ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/IO-AIO/AIO.pm

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.110 by root, Sun Jul 8 09:09:34 2007 UTC vs.
Revision 1.233 by root, Mon Aug 13 01:01:04 2012 UTC

…		…
4		4
5	=head1 SYNOPSIS	5	=head1 SYNOPSIS
6		6
7	use IO::AIO;	7	use IO::AIO;
8		8
9	aio_open "/etc/passwd", O_RDONLY, 0, sub {	9	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
10	my $fh = shift	10	my $fh = shift
11	or die "/etc/passwd: $!";	11	or die "/etc/passwd: $!";
12	...	12	...
13	};	13	};
14		14
…		…
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
…		…
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	47	While most of this works on all types of file descriptors (for
68	example sockets), using these functions on file descriptors that	48	example sockets), using these functions on file descriptors that
69	support nonblocking operation (again, sockets, pipes etc.) is very	49	support nonblocking operation (again, sockets, pipes etc.) is
70	inefficient. Use an event loop for that (such as the L<Event|Event>	50	very inefficient. Use an event loop for that (such as the L<EV>
71	module): IO::AIO will naturally fit into such an event loop itself.	51	module): IO::AIO will naturally fit into such an event loop itself.
72		52
73	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
74	requests and signal their completion. You don't need thread support	54	requests and signal their completion. You don't need thread support
75	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
…		…
85	yourself, always call C<poll_cb> from within the same thread, or never	65	yourself, always call C<poll_cb> from within the same thread, or never
86	call C<poll_cb> (or other C<aio_> functions) recursively.	66	call C<poll_cb> (or other C<aio_> functions) recursively.
87		67
88	=head2 EXAMPLE	68	=head2 EXAMPLE
89		69
90	This is a simple example that uses the Event module and loads	70	This is a simple example that uses the EV module and loads
91	F</etc/passwd> asynchronously:	71	F</etc/passwd> asynchronously:
92		72
93	use Fcntl;	73	use Fcntl;
94	use Event;	74	use EV;
95	use IO::AIO;	75	use IO::AIO;
96		76
97	# register the IO::AIO callback with Event	77	# register the IO::AIO callback with EV
98	Event->io (fd => IO::AIO::poll_fileno,	78	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
99	poll => 'r',
100	cb => \&IO::AIO::poll_cb);
101		79
102	# queue the request to open /etc/passwd	80	# queue the request to open /etc/passwd
103	aio_open "/etc/passwd", O_RDONLY, 0, sub {	81	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
104	my $fh = shift	82	my $fh = shift
105	or die "error while opening: $!";	83	or die "error while opening: $!";
106		84
107	# stat'ing filehandles is generally non-blocking	85	# stat'ing filehandles is generally non-blocking
108	my $size = -s $fh;	86	my $size = -s $fh;
…		…
117		95
118	# file contents now in $contents	96	# file contents now in $contents
119	print $contents;	97	print $contents;
120		98
121	# exit event loop and program	99	# exit event loop and program
122	Event::unloop;	100	EV::unloop;
123	};	101	};
124	};	102	};
125		103
126	# possibly queue up other requests, or open GUI windows,	104	# possibly queue up other requests, or open GUI windows,
127	# check for sockets etc. etc.	105	# check for sockets etc. etc.
128		106
129	# process events as long as there are some:	107	# process events as long as there are some:
130	Event::loop;	108	EV::loop;
131		109
132	=head1 REQUEST ANATOMY AND LIFETIME	110	=head1 REQUEST ANATOMY AND LIFETIME
133		111
134	Every C<aio_*> function creates a request. which is a C data structure not	112	Every C<aio_*> function creates a request. which is a C data structure not
135	directly visible to Perl.	113	directly visible to Perl.
…		…
183		161
184	=cut	162	=cut
185		163
186	package IO::AIO;	164	package IO::AIO;
187		165
188	no warnings;	166	use Carp ();
189	use strict 'vars';	167
		168	use common::sense;
190		169
191	use base 'Exporter';	170	use base 'Exporter';
192		171
193	BEGIN {	172	BEGIN {
194	our $VERSION = '2.4';	173	our $VERSION = '4.15';
195		174
196	our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat	175	our @AIO_REQ = qw(aio_sendfile aio_seek aio_read aio_write aio_open aio_close
197	aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink	176	aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx
198	aio_readlink aio_fsync aio_fdatasync aio_readahead aio_rename aio_link	177	aio_scandir aio_symlink aio_readlink aio_realpath aio_sync
		178	aio_fsync aio_syncfs aio_fdatasync aio_sync_file_range aio_fallocate
		179	aio_pathsync aio_readahead aio_fiemap
		180	aio_rename aio_link aio_move aio_copy aio_group
199	aio_move aio_copy aio_group aio_nop aio_mknod aio_load aio_rmtree aio_mkdir	181	aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown
200	aio_chown aio_chmod aio_utime aio_truncate);	182	aio_chmod aio_utime aio_truncate
		183	aio_msync aio_mtouch aio_mlock aio_mlockall
		184	aio_statvfs
		185	aio_wd);
		186
201	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice aio_block));	187	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice));
202	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush	188	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush
203	min_parallel max_parallel max_idle	189	min_parallel max_parallel max_idle idle_timeout
204	nreqs nready npending nthreads	190	nreqs nready npending nthreads
205	max_poll_time max_poll_reqs);	191	max_poll_time max_poll_reqs
		192	sendfile fadvise madvise
		193	mmap munmap munlock munlockall);
		194
		195	push @AIO_REQ, qw(aio_busy); # not exported
206		196
207	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';	197	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';
208		198
209	require XSLoader;	199	require XSLoader;
210	XSLoader::load ("IO::AIO", $VERSION);	200	XSLoader::load ("IO::AIO", $VERSION);
211	}	201	}
212		202
213	=head1 FUNCTIONS	203	=head1 FUNCTIONS
214		204
215	=head2 AIO REQUEST FUNCTIONS	205	=head2 QUICK OVERVIEW
		206
		207	This section simply lists the prototypes most of the functions for
		208	quick reference. See the following sections for function-by-function
		209	documentation.
		210
		211	aio_wd $pathname, $callback->($wd)
		212	aio_open $pathname, $flags, $mode, $callback->($fh)
		213	aio_close $fh, $callback->($status)
		214	aio_seek $fh,$offset,$whence, $callback->($offs)
		215	aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
		216	aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
		217	aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
		218	aio_readahead $fh,$offset,$length, $callback->($retval)
		219	aio_stat $fh_or_path, $callback->($status)
		220	aio_lstat $fh, $callback->($status)
		221	aio_statvfs $fh_or_path, $callback->($statvfs)
		222	aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
		223	aio_chown $fh_or_path, $uid, $gid, $callback->($status)
		224	aio_chmod $fh_or_path, $mode, $callback->($status)
		225	aio_truncate $fh_or_path, $offset, $callback->($status)
		226	aio_allocate $fh, $mode, $offset, $len, $callback->($status)
		227	aio_fiemap $fh, $start, $length, $flags, $count, $cb->(\@extents)
		228	aio_unlink $pathname, $callback->($status)
		229	aio_mknod $pathname, $mode, $dev, $callback->($status)
		230	aio_link $srcpath, $dstpath, $callback->($status)
		231	aio_symlink $srcpath, $dstpath, $callback->($status)
		232	aio_readlink $pathname, $callback->($link)
		233	aio_realpath $pathname, $callback->($link)
		234	aio_rename $srcpath, $dstpath, $callback->($status)
		235	aio_mkdir $pathname, $mode, $callback->($status)
		236	aio_rmdir $pathname, $callback->($status)
		237	aio_readdir $pathname, $callback->($entries)
		238	aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		239	IO::AIO::READDIR_DENTS IO::AIO::READDIR_DIRS_FIRST
		240	IO::AIO::READDIR_STAT_ORDER IO::AIO::READDIR_FOUND_UNKNOWN
		241	aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs)
		242	aio_load $pathname, $data, $callback->($status)
		243	aio_copy $srcpath, $dstpath, $callback->($status)
		244	aio_move $srcpath, $dstpath, $callback->($status)
		245	aio_rmtree $pathname, $callback->($status)
		246	aio_sync $callback->($status)
		247	aio_syncfs $fh, $callback->($status)
		248	aio_fsync $fh, $callback->($status)
		249	aio_fdatasync $fh, $callback->($status)
		250	aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		251	aio_pathsync $pathname, $callback->($status)
		252	aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		253	aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		254	aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
		255	aio_mlockall $flags, $callback->($status)
		256	aio_group $callback->(...)
