ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/IO-AIO/AIO.pm

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.107 by root, Fri Jun 1 05:52:59 2007 UTC vs.
Revision 1.281 by root, Tue Feb 20 04:32:59 2018 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
32	open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!";
33	my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb });
34
35	# Event integration
36	Event->io (fd => IO::AIO::poll_fileno,
37	poll => 'r',
38	cb => \&IO::AIO::poll_cb);
39
40	# Glib/Gtk2 integration
41	add_watch Glib::IO IO::AIO::poll_fileno,
42	in => sub { IO::AIO::poll_cb; 1 };
43
44	# Tk integration
45	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
46	readable => \&IO::AIO::poll_cb);
47
48	# Danga::Socket integration
49	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
50	\&IO::AIO::poll_cb);
51
52	=head1 DESCRIPTION	31	=head1 DESCRIPTION
53		32
54	This module implements asynchronous I/O using whatever means your	33	This module implements asynchronous I/O using whatever means your
55	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>).
56		36
57	Asynchronous means that operations that can normally block your program	37	Asynchronous means that operations that can normally block your program
58	(e.g. reading from disk) will be done asynchronously: the operation	38	(e.g. reading from disk) will be done asynchronously: the operation
59	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
60	is extremely useful for programs that need to stay interactive even	40	is extremely useful for programs that need to stay interactive even
…		…
62	etc.), but can also be used to easily do operations in parallel that are	42	etc.), but can also be used to easily do operations in parallel that are
63	normally done sequentially, e.g. stat'ing many files, which is much faster	43	normally done sequentially, e.g. stat'ing many files, which is much faster
64	on a RAID volume or over NFS when you do a number of stat operations	44	on a RAID volume or over NFS when you do a number of stat operations
65	concurrently.	45	concurrently.
66		46
67	While most of this works on all types of file descriptors (for example	47	While most of this works on all types of file descriptors (for
68	sockets), using these functions on file descriptors that support	48	example sockets), using these functions on file descriptors that
69	nonblocking operation (again, sockets, pipes etc.) is very inefficient or	49	support nonblocking operation (again, sockets, pipes etc.) is
70	might not work (aio_read fails on sockets/pipes/fifos). Use an event loop	50	very inefficient. Use an event loop for that (such as the L<EV>
71	for that (such as the L<Event|Event> module): IO::AIO will naturally fit	51	module): IO::AIO will naturally fit into such an event loop itself.
72	into such an event loop itself.
73		52
74	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
75	requests and signal their completion. You don't need thread support	54	requests and signal their completion. You don't need thread support
76	in perl, and the threads created by this module will not be visible	55	in perl, and the threads created by this module will not be visible
77	to perl. In the future, this module might make use of the native aio	56	to perl. In the future, this module might make use of the native aio
…		…
79	not well-supported or restricted (GNU/Linux doesn't allow them on normal	58	not well-supported or restricted (GNU/Linux doesn't allow them on normal
80	files currently, for example), and they would only support aio_read and	59	files currently, for example), and they would only support aio_read and
81	aio_write, so the remaining functionality would have to be implemented	60	aio_write, so the remaining functionality would have to be implemented
82	using threads anyway.	61	using threads anyway.
83		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
84	Although the module will work with in the presence of other (Perl-)	67	Although the module will work in the presence of other (Perl-) threads,
85	threads, it is currently not reentrant in any way, so use appropriate	68	it is currently not reentrant in any way, so use appropriate locking
86	locking yourself, always call C<poll_cb> from within the same thread, or	69	yourself, always call C<poll_cb> from within the same thread, or never
87	never call C<poll_cb> (or other C<aio_> functions) recursively.	70	call C<poll_cb> (or other C<aio_> functions) recursively.
88		71
89	=head2 EXAMPLE	72	=head2 EXAMPLE
90		73
91	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
92	F</etc/passwd> asynchronously:	75	F</etc/passwd> asynchronously:
93		76
94	use Fcntl;
95	use Event;	77	use EV;
96	use IO::AIO;	78	use IO::AIO;
97		79
98	# register the IO::AIO callback with Event	80	# register the IO::AIO callback with EV
99	Event->io (fd => IO::AIO::poll_fileno,	81	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
100	poll => 'r',
101	cb => \&IO::AIO::poll_cb);
102		82
103	# queue the request to open /etc/passwd	83	# queue the request to open /etc/passwd
104	aio_open "/etc/passwd", O_RDONLY, 0, sub {	84	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
105	my $fh = shift	85	my $fh = shift
106	or die "error while opening: $!";	86	or die "error while opening: $!";
107		87
108	# stat'ing filehandles is generally non-blocking	88	# stat'ing filehandles is generally non-blocking
109	my $size = -s $fh;	89	my $size = -s $fh;
…		…
118		98
119	# file contents now in $contents	99	# file contents now in $contents
120	print $contents;	100	print $contents;
121		101
122	# exit event loop and program	102	# exit event loop and program
123	Event::unloop;	103	EV::break;
124	};	104	};
125	};	105	};
126		106
127	# possibly queue up other requests, or open GUI windows,	107	# possibly queue up other requests, or open GUI windows,
128	# check for sockets etc. etc.	108	# check for sockets etc. etc.
129		109
130	# process events as long as there are some:	110	# process events as long as there are some:
131	Event::loop;	111	EV::run;
132		112
133	=head1 REQUEST ANATOMY AND LIFETIME	113	=head1 REQUEST ANATOMY AND LIFETIME
134		114
135	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
136	directly visible to Perl.	116	directly visible to Perl.
…		…
184		164
185	=cut	165	=cut
186		166
187	package IO::AIO;	167	package IO::AIO;
188		168
189	no warnings;	169	use Carp ();
190	use strict 'vars';	170
		171	use common::sense;
191		172
192	use base 'Exporter';	173	use base 'Exporter';
193		174
194	BEGIN {	175	BEGIN {
195	our $VERSION = '2.4';	176	our $VERSION = 4.4;
196		177
197	our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat	178	our @AIO_REQ = qw(aio_sendfile aio_seek aio_read aio_write aio_open aio_close
198	aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink	179	aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx
199	aio_readlink aio_fsync aio_fdatasync aio_readahead aio_rename aio_link	180	aio_scandir aio_symlink aio_readlink aio_realpath aio_fcntl aio_ioctl
		181	aio_sync aio_fsync aio_syncfs aio_fdatasync aio_sync_file_range
		182	aio_pathsync aio_readahead aio_fiemap aio_allocate
		183	aio_rename aio_rename2 aio_link aio_move aio_copy aio_group
200	aio_move aio_copy aio_group aio_nop aio_mknod aio_load aio_rmtree aio_mkdir	184	aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown
201	aio_chown aio_chmod aio_utime);	185	aio_chmod aio_utime aio_truncate
		186	aio_msync aio_mtouch aio_mlock aio_mlockall
		187	aio_statvfs
		188	aio_slurp
		189	aio_wd);
		190
202	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice aio_block));	191	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice));
203	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush	192	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush
204	min_parallel max_parallel max_idle	193	min_parallel max_parallel max_idle idle_timeout
205	nreqs nready npending nthreads	194	nreqs nready npending nthreads
206	max_poll_time max_poll_reqs);	195	max_poll_time max_poll_reqs
		196	sendfile fadvise madvise
		197	mmap munmap munlock munlockall);
		198
		199	push @AIO_REQ, qw(aio_busy); # not exported
207		200
208	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';	201	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';
209		202
210	require XSLoader;	203	require XSLoader;
211	XSLoader::load ("IO::AIO", $VERSION);	204	XSLoader::load ("IO::AIO", $VERSION);
212	}	205	}
213		206
214	=head1 FUNCTIONS	207	=head1 FUNCTIONS
215		208
216	=head2 AIO REQUEST FUNCTIONS	209	=head2 QUICK OVERVIEW
		210
		211	This section simply lists the prototypes most of the functions for
		212	quick reference. See the following sections for function-by-function
		213	documentation.
		214
		215	aio_wd $pathname, $callback->($wd)
		216	aio_open $pathname, $flags, $mode, $callback->($fh)
		217	aio_close $fh, $callback->($status)
		218	aio_seek $fh,$offset,$whence, $callback->($offs)
		219	aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
		220	aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
		221	aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
		222	aio_readahead $fh,$offset,$length, $callback->($retval)
		223	aio_stat $fh_or_path, $callback->($status)
		224	aio_lstat $fh, $callback->($status)
		225	aio_statvfs $fh_or_path, $callback->($statvfs)
		226	aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
		227	aio_chown $fh_or_path, $uid, $gid, $callback->($status)
		228	aio_chmod $fh_or_path, $mode, $callback->($status)
		229	aio_truncate $fh_or_path, $offset, $callback->($status)
		230	aio_allocate $fh, $mode, $offset, $len, $callback->($status)
		231	aio_fiemap $fh, $start, $length, $flags, $count, $cb->(\@extents)
		232	aio_unlink $pathname, $callback->($status)
		233	aio_mknod $pathname, $mode, $dev, $callback->($status)
		234	aio_link $srcpath, $dstpath, $callback->($status)
		235	aio_symlink $srcpath, $dstpath, $callback->($status)
		236	aio_readlink $pathname, $callback->($link)
		237	aio_realpath $pathname, $callback->($path)
		238	aio_rename $srcpath, $dstpath, $callback->($status)
		239	aio_rename2 $srcpath, $dstpath, $flags, $callback->($status)
		240	aio_mkdir $pathname, $mode, $callback->($status)
		241	aio_rmdir $pathname, $callback->($status)
		242	aio_readdir $pathname, $callback->($entries)
		243	aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		244	IO::AIO::READDIR_DENTS IO::AIO::READDIR_DIRS_FIRST
		245	IO::AIO::READDIR_STAT_ORDER IO::AIO::READDIR_FOUND_UNKNOWN
		246	aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs)
		247	aio_load $pathname, $data, $callback->($status)
		248	aio_copy $srcpath, $dstpath, $callback->($status)
		249	aio_move $srcpath, $dstpath, $callback->($status)
		250	aio_rmtree $pathname, $callback->($status)
		251	aio_fcntl $fh, $cmd, $arg, $callback->($status)
		252	aio_ioctl $fh, $request, $buf, $callback->($status)
		253	aio_sync $callback->($status)
		254	aio_syncfs $fh, $callback->($status)
		255	aio_fsync $fh, $callback->($status)
		256	aio_fdatasync $fh, $callback->($status)
		257	aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		258	aio_pathsync $pathname, $callback->($status)
		259	aio_msync $scalar, $offset = 0, $length = undef, flags = MS_SYNC, $callback->($status)
		260	aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		261	aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
		262	aio_mlockall $flags, $callback->($status)
		263	aio_group $callback->(...)
		264	aio_nop $callback->()
		265
		266	$prev_pri = aioreq_pri [$pri]
		267	aioreq_nice $pri_adjust
		268
		269	IO::AIO::poll_wait
		270	IO::AIO::poll_cb
		271	IO::AIO::poll
		272	IO::AIO::flush
		273	IO::AIO::max_poll_reqs $nreqs
		274	IO::AIO::max_poll_time $seconds
		275	IO::AIO::min_parallel $nthreads
		276	IO::AIO::max_parallel $nthreads
		277	IO::AIO::max_idle $nthreads
		278	IO::AIO::idle_timeout $seconds
		279	IO::AIO::max_outstanding $maxreqs
		280	IO::AIO::nreqs
		281	IO::AIO::nready
		282	IO::AIO::npending
		283	$nfd = IO::AIO::get_fdlimit [EXPERIMENTAL]
		284	IO::AIO::min_fdlimit $nfd [EXPERIMENTAL]
		285
		286	IO::AIO::sendfile $ofh, $ifh, $offset, $count
		287	IO::AIO::fadvise $fh, $offset, $len, $advice
		288	IO::AIO::mmap $scalar, $length, $prot, $flags[, $fh[, $offset]]
		289	IO::AIO::munmap $scalar
		290	IO::AIO::madvise $scalar, $offset, $length, $advice
		291	IO::AIO::mprotect $scalar, $offset, $length, $protect
		292	IO::AIO::munlock $scalar, $offset = 0, $length = undef
		293	IO::AIO::munlockall
		294
		295	=head2 API NOTES
217		296
218	All the C<aio_*> calls are more or less thin wrappers around the syscall	297	All the C<aio_*> calls are more or less thin wrappers around the syscall
219	with the same name (sans C<aio_>). The arguments are similar or identical,	298	with the same name (sans C<aio_>). The arguments are similar or identical,
220	and they all accept an additional (and optional) C<$callback> argument	299	and they all accept an additional (and optional) C<$callback> argument
221	which must be a code reference. This code reference will get called with	300	which must be a code reference. This code reference will be called after
222	the syscall return code (e.g. most syscalls return C<-1> on error, unlike	301	the syscall has been executed in an asynchronous fashion. The results
223	perl, which usually delivers "false") as it's sole argument when the given	302	of the request will be passed as arguments to the callback (and, if an
224	syscall has been executed asynchronously.	303	error occured, in C<$!>) - for most requests the syscall return code (e.g.
		304	most syscalls return C<-1> on error, unlike perl, which usually delivers
		305	"false").
		306
		307	Some requests (such as C<aio_readdir>) pass the actual results and
		308	communicate failures by passing C<undef>.
225		309
226	All functions expecting a filehandle keep a copy of the filehandle	310	All functions expecting a filehandle keep a copy of the filehandle
227	internally until the request has finished.	311	internally until the request has finished.
228		312
229	All functions return request objects of type L<IO::AIO::REQ> that allow	313	All functions return request objects of type L<IO::AIO::REQ> that allow
230	further manipulation of those requests while they are in-flight.	314	further manipulation of those requests while they are in-flight.
