2295
		2296	=over 4
		2297
		2298	=item IO::AIO::reinit
		2299
		2300	Abandons all current requests and I/O threads and simply reinitialises all
		2301	data structures. This is not an operation supported by any standards, but
		2302	happens to work on GNU/Linux and some newer BSD systems.
		2303
		2304	The only reasonable use for this function is to call it after forking, if
		2305	C<IO::AIO> was used in the parent. Calling it while IO::AIO is active in
		2306	the process will result in undefined behaviour. Calling it at any time
		2307	will also result in any undefined (by POSIX) behaviour.
		2308
		2309	=back
1339		2310
1340	=head2 MEMORY USAGE	2311	=head2 MEMORY USAGE
1341		2312
1342	Per-request usage:	2313	Per-request usage:
1343		2314

Diff Legend

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