		257	aio_nop $callback->()
		258
		259	$prev_pri = aioreq_pri [$pri]
		260	aioreq_nice $pri_adjust
		261
		262	IO::AIO::poll_wait
		263	IO::AIO::poll_cb
		264	IO::AIO::poll
		265	IO::AIO::flush
		266	IO::AIO::max_poll_reqs $nreqs
		267	IO::AIO::max_poll_time $seconds
		268	IO::AIO::min_parallel $nthreads
		269	IO::AIO::max_parallel $nthreads
		270	IO::AIO::max_idle $nthreads
		271	IO::AIO::idle_timeout $seconds
		272	IO::AIO::max_outstanding $maxreqs
		273	IO::AIO::nreqs
		274	IO::AIO::nready
		275	IO::AIO::npending
		276
		277	IO::AIO::sendfile $ofh, $ifh, $offset, $count
		278	IO::AIO::fadvise $fh, $offset, $len, $advice
		279	IO::AIO::mmap $scalar, $length, $prot, $flags[, $fh[, $offset]]
		280	IO::AIO::munmap $scalar
		281	IO::AIO::madvise $scalar, $offset, $length, $advice
		282	IO::AIO::mprotect $scalar, $offset, $length, $protect
		283	IO::AIO::munlock $scalar, $offset = 0, $length = undef
		284	IO::AIO::munlockall
		285
		286	=head2 API NOTES
216		287
217	All the C<aio_*> calls are more or less thin wrappers around the syscall	288	All the C<aio_*> calls are more or less thin wrappers around the syscall
218	with the same name (sans C<aio_>). The arguments are similar or identical,	289	with the same name (sans C<aio_>). The arguments are similar or identical,
219	and they all accept an additional (and optional) C<$callback> argument	290	and they all accept an additional (and optional) C<$callback> argument
220	which must be a code reference. This code reference will get called with	291	which must be a code reference. This code reference will be called after
221	the syscall return code (e.g. most syscalls return C<-1> on error, unlike	292	the syscall has been executed in an asynchronous fashion. The results
222	perl, which usually delivers "false") as it's sole argument when the given	293	of the request will be passed as arguments to the callback (and, if an
223	syscall has been executed asynchronously.	294	error occured, in C<$!>) - for most requests the syscall return code (e.g.
		295	most syscalls return C<-1> on error, unlike perl, which usually delivers
		296	"false").
		297
		298	Some requests (such as C<aio_readdir>) pass the actual results and
		299	communicate failures by passing C<undef>.
224		300
225	All functions expecting a filehandle keep a copy of the filehandle	301	All functions expecting a filehandle keep a copy of the filehandle
226	internally until the request has finished.	302	internally until the request has finished.
227		303
228	All functions return request objects of type L<IO::AIO::REQ> that allow	304	All functions return request objects of type L<IO::AIO::REQ> that allow
229	further manipulation of those requests while they are in-flight.	305	further manipulation of those requests while they are in-flight.
230		306
231	The pathnames you pass to these routines I<must> be absolute and	307	The pathnames you pass to these routines I<should> be absolute. The
232	encoded as octets. The reason for the former is that at the time the	308	reason for this is that at the time the request is being executed, the
233	request is being executed, the current working directory could have	309	current working directory could have changed. Alternatively, you can
234	changed. Alternatively, you can make sure that you never change the	310	make sure that you never change the current working directory anywhere
235	current working directory anywhere in the program and then use relative	311	in the program and then use relative paths. You can also take advantage
236	paths.	312	of IO::AIOs working directory abstraction, that lets you specify paths
		313	relative to some previously-opened "working directory object" - see the
		314	description of the C<IO::AIO::WD> class later in this document.
237		315
238	To encode pathnames as octets, either make sure you either: a) always pass	316	To encode pathnames as octets, either make sure you either: a) always pass
239	in filenames you got from outside (command line, readdir etc.) without	317	in filenames you got from outside (command line, readdir etc.) without
240	tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module and encode	318	tinkering, b) are in your native filesystem encoding, c) use the Encode
241	your pathnames to the locale (or other) encoding in effect in the user	319	module and encode your pathnames to the locale (or other) encoding in
242	environment, d) use Glib::filename_from_unicode on unicode filenames or e)	320	effect in the user environment, d) use Glib::filename_from_unicode on
243	use something else to ensure your scalar has the correct contents.	321	unicode filenames or e) use something else to ensure your scalar has the
		322	correct contents.
244		323
245	This works, btw. independent of the internal UTF-8 bit, which IO::AIO	324	This works, btw. independent of the internal UTF-8 bit, which IO::AIO
246	handles correctly wether it is set or not.	325	handles correctly whether it is set or not.
		326
		327	=head2 AIO REQUEST FUNCTIONS
247		328
248	=over 4	329	=over 4
249		330
250	=item $prev_pri = aioreq_pri [$pri]	331	=item $prev_pri = aioreq_pri [$pri]
251		332
…		…
281		362
282		363
283	=item aio_open $pathname, $flags, $mode, $callback->($fh)	364	=item aio_open $pathname, $flags, $mode, $callback->($fh)
284		365
285	Asynchronously open or create a file and call the callback with a newly	366	Asynchronously open or create a file and call the callback with a newly
286	created filehandle for the file.	367	created filehandle for the file (or C<undef> in case of an error).
287		368
288	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,	369	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,
289	for an explanation.	370	for an explanation.
290		371
291	The C<$flags> argument is a bitmask. See the C<Fcntl> module for a	372	The C<$flags> argument is a bitmask. See the C<Fcntl> module for a
…		…
298	by the umask in effect then the request is being executed, so better never	379	by the umask in effect then the request is being executed, so better never
299	change the umask.	380	change the umask.
300		381
301	Example:	382	Example:
302		383
303	aio_open "/etc/passwd", O_RDONLY, 0, sub {	384	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
304	if ($_[0]) {	385	if ($_[0]) {
305	print "open successful, fh is $_[0]\n";	386	print "open successful, fh is $_[0]\n";
306	...	387	...
307	} else {	388	} else {
308	die "open failed: $!\n";	389	die "open failed: $!\n";
309	}	390	}
310	};	391	};
311		392
		393	In addition to all the common open modes/flags (C<O_RDONLY>, C<O_WRONLY>,
		394	C<O_RDWR>, C<O_CREAT>, C<O_TRUNC>, C<O_EXCL> and C<O_APPEND>), the
		395	following POSIX and non-POSIX constants are available (missing ones on
		396	your system are, as usual, C<0>):
		397
		398	C<O_ASYNC>, C<O_DIRECT>, C<O_NOATIME>, C<O_CLOEXEC>, C<O_NOCTTY>, C<O_NOFOLLOW>,
		399	C<O_NONBLOCK>, C<O_EXEC>, C<O_SEARCH>, C<O_DIRECTORY>, C<O_DSYNC>,
		400	C<O_RSYNC>, C<O_SYNC> and C<O_TTY_INIT>.
		401
312		402
313	=item aio_close $fh, $callback->($status)	403	=item aio_close $fh, $callback->($status)
314		404
315	Asynchronously close a file and call the callback with the result	405	Asynchronously close a file and call the callback with the result
316	code. I<WARNING:> although accepted, you should not pass in a perl	406	code.
317	filehandle here, as perl will likely close the file descriptor another
318	time when the filehandle is destroyed. Normally, you can safely call perls
319	C<close> or just let filehandles go out of scope.
320		407
321	This is supposed to be a bug in the API, so that might change. It's	408	Unfortunately, you can't do this to perl. Perl I<insists> very strongly on
322	therefore best to avoid this function.	409	closing the file descriptor associated with the filehandle itself.
323		410
		411	Therefore, C<aio_close> will not close the filehandle - instead it will
		412	use dup2 to overwrite the file descriptor with the write-end of a pipe
		413	(the pipe fd will be created on demand and will be cached).
		414
		415	Or in other words: the file descriptor will be closed, but it will not be
		416	free for reuse until the perl filehandle is closed.
		417
		418	=cut
		419
		420	=item aio_seek $fh, $offset, $whence, $callback->($offs)
		421
		422	Seeks the filehandle to the new C<$offset>, similarly to perl's
		423	C<sysseek>. The C<$whence> can use the traditional values (C<0> for
		424	C<IO::AIO::SEEK_SET>, C<1> for C<IO::AIO::SEEK_CUR> or C<2> for
		425	C<IO::AIO::SEEK_END>).
		426
		427	The resulting absolute offset will be passed to the callback, or C<-1> in
		428	case of an error.
		429
		430	In theory, the C<$whence> constants could be different than the
		431	corresponding values from L<Fcntl>, but perl guarantees they are the same,
		432	so don't panic.
		433
		434	As a GNU/Linux (and maybe Solaris) extension, also the constants
		435	C<IO::AIO::SEEK_DATA> and C<IO::AIO::SEEK_HOLE> are available, if they
		436	could be found. No guarantees about suitability for use in C<aio_seek> or
		437	Perl's C<sysseek> can be made though, although I would naively assume they
		438	"just work".
324		439
325	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	440	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
326		441
327	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	442	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
328		443
329	Reads or writes C<$length> bytes from the specified C<$fh> and C<$offset>	444	Reads or writes C<$length> bytes from or to the specified C<$fh> and
330	into the scalar given by C<$data> and offset C<$dataoffset> and calls the	445	C<$offset> into the scalar given by C<$data> and offset C<$dataoffset>
331	callback without the actual number of bytes read (or -1 on error, just	446	and calls the callback without the actual number of bytes read (or -1 on
332	like the syscall).	447	error, just like the syscall).
333		448
		449	C<aio_read> will, like C<sysread>, shrink or grow the C<$data> scalar to
		450	offset plus the actual number of bytes read.
		451
334	If C<$offset> is undefined, then the current file offset will be used (and	452	If C<$offset> is undefined, then the current file descriptor offset will
335	updated), otherwise the file offset will not be changed by these calls.	453	be used (and updated), otherwise the file descriptor offset will not be
		454	changed by these calls.