231		315
232	The pathnames you pass to these routines I<must> be absolute and	316	The pathnames you pass to these routines I<should> be absolute. The
233	encoded as octets. The reason for the former is that at the time the	317	reason for this is that at the time the request is being executed, the
234	request is being executed, the current working directory could have	318	current working directory could have changed. Alternatively, you can
235	changed. Alternatively, you can make sure that you never change the	319	make sure that you never change the current working directory anywhere
236	current working directory anywhere in the program and then use relative	320	in the program and then use relative paths. You can also take advantage
237	paths.	321	of IO::AIOs working directory abstraction, that lets you specify paths
		322	relative to some previously-opened "working directory object" - see the
		323	description of the C<IO::AIO::WD> class later in this document.
238		324
239	To encode pathnames as octets, either make sure you either: a) always pass	325	To encode pathnames as octets, either make sure you either: a) always pass
240	in filenames you got from outside (command line, readdir etc.) without	326	in filenames you got from outside (command line, readdir etc.) without
241	tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module and encode	327	tinkering, b) are in your native filesystem encoding, c) use the Encode
242	your pathnames to the locale (or other) encoding in effect in the user	328	module and encode your pathnames to the locale (or other) encoding in
243	environment, d) use Glib::filename_from_unicode on unicode filenames or e)	329	effect in the user environment, d) use Glib::filename_from_unicode on
244	use something else to ensure your scalar has the correct contents.	330	unicode filenames or e) use something else to ensure your scalar has the
		331	correct contents.
245		332
246	This works, btw. independent of the internal UTF-8 bit, which IO::AIO	333	This works, btw. independent of the internal UTF-8 bit, which IO::AIO
247	handles correctly wether it is set or not.	334	handles correctly whether it is set or not.
		335
		336	=head2 AIO REQUEST FUNCTIONS
248		337
249	=over 4	338	=over 4
250		339
251	=item $prev_pri = aioreq_pri [$pri]	340	=item $prev_pri = aioreq_pri [$pri]
252		341
…		…
282		371
283		372
284	=item aio_open $pathname, $flags, $mode, $callback->($fh)	373	=item aio_open $pathname, $flags, $mode, $callback->($fh)
285		374
286	Asynchronously open or create a file and call the callback with a newly	375	Asynchronously open or create a file and call the callback with a newly
287	created filehandle for the file.	376	created filehandle for the file (or C<undef> in case of an error).
288		377
289	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,	378	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,
290	for an explanation.	379	for an explanation.
291		380
292	The C<$flags> argument is a bitmask. See the C<Fcntl> module for a	381	The C<$flags> argument is a bitmask. See the C<Fcntl> module for a
…		…
299	by the umask in effect then the request is being executed, so better never	388	by the umask in effect then the request is being executed, so better never
300	change the umask.	389	change the umask.
301		390
302	Example:	391	Example:
303		392
304	aio_open "/etc/passwd", O_RDONLY, 0, sub {	393	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
305	if ($_[0]) {	394	if ($_[0]) {
306	print "open successful, fh is $_[0]\n";	395	print "open successful, fh is $_[0]\n";
307	...	396	...
308	} else {	397	} else {
309	die "open failed: $!\n";	398	die "open failed: $!\n";
310	}	399	}
311	};	400	};
312		401
		402	In addition to all the common open modes/flags (C<O_RDONLY>, C<O_WRONLY>,
		403	C<O_RDWR>, C<O_CREAT>, C<O_TRUNC>, C<O_EXCL> and C<O_APPEND>), the
		404	following POSIX and non-POSIX constants are available (missing ones on
		405	your system are, as usual, C<0>):
		406
		407	C<O_ASYNC>, C<O_DIRECT>, C<O_NOATIME>, C<O_CLOEXEC>, C<O_NOCTTY>, C<O_NOFOLLOW>,
		408	C<O_NONBLOCK>, C<O_EXEC>, C<O_SEARCH>, C<O_DIRECTORY>, C<O_DSYNC>,
		409	C<O_RSYNC>, C<O_SYNC>, C<O_PATH>, C<O_TMPFILE>, and C<O_TTY_INIT>.
		410
313		411
314	=item aio_close $fh, $callback->($status)	412	=item aio_close $fh, $callback->($status)
315		413
316	Asynchronously close a file and call the callback with the result	414	Asynchronously close a file and call the callback with the result
317	code. I<WARNING:> although accepted, you should not pass in a perl	415	code.
318	filehandle here, as perl will likely close the file descriptor another
319	time when the filehandle is destroyed. Normally, you can safely call perls
320	C<close> or just let filehandles go out of scope.
321		416
322	This is supposed to be a bug in the API, so that might change. It's	417	Unfortunately, you can't do this to perl. Perl I<insists> very strongly on
323	therefore best to avoid this function.	418	closing the file descriptor associated with the filehandle itself.
324		419
		420	Therefore, C<aio_close> will not close the filehandle - instead it will
		421	use dup2 to overwrite the file descriptor with the write-end of a pipe
		422	(the pipe fd will be created on demand and will be cached).
		423
		424	Or in other words: the file descriptor will be closed, but it will not be
		425	free for reuse until the perl filehandle is closed.
		426
		427	=cut
		428
		429	=item aio_seek $fh, $offset, $whence, $callback->($offs)
		430
		431	Seeks the filehandle to the new C<$offset>, similarly to perl's
		432	C<sysseek>. The C<$whence> can use the traditional values (C<0> for
		433	C<IO::AIO::SEEK_SET>, C<1> for C<IO::AIO::SEEK_CUR> or C<2> for
		434	C<IO::AIO::SEEK_END>).
		435
		436	The resulting absolute offset will be passed to the callback, or C<-1> in
		437	case of an error.
		438
		439	In theory, the C<$whence> constants could be different than the
		440	corresponding values from L<Fcntl>, but perl guarantees they are the same,
		441	so don't panic.
		442
		443	As a GNU/Linux (and maybe Solaris) extension, also the constants
		444	C<IO::AIO::SEEK_DATA> and C<IO::AIO::SEEK_HOLE> are available, if they
		445	could be found. No guarantees about suitability for use in C<aio_seek> or
		446	Perl's C<sysseek> can be made though, although I would naively assume they
		447	"just work".
325		448
326	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	449	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
327		450
328	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	451	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
329		452
330	Reads or writes C<length> bytes from the specified C<fh> and C<offset>	453	Reads or writes C<$length> bytes from or to the specified C<$fh> and
331	into the scalar given by C<data> and offset C<dataoffset> and calls the	454	C<$offset> into the scalar given by C<$data> and offset C<$dataoffset> and
332	callback without the actual number of bytes read (or -1 on error, just	455	calls the callback with the actual number of bytes transferred (or -1 on
333	like the syscall).	456	error, just like the syscall).
		457
		458	C<aio_read> will, like C<sysread>, shrink or grow the C<$data> scalar to
		459	offset plus the actual number of bytes read.
		460
		461	If C<$offset> is undefined, then the current file descriptor offset will
		462	be used (and updated), otherwise the file descriptor offset will not be
		463	changed by these calls.
		464
		465	If C<$length> is undefined in C<aio_write>, use the remaining length of
		466	C<$data>.
		467
		468	If C<$dataoffset> is less than zero, it will be counted from the end of
		469	C<$data>.
334		470
335	The C<$data> scalar I<MUST NOT> be modified in any way while the request	471	The C<$data> scalar I<MUST NOT> be modified in any way while the request
336	is outstanding. Modifying it can result in segfaults or WW3 (if the	472	is outstanding. Modifying it can result in segfaults or World War III (if
337	necessary/optional hardware is installed).	473	the necessary/optional hardware is installed).
338		474
339	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at	475	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at
340	offset C<0> within the scalar:	476	offset C<0> within the scalar:
341		477
342	aio_read $fh, 7, 15, $buffer, 0, sub {	478	aio_read $fh, 7, 15, $buffer, 0, sub {
…		…
349		485
350	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts	486	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
351	reading at byte offset C<$in_offset>, and starts writing at the current	487	reading at byte offset C<$in_offset>, and starts writing at the current
352	file offset of C<$out_fh>. Because of that, it is not safe to issue more	488	file offset of C<$out_fh>. Because of that, it is not safe to issue more
353	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each	489	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each
354	other.	490	other. The same C<$in_fh> works fine though, as this function does not
		491	move or use the file offset of C<$in_fh>.
355		492
		493	Please note that C<aio_sendfile> can read more bytes from C<$in_fh> than
		494	are written, and there is no way to find out how many more bytes have been
		495	read from C<aio_sendfile> alone, as C<aio_sendfile> only provides the
		496	number of bytes written to C<$out_fh>. Only if the result value equals
		497	C<$length> one can assume that C<$length> bytes have been read.
		498
		499	Unlike with other C<aio_> functions, it makes a lot of sense to use
		500	C<aio_sendfile> on non-blocking sockets, as long as one end (typically
		501	the C<$in_fh>) is a file - the file I/O will then be asynchronous, while
		502	the socket I/O will be non-blocking. Note, however, that you can run
		503	into a trap where C<aio_sendfile> reads some data with readahead, then
		504	fails to write all data, and when the socket is ready the next time, the
		505	data in the cache is already lost, forcing C<aio_sendfile> to again hit
		506	the disk. Explicit C<aio_read> + C<aio_write> let's you better control
		507	resource usage.
		508
356	This call tries to make use of a native C<sendfile> syscall to provide	509	This call tries to make use of a native C<sendfile>-like syscall to
357	zero-copy operation. For this to work, C<$out_fh> should refer to a	510	provide zero-copy operation. For this to work, C<$out_fh> should refer to
358	socket, and C<$in_fh> should refer to mmap'able file.	511	a socket, and C<$in_fh> should refer to an mmap'able file.
359		512
360	If the native sendfile call fails or is not implemented, it will be	513	If a native sendfile cannot be found or it fails with C<ENOSYS>,
361	emulated, so you can call C<aio_sendfile> on any type of filehandle	514	C<EINVAL>, C<ENOTSUP>, C<EOPNOTSUPP>, C<EAFNOSUPPORT>, C<EPROTOTYPE> or
		515	C<ENOTSOCK>, it will be emulated, so you can call C<aio_sendfile> on any
362	regardless of the limitations of the operating system.	516	type of filehandle regardless of the limitations of the operating system.
363		517
364	Please note, however, that C<aio_sendfile> can read more bytes from	518	As native sendfile syscalls (as practically any non-POSIX interface hacked
365	C<$in_fh> than are written, and there is no way to find out how many	519	together in a hurry to improve benchmark numbers) tend to be rather buggy
366	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only	520	on many systems, this implementation tries to work around some known bugs
367	provides the number of bytes written to C<$out_fh>. Only if the result	521	in Linux and FreeBSD kernels (probably others, too), but that might fail,
368	value equals C<$length> one can assume that C<$length> bytes have been	522	so you really really should check the return value of C<aio_sendfile> -
369	read.	523	fewer bytes than expected might have been transferred.
370		524
371		525
372	=item aio_readahead $fh,$offset,$length, $callback->($retval)	526	=item aio_readahead $fh,$offset,$length, $callback->($retval)
373		527
374	C<aio_readahead> populates the page cache with data from a file so that	528	C<aio_readahead> populates the page cache with data from a file so that
…		…
378	whole pages, so that offset is effectively rounded down to a page boundary	532	whole pages, so that offset is effectively rounded down to a page boundary
379	and bytes are read up to the next page boundary greater than or equal to	533	and bytes are read up to the next page boundary greater than or equal to
380	(off-set+length). C<aio_readahead> does not read beyond the end of the	534	(off-set+length). C<aio_readahead> does not read beyond the end of the
381	file. The current file offset of the file is left unchanged.	535	file. The current file offset of the file is left unchanged.
382		536
383	If that syscall doesn't exist (likely if your OS isn't Linux) it will be	537	If that syscall doesn't exist (likely if your kernel isn't Linux) it will
384	emulated by simply reading the data, which would have a similar effect.	538	be emulated by simply reading the data, which would have a similar effect.
385		539
386		540
387	=item aio_stat $fh_or_path, $callback->($status)	541	=item aio_stat $fh_or_path, $callback->($status)
388		542
389	=item aio_lstat $fh, $callback->($status)	543	=item aio_lstat $fh, $callback->($status)
…		…
396	for an explanation.	550	for an explanation.
397		551
398	Currently, the stats are always 64-bit-stats, i.e. instead of returning an	552	Currently, the stats are always 64-bit-stats, i.e. instead of returning an
399	error when stat'ing a large file, the results will be silently truncated	553	error when stat'ing a large file, the results will be silently truncated
400	unless perl itself is compiled with large file support.	554	unless perl itself is compiled with large file support.
		555
		556	To help interpret the mode and dev/rdev stat values, IO::AIO offers the
		557	following constants and functions (if not implemented, the constants will
		558	be C<0> and the functions will either C<croak> or fall back on traditional
		559	behaviour).
		560
		561	C<S_IFMT>, C<S_IFIFO>, C<S_IFCHR>, C<S_IFBLK>, C<S_IFLNK>, C<S_IFREG>,
		562	C<S_IFDIR>, C<S_IFWHT>, C<S_IFSOCK>, C<IO::AIO::major $dev_t>,
		563	C<IO::AIO::minor $dev_t>, C<IO::AIO::makedev $major, $minor>.
401		564
402	Example: Print the length of F</etc/passwd>:	565	Example: Print the length of F</etc/passwd>:
403		566
404	aio_stat "/etc/passwd", sub {	567	aio_stat "/etc/passwd", sub {
405	$_[0] and die "stat failed: $!";	568	$_[0] and die "stat failed: $!";
406	print "size is ", -s _, "\n";	569	print "size is ", -s _, "\n";
407	};	570	};
408		571
409		572
		573	=item aio_statvfs $fh_or_path, $callback->($statvfs)
		574
		575	Works like the POSIX C<statvfs> or C<fstatvfs> syscalls, depending on
		576	whether a file handle or path was passed.
		577
		578	On success, the callback is passed a hash reference with the following
		579	members: C<bsize>, C<frsize>, C<blocks>, C<bfree>, C<bavail>, C<files>,
		580	C<ffree>, C<favail>, C<fsid>, C<flag> and C<namemax>. On failure, C<undef>
		581	is passed.
		582
		583	The following POSIX IO::AIO::ST_* constants are defined: C<ST_RDONLY> and
		584	C<ST_NOSUID>.
		585
		586	The following non-POSIX IO::AIO::ST_* flag masks are defined to
		587	their correct value when available, or to C<0> on systems that do
		588	not support them: C<ST_NODEV>, C<ST_NOEXEC>, C<ST_SYNCHRONOUS>,
		589	C<ST_MANDLOCK>, C<ST_WRITE>, C<ST_APPEND>, C<ST_IMMUTABLE>, C<ST_NOATIME>,
		590	C<ST_NODIRATIME> and C<ST_RELATIME>.
		591
		592	Example: stat C</wd> and dump out the data if successful.
		593
		594	aio_statvfs "/wd", sub {
		595	my $f = $_[0]
		596	or die "statvfs: $!";
		597
		598	use Data::Dumper;
		599	say Dumper $f;
		600	};
		601
		602	# result:
		603	{
		604	bsize => 1024,
		605	bfree => 4333064312,
		606	blocks => 10253828096,
		607	files => 2050765568,
		608	flag => 4096,
		609	favail => 2042092649,
		610	bavail => 4333064312,
		611	ffree => 2042092649,
		612	namemax => 255,
		613	frsize => 1024,
		614	fsid => 1810
		615	}
		616
410	=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)	617	=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
411		618
412	Works like perl's C<utime> function (including the special case of $atime	619	Works like perl's C<utime> function (including the special case of $atime
413	and $mtime being undef). Fractional times are supported if the underlying	620	and $mtime being undef). Fractional times are supported if the underlying
414	syscalls support them.	621	syscalls support them.
…		…
436	aio_chown "path", 0, -1;	643	aio_chown "path", 0, -1;
437	# same as above:	644	# same as above:
438	aio_chown "path", 0, undef;	645	aio_chown "path", 0, undef;
439		646
440		647
		648	=item aio_truncate $fh_or_path, $offset, $callback->($status)
		649
		650	Works like truncate(2) or ftruncate(2).
		651
		652
		653	=item aio_allocate $fh, $mode, $offset, $len, $callback->($status)
		654
		655	Allocates or frees disk space according to the C<$mode> argument. See the
		656	linux C<fallocate> documentation for details.
		657
		658	C<$mode> is usually C<0> or C<IO::AIO::FALLOC_FL_KEEP_SIZE> to allocate
		659	space, or C<IO::AIO::FALLOC_FL_PUNCH_HOLE | IO::AIO::FALLOC_FL_KEEP_SIZE>,
		660	to deallocate a file range.
		661
		662	IO::AIO also supports C<FALLOC_FL_COLLAPSE_RANGE>, to remove a range
		663	(without leaving a hole), C<FALLOC_FL_ZERO_RANGE>, to zero a range,
		664	C<FALLOC_FL_INSERT_RANGE> to insert a range and C<FALLOC_FL_UNSHARE_RANGE>
		665	to unshare shared blocks (see your L<fallocate(2)> manpage).
		666
		667	The file system block size used by C<fallocate> is presumably the
		668	C<f_bsize> returned by C<statvfs>, but different filesystems and filetypes
		669	can dictate other limitations.
		670
		671	If C<fallocate> isn't available or cannot be emulated (currently no
		672	emulation will be attempted), passes C<-1> and sets C<$!> to C<ENOSYS>.
		673
		674
441	=item aio_chmod $fh_or_path, $mode, $callback->($status)	675	=item aio_chmod $fh_or_path, $mode, $callback->($status)
442		676
443	Works like perl's C<chmod> function.	677	Works like perl's C<chmod> function.
444		678
445		679
…		…
447		681
448	Asynchronously unlink (delete) a file and call the callback with the	682	Asynchronously unlink (delete) a file and call the callback with the
449	result code.	683	result code.
450		684
451		685
452	=item aio_mknod $path, $mode, $dev, $callback->($status)	686	=item aio_mknod $pathname, $mode, $dev, $callback->($status)
453		687
454	[EXPERIMENTAL]	688	[EXPERIMENTAL]
455		689
456	Asynchronously create a device node (or fifo). See mknod(2).	690	Asynchronously create a device node (or fifo). See mknod(2).
457		691
458	The only (POSIX-) portable way of calling this function is:	692	The only (POSIX-) portable way of calling this function is:
459		693
460	aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ...	694	aio_mknod $pathname, IO::AIO::S_IFIFO | $mode, 0, sub { ...
461		695
		696	See C<aio_stat> for info about some potentially helpful extra constants
		697	and functions.
462		698
463	=item aio_link $srcpath, $dstpath, $callback->($status)	699	=item aio_link $srcpath, $dstpath, $callback->($status)
464		700
465	Asynchronously create a new link to the existing object at C<$srcpath> at	701	Asynchronously create a new link to the existing object at C<$srcpath> at
466	the path C<$dstpath> and call the callback with the result code.	702	the path C<$dstpath> and call the callback with the result code.
…		…
470		706
471	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at	707	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at
472	the path C<$dstpath> and call the callback with the result code.	708	the path C<$dstpath> and call the callback with the result code.
473		709
474		710
475	=item aio_readlink $path, $callback->($link)	711	=item aio_readlink $pathname, $callback->($link)
476		712
477	Asynchronously read the symlink specified by C<$path> and pass it to	713	Asynchronously read the symlink specified by C<$path> and pass it to
478	the callback. If an error occurs, nothing or undef gets passed to the	714	the callback. If an error occurs, nothing or undef gets passed to the
479	callback.	715	callback.
480		716
481		717
		718	=item aio_realpath $pathname, $callback->($path)
		719
		720	Asynchronously make the path absolute and resolve any symlinks in
		721	C<$path>. The resulting path only consists of directories (same as
		722	L<Cwd::realpath>).
		723
		724	This request can be used to get the absolute path of the current working
		725	directory by passing it a path of F<.> (a single dot).
		726
		727
482	=item aio_rename $srcpath, $dstpath, $callback->($status)	728	=item aio_rename $srcpath, $dstpath, $callback->($status)
483		729
484	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as	730	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as
485	rename(2) and call the callback with the result code.	731	rename(2) and call the callback with the result code.
		732
		733	On systems that support the AIO::WD working directory abstraction
		734	natively, the case C<[$wd, "."]> as C<$srcpath> is specialcased - instead
		735	of failing, C<rename> is called on the absolute path of C<$wd>.
		736
		737
		738	=item aio_rename2 $srcpath, $dstpath, $flags, $callback->($status)
		739
		740	Basically a version of C<aio_rename> with an additional C<$flags>
		741	argument. Calling this with C<$flags=0> is the same as calling
		742	C<aio_rename>.
		743
		744	Non-zero flags are currently only supported on GNU/Linux systems that
		745	support renameat2. Other systems fail with C<ENOSYS> in this case.
		746
		747	The following constants are available (missing ones are, as usual C<0>),
		748	see renameat2(2) for details:
		749
		750	C<IO::AIO::RENAME_NOREPLACE>, C<IO::AIO::RENAME_EXCHANGE>
		751	and C<IO::AIO::RENAME_WHITEOUT>.
486		752
487		753
488	=item aio_mkdir $pathname, $mode, $callback->($status)	754	=item aio_mkdir $pathname, $mode, $callback->($status)
489		755
490	Asynchronously mkdir (create) a directory and call the callback with	756	Asynchronously mkdir (create) a directory and call the callback with
…		…
495	=item aio_rmdir $pathname, $callback->($status)	761	=item aio_rmdir $pathname, $callback->($status)
496		762
497	Asynchronously rmdir (delete) a directory and call the callback with the	763	Asynchronously rmdir (delete) a directory and call the callback with the
498	result code.	764	result code.
499		765
		766	On systems that support the AIO::WD working directory abstraction
		767	natively, the case C<[$wd, "."]> is specialcased - instead of failing,
		768	C<rmdir> is called on the absolute path of C<$wd>.
		769
500		770
501	=item aio_readdir $pathname, $callback->($entries)	771	=item aio_readdir $pathname, $callback->($entries)
502		772
503	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire	773	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
504	directory (i.e. opendir + readdir + closedir). The entries will not be	774	directory (i.e. opendir + readdir + closedir). The entries will not be
505	sorted, and will B<NOT> include the C<.> and C<..> entries.	775	sorted, and will B<NOT> include the C<.> and C<..> entries.
506		776
507	The callback a single argument which is either C<undef> or an array-ref	777	The callback is passed a single argument which is either C<undef> or an
508	with the filenames.	778	array-ref with the filenames.
509		779
510		780
		781	=item aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		782
		783	Quite similar to C<aio_readdir>, but the C<$flags> argument allows one to
		784	tune behaviour and output format. In case of an error, C<$entries> will be
		785	C<undef>.
		786
		787	The flags are a combination of the following constants, ORed together (the
		788	flags will also be passed to the callback, possibly modified):
		789
		790	=over 4
		791
		792	=item IO::AIO::READDIR_DENTS
		793
		794	When this flag is off, then the callback gets an arrayref consisting of
		795	names only (as with C<aio_readdir>), otherwise it gets an arrayref with
		796	C<[$name, $type, $inode]> arrayrefs, each describing a single directory
		797	entry in more detail.
		798
		799	C<$name> is the name of the entry.
		800
		801	C<$type> is one of the C<IO::AIO::DT_xxx> constants:
		802
		803	C<IO::AIO::DT_UNKNOWN>, C<IO::AIO::DT_FIFO>, C<IO::AIO::DT_CHR>, C<IO::AIO::DT_DIR>,
		804	C<IO::AIO::DT_BLK>, C<IO::AIO::DT_REG>, C<IO::AIO::DT_LNK>, C<IO::AIO::DT_SOCK>,
		805	C<IO::AIO::DT_WHT>.
		806
		807	C<IO::AIO::DT_UNKNOWN> means just that: readdir does not know. If you need to
		808	know, you have to run stat yourself. Also, for speed reasons, the C<$type>
		809	scalars are read-only: you can not modify them.
		810
		811	C<$inode> is the inode number (which might not be exact on systems with 64
		812	bit inode numbers and 32 bit perls). This field has unspecified content on
		813	systems that do not deliver the inode information.
		814
		815	=item IO::AIO::READDIR_DIRS_FIRST
		816
		817	When this flag is set, then the names will be returned in an order where
		818	likely directories come first, in optimal stat order. This is useful when
		819	you need to quickly find directories, or you want to find all directories
		820	while avoiding to stat() each entry.
		821
		822	If the system returns type information in readdir, then this is used
		823	to find directories directly. Otherwise, likely directories are names
		824	beginning with ".", or otherwise names with no dots, of which names with
		825	short names are tried first.
		826
		827	=item IO::AIO::READDIR_STAT_ORDER
		828
		829	When this flag is set, then the names will be returned in an order
		830	suitable for stat()'ing each one. That is, when you plan to stat()
		831	all files in the given directory, then the returned order will likely
		832	be fastest.
		833
		834	If both this flag and C<IO::AIO::READDIR_DIRS_FIRST> are specified, then
		835	the likely dirs come first, resulting in a less optimal stat order.
		836
		837	=item IO::AIO::READDIR_FOUND_UNKNOWN
		838
		839	This flag should not be set when calling C<aio_readdirx>. Instead, it
		840	is being set by C<aio_readdirx>, when any of the C<$type>'s found were
		841	C<IO::AIO::DT_UNKNOWN>. The absence of this flag therefore indicates that all
		842	C<$type>'s are known, which can be used to speed up some algorithms.
		843
		844	=back
		845
		846
		847	=item aio_slurp $pathname, $offset, $length, $data, $callback->($status)
		848
		849	Opens, reads and closes the given file. The data is put into C<$data>,
		850	which is resized as required.
		851
		852	If C<$offset> is negative, then it is counted from the end of the file.
		853
		854	If C<$length> is zero, then the remaining length of the file is
		855	used. Also, in this case, the same limitations to modifying C<$data> apply
		856	as when IO::AIO::mmap is used, i.e. it must only be modified in-place
		857	with C<substr>. If the size of the file is known, specifying a non-zero
		858	C<$length> results in a performance advantage.
		859
		860	This request is similar to the older C<aio_load> request, but since it is
		861	a single request, it might be more efficient to use.
		862
		863	Example: load F</etc/passwd> into C<$passwd>.
		864
		865	my $passwd;
		866	aio_slurp "/etc/passwd", 0, 0, $passwd, sub {
		867	$_[0] >= 0
		868	or die "/etc/passwd: $!\n";
		869
		870	printf "/etc/passwd is %d bytes long, and contains:\n", length $passwd;
		871	print $passwd;
		872	};
		873	IO::AIO::flush;
		874
		875
511	=item aio_load $path, $data, $callback->($status)	876	=item aio_load $pathname, $data, $callback->($status)
512		877
513	This is a composite request that tries to fully load the given file into	878	This is a composite request that tries to fully load the given file into
514	memory. Status is the same as with aio_read.	879	memory. Status is the same as with aio_read.