336		455
337	If C<$length> is undefined in C<aio_write>, use the remaining length of C<$data>.	456	If C<$length> is undefined in C<aio_write>, use the remaining length of
		457	C<$data>.
338		458
339	If C<$dataoffset> is less than zero, it will be counted from the end of	459	If C<$dataoffset> is less than zero, it will be counted from the end of
340	C<$data>.	460	C<$data>.
341		461
342	The C<$data> scalar I<MUST NOT> be modified in any way while the request	462	The C<$data> scalar I<MUST NOT> be modified in any way while the request
…		…
356		476
357	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts	477	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
358	reading at byte offset C<$in_offset>, and starts writing at the current	478	reading at byte offset C<$in_offset>, and starts writing at the current
359	file offset of C<$out_fh>. Because of that, it is not safe to issue more	479	file offset of C<$out_fh>. Because of that, it is not safe to issue more
360	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each	480	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each
361	other.	481	other. The same C<$in_fh> works fine though, as this function does not
		482	move or use the file offset of C<$in_fh>.
362		483
		484	Please note that C<aio_sendfile> can read more bytes from C<$in_fh> than
		485	are written, and there is no way to find out how many more bytes have been
		486	read from C<aio_sendfile> alone, as C<aio_sendfile> only provides the
		487	number of bytes written to C<$out_fh>. Only if the result value equals
		488	C<$length> one can assume that C<$length> bytes have been read.
		489
		490	Unlike with other C<aio_> functions, it makes a lot of sense to use
		491	C<aio_sendfile> on non-blocking sockets, as long as one end (typically
		492	the C<$in_fh>) is a file - the file I/O will then be asynchronous, while
		493	the socket I/O will be non-blocking. Note, however, that you can run
		494	into a trap where C<aio_sendfile> reads some data with readahead, then
		495	fails to write all data, and when the socket is ready the next time, the
		496	data in the cache is already lost, forcing C<aio_sendfile> to again hit
		497	the disk. Explicit C<aio_read> + C<aio_write> let's you better control
		498	resource usage.
		499
363	This call tries to make use of a native C<sendfile> syscall to provide	500	This call tries to make use of a native C<sendfile>-like syscall to
364	zero-copy operation. For this to work, C<$out_fh> should refer to a	501	provide zero-copy operation. For this to work, C<$out_fh> should refer to
365	socket, and C<$in_fh> should refer to mmap'able file.	502	a socket, and C<$in_fh> should refer to an mmap'able file.
366		503
367	If the native sendfile call fails or is not implemented, it will be	504	If a native sendfile cannot be found or it fails with C<ENOSYS>,
368	emulated, so you can call C<aio_sendfile> on any type of filehandle	505	C<EINVAL>, C<ENOTSUP>, C<EOPNOTSUPP>, C<EAFNOSUPPORT>, C<EPROTOTYPE> or
		506	C<ENOTSOCK>, it will be emulated, so you can call C<aio_sendfile> on any
369	regardless of the limitations of the operating system.	507	type of filehandle regardless of the limitations of the operating system.
370		508
371	Please note, however, that C<aio_sendfile> can read more bytes from	509	As native sendfile syscalls (as practically any non-POSIX interface hacked
372	C<$in_fh> than are written, and there is no way to find out how many	510	together in a hurry to improve benchmark numbers) tend to be rather buggy
373	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only	511	on many systems, this implementation tries to work around some known bugs
374	provides the number of bytes written to C<$out_fh>. Only if the result	512	in Linux and FreeBSD kernels (probably others, too), but that might fail,
375	value equals C<$length> one can assume that C<$length> bytes have been	513	so you really really should check the return value of C<aio_sendfile> -
376	read.	514	fewre bytes than expected might have been transferred.
377		515
378		516
379	=item aio_readahead $fh,$offset,$length, $callback->($retval)	517	=item aio_readahead $fh,$offset,$length, $callback->($retval)
380		518
381	C<aio_readahead> populates the page cache with data from a file so that	519	C<aio_readahead> populates the page cache with data from a file so that
…		…
404		542
405	Currently, the stats are always 64-bit-stats, i.e. instead of returning an	543	Currently, the stats are always 64-bit-stats, i.e. instead of returning an
406	error when stat'ing a large file, the results will be silently truncated	544	error when stat'ing a large file, the results will be silently truncated
407	unless perl itself is compiled with large file support.	545	unless perl itself is compiled with large file support.
408		546
		547	To help interpret the mode and dev/rdev stat values, IO::AIO offers the
		548	following constants and functions (if not implemented, the constants will
		549	be C<0> and the functions will either C<croak> or fall back on traditional
		550	behaviour).
		551
		552	C<S_IFMT>, C<S_IFIFO>, C<S_IFCHR>, C<S_IFBLK>, C<S_IFLNK>, C<S_IFREG>,
		553	C<S_IFDIR>, C<S_IFWHT>, C<S_IFSOCK>, C<IO::AIO::major $dev_t>,
		554	C<IO::AIO::minor $dev_t>, C<IO::AIO::makedev $major, $minor>.
		555
409	Example: Print the length of F</etc/passwd>:	556	Example: Print the length of F</etc/passwd>:
410		557
411	aio_stat "/etc/passwd", sub {	558	aio_stat "/etc/passwd", sub {
412	$_[0] and die "stat failed: $!";	559	$_[0] and die "stat failed: $!";
413	print "size is ", -s _, "\n";	560	print "size is ", -s _, "\n";
414	};	561	};
415		562
416		563
		564	=item aio_statvfs $fh_or_path, $callback->($statvfs)
		565
		566	Works like the POSIX C<statvfs> or C<fstatvfs> syscalls, depending on
		567	whether a file handle or path was passed.
		568
		569	On success, the callback is passed a hash reference with the following
		570	members: C<bsize>, C<frsize>, C<blocks>, C<bfree>, C<bavail>, C<files>,
		571	C<ffree>, C<favail>, C<fsid>, C<flag> and C<namemax>. On failure, C<undef>
		572	is passed.
		573
		574	The following POSIX IO::AIO::ST_* constants are defined: C<ST_RDONLY> and
		575	C<ST_NOSUID>.
		576
		577	The following non-POSIX IO::AIO::ST_* flag masks are defined to
		578	their correct value when available, or to C<0> on systems that do
		579	not support them: C<ST_NODEV>, C<ST_NOEXEC>, C<ST_SYNCHRONOUS>,
		580	C<ST_MANDLOCK>, C<ST_WRITE>, C<ST_APPEND>, C<ST_IMMUTABLE>, C<ST_NOATIME>,
		581	C<ST_NODIRATIME> and C<ST_RELATIME>.
		582
		583	Example: stat C</wd> and dump out the data if successful.
		584
		585	aio_statvfs "/wd", sub {
		586	my $f = $_[0]
		587	or die "statvfs: $!";
		588
		589	use Data::Dumper;
		590	say Dumper $f;
		591	};
		592
		593	# result:
		594	{
		595	bsize => 1024,
		596	bfree => 4333064312,
		597	blocks => 10253828096,
		598	files => 2050765568,
		599	flag => 4096,
		600	favail => 2042092649,
		601	bavail => 4333064312,
		602	ffree => 2042092649,
		603	namemax => 255,
		604	frsize => 1024,
		605	fsid => 1810
		606	}
		607
		608
417	=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)	609	=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
418		610
419	Works like perl's C<utime> function (including the special case of $atime	611	Works like perl's C<utime> function (including the special case of $atime
420	and $mtime being undef). Fractional times are supported if the underlying	612	and $mtime being undef). Fractional times are supported if the underlying
421	syscalls support them.	613	syscalls support them.
…		…
448	=item aio_truncate $fh_or_path, $offset, $callback->($status)	640	=item aio_truncate $fh_or_path, $offset, $callback->($status)
449		641
450	Works like truncate(2) or ftruncate(2).	642	Works like truncate(2) or ftruncate(2).
451		643
452		644
		645	=item aio_allocate $fh, $mode, $offset, $len, $callback->($status)
		646
		647	Allocates or freed disk space according to the C<$mode> argument. See the
		648	linux C<fallocate> docuemntation for details.
		649
		650	C<$mode> can currently be C<0> or C<IO::AIO::FALLOC_FL_KEEP_SIZE>
		651	to allocate space, or C<IO::AIO::FALLOC_FL_PUNCH_HOLE |
		652	IO::AIO::FALLOC_FL_KEEP_SIZE>, to deallocate a file range.
		653
		654	The file system block size used by C<fallocate> is presumably the
		655	C<f_bsize> returned by C<statvfs>.
		656
		657	If C<fallocate> isn't available or cannot be emulated (currently no
		658	emulation will be attempted), passes C<-1> and sets C<$!> to C<ENOSYS>.
		659
		660
453	=item aio_chmod $fh_or_path, $mode, $callback->($status)	661	=item aio_chmod $fh_or_path, $mode, $callback->($status)
454		662
455	Works like perl's C<chmod> function.	663	Works like perl's C<chmod> function.
456		664
457		665
…		…
459		667
460	Asynchronously unlink (delete) a file and call the callback with the	668	Asynchronously unlink (delete) a file and call the callback with the
461	result code.	669	result code.
462		670
463		671
464	=item aio_mknod $path, $mode, $dev, $callback->($status)	672	=item aio_mknod $pathname, $mode, $dev, $callback->($status)
465		673
466	[EXPERIMENTAL]	674	[EXPERIMENTAL]
467		675
468	Asynchronously create a device node (or fifo). See mknod(2).	676	Asynchronously create a device node (or fifo). See mknod(2).
469		677
470	The only (POSIX-) portable way of calling this function is:	678	The only (POSIX-) portable way of calling this function is:
471		679
472	aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ...	680	aio_mknod $pathname, IO::AIO::S_IFIFO | $mode, 0, sub { ...
473		681
		682	See C<aio_stat> for info about some potentially helpful extra constants
		683	and functions.
474		684
475	=item aio_link $srcpath, $dstpath, $callback->($status)	685	=item aio_link $srcpath, $dstpath, $callback->($status)
476		686
477	Asynchronously create a new link to the existing object at C<$srcpath> at	687	Asynchronously create a new link to the existing object at C<$srcpath> at
478	the path C<$dstpath> and call the callback with the result code.	688	the path C<$dstpath> and call the callback with the result code.
…		…
482		692
483	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at	693	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at
484	the path C<$dstpath> and call the callback with the result code.	694	the path C<$dstpath> and call the callback with the result code.
485		695
486		696
487	=item aio_readlink $path, $callback->($link)	697	=item aio_readlink $pathname, $callback->($link)
488		698
489	Asynchronously read the symlink specified by C<$path> and pass it to	699	Asynchronously read the symlink specified by C<$path> and pass it to
490	the callback. If an error occurs, nothing or undef gets passed to the	700	the callback. If an error occurs, nothing or undef gets passed to the
491	callback.	701	callback.
492		702
493		703
		704	=item aio_realpath $pathname, $callback->($path)
		705
		706	Asynchronously make the path absolute and resolve any symlinks in
		707	C<$path>. The resulting path only consists of directories (Same as
		708	L<Cwd::realpath>).
		709
		710	This request can be used to get the absolute path of the current working
		711	directory by passing it a path of F<.> (a single dot).
		712
		713
494	=item aio_rename $srcpath, $dstpath, $callback->($status)	714	=item aio_rename $srcpath, $dstpath, $callback->($status)
495		715
496	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as	716	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as
497	rename(2) and call the callback with the result code.	717	rename(2) and call the callback with the result code.
498		718
…		…
514		734
515	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire	735	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
516	directory (i.e. opendir + readdir + closedir). The entries will not be	736	directory (i.e. opendir + readdir + closedir). The entries will not be
517	sorted, and will B<NOT> include the C<.> and C<..> entries.	737	sorted, and will B<NOT> include the C<.> and C<..> entries.
518		738
519	The callback a single argument which is either C<undef> or an array-ref	739	The callback is passed a single argument which is either C<undef> or an
520	with the filenames.	740	array-ref with the filenames.
521		741
522		742
		743	=item aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		744
		745	Quite similar to C<aio_readdir>, but the C<$flags> argument allows one to
		746	tune behaviour and output format. In case of an error, C<$entries> will be
		747	C<undef>.
		748
		749	The flags are a combination of the following constants, ORed together (the
		750	flags will also be passed to the callback, possibly modified):
		751
		752	=over 4
		753
		754	=item IO::AIO::READDIR_DENTS
		755
		756	When this flag is off, then the callback gets an arrayref consisting of
		757	names only (as with C<aio_readdir>), otherwise it gets an arrayref with
		758	C<[$name, $type, $inode]> arrayrefs, each describing a single directory
		759	entry in more detail.
		760
		761	C<$name> is the name of the entry.
		762
		763	C<$type> is one of the C<IO::AIO::DT_xxx> constants:
		764
		765	C<IO::AIO::DT_UNKNOWN>, C<IO::AIO::DT_FIFO>, C<IO::AIO::DT_CHR>, C<IO::AIO::DT_DIR>,
		766	C<IO::AIO::DT_BLK>, C<IO::AIO::DT_REG>, C<IO::AIO::DT_LNK>, C<IO::AIO::DT_SOCK>,
		767	C<IO::AIO::DT_WHT>.
		768
		769	C<IO::AIO::DT_UNKNOWN> means just that: readdir does not know. If you need to
		770	know, you have to run stat yourself. Also, for speed reasons, the C<$type>
		771	scalars are read-only: you can not modify them.
		772
		773	C<$inode> is the inode number (which might not be exact on systems with 64
		774	bit inode numbers and 32 bit perls). This field has unspecified content on
		775	systems that do not deliver the inode information.
		776
		777	=item IO::AIO::READDIR_DIRS_FIRST
		778
		779	When this flag is set, then the names will be returned in an order where
		780	likely directories come first, in optimal stat order. This is useful when
		781	you need to quickly find directories, or you want to find all directories
		782	while avoiding to stat() each entry.
		783
		784	If the system returns type information in readdir, then this is used
		785	to find directories directly. Otherwise, likely directories are names
		786	beginning with ".", or otherwise names with no dots, of which names with
		787	short names are tried first.
		788
		789	=item IO::AIO::READDIR_STAT_ORDER
		790
		791	When this flag is set, then the names will be returned in an order
		792	suitable for stat()'ing each one. That is, when you plan to stat()
		793	all files in the given directory, then the returned order will likely
		794	be fastest.
		795
		796	If both this flag and C<IO::AIO::READDIR_DIRS_FIRST> are specified, then
		797	the likely dirs come first, resulting in a less optimal stat order.
		798
		799	=item IO::AIO::READDIR_FOUND_UNKNOWN
		800
		801	This flag should not be set when calling C<aio_readdirx>. Instead, it
		802	is being set by C<aio_readdirx>, when any of the C<$type>'s found were
		803	C<IO::AIO::DT_UNKNOWN>. The absence of this flag therefore indicates that all
		804	C<$type>'s are known, which can be used to speed up some algorithms.
		805
		806	=back
		807
		808
523	=item aio_load $path, $data, $callback->($status)	809	=item aio_load $pathname, $data, $callback->($status)
524		810
525	This is a composite request that tries to fully load the given file into	811	This is a composite request that tries to fully load the given file into
526	memory. Status is the same as with aio_read.	812	memory. Status is the same as with aio_read.
527		813
528	=cut	814	=cut
529		815
530	sub aio_load($$;$) {	816	sub aio_load($$;$) {
531	aio_block {
532	my ($path, undef, $cb) = @_;	817	my ($path, undef, $cb) = @_;
533	my $data = \$_[1];	818	my $data = \$_[1];
534		819
535	my $pri = aioreq_pri;	820	my $pri = aioreq_pri;
536	my $grp = aio_group $cb;	821	my $grp = aio_group $cb;
		822
		823	aioreq_pri $pri;
		824	add $grp aio_open $path, O_RDONLY, 0, sub {
		825	my $fh = shift
		826	or return $grp->result (-1);
537		827
538	aioreq_pri $pri;	828	aioreq_pri $pri;
539	add $grp aio_open $path, O_RDONLY, 0, sub {
540	my $fh = shift
541	or return $grp->result (-1);
542
543	aioreq_pri $pri;
544	add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub {	829	add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub {
545	$grp->result ($_[0]);	830	$grp->result ($_[0]);
546	};
547	};	831	};
548
549	$grp
550	}	832	};
		833
		834	$grp
551	}	835	}
552		836
553	=item aio_copy $srcpath, $dstpath, $callback->($status)	837	=item aio_copy $srcpath, $dstpath, $callback->($status)
554		838
555	Try to copy the I<file> (directories not supported as either source or	839	Try to copy the I<file> (directories not supported as either source or
556	destination) from C<$srcpath> to C<$dstpath> and call the callback with	840	destination) from C<$srcpath> to C<$dstpath> and call the callback with
557	the C<0> (error) or C<-1> ok.	841	a status of C<0> (ok) or C<-1> (error, see C<$!>).
558		842
559	This is a composite request that it creates the destination file with	843	This is a composite request that creates the destination file with
560	mode 0200 and copies the contents of the source file into it using	844	mode 0200 and copies the contents of the source file into it using
561	C<aio_sendfile>, followed by restoring atime, mtime, access mode and	845	C<aio_sendfile>, followed by restoring atime, mtime, access mode and
562	uid/gid, in that order.	846	uid/gid, in that order.
563		847
564	If an error occurs, the partial destination file will be unlinked, if	848	If an error occurs, the partial destination file will be unlinked, if
…		…
566	errors are being ignored.	850	errors are being ignored.
567		851
568	=cut	852	=cut
569		853
570	sub aio_copy($$;$) {	854	sub aio_copy($$;$) {
571	aio_block {
572	my ($src, $dst, $cb) = @_;	855	my ($src, $dst, $cb) = @_;
573		856
574	my $pri = aioreq_pri;	857	my $pri = aioreq_pri;
575	my $grp = aio_group $cb;	858	my $grp = aio_group $cb;
576		859
577	aioreq_pri $pri;	860	aioreq_pri $pri;
578	add $grp aio_open $src, O_RDONLY, 0, sub {	861	add $grp aio_open $src, O_RDONLY, 0, sub {
579	if (my $src_fh = $_[0]) {	862	if (my $src_fh = $_[0]) {
580	my @stat = stat $src_fh;	863	my @stat = stat $src_fh; # hmm, might block over nfs?
581		864
582	aioreq_pri $pri;	865	aioreq_pri $pri;
583	add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {	866	add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {
584	if (my $dst_fh = $_[0]) {	867	if (my $dst_fh = $_[0]) {
585	aioreq_pri $pri;	868	aioreq_pri $pri;
586	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {	869	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
587	if ($_[0] == $stat[7]) {	870	if ($_[0] == $stat[7]) {
588	$grp->result (0);	871	$grp->result (0);
589	close $src_fh;	872	close $src_fh;
590		873
591	# those should not normally block. should. should.