515		880
		881	Using C<aio_slurp> might be more efficient, as it is a single request.
		882
516	=cut	883	=cut
517		884
518	sub aio_load($$;$) {	885	sub aio_load($$;$) {
519	aio_block {
520	my ($path, undef, $cb) = @_;	886	my ($path, undef, $cb) = @_;
521	my $data = \$_[1];	887	my $data = \$_[1];
522		888
523	my $pri = aioreq_pri;	889	my $pri = aioreq_pri;
524	my $grp = aio_group $cb;	890	my $grp = aio_group $cb;
		891
		892	aioreq_pri $pri;
		893	add $grp aio_open $path, O_RDONLY, 0, sub {
		894	my $fh = shift
		895	or return $grp->result (-1);
525		896
526	aioreq_pri $pri;	897	aioreq_pri $pri;
527	add $grp aio_open $path, O_RDONLY, 0, sub {
528	my $fh = shift
529	or return $grp->result (-1);
530
531	aioreq_pri $pri;
532	add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub {	898	add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub {
533	$grp->result ($_[0]);	899	$grp->result ($_[0]);
534	};
535	};	900	};
536
537	$grp
538	}	901	};
		902
		903	$grp
539	}	904	}
540		905
541	=item aio_copy $srcpath, $dstpath, $callback->($status)	906	=item aio_copy $srcpath, $dstpath, $callback->($status)
542		907
543	Try to copy the I<file> (directories not supported as either source or	908	Try to copy the I<file> (directories not supported as either source or
544	destination) from C<$srcpath> to C<$dstpath> and call the callback with	909	destination) from C<$srcpath> to C<$dstpath> and call the callback with
545	the C<0> (error) or C<-1> ok.	910	a status of C<0> (ok) or C<-1> (error, see C<$!>).
546		911
		912	Existing destination files will be truncated.
		913
547	This is a composite request that it creates the destination file with	914	This is a composite request that creates the destination file with
548	mode 0200 and copies the contents of the source file into it using	915	mode 0200 and copies the contents of the source file into it using
549	C<aio_sendfile>, followed by restoring atime, mtime, access mode and	916	C<aio_sendfile>, followed by restoring atime, mtime, access mode and
550	uid/gid, in that order.	917	uid/gid, in that order.
551		918
552	If an error occurs, the partial destination file will be unlinked, if	919	If an error occurs, the partial destination file will be unlinked, if
…		…
554	errors are being ignored.	921	errors are being ignored.
555		922
556	=cut	923	=cut
557		924
558	sub aio_copy($$;$) {	925	sub aio_copy($$;$) {
559	aio_block {
560	my ($src, $dst, $cb) = @_;	926	my ($src, $dst, $cb) = @_;
561		927
562	my $pri = aioreq_pri;	928	my $pri = aioreq_pri;
563	my $grp = aio_group $cb;	929	my $grp = aio_group $cb;
564		930
565	aioreq_pri $pri;	931	aioreq_pri $pri;
566	add $grp aio_open $src, O_RDONLY, 0, sub {	932	add $grp aio_open $src, O_RDONLY, 0, sub {
567	if (my $src_fh = $_[0]) {	933	if (my $src_fh = $_[0]) {
568	my @stat = stat $src_fh;	934	my @stat = stat $src_fh; # hmm, might block over nfs?
569		935
570	aioreq_pri $pri;	936	aioreq_pri $pri;
571	add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {	937	add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {
572	if (my $dst_fh = $_[0]) {	938	if (my $dst_fh = $_[0]) {
573	aioreq_pri $pri;	939	aioreq_pri $pri;
574	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {	940	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
575	if ($_[0] == $stat[7]) {	941	if ($_[0] == $stat[7]) {
576	$grp->result (0);	942	$grp->result (0);
577	close $src_fh;	943	close $src_fh;
578		944
579	# those should not normally block. should. should.
580	utime $stat[8], $stat[9], $dst;
581	chmod $stat[2] & 07777, $dst_fh;
582	chown $stat[4], $stat[5], $dst_fh;
583	close $dst_fh;
584	} else {	945	my $ch = sub {
585	$grp->result (-1);
586	close $src_fh;
587	close $dst_fh;
588
589	aioreq $pri;	946	aioreq_pri $pri;
		947	add $grp aio_chmod $dst_fh, $stat[2] & 07777, sub {
		948	aioreq_pri $pri;
		949	add $grp aio_chown $dst_fh, $stat[4], $stat[5], sub {
		950	aioreq_pri $pri;
590	add $grp aio_unlink $dst;	951	add $grp aio_close $dst_fh;
		952	}
		953	};
591	}	954	};
		955
		956	aioreq_pri $pri;
		957	add $grp aio_utime $dst_fh, $stat[8], $stat[9], sub {
		958	if ($_[0] < 0 && $! == ENOSYS) {
		959	aioreq_pri $pri;
		960	add $grp aio_utime $dst, $stat[8], $stat[9], $ch;
		961	} else {
		962	$ch->();
		963	}
		964	};
		965	} else {
		966	$grp->result (-1);
		967	close $src_fh;
		968	close $dst_fh;
		969
		970	aioreq $pri;
		971	add $grp aio_unlink $dst;
592	};	972	}
593	} else {
594	$grp->result (-1);
595	}	973	};
		974	} else {
		975	$grp->result (-1);
596	},	976	}
597
598	} else {
599	$grp->result (-1);
600	}	977	},
		978
		979	} else {
		980	$grp->result (-1);
601	};	981	}
602
603	$grp
604	}	982	};
		983
		984	$grp
605	}	985	}
606		986
607	=item aio_move $srcpath, $dstpath, $callback->($status)	987	=item aio_move $srcpath, $dstpath, $callback->($status)
608		988
609	Try to move the I<file> (directories not supported as either source or	989	Try to move the I<file> (directories not supported as either source or
610	destination) from C<$srcpath> to C<$dstpath> and call the callback with	990	destination) from C<$srcpath> to C<$dstpath> and call the callback with
611	the C<0> (error) or C<-1> ok.	991	a status of C<0> (ok) or C<-1> (error, see C<$!>).
612		992
613	This is a composite request that tries to rename(2) the file first. If	993	This is a composite request that tries to rename(2) the file first; if
614	rename files with C<EXDEV>, it copies the file with C<aio_copy> and, if	994	rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if
615	that is successful, unlinking the C<$srcpath>.	995	that is successful, unlinks the C<$srcpath>.
616		996
617	=cut	997	=cut
618		998
619	sub aio_move($$;$) {	999	sub aio_move($$;$) {
620	aio_block {
621	my ($src, $dst, $cb) = @_;	1000	my ($src, $dst, $cb) = @_;
622		1001
623	my $pri = aioreq_pri;	1002	my $pri = aioreq_pri;
624	my $grp = aio_group $cb;	1003	my $grp = aio_group $cb;
625		1004
626	aioreq_pri $pri;	1005	aioreq_pri $pri;
627	add $grp aio_rename $src, $dst, sub {	1006	add $grp aio_rename $src, $dst, sub {
628	if ($_[0] && $! == EXDEV) {	1007	if ($_[0] && $! == EXDEV) {
629	aioreq_pri $pri;	1008	aioreq_pri $pri;
630	add $grp aio_copy $src, $dst, sub {	1009	add $grp aio_copy $src, $dst, sub {
631	$grp->result ($_[0]);
632
633	if (!$_[0]) {
634	aioreq_pri $pri;
635	add $grp aio_unlink $src;
636	}
637	};
638	} else {
639	$grp->result ($_[0]);	1010	$grp->result ($_[0]);
		1011
		1012	unless ($_[0]) {
		1013	aioreq_pri $pri;
		1014	add $grp aio_unlink $src;
		1015	}
640	}	1016	};
		1017	} else {
		1018	$grp->result ($_[0]);
641	};	1019	}
642
643	$grp
644	}	1020	};
		1021
		1022	$grp
645	}	1023	}
646		1024
647	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)	1025	=item aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs)
648		1026
649	Scans a directory (similar to C<aio_readdir>) but additionally tries to	1027	Scans a directory (similar to C<aio_readdir>) but additionally tries to
650	efficiently separate the entries of directory C<$path> into two sets of	1028	efficiently separate the entries of directory C<$path> into two sets of
651	names, directories you can recurse into (directories), and ones you cannot	1029	names, directories you can recurse into (directories), and ones you cannot
652	recurse into (everything else, including symlinks to directories).	1030	recurse into (everything else, including symlinks to directories).
653		1031
654	C<aio_scandir> is a composite request that creates of many sub requests_	1032	C<aio_scandir> is a composite request that generates many sub requests.
655	C<$maxreq> specifies the maximum number of outstanding aio requests that	1033	C<$maxreq> specifies the maximum number of outstanding aio requests that
656	this function generates. If it is C<< <= 0 >>, then a suitable default	1034	this function generates. If it is C<< <= 0 >>, then a suitable default
657	will be chosen (currently 4).	1035	will be chosen (currently 4).
658		1036
659	On error, the callback is called without arguments, otherwise it receives	1037	On error, the callback is called without arguments, otherwise it receives
…		…
669		1047
670	Implementation notes.	1048	Implementation notes.
671		1049
672	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.	1050	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.
673		1051
		1052	If readdir returns file type information, then this is used directly to
		1053	find directories.
		1054
674	After reading the directory, the modification time, size etc. of the	1055	Otherwise, after reading the directory, the modification time, size etc.
675	directory before and after the readdir is checked, and if they match (and	1056	of the directory before and after the readdir is checked, and if they
676	isn't the current time), the link count will be used to decide how many	1057	match (and isn't the current time), the link count will be used to decide
677	entries are directories (if >= 2). Otherwise, no knowledge of the number	1058	how many entries are directories (if >= 2). Otherwise, no knowledge of the
678	of subdirectories will be assumed.	1059	number of subdirectories will be assumed.
679		1060
680	Then entries will be sorted into likely directories (everything without	1061	Then entries will be sorted into likely directories a non-initial dot
681	a non-initial dot currently) and likely non-directories (everything	1062	currently) and likely non-directories (see C<aio_readdirx>). Then every
682	else). Then every entry plus an appended C</.> will be C<stat>'ed,	1063	entry plus an appended C</.> will be C<stat>'ed, likely directories first,
683	likely directories first. If that succeeds, it assumes that the entry	1064	in order of their inode numbers. If that succeeds, it assumes that the
684	is a directory or a symlink to directory (which will be checked	1065	entry is a directory or a symlink to directory (which will be checked
685	seperately). This is often faster than stat'ing the entry itself because	1066	separately). This is often faster than stat'ing the entry itself because
686	filesystems might detect the type of the entry without reading the inode	1067	filesystems might detect the type of the entry without reading the inode
687	data (e.g. ext2fs filetype feature).	1068	data (e.g. ext2fs filetype feature), even on systems that cannot return
		1069	the filetype information on readdir.
688		1070
689	If the known number of directories (link count - 2) has been reached, the	1071	If the known number of directories (link count - 2) has been reached, the
690	rest of the entries is assumed to be non-directories.	1072	rest of the entries is assumed to be non-directories.
691		1073
692	This only works with certainty on POSIX (= UNIX) filesystems, which	1074	This only works with certainty on POSIX (= UNIX) filesystems, which
…		…
697	directory counting heuristic.	1079	directory counting heuristic.
698		1080
699	=cut	1081	=cut
700		1082
701	sub aio_scandir($$;$) {	1083	sub aio_scandir($$;$) {
702	aio_block {
703	my ($path, $maxreq, $cb) = @_;	1084	my ($path, $maxreq, $cb) = @_;
704		1085
705	my $pri = aioreq_pri;	1086	my $pri = aioreq_pri;
706		1087
707	my $grp = aio_group $cb;	1088	my $grp = aio_group $cb;
708		1089
709	$maxreq = 4 if $maxreq <= 0;	1090	$maxreq = 4 if $maxreq <= 0;
		1091
		1092	# get a wd object
		1093	aioreq_pri $pri;
		1094	add $grp aio_wd $path, sub {
		1095	$_[0]
		1096	or return $grp->result ();
		1097
		1098	my $wd = [shift, "."];
710		1099
711	# stat once	1100	# stat once
712	aioreq_pri $pri;	1101	aioreq_pri $pri;
713	add $grp aio_stat $path, sub {	1102	add $grp aio_stat $wd, sub {
714	return $grp->result () if $_[0];	1103	return $grp->result () if $_[0];
715	my $now = time;	1104	my $now = time;
716	my $hash1 = join ":", (stat _)[0,1,3,7,9];	1105	my $hash1 = join ":", (stat _)[0,1,3,7,9];
717		1106
718	# read the directory entries	1107	# read the directory entries
719	aioreq_pri $pri;	1108	aioreq_pri $pri;
720	add $grp aio_readdir $path, sub {	1109	add $grp aio_readdirx $wd, READDIR_DIRS_FIRST, sub {
721	my $entries = shift	1110	my $entries = shift
722	or return $grp->result ();	1111	or return $grp->result ();
723		1112
724	# stat the dir another time	1113	# stat the dir another time
725	aioreq_pri $pri;	1114	aioreq_pri $pri;
726	add $grp aio_stat $path, sub {	1115	add $grp aio_stat $wd, sub {
727	my $hash2 = join ":", (stat _)[0,1,3,7,9];	1116	my $hash2 = join ":", (stat _)[0,1,3,7,9];
728		1117
729	my $ndirs;	1118	my $ndirs;
730		1119
731	# take the slow route if anything looks fishy	1120	# take the slow route if anything looks fishy
732	if ($hash1 ne $hash2 or (stat _)[9] == $now) {	1121	if ($hash1 ne $hash2 or (stat _)[9] == $now) {
733	$ndirs = -1;	1122	$ndirs = -1;
734	} else {	1123	} else {
735	# if nlink == 2, we are finished	1124	# if nlink == 2, we are finished
736	# on non-posix-fs's, we rely on nlink < 2	1125	# for non-posix-fs's, we rely on nlink < 2
737	$ndirs = (stat _)[3] - 2	1126	$ndirs = (stat _)[3] - 2
738	or return $grp->result ([], $entries);	1127	or return $grp->result ([], $entries);
739	}	1128	}
740		1129
741	# sort into likely dirs and likely nondirs
742	# dirs == files without ".", short entries first
743	$entries = [map $_->[0],
744	sort { $b->[1] cmp $a->[1] }
745	map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],
746	@$entries];
747
748	my (@dirs, @nondirs);	1130	my (@dirs, @nondirs);
749		1131
750	my $statgrp = add $grp aio_group sub {	1132	my $statgrp = add $grp aio_group sub {
751	$grp->result (\@dirs, \@nondirs);	1133	$grp->result (\@dirs, \@nondirs);
752	};	1134	};
753		1135
754	limit $statgrp $maxreq;	1136	limit $statgrp $maxreq;
755	feed $statgrp sub {	1137	feed $statgrp sub {
756	return unless @$entries;	1138	return unless @$entries;
757	my $entry = pop @$entries;	1139	my $entry = shift @$entries;
758		1140
759	aioreq_pri $pri;	1141	aioreq_pri $pri;
		1142	$wd->[1] = "$entry/.";
760	add $statgrp aio_stat "$path/$entry/.", sub {	1143	add $statgrp aio_stat $wd, sub {
761	if ($_[0] < 0) {	1144	if ($_[0] < 0) {
762	push @nondirs, $entry;	1145	push @nondirs, $entry;
763	} else {	1146	} else {
764	# need to check for real directory	1147	# need to check for real directory
765	aioreq_pri $pri;	1148	aioreq_pri $pri;
		1149	$wd->[1] = $entry;
766	add $statgrp aio_lstat "$path/$entry", sub {	1150	add $statgrp aio_lstat $wd, sub {
767	if (-d _) {	1151	if (-d _) {
768	push @dirs, $entry;	1152	push @dirs, $entry;
769		1153
770	unless (--$ndirs) {	1154	unless (--$ndirs) {
771	push @nondirs, @$entries;	1155	push @nondirs, @$entries;
…		…
779	};	1163	};
780	};	1164	};
781	};	1165	};
782	};	1166	};
783	};	1167	};
784
785	$grp
786	}	1168	};
		1169
		1170	$grp
787	}	1171	}
788		1172
789	=item aio_rmtree $path, $callback->($status)	1173	=item aio_rmtree $pathname, $callback->($status)
790		1174
791	Delete a directory tree starting (and including) C<$path>, return the	1175	Delete a directory tree starting (and including) C<$path>, return the
792	status of the final C<rmdir> only. This is a composite request that	1176	status of the final C<rmdir> only. This is a composite request that
793	uses C<aio_scandir> to recurse into and rmdir directories, and unlink	1177	uses C<aio_scandir> to recurse into and rmdir directories, and unlink
794	everything else.	1178	everything else.