592	utime $stat[8], $stat[9], $dst;
593	chmod $stat[2] & 07777, $dst_fh;
594	chown $stat[4], $stat[5], $dst_fh;
595	close $dst_fh;
596	} else {	874	my $ch = sub {
597	$grp->result (-1);
598	close $src_fh;
599	close $dst_fh;
600
601	aioreq $pri;	875	aioreq_pri $pri;
		876	add $grp aio_chmod $dst_fh, $stat[2] & 07777, sub {
		877	aioreq_pri $pri;
		878	add $grp aio_chown $dst_fh, $stat[4], $stat[5], sub {
		879	aioreq_pri $pri;
602	add $grp aio_unlink $dst;	880	add $grp aio_close $dst_fh;
		881	}
		882	};
603	}	883	};
		884
		885	aioreq_pri $pri;
		886	add $grp aio_utime $dst_fh, $stat[8], $stat[9], sub {
		887	if ($_[0] < 0 && $! == ENOSYS) {
		888	aioreq_pri $pri;
		889	add $grp aio_utime $dst, $stat[8], $stat[9], $ch;
		890	} else {
		891	$ch->();
		892	}
		893	};
		894	} else {
		895	$grp->result (-1);
		896	close $src_fh;
		897	close $dst_fh;
		898
		899	aioreq $pri;
		900	add $grp aio_unlink $dst;
604	};	901	}
605	} else {
606	$grp->result (-1);
607	}	902	};
		903	} else {
		904	$grp->result (-1);
608	},	905	}
609
610	} else {
611	$grp->result (-1);
612	}	906	},
		907
		908	} else {
		909	$grp->result (-1);
613	};	910	}
614
615	$grp
616	}	911	};
		912
		913	$grp
617	}	914	}
618		915
619	=item aio_move $srcpath, $dstpath, $callback->($status)	916	=item aio_move $srcpath, $dstpath, $callback->($status)
620		917
621	Try to move the I<file> (directories not supported as either source or	918	Try to move the I<file> (directories not supported as either source or
622	destination) from C<$srcpath> to C<$dstpath> and call the callback with	919	destination) from C<$srcpath> to C<$dstpath> and call the callback with
623	the C<0> (error) or C<-1> ok.	920	a status of C<0> (ok) or C<-1> (error, see C<$!>).
624		921
625	This is a composite request that tries to rename(2) the file first. If	922	This is a composite request that tries to rename(2) the file first; if
626	rename files with C<EXDEV>, it copies the file with C<aio_copy> and, if	923	rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if
627	that is successful, unlinking the C<$srcpath>.	924	that is successful, unlinks the C<$srcpath>.
628		925
629	=cut	926	=cut
630		927
631	sub aio_move($$;$) {	928	sub aio_move($$;$) {
632	aio_block {
633	my ($src, $dst, $cb) = @_;	929	my ($src, $dst, $cb) = @_;
634		930
635	my $pri = aioreq_pri;	931	my $pri = aioreq_pri;
636	my $grp = aio_group $cb;	932	my $grp = aio_group $cb;
637		933
638	aioreq_pri $pri;	934	aioreq_pri $pri;
639	add $grp aio_rename $src, $dst, sub {	935	add $grp aio_rename $src, $dst, sub {
640	if ($_[0] && $! == EXDEV) {	936	if ($_[0] && $! == EXDEV) {
641	aioreq_pri $pri;	937	aioreq_pri $pri;
642	add $grp aio_copy $src, $dst, sub {	938	add $grp aio_copy $src, $dst, sub {
643	$grp->result ($_[0]);
644
645	if (!$_[0]) {
646	aioreq_pri $pri;
647	add $grp aio_unlink $src;
648	}
649	};
650	} else {
651	$grp->result ($_[0]);	939	$grp->result ($_[0]);
		940
		941	unless ($_[0]) {
		942	aioreq_pri $pri;
		943	add $grp aio_unlink $src;
		944	}
652	}	945	};
		946	} else {
		947	$grp->result ($_[0]);
653	};	948	}
654
655	$grp
656	}	949	};
		950
		951	$grp
657	}	952	}
658		953
659	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)	954	=item aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs)
660		955
661	Scans a directory (similar to C<aio_readdir>) but additionally tries to	956	Scans a directory (similar to C<aio_readdir>) but additionally tries to
662	efficiently separate the entries of directory C<$path> into two sets of	957	efficiently separate the entries of directory C<$path> into two sets of
663	names, directories you can recurse into (directories), and ones you cannot	958	names, directories you can recurse into (directories), and ones you cannot
664	recurse into (everything else, including symlinks to directories).	959	recurse into (everything else, including symlinks to directories).
…		…
681		976
682	Implementation notes.	977	Implementation notes.
683		978
684	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.	979	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.
685		980
		981	If readdir returns file type information, then this is used directly to
		982	find directories.
		983
686	After reading the directory, the modification time, size etc. of the	984	Otherwise, after reading the directory, the modification time, size etc.
687	directory before and after the readdir is checked, and if they match (and	985	of the directory before and after the readdir is checked, and if they
688	isn't the current time), the link count will be used to decide how many	986	match (and isn't the current time), the link count will be used to decide
689	entries are directories (if >= 2). Otherwise, no knowledge of the number	987	how many entries are directories (if >= 2). Otherwise, no knowledge of the
690	of subdirectories will be assumed.	988	number of subdirectories will be assumed.
691		989
692	Then entries will be sorted into likely directories (everything without	990	Then entries will be sorted into likely directories a non-initial dot
693	a non-initial dot currently) and likely non-directories (everything	991	currently) and likely non-directories (see C<aio_readdirx>). Then every
694	else). Then every entry plus an appended C</.> will be C<stat>'ed,	992	entry plus an appended C</.> will be C<stat>'ed, likely directories first,
695	likely directories first. If that succeeds, it assumes that the entry	993	in order of their inode numbers. If that succeeds, it assumes that the
696	is a directory or a symlink to directory (which will be checked	994	entry is a directory or a symlink to directory (which will be checked
697	seperately). This is often faster than stat'ing the entry itself because	995	separately). This is often faster than stat'ing the entry itself because
698	filesystems might detect the type of the entry without reading the inode	996	filesystems might detect the type of the entry without reading the inode
699	data (e.g. ext2fs filetype feature).	997	data (e.g. ext2fs filetype feature), even on systems that cannot return
		998	the filetype information on readdir.
700		999
701	If the known number of directories (link count - 2) has been reached, the	1000	If the known number of directories (link count - 2) has been reached, the
702	rest of the entries is assumed to be non-directories.	1001	rest of the entries is assumed to be non-directories.
703		1002
704	This only works with certainty on POSIX (= UNIX) filesystems, which	1003	This only works with certainty on POSIX (= UNIX) filesystems, which
…		…
709	directory counting heuristic.	1008	directory counting heuristic.
710		1009
711	=cut	1010	=cut
712		1011
713	sub aio_scandir($$;$) {	1012	sub aio_scandir($$;$) {
714	aio_block {
715	my ($path, $maxreq, $cb) = @_;	1013	my ($path, $maxreq, $cb) = @_;
716		1014
717	my $pri = aioreq_pri;	1015	my $pri = aioreq_pri;
718		1016
719	my $grp = aio_group $cb;	1017	my $grp = aio_group $cb;
720		1018
721	$maxreq = 4 if $maxreq <= 0;	1019	$maxreq = 4 if $maxreq <= 0;
		1020
		1021	# get a wd object
		1022	aioreq_pri $pri;
		1023	add $grp aio_wd $path, sub {
		1024	$_[0]
		1025	or return $grp->result ();
		1026
		1027	my $wd = [shift, "."];
722		1028
723	# stat once	1029	# stat once
724	aioreq_pri $pri;	1030	aioreq_pri $pri;
725	add $grp aio_stat $path, sub {	1031	add $grp aio_stat $wd, sub {
726	return $grp->result () if $_[0];	1032	return $grp->result () if $_[0];
727	my $now = time;	1033	my $now = time;
728	my $hash1 = join ":", (stat _)[0,1,3,7,9];	1034	my $hash1 = join ":", (stat _)[0,1,3,7,9];
729		1035
730	# read the directory entries	1036	# read the directory entries
731	aioreq_pri $pri;	1037	aioreq_pri $pri;
732	add $grp aio_readdir $path, sub {	1038	add $grp aio_readdirx $wd, READDIR_DIRS_FIRST, sub {
733	my $entries = shift	1039	my $entries = shift
734	or return $grp->result ();	1040	or return $grp->result ();
735		1041
736	# stat the dir another time	1042	# stat the dir another time
737	aioreq_pri $pri;	1043	aioreq_pri $pri;
738	add $grp aio_stat $path, sub {	1044	add $grp aio_stat $wd, sub {
739	my $hash2 = join ":", (stat _)[0,1,3,7,9];	1045	my $hash2 = join ":", (stat _)[0,1,3,7,9];
740		1046
741	my $ndirs;	1047	my $ndirs;
742		1048
743	# take the slow route if anything looks fishy	1049	# take the slow route if anything looks fishy
744	if ($hash1 ne $hash2 or (stat _)[9] == $now) {	1050	if ($hash1 ne $hash2 or (stat _)[9] == $now) {
745	$ndirs = -1;	1051	$ndirs = -1;
746	} else {	1052	} else {
747	# if nlink == 2, we are finished	1053	# if nlink == 2, we are finished
748	# on non-posix-fs's, we rely on nlink < 2	1054	# for non-posix-fs's, we rely on nlink < 2
749	$ndirs = (stat _)[3] - 2	1055	$ndirs = (stat _)[3] - 2
750	or return $grp->result ([], $entries);	1056	or return $grp->result ([], $entries);
751	}	1057	}
752		1058
753	# sort into likely dirs and likely nondirs
754	# dirs == files without ".", short entries first
755	$entries = [map $_->[0],
756	sort { $b->[1] cmp $a->[1] }
757	map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],
758	@$entries];
759
760	my (@dirs, @nondirs);	1059	my (@dirs, @nondirs);
761		1060
762	my $statgrp = add $grp aio_group sub {	1061	my $statgrp = add $grp aio_group sub {
763	$grp->result (\@dirs, \@nondirs);	1062	$grp->result (\@dirs, \@nondirs);
764	};	1063	};
765		1064
766	limit $statgrp $maxreq;	1065	limit $statgrp $maxreq;
767	feed $statgrp sub {	1066	feed $statgrp sub {
768	return unless @$entries;	1067	return unless @$entries;
769	my $entry = pop @$entries;	1068	my $entry = shift @$entries;
770		1069
771	aioreq_pri $pri;	1070	aioreq_pri $pri;
		1071	$wd->[1] = "$entry/.";
772	add $statgrp aio_stat "$path/$entry/.", sub {	1072	add $statgrp aio_stat $wd, sub {
773	if ($_[0] < 0) {	1073	if ($_[0] < 0) {
774	push @nondirs, $entry;	1074	push @nondirs, $entry;
775	} else {	1075	} else {
776	# need to check for real directory	1076	# need to check for real directory
777	aioreq_pri $pri;	1077	aioreq_pri $pri;
		1078	$wd->[1] = $entry;
778	add $statgrp aio_lstat "$path/$entry", sub {	1079	add $statgrp aio_lstat $wd, sub {
779	if (-d _) {	1080	if (-d _) {
780	push @dirs, $entry;	1081	push @dirs, $entry;
781		1082
782	unless (--$ndirs) {	1083	unless (--$ndirs) {
783	push @nondirs, @$entries;	1084	push @nondirs, @$entries;
…		…
791	};	1092	};
792	};	1093	};
793	};	1094	};
794	};	1095	};
795	};	1096	};
796
797	$grp
798	}	1097	};
		1098
		1099	$grp
799	}	1100	}
800		1101
801	=item aio_rmtree $path, $callback->($status)	1102	=item aio_rmtree $pathname, $callback->($status)
802		1103
803	Delete a directory tree starting (and including) C<$path>, return the	1104	Delete a directory tree starting (and including) C<$path>, return the
804	status of the final C<rmdir> only. This is a composite request that	1105	status of the final C<rmdir> only. This is a composite request that
805	uses C<aio_scandir> to recurse into and rmdir directories, and unlink	1106	uses C<aio_scandir> to recurse into and rmdir directories, and unlink
806	everything else.	1107	everything else.
807		1108
808	=cut	1109	=cut
809		1110
810	sub aio_rmtree;	1111	sub aio_rmtree;
811	sub aio_rmtree($;$) {	1112	sub aio_rmtree($;$) {
812	aio_block {
813	my ($path, $cb) = @_;	1113	my ($path, $cb) = @_;
814		1114
815	my $pri = aioreq_pri;	1115	my $pri = aioreq_pri;
816	my $grp = aio_group $cb;	1116	my $grp = aio_group $cb;
817		1117
818	aioreq_pri $pri;	1118	aioreq_pri $pri;
819	add $grp aio_scandir $path, 0, sub {	1119	add $grp aio_scandir $path, 0, sub {
820	my ($dirs, $nondirs) = @_;	1120	my ($dirs, $nondirs) = @_;
821		1121
822	my $dirgrp = aio_group sub {	1122	my $dirgrp = aio_group sub {
823	add $grp aio_rmdir $path, sub {	1123	add $grp aio_rmdir $path, sub {
824	$grp->result ($_[0]);	1124	$grp->result ($_[0]);
825	};
826	};	1125	};
827
828	(aioreq_pri $pri), add $dirgrp aio_rmtree "$path/$_" for @$dirs;
829	(aioreq_pri $pri), add $dirgrp aio_unlink "$path/$_" for @$nondirs;
830
831	add $grp $dirgrp;
832	};	1126	};
833		1127
834	$grp	1128	(aioreq_pri $pri), add $dirgrp aio_rmtree "$path/$_" for @$dirs;
		1129	(aioreq_pri $pri), add $dirgrp aio_unlink "$path/$_" for @$nondirs;
		1130
		1131	add $grp $dirgrp;
835	}	1132	};
		1133
		1134	$grp
836	}	1135	}
		1136
		1137	=item aio_sync $callback->($status)
		1138
		1139	Asynchronously call sync and call the callback when finished.
837		1140
838	=item aio_fsync $fh, $callback->($status)	1141	=item aio_fsync $fh, $callback->($status)
839		1142
840	Asynchronously call fsync on the given filehandle and call the callback	1143	Asynchronously call fsync on the given filehandle and call the callback
841	with the fsync result code.	1144	with the fsync result code.
…		…
845	Asynchronously call fdatasync on the given filehandle and call the	1148	Asynchronously call fdatasync on the given filehandle and call the
846	callback with the fdatasync result code.	1149	callback with the fdatasync result code.
847		1150
848	If this call isn't available because your OS lacks it or it couldn't be	1151	If this call isn't available because your OS lacks it or it couldn't be
849	detected, it will be emulated by calling C<fsync> instead.	1152	detected, it will be emulated by calling C<fsync> instead.
		1153
		1154	=item aio_syncfs $fh, $callback->($status)
		1155
		1156	Asynchronously call the syncfs syscall to sync the filesystem associated
		1157	to the given filehandle and call the callback with the syncfs result
		1158	code. If syncfs is not available, calls sync(), but returns C<-1> and sets
		1159	errno to C<ENOSYS> nevertheless.
		1160
		1161	=item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		1162
		1163	Sync the data portion of the file specified by C<$offset> and C<$length>
		1164	to disk (but NOT the metadata), by calling the Linux-specific
		1165	sync_file_range call. If sync_file_range is not available or it returns
		1166	ENOSYS, then fdatasync or fsync is being substituted.
		1167
		1168	C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>,
		1169	C<IO::AIO::SYNC_FILE_RANGE_WRITE> and
		1170	C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range
		1171	manpage for details.
		1172
		1173	=item aio_pathsync $pathname, $callback->($status)
		1174
		1175	This request tries to open, fsync and close the given path. This is a
		1176	composite request intended to sync directories after directory operations
		1177	(E.g. rename). This might not work on all operating systems or have any
		1178	specific effect, but usually it makes sure that directory changes get
		1179	written to disc. It works for anything that can be opened for read-only,
		1180	not just directories.
		1181
		1182	Future versions of this function might fall back to other methods when
		1183	C<fsync> on the directory fails (such as calling C<sync>).
		1184
		1185	Passes C<0> when everything went ok, and C<-1> on error.
		1186
		1187	=cut
		1188
		1189	sub aio_pathsync($;$) {
		1190	my ($path, $cb) = @_;
		1191
		1192	my $pri = aioreq_pri;
		1193	my $grp = aio_group $cb;
		1194
		1195	aioreq_pri $pri;
		1196	add $grp aio_open $path, O_RDONLY, 0, sub {
		1197	my ($fh) = @_;
		1198	if ($fh) {
		1199	aioreq_pri $pri;
		1200	add $grp aio_fsync $fh, sub {
		1201	$grp->result ($_[0]);
		1202
		1203	aioreq_pri $pri;
		1204	add $grp aio_close $fh;
		1205	};
		1206	} else {
		1207	$grp->result (-1);
		1208	}
		1209	};
		1210
		1211	$grp
		1212	}
		1213
		1214	=item aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		1215
		1216	This is a rather advanced IO::AIO call, which only works on mmap(2)ed
		1217	scalars (see the C<IO::AIO::mmap> function, although it also works on data
		1218	scalars managed by the L<Sys::Mmap> or L<Mmap> modules, note that the
		1219	scalar must only be modified in-place while an aio operation is pending on
		1220	it).
		1221
		1222	It calls the C<msync> function of your OS, if available, with the memory
		1223	area starting at C<$offset> in the string and ending C<$length> bytes
		1224	later. If C<$length> is negative, counts from the end, and if C<$length>
		1225	is C<undef>, then it goes till the end of the string. The flags can be
		1226	a combination of C<IO::AIO::MS_ASYNC>, C<IO::AIO::MS_INVALIDATE> and
		1227	C<IO::AIO::MS_SYNC>.
		1228
		1229	=item aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		1230
		1231	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1232	scalars.
		1233
		1234	It touches (reads or writes) all memory pages in the specified
		1235	range inside the scalar. All caveats and parameters are the same
		1236	as for C<aio_msync>, above, except for flags, which must be either
		1237	C<0> (which reads all pages and ensures they are instantiated) or
		1238	C<IO::AIO::MT_MODIFY>, which modifies the memory page s(by reading and
		1239	writing an octet from it, which dirties the page).
		1240
		1241	=item aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
		1242
		1243	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1244	scalars.
		1245
		1246	It reads in all the pages of the underlying storage into memory (if any)
		1247	and locks them, so they are not getting swapped/paged out or removed.
		1248
		1249	If C<$length> is undefined, then the scalar will be locked till the end.
		1250
		1251	On systems that do not implement C<mlock>, this function returns C<-1>
		1252	and sets errno to C<ENOSYS>.
		1253
		1254	Note that the corresponding C<munlock> is synchronous and is
		1255	documented under L<MISCELLANEOUS FUNCTIONS>.