795		1179
796	=cut	1180	=cut
797		1181
798	sub aio_rmtree;	1182	sub aio_rmtree;
799	sub aio_rmtree($;$) {	1183	sub aio_rmtree($;$) {
800	aio_block {
801	my ($path, $cb) = @_;	1184	my ($path, $cb) = @_;
802		1185
803	my $pri = aioreq_pri;	1186	my $pri = aioreq_pri;
804	my $grp = aio_group $cb;	1187	my $grp = aio_group $cb;
805		1188
806	aioreq_pri $pri;	1189	aioreq_pri $pri;
807	add $grp aio_scandir $path, 0, sub {	1190	add $grp aio_scandir $path, 0, sub {
808	my ($dirs, $nondirs) = @_;	1191	my ($dirs, $nondirs) = @_;
809		1192
810	my $dirgrp = aio_group sub {	1193	my $dirgrp = aio_group sub {
811	add $grp aio_rmdir $path, sub {	1194	add $grp aio_rmdir $path, sub {
812	$grp->result ($_[0]);	1195	$grp->result ($_[0]);
813	};
814	};	1196	};
815
816	(aioreq_pri $pri), add $dirgrp aio_rmtree "$path/$_" for @$dirs;
817	(aioreq_pri $pri), add $dirgrp aio_unlink "$path/$_" for @$nondirs;
818
819	add $grp $dirgrp;
820	};	1197	};
821		1198
822	$grp	1199	(aioreq_pri $pri), add $dirgrp aio_rmtree "$path/$_" for @$dirs;
		1200	(aioreq_pri $pri), add $dirgrp aio_unlink "$path/$_" for @$nondirs;
		1201
		1202	add $grp $dirgrp;
823	}	1203	};
		1204
		1205	$grp
824	}	1206	}
		1207
		1208	=item aio_fcntl $fh, $cmd, $arg, $callback->($status)
		1209
		1210	=item aio_ioctl $fh, $request, $buf, $callback->($status)
		1211
		1212	These work just like the C<fcntl> and C<ioctl> built-in functions, except
		1213	they execute asynchronously and pass the return value to the callback.
		1214
		1215	Both calls can be used for a lot of things, some of which make more sense
		1216	to run asynchronously in their own thread, while some others make less
		1217	sense. For example, calls that block waiting for external events, such
		1218	as locking, will also lock down an I/O thread while it is waiting, which
		1219	can deadlock the whole I/O system. At the same time, there might be no
		1220	alternative to using a thread to wait.
		1221
		1222	So in general, you should only use these calls for things that do
		1223	(filesystem) I/O, not for things that wait for other events (network,
		1224	other processes), although if you are careful and know what you are doing,
		1225	you still can.
		1226
		1227	The following constants are available (missing ones are, as usual C<0>):
		1228
		1229	C<F_DUPFD_CLOEXEC>,
		1230
		1231	C<F_OFD_GETLK>, C<F_OFD_SETLK>, C<F_OFD_GETLKW>,
		1232
		1233	C<FIFREEZE>, C<FITHAW>, C<FITRIM>, C<FICLONE>, C<FICLONERANGE>, C<FIDEDUPERANGE>.
		1234
		1235	C<FS_IOC_GETFLAGS>, C<FS_IOC_SETFLAGS>, C<FS_IOC_GETVERSION>, C<FS_IOC_SETVERSION>,
		1236	C<FS_IOC_FIEMAP>.
		1237
		1238	C<FS_IOC_FSGETXATTR>, C<FS_IOC_FSSETXATTR>, C<FS_IOC_SET_ENCRYPTION_POLICY>,
		1239	C<FS_IOC_GET_ENCRYPTION_PWSALT>, C<FS_IOC_GET_ENCRYPTION_POLICY>, C<FS_KEY_DESCRIPTOR_SIZE>.
		1240
		1241	C<FS_SECRM_FL>, C<FS_UNRM_FL>, C<FS_COMPR_FL>, C<FS_SYNC_FL>, C<FS_IMMUTABLE_FL>,
		1242	C<FS_APPEND_FL>, C<FS_NODUMP_FL>, C<FS_NOATIME_FL>, C<FS_DIRTY_FL>,
		1243	C<FS_COMPRBLK_FL>, C<FS_NOCOMP_FL>, C<FS_ENCRYPT_FL>, C<FS_BTREE_FL>,
		1244	C<FS_INDEX_FL>, C<FS_JOURNAL_DATA_FL>, C<FS_NOTAIL_FL>, C<FS_DIRSYNC_FL>, C<FS_TOPDIR_FL>,
		1245	C<FS_FL_USER_MODIFIABLE>.
		1246
		1247	C<FS_XFLAG_REALTIME>, C<FS_XFLAG_PREALLOC>, C<FS_XFLAG_IMMUTABLE>, C<FS_XFLAG_APPEND>,
		1248	C<FS_XFLAG_SYNC>, C<FS_XFLAG_NOATIME>, C<FS_XFLAG_NODUMP>, C<FS_XFLAG_RTINHERIT>,
		1249	C<FS_XFLAG_PROJINHERIT>, C<FS_XFLAG_NOSYMLINKS>, C<FS_XFLAG_EXTSIZE>, C<FS_XFLAG_EXTSZINHERIT>,
		1250	C<FS_XFLAG_NODEFRAG>, C<FS_XFLAG_FILESTREAM>, C<FS_XFLAG_DAX>, C<FS_XFLAG_HASATTR>,
		1251
		1252	=item aio_sync $callback->($status)
		1253
		1254	Asynchronously call sync and call the callback when finished.
825		1255
826	=item aio_fsync $fh, $callback->($status)	1256	=item aio_fsync $fh, $callback->($status)
827		1257
828	Asynchronously call fsync on the given filehandle and call the callback	1258	Asynchronously call fsync on the given filehandle and call the callback
829	with the fsync result code.	1259	with the fsync result code.
…		…
833	Asynchronously call fdatasync on the given filehandle and call the	1263	Asynchronously call fdatasync on the given filehandle and call the
834	callback with the fdatasync result code.	1264	callback with the fdatasync result code.
835		1265
836	If this call isn't available because your OS lacks it or it couldn't be	1266	If this call isn't available because your OS lacks it or it couldn't be
837	detected, it will be emulated by calling C<fsync> instead.	1267	detected, it will be emulated by calling C<fsync> instead.
		1268
		1269	=item aio_syncfs $fh, $callback->($status)
		1270
		1271	Asynchronously call the syncfs syscall to sync the filesystem associated
		1272	to the given filehandle and call the callback with the syncfs result
		1273	code. If syncfs is not available, calls sync(), but returns C<-1> and sets
		1274	errno to C<ENOSYS> nevertheless.
		1275
		1276	=item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		1277
		1278	Sync the data portion of the file specified by C<$offset> and C<$length>
		1279	to disk (but NOT the metadata), by calling the Linux-specific
		1280	sync_file_range call. If sync_file_range is not available or it returns
		1281	ENOSYS, then fdatasync or fsync is being substituted.
		1282
		1283	C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>,
		1284	C<IO::AIO::SYNC_FILE_RANGE_WRITE> and
		1285	C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range
		1286	manpage for details.
		1287
		1288	=item aio_pathsync $pathname, $callback->($status)
		1289
		1290	This request tries to open, fsync and close the given path. This is a
		1291	composite request intended to sync directories after directory operations
		1292	(E.g. rename). This might not work on all operating systems or have any
		1293	specific effect, but usually it makes sure that directory changes get
		1294	written to disc. It works for anything that can be opened for read-only,
		1295	not just directories.
		1296
		1297	Future versions of this function might fall back to other methods when
		1298	C<fsync> on the directory fails (such as calling C<sync>).
		1299
		1300	Passes C<0> when everything went ok, and C<-1> on error.
		1301
		1302	=cut
		1303
		1304	sub aio_pathsync($;$) {
		1305	my ($path, $cb) = @_;
		1306
		1307	my $pri = aioreq_pri;
		1308	my $grp = aio_group $cb;
		1309
		1310	aioreq_pri $pri;
		1311	add $grp aio_open $path, O_RDONLY, 0, sub {
		1312	my ($fh) = @_;
		1313	if ($fh) {
		1314	aioreq_pri $pri;
		1315	add $grp aio_fsync $fh, sub {
		1316	$grp->result ($_[0]);
		1317
		1318	aioreq_pri $pri;
		1319	add $grp aio_close $fh;
		1320	};
		1321	} else {
		1322	$grp->result (-1);
		1323	}
		1324	};
		1325
		1326	$grp
		1327	}
		1328
		1329	=item aio_msync $scalar, $offset = 0, $length = undef, flags = MS_SYNC, $callback->($status)
		1330
		1331	This is a rather advanced IO::AIO call, which only works on mmap(2)ed
		1332	scalars (see the C<IO::AIO::mmap> function, although it also works on data
		1333	scalars managed by the L<Sys::Mmap> or L<Mmap> modules, note that the
		1334	scalar must only be modified in-place while an aio operation is pending on
		1335	it).
		1336
		1337	It calls the C<msync> function of your OS, if available, with the memory
		1338	area starting at C<$offset> in the string and ending C<$length> bytes
		1339	later. If C<$length> is negative, counts from the end, and if C<$length>
		1340	is C<undef>, then it goes till the end of the string. The flags can be
		1341	either C<IO::AIO::MS_ASYNC> or C<IO::AIO::MS_SYNC>, plus an optional
		1342	C<IO::AIO::MS_INVALIDATE>.
		1343
		1344	=item aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		1345
		1346	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1347	scalars.
		1348
		1349	It touches (reads or writes) all memory pages in the specified
		1350	range inside the scalar. All caveats and parameters are the same
		1351	as for C<aio_msync>, above, except for flags, which must be either
		1352	C<0> (which reads all pages and ensures they are instantiated) or
		1353	C<IO::AIO::MT_MODIFY>, which modifies the memory pages (by reading and
		1354	writing an octet from it, which dirties the page).
		1355
		1356	=item aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
		1357
		1358	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1359	scalars.
		1360
		1361	It reads in all the pages of the underlying storage into memory (if any)
		1362	and locks them, so they are not getting swapped/paged out or removed.
		1363
		1364	If C<$length> is undefined, then the scalar will be locked till the end.
		1365
		1366	On systems that do not implement C<mlock>, this function returns C<-1>
		1367	and sets errno to C<ENOSYS>.
		1368
		1369	Note that the corresponding C<munlock> is synchronous and is
		1370	documented under L<MISCELLANEOUS FUNCTIONS>.
		1371
		1372	Example: open a file, mmap and mlock it - both will be undone when
		1373	C<$data> gets destroyed.
		1374
		1375	open my $fh, "<", $path or die "$path: $!";
		1376	my $data;
		1377	IO::AIO::mmap $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh;
		1378	aio_mlock $data; # mlock in background
		1379
		1380	=item aio_mlockall $flags, $callback->($status)
		1381
		1382	Calls the C<mlockall> function with the given C<$flags> (a combination of
		1383	C<IO::AIO::MCL_CURRENT> and C<IO::AIO::MCL_FUTURE>).
		1384
		1385	On systems that do not implement C<mlockall>, this function returns C<-1>
		1386	and sets errno to C<ENOSYS>.
		1387
		1388	Note that the corresponding C<munlockall> is synchronous and is
		1389	documented under L<MISCELLANEOUS FUNCTIONS>.
		1390
		1391	Example: asynchronously lock all current and future pages into memory.
		1392
		1393	aio_mlockall IO::AIO::MCL_FUTURE;
		1394
		1395	=item aio_fiemap $fh, $start, $length, $flags, $count, $cb->(\@extents)
		1396
		1397	Queries the extents of the given file (by calling the Linux C<FIEMAP>
		1398	ioctl, see L<http://cvs.schmorp.de/IO-AIO/doc/fiemap.txt> for details). If
		1399	the ioctl is not available on your OS, then this request will fail with
		1400	C<ENOSYS>.
		1401
		1402	C<$start> is the starting offset to query extents for, C<$length> is the
		1403	size of the range to query - if it is C<undef>, then the whole file will
		1404	be queried.
		1405
		1406	C<$flags> is a combination of flags (C<IO::AIO::FIEMAP_FLAG_SYNC> or
		1407	C<IO::AIO::FIEMAP_FLAG_XATTR> - C<IO::AIO::FIEMAP_FLAGS_COMPAT> is also
		1408	exported), and is normally C<0> or C<IO::AIO::FIEMAP_FLAG_SYNC> to query
		1409	the data portion.
		1410
		1411	C<$count> is the maximum number of extent records to return. If it is
		1412	C<undef>, then IO::AIO queries all extents of the range. As a very special
		1413	case, if it is C<0>, then the callback receives the number of extents
		1414	instead of the extents themselves (which is unreliable, see below).
		1415
		1416	If an error occurs, the callback receives no arguments. The special
		1417	C<errno> value C<IO::AIO::EBADR> is available to test for flag errors.
		1418
		1419	Otherwise, the callback receives an array reference with extent
		1420	structures. Each extent structure is an array reference itself, with the
		1421	following members:
		1422
		1423	[$logical, $physical, $length, $flags]
		1424
		1425	Flags is any combination of the following flag values (typically either C<0>
		1426	or C<IO::AIO::FIEMAP_EXTENT_LAST> (1)):
		1427
		1428	C<IO::AIO::FIEMAP_EXTENT_LAST>, C<IO::AIO::FIEMAP_EXTENT_UNKNOWN>,
		1429	C<IO::AIO::FIEMAP_EXTENT_DELALLOC>, C<IO::AIO::FIEMAP_EXTENT_ENCODED>,
		1430	C<IO::AIO::FIEMAP_EXTENT_DATA_ENCRYPTED>, C<IO::AIO::FIEMAP_EXTENT_NOT_ALIGNED>,
		1431	C<IO::AIO::FIEMAP_EXTENT_DATA_INLINE>, C<IO::AIO::FIEMAP_EXTENT_DATA_TAIL>,
		1432	C<IO::AIO::FIEMAP_EXTENT_UNWRITTEN>, C<IO::AIO::FIEMAP_EXTENT_MERGED> or
		1433	C<IO::AIO::FIEMAP_EXTENT_SHARED>.
		1434
		1435	At the time of this writing (Linux 3.2), this request is unreliable unless
		1436	C<$count> is C<undef>, as the kernel has all sorts of bugs preventing
		1437	it to return all extents of a range for files with a large number of
		1438	extents. The code (only) works around all these issues if C<$count> is
		1439	C<undef>.
838		1440
839	=item aio_group $callback->(...)	1441	=item aio_group $callback->(...)
840		1442
841	This is a very special aio request: Instead of doing something, it is a	1443	This is a very special aio request: Instead of doing something, it is a
842	container for other aio requests, which is useful if you want to bundle	1444	container for other aio requests, which is useful if you want to bundle
…		…
880	immense (it blocks a thread for a long time) so do not use this function	1482	immense (it blocks a thread for a long time) so do not use this function
881	except to put your application under artificial I/O pressure.	1483	except to put your application under artificial I/O pressure.
882		1484
883	=back	1485	=back
884		1486
		1487
		1488	=head2 IO::AIO::WD - multiple working directories
		1489
		1490	Your process only has one current working directory, which is used by all
		1491	threads. This makes it hard to use relative paths (some other component
		1492	could call C<chdir> at any time, and it is hard to control when the path
		1493	will be used by IO::AIO).
		1494
		1495	One solution for this is to always use absolute paths. This usually works,
		1496	but can be quite slow (the kernel has to walk the whole path on every
		1497	access), and can also be a hassle to implement.
		1498
		1499	Newer POSIX systems have a number of functions (openat, fdopendir,
		1500	futimensat and so on) that make it possible to specify working directories
		1501	per operation.
		1502
		1503	For portability, and because the clowns who "designed", or shall I write,
		1504	perpetrated this new interface were obviously half-drunk, this abstraction
		1505	cannot be perfect, though.
		1506
		1507	IO::AIO allows you to convert directory paths into a so-called IO::AIO::WD
		1508	object. This object stores the canonicalised, absolute version of the
		1509	path, and on systems that allow it, also a directory file descriptor.
		1510
		1511	Everywhere where a pathname is accepted by IO::AIO (e.g. in C<aio_stat>
		1512	or C<aio_unlink>), one can specify an array reference with an IO::AIO::WD
		1513	object and a pathname instead (or the IO::AIO::WD object alone, which
		1514	gets interpreted as C<[$wd, "."]>). If the pathname is absolute, the
		1515	IO::AIO::WD object is ignored, otherwise the pathname is resolved relative
		1516	to that IO::AIO::WD object.
		1517
		1518	For example, to get a wd object for F</etc> and then stat F<passwd>
		1519	inside, you would write:
		1520
		1521	aio_wd "/etc", sub {
		1522	my $etcdir = shift;
		1523
		1524	# although $etcdir can be undef on error, there is generally no reason
		1525	# to check for errors here, as aio_stat will fail with ENOENT
		1526	# when $etcdir is undef.
		1527
		1528	aio_stat [$etcdir, "passwd"], sub {
		1529	# yay
		1530	};
		1531	};
		1532
		1533	The fact that C<aio_wd> is a request and not a normal function shows that
		1534	creating an IO::AIO::WD object is itself a potentially blocking operation,
		1535	which is why it is done asynchronously.
		1536
		1537	To stat the directory obtained with C<aio_wd> above, one could write
		1538	either of the following three request calls:
		1539
		1540	aio_lstat "/etc" , sub { ... # pathname as normal string
		1541	aio_lstat [$wd, "."], sub { ... # "." relative to $wd (i.e. $wd itself)
		1542	aio_lstat $wd , sub { ... # shorthand for the previous
		1543
		1544	As with normal pathnames, IO::AIO keeps a copy of the working directory
		1545	object and the pathname string, so you could write the following without
		1546	causing any issues due to C<$path> getting reused:
		1547
		1548	my $path = [$wd, undef];
		1549
		1550	for my $name (qw(abc def ghi)) {
		1551	$path->[1] = $name;
		1552	aio_stat $path, sub {
		1553	# ...
		1554	};
		1555	}
		1556
		1557	There are some caveats: when directories get renamed (or deleted), the
		1558	pathname string doesn't change, so will point to the new directory (or
		1559	nowhere at all), while the directory fd, if available on the system,
		1560	will still point to the original directory. Most functions accepting a
		1561	pathname will use the directory fd on newer systems, and the string on
		1562	older systems. Some functions (such as C<aio_realpath>) will always rely on
		1563	the string form of the pathname.
		1564
		1565	So this functionality is mainly useful to get some protection against
		1566	C<chdir>, to easily get an absolute path out of a relative path for future
		1567	reference, and to speed up doing many operations in the same directory
		1568	(e.g. when stat'ing all files in a directory).
		1569
		1570	The following functions implement this working directory abstraction:
		1571
		1572	=over 4
		1573
		1574	=item aio_wd $pathname, $callback->($wd)
		1575
		1576	Asynchonously canonicalise the given pathname and convert it to an
		1577	IO::AIO::WD object representing it. If possible and supported on the
		1578	system, also open a directory fd to speed up pathname resolution relative
		1579	to this working directory.
		1580
		1581	If something goes wrong, then C<undef> is passwd to the callback instead
		1582	of a working directory object and C<$!> is set appropriately. Since
		1583	passing C<undef> as working directory component of a pathname fails the
		1584	request with C<ENOENT>, there is often no need for error checking in the
		1585	C<aio_wd> callback, as future requests using the value will fail in the
		1586	expected way.
		1587
		1588	=item IO::AIO::CWD
		1589
		1590	This is a compiletime constant (object) that represents the process
		1591	current working directory.
		1592
		1593	Specifying this object as working directory object for a pathname is as if
		1594	the pathname would be specified directly, without a directory object. For
		1595	example, these calls are functionally identical:
		1596
		1597	aio_stat "somefile", sub { ... };
		1598	aio_stat [IO::AIO::CWD, "somefile"], sub { ... };
		1599
		1600	=back
		1601
		1602	To recover the path associated with an IO::AIO::WD object, you can use
		1603	C<aio_realpath>:
		1604
		1605	aio_realpath $wd, sub {
		1606	warn "path is $_[0]\n";
		1607	};
		1608
		1609	Currently, C<aio_statvfs> always, and C<aio_rename> and C<aio_rmdir>
		1610	sometimes, fall back to using an absolue path.
		1611
885	=head2 IO::AIO::REQ CLASS	1612	=head2 IO::AIO::REQ CLASS
886		1613
887	All non-aggregate C<aio_*> functions return an object of this class when	1614	All non-aggregate C<aio_*> functions return an object of this class when
888	called in non-void context.	1615	called in non-void context.
889		1616
…		…
892	=item cancel $req	1619	=item cancel $req
893		1620
894	Cancels the request, if possible. Has the effect of skipping execution	1621	Cancels the request, if possible. Has the effect of skipping execution
895	when entering the B<execute> state and skipping calling the callback when	1622	when entering the B<execute> state and skipping calling the callback when
896	entering the the B<result> state, but will leave the request otherwise	1623	entering the the B<result> state, but will leave the request otherwise
897	untouched. That means that requests that currently execute will not be	1624	untouched (with the exception of readdir). That means that requests that
898	stopped and resources held by the request will not be freed prematurely.	1625	currently execute will not be stopped and resources held by the request
		1626	will not be freed prematurely.
899		1627
900	=item cb $req $callback->(...)	1628	=item cb $req $callback->(...)
901		1629
902	Replace (or simply set) the callback registered to the request.	1630	Replace (or simply set) the callback registered to the request.
903		1631
…		…
954	Their lifetime, simplified, looks like this: when they are empty, they	1682	Their lifetime, simplified, looks like this: when they are empty, they
955	will finish very quickly. If they contain only requests that are in the	1683	will finish very quickly. If they contain only requests that are in the
956	C<done> state, they will also finish. Otherwise they will continue to	1684	C<done> state, they will also finish. Otherwise they will continue to
957	exist.	1685	exist.
958		1686
959	That means after creating a group you have some time to add requests. And	1687	That means after creating a group you have some time to add requests
960	in the callbacks of those requests, you can add further requests to the	1688	(precisely before the callback has been invoked, which is only done within
961	group. And only when all those requests have finished will the the group	1689	the C<poll_cb>). And in the callbacks of those requests, you can add
962	itself finish.	1690	further requests to the group. And only when all those requests have
		1691	finished will the the group itself finish.
963		1692
964	=over 4	1693	=over 4
965		1694
966	=item add $grp ...	1695	=item add $grp ...
967		1696
…		…
976	=item $grp->cancel_subs	1705	=item $grp->cancel_subs
977		1706
978	Cancel all subrequests and clears any feeder, but not the group request	1707	Cancel all subrequests and clears any feeder, but not the group request
979	itself. Useful when you queued a lot of events but got a result early.	1708	itself. Useful when you queued a lot of events but got a result early.
980		1709
		1710	The group request will finish normally (you cannot add requests to the
		1711	group).
		1712
981	=item $grp->result (...)	1713	=item $grp->result (...)
982		1714
983	Set the result value(s) that will be passed to the group callback when all	1715	Set the result value(s) that will be passed to the group callback when all
984	subrequests have finished and set thre groups errno to the current value	1716	subrequests have finished and set the groups errno to the current value
985	of errno (just like calling C<errno> without an error number). By default,	1717	of errno (just like calling C<errno> without an error number). By default,
986	no argument will be passed and errno is zero.	1718	no argument will be passed and errno is zero.
987		1719
988	=item $grp->errno ([$errno])	1720	=item $grp->errno ([$errno])
989		1721
…		…
1000	=item feed $grp $callback->($grp)	1732	=item feed $grp $callback->($grp)
1001		1733
1002	Sets a feeder/generator on this group: every group can have an attached	1734	Sets a feeder/generator on this group: every group can have an attached
1003	generator that generates requests if idle. The idea behind this is that,	1735	generator that generates requests if idle. The idea behind this is that,
1004	although you could just queue as many requests as you want in a group,	1736	although you could just queue as many requests as you want in a group,
1005	this might starve other requests for a potentially long time. For	1737	this might starve other requests for a potentially long time. For example,
1006	example, C<aio_scandir> might generate hundreds of thousands C<aio_stat>	1738	C<aio_scandir> might generate hundreds of thousands of C<aio_stat>
1007	requests, delaying any later requests for a long time.	1739	requests, delaying any later requests for a long time.
1008		1740
1009	To avoid this, and allow incremental generation of requests, you can	1741	To avoid this, and allow incremental generation of requests, you can
1010	instead a group and set a feeder on it that generates those requests. The	1742	instead a group and set a feeder on it that generates those requests. The
1011	feed callback will be called whenever there are few enough (see C<limit>,	1743	feed callback will be called whenever there are few enough (see C<limit>,
…		…
1016	not impose any limits).	1748	not impose any limits).
1017		1749
1018	If the feed does not queue more requests when called, it will be	1750	If the feed does not queue more requests when called, it will be
1019	automatically removed from the group.	1751	automatically removed from the group.
1020		1752
1021	If the feed limit is C<0>, it will be set to C<2> automatically.	1753	If the feed limit is C<0> when this method is called, it will be set to
		1754	C<2> automatically.
1022		1755
1023	Example:	1756	Example:
1024		1757
1025	# stat all files in @files, but only ever use four aio requests concurrently:	1758	# stat all files in @files, but only ever use four aio requests concurrently:
1026		1759
…		…
1038	Sets the feeder limit for the group: The feeder will be called whenever	1771	Sets the feeder limit for the group: The feeder will be called whenever
1039	the group contains less than this many requests.	1772	the group contains less than this many requests.