		1256
		1257	Example: open a file, mmap and mlock it - both will be undone when
		1258	C<$data> gets destroyed.
		1259
		1260	open my $fh, "<", $path or die "$path: $!";
		1261	my $data;
		1262	IO::AIO::mmap $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh;
		1263	aio_mlock $data; # mlock in background
		1264
		1265	=item aio_mlockall $flags, $callback->($status)
		1266
		1267	Calls the C<mlockall> function with the given C<$flags> (a combination of
		1268	C<IO::AIO::MCL_CURRENT> and C<IO::AIO::MCL_FUTURE>).
		1269
		1270	On systems that do not implement C<mlockall>, this function returns C<-1>
		1271	and sets errno to C<ENOSYS>.
		1272
		1273	Note that the corresponding C<munlockall> is synchronous and is
		1274	documented under L<MISCELLANEOUS FUNCTIONS>.
		1275
		1276	Example: asynchronously lock all current and future pages into memory.
		1277
		1278	aio_mlockall IO::AIO::MCL_FUTURE;
		1279
		1280	=item aio_fiemap $fh, $start, $length, $flags, $count, $cb->(\@extents)
		1281
		1282	Queries the extents of the given file (by calling the Linux FIEMAP ioctl,
		1283	see L<http://cvs.schmorp.de/IO-AIO/doc/fiemap.txt> for details). If the
		1284	C<ioctl> is not available on your OS, then this request will fail with
		1285	C<ENOSYS>.
		1286
		1287	C<$start> is the starting offset to query extents for, C<$length> is the
		1288	size of the range to query - if it is C<undef>, then the whole file will
		1289	be queried.
		1290
		1291	C<$flags> is a combination of flags (C<IO::AIO::FIEMAP_FLAG_SYNC> or
		1292	C<IO::AIO::FIEMAP_FLAG_XATTR> - C<IO::AIO::FIEMAP_FLAGS_COMPAT> is also
		1293	exported), and is normally C<0> or C<IO::AIO::FIEMAP_FLAG_SYNC> to query
		1294	the data portion.
		1295
		1296	C<$count> is the maximum number of extent records to return. If it is
		1297	C<undef>, then IO::AIO queries all extents of the range. As a very special
		1298	case, if it is C<0>, then the callback receives the number of extents
		1299	instead of the extents themselves (which is unreliable, see below).
		1300
		1301	If an error occurs, the callback receives no arguments. The special
		1302	C<errno> value C<IO::AIO::EBADR> is available to test for flag errors.
		1303
		1304	Otherwise, the callback receives an array reference with extent
		1305	structures. Each extent structure is an array reference itself, with the
		1306	following members:
		1307
		1308	[$logical, $physical, $length, $flags]
		1309
		1310	Flags is any combination of the following flag values (typically either C<0>
		1311	or C<IO::AIO::FIEMAP_EXTENT_LAST> (1)):
		1312
		1313	C<IO::AIO::FIEMAP_EXTENT_LAST>, C<IO::AIO::FIEMAP_EXTENT_UNKNOWN>,
		1314	C<IO::AIO::FIEMAP_EXTENT_DELALLOC>, C<IO::AIO::FIEMAP_EXTENT_ENCODED>,
		1315	C<IO::AIO::FIEMAP_EXTENT_DATA_ENCRYPTED>, C<IO::AIO::FIEMAP_EXTENT_NOT_ALIGNED>,
		1316	C<IO::AIO::FIEMAP_EXTENT_DATA_INLINE>, C<IO::AIO::FIEMAP_EXTENT_DATA_TAIL>,
		1317	C<IO::AIO::FIEMAP_EXTENT_UNWRITTEN>, C<IO::AIO::FIEMAP_EXTENT_MERGED> or
		1318	C<IO::AIO::FIEMAP_EXTENT_SHARED>.
		1319
		1320	At the time of this writing (Linux 3.2), this requets is unreliable unless
		1321	C<$count> is C<undef>, as the kernel has all sorts of bugs preventing
		1322	it to return all extents of a range for files with large number of
		1323	extents. The code works around all these issues if C<$count> is undef.
850		1324
851	=item aio_group $callback->(...)	1325	=item aio_group $callback->(...)
852		1326
853	This is a very special aio request: Instead of doing something, it is a	1327	This is a very special aio request: Instead of doing something, it is a
854	container for other aio requests, which is useful if you want to bundle	1328	container for other aio requests, which is useful if you want to bundle
…		…
892	immense (it blocks a thread for a long time) so do not use this function	1366	immense (it blocks a thread for a long time) so do not use this function
893	except to put your application under artificial I/O pressure.	1367	except to put your application under artificial I/O pressure.
894		1368
895	=back	1369	=back
896		1370
		1371
		1372	=head2 IO::AIO::WD - multiple working directories
		1373
		1374	Your process only has one current working directory, which is used by all
		1375	threads. This makes it hard to use relative paths (some other component
		1376	could call C<chdir> at any time, and it is hard to control when the path
		1377	will be used by IO::AIO).
		1378
		1379	One solution for this is to always use absolute paths. This usually works,
		1380	but can be quite slow (the kernel has to walk the whole path on every
		1381	access), and can also be a hassle to implement.
		1382
		1383	Newer POSIX systems have a number of functions (openat, fdopendir,
		1384	futimensat and so on) that make it possible to specify working directories
		1385	per operation.
		1386
		1387	For portability, and because the clowns who "designed", or shall I write,
		1388	perpetrated this new interface were obviously half-drunk, this abstraction
		1389	cannot be perfect, though.
		1390
		1391	IO::AIO allows you to convert directory paths into a so-called IO::AIO::WD
		1392	object. This object stores the canonicalised, absolute version of the
		1393	path, and on systems that allow it, also a directory file descriptor.
		1394
		1395	Everywhere where a pathname is accepted by IO::AIO (e.g. in C<aio_stat>
		1396	or C<aio_unlink>), one can specify an array reference with an IO::AIO::WD
		1397	object and a pathname instead (or the IO::AIO::WD object alone, which
		1398	gets interpreted as C<[$wd, "."]>). If the pathname is absolute, the
		1399	IO::AIO::WD object is ignored, otherwise the pathname is resolved relative
		1400	to that IO::AIO::WD object.
		1401
		1402	For example, to get a wd object for F</etc> and then stat F<passwd>
		1403	inside, you would write:
		1404
		1405	aio_wd "/etc", sub {
		1406	my $etcdir = shift;
		1407
		1408	# although $etcdir can be undef on error, there is generally no reason
		1409	# to check for errors here, as aio_stat will fail with ENOENT
		1410	# when $etcdir is undef.
		1411
		1412	aio_stat [$etcdir, "passwd"], sub {
		1413	# yay
		1414	};
		1415	};
		1416
		1417	That C<aio_wd> is a request and not a normal function shows that creating
		1418	an IO::AIO::WD object is itself a potentially blocking operation, which is
		1419	why it is done asynchronously.
		1420
		1421	To stat the directory obtained with C<aio_wd> above, one could write
		1422	either of the following three request calls:
		1423
		1424	aio_lstat "/etc" , sub { ... # pathname as normal string
		1425	aio_lstat [$wd, "."], sub { ... # "." relative to $wd (i.e. $wd itself)
		1426	aio_lstat $wd , sub { ... # shorthand for the previous
		1427
		1428	As with normal pathnames, IO::AIO keeps a copy of the working directory
		1429	object and the pathname string, so you could write the following without
		1430	causing any issues due to C<$path> getting reused:
		1431
		1432	my $path = [$wd, undef];
		1433
		1434	for my $name (qw(abc def ghi)) {
		1435	$path->[1] = $name;
		1436	aio_stat $path, sub {
		1437	# ...
		1438	};
		1439	}
		1440
		1441	There are some caveats: when directories get renamed (or deleted), the
		1442	pathname string doesn't change, so will point to the new directory (or
		1443	nowhere at all), while the directory fd, if available on the system,
		1444	will still point to the original directory. Most functions accepting a
		1445	pathname will use the directory fd on newer systems, and the string on
		1446	older systems. Some functions (such as realpath) will always rely on the
		1447	string form of the pathname.
		1448
		1449	So this fucntionality is mainly useful to get some protection against
		1450	C<chdir>, to easily get an absolute path out of a relative path for future
		1451	reference, and to speed up doing many operations in the same directory
		1452	(e.g. when stat'ing all files in a directory).
		1453
		1454	The following functions implement this working directory abstraction:
		1455
		1456	=over 4
		1457
		1458	=item aio_wd $pathname, $callback->($wd)
		1459
		1460	Asynchonously canonicalise the given pathname and convert it to an
		1461	IO::AIO::WD object representing it. If possible and supported on the
		1462	system, also open a directory fd to speed up pathname resolution relative
		1463	to this working directory.
		1464
		1465	If something goes wrong, then C<undef> is passwd to the callback instead
		1466	of a working directory object and C<$!> is set appropriately. Since
		1467	passing C<undef> as working directory component of a pathname fails the
		1468	request with C<ENOENT>, there is often no need for error checking in the
		1469	C<aio_wd> callback, as future requests using the value will fail in the
		1470	expected way.
		1471
		1472	If this call isn't available because your OS lacks it or it couldn't be
		1473	detected, it will be emulated by calling C<fsync> instead.
		1474
		1475	=item IO::AIO::CWD
		1476
		1477	This is a compiletime constant (object) that represents the process
		1478	current working directory.