1040		1773
1041	Setting the limit to C<0> will pause the feeding process.	1774	Setting the limit to C<0> will pause the feeding process.
1042		1775
		1776	The default value for the limit is C<0>, but note that setting a feeder
		1777	automatically bumps it up to C<2>.
		1778
1043	=back	1779	=back
1044		1780
1045	=head2 SUPPORT FUNCTIONS	1781	=head2 SUPPORT FUNCTIONS
1046		1782
1047	=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION	1783	=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION
…		…
1049	=over 4	1785	=over 4
1050		1786
1051	=item $fileno = IO::AIO::poll_fileno	1787	=item $fileno = IO::AIO::poll_fileno
1052		1788
1053	Return the I<request result pipe file descriptor>. This filehandle must be	1789	Return the I<request result pipe file descriptor>. This filehandle must be
1054	polled for reading by some mechanism outside this module (e.g. Event or	1790	polled for reading by some mechanism outside this module (e.g. EV, Glib,
1055	select, see below or the SYNOPSIS). If the pipe becomes readable you have	1791	select and so on, see below or the SYNOPSIS). If the pipe becomes readable
1056	to call C<poll_cb> to check the results.	1792	you have to call C<poll_cb> to check the results.
1057		1793
1058	See C<poll_cb> for an example.	1794	See C<poll_cb> for an example.
1059		1795
1060	=item IO::AIO::poll_cb	1796	=item IO::AIO::poll_cb
1061		1797
1062	Process some outstanding events on the result pipe. You have to call this	1798	Process some requests that have reached the result phase (i.e. they have
1063	regularly. Returns the number of events processed. Returns immediately	1799	been executed but the results are not yet reported). You have to call
1064	when no events are outstanding. The amount of events processed depends on	1800	this "regularly" to finish outstanding requests.
1065	the settings of C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>.
1066		1801
		1802	Returns C<0> if all events could be processed (or there were no
		1803	events to process), or C<-1> if it returned earlier for whatever
		1804	reason. Returns immediately when no events are outstanding. The amount
		1805	of events processed depends on the settings of C<IO::AIO::max_poll_req>,
		1806	C<IO::AIO::max_poll_time> and C<IO::AIO::max_outstanding>.
		1807
1067	If not all requests were processed for whatever reason, the filehandle	1808	If not all requests were processed for whatever reason, the poll file
1068	will still be ready when C<poll_cb> returns.	1809	descriptor will still be ready when C<poll_cb> returns, so normally you
		1810	don't have to do anything special to have it called later.
		1811
		1812	Apart from calling C<IO::AIO::poll_cb> when the event filehandle becomes
		1813	ready, it can be beneficial to call this function from loops which submit
		1814	a lot of requests, to make sure the results get processed when they become
		1815	available and not just when the loop is finished and the event loop takes
		1816	over again. This function returns very fast when there are no outstanding
		1817	requests.
1069		1818
1070	Example: Install an Event watcher that automatically calls	1819	Example: Install an Event watcher that automatically calls
1071	IO::AIO::poll_cb with high priority:	1820	IO::AIO::poll_cb with high priority (more examples can be found in the
		1821	SYNOPSIS section, at the top of this document):
1072		1822
1073	Event->io (fd => IO::AIO::poll_fileno,	1823	Event->io (fd => IO::AIO::poll_fileno,
1074	poll => 'r', async => 1,	1824	poll => 'r', async => 1,
1075	cb => \&IO::AIO::poll_cb);	1825	cb => \&IO::AIO::poll_cb);
		1826
		1827	=item IO::AIO::poll_wait
		1828
		1829	Wait until either at least one request is in the result phase or no
		1830	requests are outstanding anymore.
		1831
		1832	This is useful if you want to synchronously wait for some requests to
		1833	become ready, without actually handling them.
		1834
		1835	See C<nreqs> for an example.
		1836
		1837	=item IO::AIO::poll
		1838
		1839	Waits until some requests have been handled.
		1840
		1841	Returns the number of requests processed, but is otherwise strictly
		1842	equivalent to:
		1843
		1844	IO::AIO::poll_wait, IO::AIO::poll_cb
		1845
		1846	=item IO::AIO::flush
		1847
		1848	Wait till all outstanding AIO requests have been handled.
		1849
		1850	Strictly equivalent to:
		1851
		1852	IO::AIO::poll_wait, IO::AIO::poll_cb
		1853	while IO::AIO::nreqs;
1076		1854
1077	=item IO::AIO::max_poll_reqs $nreqs	1855	=item IO::AIO::max_poll_reqs $nreqs
1078		1856
1079	=item IO::AIO::max_poll_time $seconds	1857	=item IO::AIO::max_poll_time $seconds
1080		1858
…		…
1105	# use a low priority so other tasks have priority	1883	# use a low priority so other tasks have priority
1106	Event->io (fd => IO::AIO::poll_fileno,	1884	Event->io (fd => IO::AIO::poll_fileno,
1107	poll => 'r', nice => 1,	1885	poll => 'r', nice => 1,
1108	cb => &IO::AIO::poll_cb);	1886	cb => &IO::AIO::poll_cb);
1109		1887
1110	=item IO::AIO::poll_wait
1111
1112	If there are any outstanding requests and none of them in the result
1113	phase, wait till the result filehandle becomes ready for reading (simply
1114	does a C<select> on the filehandle. This is useful if you want to
1115	synchronously wait for some requests to finish).
1116
1117	See C<nreqs> for an example.
1118
1119	=item IO::AIO::poll
1120
1121	Waits until some requests have been handled.
1122
1123	Returns the number of requests processed, but is otherwise strictly
1124	equivalent to:
1125
1126	IO::AIO::poll_wait, IO::AIO::poll_cb
1127
1128	=item IO::AIO::flush
1129
1130	Wait till all outstanding AIO requests have been handled.
1131
1132	Strictly equivalent to:
1133
1134	IO::AIO::poll_wait, IO::AIO::poll_cb
1135	while IO::AIO::nreqs;
1136
1137	=back	1888	=back
1138		1889
1139	=head3 CONTROLLING THE NUMBER OF THREADS	1890	=head3 CONTROLLING THE NUMBER OF THREADS
1140		1891
1141	=over	1892	=over
…		…
1174		1925
1175	Under normal circumstances you don't need to call this function.	1926	Under normal circumstances you don't need to call this function.
1176		1927
1177	=item IO::AIO::max_idle $nthreads	1928	=item IO::AIO::max_idle $nthreads
1178		1929
1179	Limit the number of threads (default: 4) that are allowed to idle (i.e.,	1930	Limit the number of threads (default: 4) that are allowed to idle
1180	threads that did not get a request to process within 10 seconds). That	1931	(i.e., threads that did not get a request to process within the idle
1181	means if a thread becomes idle while C<$nthreads> other threads are also	1932	timeout (default: 10 seconds). That means if a thread becomes idle while
1182	idle, it will free its resources and exit.	1933	C<$nthreads> other threads are also idle, it will free its resources and
		1934	exit.
1183		1935
1184	This is useful when you allow a large number of threads (e.g. 100 or 1000)	1936	This is useful when you allow a large number of threads (e.g. 100 or 1000)
1185	to allow for extremely high load situations, but want to free resources	1937	to allow for extremely high load situations, but want to free resources
1186	under normal circumstances (1000 threads can easily consume 30MB of RAM).	1938	under normal circumstances (1000 threads can easily consume 30MB of RAM).
1187		1939
1188	The default is probably ok in most situations, especially if thread	1940	The default is probably ok in most situations, especially if thread
1189	creation is fast. If thread creation is very slow on your system you might	1941	creation is fast. If thread creation is very slow on your system you might
1190	want to use larger values.	1942	want to use larger values.
1191		1943
		1944	=item IO::AIO::idle_timeout $seconds
		1945
		1946	Sets the minimum idle timeout (default 10) after which worker threads are
		1947	allowed to exit. SEe C<IO::AIO::max_idle>.
		1948
1192	=item $oldmaxreqs = IO::AIO::max_outstanding $maxreqs	1949	=item IO::AIO::max_outstanding $maxreqs
		1950
		1951	Sets the maximum number of outstanding requests to C<$nreqs>. If
		1952	you do queue up more than this number of requests, the next call to
		1953	C<IO::AIO::poll_cb> (and other functions calling C<poll_cb>, such as
		1954	C<IO::AIO::flush> or C<IO::AIO::poll>) will block until the limit is no
		1955	longer exceeded.
		1956
		1957	In other words, this setting does not enforce a queue limit, but can be
		1958	used to make poll functions block if the limit is exceeded.
1193		1959
1194	This is a very bad function to use in interactive programs because it	1960	This is a very bad function to use in interactive programs because it
1195	blocks, and a bad way to reduce concurrency because it is inexact: Better	1961	blocks, and a bad way to reduce concurrency because it is inexact: Better
1196	use an C<aio_group> together with a feed callback.	1962	use an C<aio_group> together with a feed callback.
1197		1963
1198	Sets the maximum number of outstanding requests to C<$nreqs>. If you	1964	Its main use is in scripts without an event loop - when you want to stat
1199	to queue up more than this number of requests, the next call to the	1965	a lot of files, you can write something like this:
1200	C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>)
1201	function will block until the limit is no longer exceeded.
1202		1966
1203	The default value is very large, so there is no practical limit on the	1967	IO::AIO::max_outstanding 32;
1204	number of outstanding requests.
1205		1968
1206	You can still queue as many requests as you want. Therefore,	1969	for my $path (...) {
1207	C<max_oustsanding> is mainly useful in simple scripts (with low values) or	1970	aio_stat $path , ...;
1208	as a stop gap to shield against fatal memory overflow (with large values).	1971	IO::AIO::poll_cb;
		1972	}
		1973
		1974	IO::AIO::flush;
		1975
		1976	The call to C<poll_cb> inside the loop will normally return instantly, but
		1977	as soon as more thna C<32> reqeusts are in-flight, it will block until
		1978	some requests have been handled. This keeps the loop from pushing a large
		1979	number of C<aio_stat> requests onto the queue.
		1980
		1981	The default value for C<max_outstanding> is very large, so there is no
		1982	practical limit on the number of outstanding requests.
1209		1983
1210	=back	1984	=back
1211		1985
1212	=head3 STATISTICAL INFORMATION	1986	=head3 STATISTICAL INFORMATION
1213		1987
…		…
1233	Returns the number of requests currently in the pending state (executed,	2007	Returns the number of requests currently in the pending state (executed,
1234	but not yet processed by poll_cb).	2008	but not yet processed by poll_cb).
1235		2009
1236	=back	2010	=back
1237		2011
		2012	=head3 MISCELLANEOUS FUNCTIONS
		2013
		2014	IO::AIO implements some functions that are useful when you want to use
		2015	some "Advanced I/O" function not available to in Perl, without going the
		2016	"Asynchronous I/O" route. Many of these have an asynchronous C<aio_*>
		2017	counterpart.
		2018
		2019	=over 4
		2020
		2021	=item $numfd = IO::AIO::get_fdlimit
		2022
		2023	This function is I<EXPERIMENTAL> and subject to change.
		2024
		2025	Tries to find the current file descriptor limit and returns it, or
		2026	C<undef> and sets C<$!> in case of an error. The limit is one larger than
		2027	the highest valid file descriptor number.
		2028
		2029	=item IO::AIO::min_fdlimit [$numfd]
		2030
		2031	This function is I<EXPERIMENTAL> and subject to change.
		2032
		2033	Try to increase the current file descriptor limit(s) to at least C<$numfd>
		2034	by changing the soft or hard file descriptor resource limit. If C<$numfd>
		2035	is missing, it will try to set a very high limit, although this is not
		2036	recommended when you know the actual minimum that you require.
		2037
		2038	If the limit cannot be raised enough, the function makes a best-effort
		2039	attempt to increase the limit as much as possible, using various
		2040	tricks, while still failing. You can query the resulting limit using
		2041	C<IO::AIO::get_fdlimit>.
		2042
		2043	If an error occurs, returns C<undef> and sets C<$!>, otherwise returns
		2044	true.
		2045
		2046	=item IO::AIO::sendfile $ofh, $ifh, $offset, $count
		2047
		2048	Calls the C<eio_sendfile_sync> function, which is like C<aio_sendfile>,
		2049	but is blocking (this makes most sense if you know the input data is
		2050	likely cached already and the output filehandle is set to non-blocking
		2051	operations).
		2052
		2053	Returns the number of bytes copied, or C<-1> on error.
		2054
		2055	=item IO::AIO::fadvise $fh, $offset, $len, $advice
		2056
		2057	Simply calls the C<posix_fadvise> function (see its
		2058	manpage for details). The following advice constants are
		2059	available: C<IO::AIO::FADV_NORMAL>, C<IO::AIO::FADV_SEQUENTIAL>,
		2060	C<IO::AIO::FADV_RANDOM>, C<IO::AIO::FADV_NOREUSE>,
		2061	C<IO::AIO::FADV_WILLNEED>, C<IO::AIO::FADV_DONTNEED>.
		2062
		2063	On systems that do not implement C<posix_fadvise>, this function returns
		2064	ENOSYS, otherwise the return value of C<posix_fadvise>.
		2065
		2066	=item IO::AIO::madvise $scalar, $offset, $len, $advice
		2067
		2068	Simply calls the C<posix_madvise> function (see its
		2069	manpage for details). The following advice constants are
		2070	available: C<IO::AIO::MADV_NORMAL>, C<IO::AIO::MADV_SEQUENTIAL>,
		2071	C<IO::AIO::MADV_RANDOM>, C<IO::AIO::MADV_WILLNEED>,
		2072	C<IO::AIO::MADV_DONTNEED>.
		2073
		2074	If C<$offset> is negative, counts from the end. If C<$length> is negative,
		2075	the remaining length of the C<$scalar> is used. If possible, C<$length>
		2076	will be reduced to fit into the C<$scalar>.
		2077
		2078	On systems that do not implement C<posix_madvise>, this function returns
		2079	ENOSYS, otherwise the return value of C<posix_madvise>.
		2080
		2081	=item IO::AIO::mprotect $scalar, $offset, $len, $protect
		2082
		2083	Simply calls the C<mprotect> function on the preferably AIO::mmap'ed
		2084	$scalar (see its manpage for details). The following protect
		2085	constants are available: C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_READ>,
		2086	C<IO::AIO::PROT_WRITE>, C<IO::AIO::PROT_EXEC>.
		2087
		2088	If C<$offset> is negative, counts from the end. If C<$length> is negative,
		2089	the remaining length of the C<$scalar> is used. If possible, C<$length>
		2090	will be reduced to fit into the C<$scalar>.
		2091
		2092	On systems that do not implement C<mprotect>, this function returns
		2093	ENOSYS, otherwise the return value of C<mprotect>.
		2094
		2095	=item IO::AIO::mmap $scalar, $length, $prot, $flags, $fh[, $offset]
		2096
		2097	Memory-maps a file (or anonymous memory range) and attaches it to the
		2098	given C<$scalar>, which will act like a string scalar. Returns true on
		2099	success, and false otherwise.
		2100
		2101	The scalar must exist, but its contents do not matter - this means you
		2102	cannot use a nonexistant array or hash element. When in doubt, C<undef>
		2103	the scalar first.
		2104
		2105	The only operations allowed on the mmapped scalar are C<substr>/C<vec>,
		2106	which don't change the string length, and most read-only operations such
		2107	as copying it or searching it with regexes and so on.
		2108
		2109	Anything else is unsafe and will, at best, result in memory leaks.
		2110
		2111	The memory map associated with the C<$scalar> is automatically removed
		2112	when the C<$scalar> is undef'd or destroyed, or when the C<IO::AIO::mmap>
		2113	or C<IO::AIO::munmap> functions are called on it.
		2114
		2115	This calls the C<mmap>(2) function internally. See your system's manual
		2116	page for details on the C<$length>, C<$prot> and C<$flags> parameters.
		2117
		2118	The C<$length> must be larger than zero and smaller than the actual
		2119	filesize.
		2120
		2121	C<$prot> is a combination of C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_EXEC>,
		2122	C<IO::AIO::PROT_READ> and/or C<IO::AIO::PROT_WRITE>,
		2123
		2124	C<$flags> can be a combination of
		2125	C<IO::AIO::MAP_SHARED> or
		2126	C<IO::AIO::MAP_PRIVATE>,
		2127	or a number of system-specific flags (when not available, the are C<0>):
		2128	C<IO::AIO::MAP_ANONYMOUS> (which is set to C<MAP_ANON> if your system only provides this constant),
		2129	C<IO::AIO::MAP_LOCKED>,
		2130	C<IO::AIO::MAP_NORESERVE>,
		2131	C<IO::AIO::MAP_POPULATE>,
		2132	C<IO::AIO::MAP_NONBLOCK>,
		2133	C<IO::AIO::MAP_FIXED>,
		2134	C<IO::AIO::MAP_GROWSDOWN>,
		2135	C<IO::AIO::MAP_32BIT>,
		2136	C<IO::AIO::MAP_HUGETLB> or
		2137	C<IO::AIO::MAP_STACK>.
		2138
		2139	If C<$fh> is C<undef>, then a file descriptor of C<-1> is passed.
		2140
		2141	C<$offset> is the offset from the start of the file - it generally must be
		2142	a multiple of C<IO::AIO::PAGESIZE> and defaults to C<0>.
		2143
		2144	Example:
		2145
		2146	use Digest::MD5;
		2147	use IO::AIO;
		2148
		2149	open my $fh, "<verybigfile"
		2150	or die "$!";
		2151
		2152	IO::AIO::mmap my $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh
		2153	or die "verybigfile: $!";
		2154
		2155	my $fast_md5 = md5 $data;
		2156
		2157	=item IO::AIO::munmap $scalar
		2158
		2159	Removes a previous mmap and undefines the C<$scalar>.
		2160
		2161	=item IO::AIO::munlock $scalar, $offset = 0, $length = undef
		2162
		2163	Calls the C<munlock> function, undoing the effects of a previous
		2164	C<aio_mlock> call (see its description for details).
		2165
		2166	=item IO::AIO::munlockall
		2167
		2168	Calls the C<munlockall> function.
		2169
		2170	On systems that do not implement C<munlockall>, this function returns
		2171	ENOSYS, otherwise the return value of C<munlockall>.
		2172
		2173	=item IO::AIO::splice $r_fh, $r_off, $w_fh, $w_off, $length, $flags
		2174
		2175	Calls the GNU/Linux C<splice(2)> syscall, if available. If C<$r_off> or
		2176	C<$w_off> are C<undef>, then C<NULL> is passed for these, otherwise they
		2177	should be the file offset.
		2178
		2179	C<$r_fh> and C<$w_fh> should not refer to the same file, as splice might
		2180	silently corrupt the data in this case.
		2181
		2182	The following symbol flag values are available: C<IO::AIO::SPLICE_F_MOVE>,
		2183	C<IO::AIO::SPLICE_F_NONBLOCK>, C<IO::AIO::SPLICE_F_MORE> and
		2184	C<IO::AIO::SPLICE_F_GIFT>.
		2185
		2186	See the C<splice(2)> manpage for details.
		2187
		2188	=item IO::AIO::tee $r_fh, $w_fh, $length, $flags
		2189
		2190	Calls the GNU/Linux C<tee(2)> syscall, see its manpage and the
		2191	description for C<IO::AIO::splice> above for details.
		2192
		2193	=item $actual_size = IO::AIO::pipesize $r_fh[, $new_size]
		2194
		2195	Attempts to query or change the pipe buffer size. Obviously works only
		2196	on pipes, and currently works only on GNU/Linux systems, and fails with
		2197	C<-1>/C<ENOSYS> everywhere else. If anybody knows how to influence pipe buffer
		2198	size on other systems, drop me a note.
		2199
		2200	=item ($rfh, $wfh) = IO::AIO::pipe2 [$flags]
		2201
		2202	This is a direct interface to the Linux L<pipe2(2)> system call. If
		2203	C<$flags> is missing or C<0>, then this should be the same as a call to
		2204	perl's built-in C<pipe> function and create a new pipe, and works on
		2205	systems that lack the pipe2 syscall. On win32, this case invokes C<_pipe
		2206	(..., 4096, O_BINARY)>.
		2207
		2208	If C<$flags> is non-zero, it tries to invoke the pipe2 system call with
		2209	the given flags (Linux 2.6.27, glibc 2.9).
		2210
		2211	On success, the read and write file handles are returned.
		2212
		2213	On error, nothing will be returned. If the pipe2 syscall is missing and
		2214	C<$flags> is non-zero, fails with C<ENOSYS>.
		2215
		2216	Please refer to L<pipe2(2)> for more info on the C<$flags>, but at the
		2217	time of this writing, C<IO::AIO::O_CLOEXEC>, C<IO::AIO::O_NONBLOCK> and
		2218	C<IO::AIO::O_DIRECT> (Linux 3.4, for packet-based pipes) were supported.
		2219
		2220	Example: create a pipe race-free w.r.t. threads and fork:
		2221
		2222	my ($rfh, $wfh) = IO::AIO::pipe2 IO::AIO::O_CLOEXEC
		2223	or die "pipe2: $!\n";
		2224
		2225	=item $fh = IO::AIO::eventfd ([$initval, [$flags]])
		2226
		2227	This is a direct interface to the Linux L<eventfd(2)> system call. The
		2228	(unhelpful) defaults for C<$initval> and C<$flags> are C<0> for both.
		2229
		2230	On success, the new eventfd filehandle is returned, otherwise returns
		2231	C<undef>. If the eventfd syscall is missing, fails with C<ENOSYS>.
		2232
		2233	Please refer to L<eventfd(2)> for more info on this call.
		2234
		2235	The following symbol flag values are available: C<IO::AIO::EFD_CLOEXEC>,
		2236	C<IO::AIO::EFD_NONBLOCK> and C<IO::AIO::EFD_SEMAPHORE> (Linux 2.6.30).
		2237
		2238	=back
		2239
1238	=cut	2240	=cut
1239		2241
1240	# support function to convert a fd into a perl filehandle
1241	sub _fd2fh {
1242	return undef if $_[0] < 0;
1243
1244	# try to generate nice filehandles
1245	my $sym = "IO::AIO::fd#$_[0]";
1246	local *$sym;
1247
1248	open *$sym, "+<&=$_[0]" # usually works under any unix
1249	or open *$sym, "<&=$_[0]" # cygwin needs this
1250	or open *$sym, ">&=$_[0]" # or this
1251	or return undef;
1252
1253	*$sym
1254	}
1255
1256	min_parallel 8;	2242	min_parallel 8;
1257		2243
1258	END { flush }	2244	END { flush }
1259		2245
1260	1;	2246	1;
1261		2247
		2248	=head1 EVENT LOOP INTEGRATION
		2249
		2250	It is recommended to use L<AnyEvent::AIO> to integrate IO::AIO
		2251	automatically into many event loops:
		2252
		2253	# AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...)
		2254	use AnyEvent::AIO;
		2255
		2256	You can also integrate IO::AIO manually into many event loops, here are
		2257	some examples of how to do this:
		2258
		2259	# EV integration
		2260	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
		2261
		2262	# Event integration
		2263	Event->io (fd => IO::AIO::poll_fileno,
		2264	poll => 'r',
		2265	cb => \&IO::AIO::poll_cb);
		2266
		2267	# Glib/Gtk2 integration
		2268	add_watch Glib::IO IO::AIO::poll_fileno,
		2269	in => sub { IO::AIO::poll_cb; 1 };
		2270
		2271	# Tk integration
		2272	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
		2273	readable => \&IO::AIO::poll_cb);
		2274
		2275	# Danga::Socket integration
		2276	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
		2277	\&IO::AIO::poll_cb);
		2278
1262	=head2 FORK BEHAVIOUR	2279	=head2 FORK BEHAVIOUR
1263		2280
1264	This module should do "the right thing" when the process using it forks:	2281	Usage of pthreads in a program changes the semantics of fork
		2282	considerably. Specifically, only async-safe functions can be called after
		2283	fork. Perl doesn't know about this, so in general, you cannot call fork
		2284	with defined behaviour in perl if pthreads are involved. IO::AIO uses
		2285	pthreads, so this applies, but many other extensions and (for inexplicable
		2286	reasons) perl itself often is linked against pthreads, so this limitation
		2287	applies to quite a lot of perls.
1265		2288
1266	Before the fork, IO::AIO enters a quiescent state where no requests	2289	This module no longer tries to fight your OS, or POSIX. That means IO::AIO
1267	can be added in other threads and no results will be processed. After	2290	only works in the process that loaded it. Forking is fully supported, but
1268	the fork the parent simply leaves the quiescent state and continues	2291	using IO::AIO in the child is not.
1269	request/result processing, while the child frees the request/result queue
1270	(so that the requests started before the fork will only be handled in the
1271	parent). Threads will be started on demand until the limit set in the
1272	parent process has been reached again.
1273		2292
1274	In short: the parent will, after a short pause, continue as if fork had	2293	You might get around by not I<using> IO::AIO before (or after)
1275	not been called, while the child will act as if IO::AIO has not been used	2294	forking. You could also try to call the L<IO::AIO::reinit> function in the
1276	yet.	2295	child:
		2296
		2297	=over 4
		2298
		2299	=item IO::AIO::reinit
		2300
		2301	Abandons all current requests and I/O threads and simply reinitialises all
		2302	data structures. This is not an operation supported by any standards, but
		2303	happens to work on GNU/Linux and some newer BSD systems.
		2304
		2305	The only reasonable use for this function is to call it after forking, if
		2306	C<IO::AIO> was used in the parent. Calling it while IO::AIO is active in
		2307	the process will result in undefined behaviour. Calling it at any time
		2308	will also result in any undefined (by POSIX) behaviour.
		2309
		2310	=back
1277		2311
1278	=head2 MEMORY USAGE	2312	=head2 MEMORY USAGE
1279		2313
1280	Per-request usage:	2314	Per-request usage:
1281		2315
…		…
1283	bytes of memory. In addition, stat requests need a stat buffer (possibly	2317	bytes of memory. In addition, stat requests need a stat buffer (possibly
1284	a few hundred bytes), readdir requires a result buffer and so on. Perl	2318	a few hundred bytes), readdir requires a result buffer and so on. Perl
1285	scalars and other data passed into aio requests will also be locked and	2319	scalars and other data passed into aio requests will also be locked and
1286	will consume memory till the request has entered the done state.	2320	will consume memory till the request has entered the done state.
1287		2321
1288	This is now awfully much, so queuing lots of requests is not usually a	2322	This is not awfully much, so queuing lots of requests is not usually a
1289	problem.	2323	problem.
1290		2324
1291	Per-thread usage:	2325	Per-thread usage:
1292		2326
1293	In the execution phase, some aio requests require more memory for	2327	In the execution phase, some aio requests require more memory for
…		…
1298		2332
1299	Known bugs will be fixed in the next release.	2333	Known bugs will be fixed in the next release.
1300		2334
1301	=head1 SEE ALSO	2335	=head1 SEE ALSO
1302		2336
1303	L<Coro::AIO>.	2337	L<AnyEvent::AIO> for easy integration into event loops, L<Coro::AIO> for a
		2338	more natural syntax.
1304		2339
1305	=head1 AUTHOR	2340	=head1 AUTHOR
1306		2341
1307	Marc Lehmann <schmorp@schmorp.de>	2342	Marc Lehmann <schmorp@schmorp.de>
1308	http://home.schmorp.de/	2343	http://home.schmorp.de/

Diff Legend

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