		1479
		1480	Specifying this object as working directory object for a pathname is as
		1481	if the pathname would be specified directly, without a directory object,
		1482	e.g., these calls are functionally identical:
		1483
		1484	aio_stat "somefile", sub { ... };
		1485	aio_stat [IO::AIO::CWD, "somefile"], sub { ... };
		1486
		1487	=back
		1488
		1489
897	=head2 IO::AIO::REQ CLASS	1490	=head2 IO::AIO::REQ CLASS
898		1491
899	All non-aggregate C<aio_*> functions return an object of this class when	1492	All non-aggregate C<aio_*> functions return an object of this class when
900	called in non-void context.	1493	called in non-void context.
901		1494
…		…
904	=item cancel $req	1497	=item cancel $req
905		1498
906	Cancels the request, if possible. Has the effect of skipping execution	1499	Cancels the request, if possible. Has the effect of skipping execution
907	when entering the B<execute> state and skipping calling the callback when	1500	when entering the B<execute> state and skipping calling the callback when
908	entering the the B<result> state, but will leave the request otherwise	1501	entering the the B<result> state, but will leave the request otherwise
909	untouched. That means that requests that currently execute will not be	1502	untouched (with the exception of readdir). That means that requests that
910	stopped and resources held by the request will not be freed prematurely.	1503	currently execute will not be stopped and resources held by the request
		1504	will not be freed prematurely.
911		1505
912	=item cb $req $callback->(...)	1506	=item cb $req $callback->(...)
913		1507
914	Replace (or simply set) the callback registered to the request.	1508	Replace (or simply set) the callback registered to the request.
915		1509
…		…
966	Their lifetime, simplified, looks like this: when they are empty, they	1560	Their lifetime, simplified, looks like this: when they are empty, they
967	will finish very quickly. If they contain only requests that are in the	1561	will finish very quickly. If they contain only requests that are in the
968	C<done> state, they will also finish. Otherwise they will continue to	1562	C<done> state, they will also finish. Otherwise they will continue to
969	exist.	1563	exist.
970		1564
971	That means after creating a group you have some time to add requests. And	1565	That means after creating a group you have some time to add requests
972	in the callbacks of those requests, you can add further requests to the	1566	(precisely before the callback has been invoked, which is only done within
973	group. And only when all those requests have finished will the the group	1567	the C<poll_cb>). And in the callbacks of those requests, you can add
974	itself finish.	1568	further requests to the group. And only when all those requests have
		1569	finished will the the group itself finish.
975		1570
976	=over 4	1571	=over 4
977		1572
978	=item add $grp ...	1573	=item add $grp ...
979		1574
…		…
988	=item $grp->cancel_subs	1583	=item $grp->cancel_subs
989		1584
990	Cancel all subrequests and clears any feeder, but not the group request	1585	Cancel all subrequests and clears any feeder, but not the group request
991	itself. Useful when you queued a lot of events but got a result early.	1586	itself. Useful when you queued a lot of events but got a result early.
992		1587
		1588	The group request will finish normally (you cannot add requests to the
		1589	group).
		1590
993	=item $grp->result (...)	1591	=item $grp->result (...)
994		1592
995	Set the result value(s) that will be passed to the group callback when all	1593	Set the result value(s) that will be passed to the group callback when all
996	subrequests have finished and set thre groups errno to the current value	1594	subrequests have finished and set the groups errno to the current value
997	of errno (just like calling C<errno> without an error number). By default,	1595	of errno (just like calling C<errno> without an error number). By default,
998	no argument will be passed and errno is zero.	1596	no argument will be passed and errno is zero.
999		1597
1000	=item $grp->errno ([$errno])	1598	=item $grp->errno ([$errno])
1001		1599
…		…
1012	=item feed $grp $callback->($grp)	1610	=item feed $grp $callback->($grp)
1013		1611
1014	Sets a feeder/generator on this group: every group can have an attached	1612	Sets a feeder/generator on this group: every group can have an attached
1015	generator that generates requests if idle. The idea behind this is that,	1613	generator that generates requests if idle. The idea behind this is that,
1016	although you could just queue as many requests as you want in a group,	1614	although you could just queue as many requests as you want in a group,
1017	this might starve other requests for a potentially long time. For	1615	this might starve other requests for a potentially long time. For example,
1018	example, C<aio_scandir> might generate hundreds of thousands C<aio_stat>	1616	C<aio_scandir> might generate hundreds of thousands of C<aio_stat>
1019	requests, delaying any later requests for a long time.	1617	requests, delaying any later requests for a long time.
1020		1618
1021	To avoid this, and allow incremental generation of requests, you can	1619	To avoid this, and allow incremental generation of requests, you can
1022	instead a group and set a feeder on it that generates those requests. The	1620	instead a group and set a feeder on it that generates those requests. The
1023	feed callback will be called whenever there are few enough (see C<limit>,	1621	feed callback will be called whenever there are few enough (see C<limit>,
…		…
1028	not impose any limits).	1626	not impose any limits).
1029		1627
1030	If the feed does not queue more requests when called, it will be	1628	If the feed does not queue more requests when called, it will be
1031	automatically removed from the group.	1629	automatically removed from the group.
1032		1630
1033	If the feed limit is C<0>, it will be set to C<2> automatically.	1631	If the feed limit is C<0> when this method is called, it will be set to
		1632	C<2> automatically.
1034		1633
1035	Example:	1634	Example:
1036		1635
1037	# stat all files in @files, but only ever use four aio requests concurrently:	1636	# stat all files in @files, but only ever use four aio requests concurrently:
1038		1637
…		…
1050	Sets the feeder limit for the group: The feeder will be called whenever	1649	Sets the feeder limit for the group: The feeder will be called whenever
1051	the group contains less than this many requests.	1650	the group contains less than this many requests.
1052		1651
1053	Setting the limit to C<0> will pause the feeding process.	1652	Setting the limit to C<0> will pause the feeding process.
1054		1653
		1654	The default value for the limit is C<0>, but note that setting a feeder
		1655	automatically bumps it up to C<2>.
		1656
1055	=back	1657	=back
1056		1658
1057	=head2 SUPPORT FUNCTIONS	1659	=head2 SUPPORT FUNCTIONS
1058		1660
1059	=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION	1661	=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION
…		…
1061	=over 4	1663	=over 4
1062		1664
1063	=item $fileno = IO::AIO::poll_fileno	1665	=item $fileno = IO::AIO::poll_fileno
1064		1666
1065	Return the I<request result pipe file descriptor>. This filehandle must be	1667	Return the I<request result pipe file descriptor>. This filehandle must be
1066	polled for reading by some mechanism outside this module (e.g. Event or	1668	polled for reading by some mechanism outside this module (e.g. EV, Glib,
1067	select, see below or the SYNOPSIS). If the pipe becomes readable you have	1669	select and so on, see below or the SYNOPSIS). If the pipe becomes readable
1068	to call C<poll_cb> to check the results.	1670	you have to call C<poll_cb> to check the results.
1069		1671
1070	See C<poll_cb> for an example.	1672	See C<poll_cb> for an example.
1071		1673
1072	=item IO::AIO::poll_cb	1674	=item IO::AIO::poll_cb
1073		1675
1074	Process some outstanding events on the result pipe. You have to call this	1676	Process some outstanding events on the result pipe. You have to call
1075	regularly. Returns the number of events processed. Returns immediately	1677	this regularly. Returns C<0> if all events could be processed (or there
1076	when no events are outstanding. The amount of events processed depends on	1678	were no events to process), or C<-1> if it returned earlier for whatever
1077	the settings of C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>.	1679	reason. Returns immediately when no events are outstanding. The amount of
		1680	events processed depends on the settings of C<IO::AIO::max_poll_req> and
		1681	C<IO::AIO::max_poll_time>.
1078		1682
1079	If not all requests were processed for whatever reason, the filehandle	1683	If not all requests were processed for whatever reason, the filehandle
1080	will still be ready when C<poll_cb> returns.	1684	will still be ready when C<poll_cb> returns, so normally you don't have to
		1685	do anything special to have it called later.
		1686
		1687	Apart from calling C<IO::AIO::poll_cb> when the event filehandle becomes
		1688	ready, it can be beneficial to call this function from loops which submit
		1689	a lot of requests, to make sure the results get processed when they become
		1690	available and not just when the loop is finished and the event loop takes
		1691	over again. This function returns very fast when there are no outstanding
		1692	requests.
1081		1693
1082	Example: Install an Event watcher that automatically calls	1694	Example: Install an Event watcher that automatically calls
1083	IO::AIO::poll_cb with high priority:	1695	IO::AIO::poll_cb with high priority (more examples can be found in the
		1696	SYNOPSIS section, at the top of this document):
1084		1697
1085	Event->io (fd => IO::AIO::poll_fileno,	1698	Event->io (fd => IO::AIO::poll_fileno,
1086	poll => 'r', async => 1,	1699	poll => 'r', async => 1,
1087	cb => \&IO::AIO::poll_cb);	1700	cb => \&IO::AIO::poll_cb);
		1701
		1702	=item IO::AIO::poll_wait
		1703
		1704	If there are any outstanding requests and none of them in the result
		1705	phase, wait till the result filehandle becomes ready for reading (simply
		1706	does a C<select> on the filehandle. This is useful if you want to
		1707	synchronously wait for some requests to finish).
		1708
		1709	See C<nreqs> for an example.
		1710
		1711	=item IO::AIO::poll
		1712
		1713	Waits until some requests have been handled.
		1714
		1715	Returns the number of requests processed, but is otherwise strictly
		1716	equivalent to:
		1717
		1718	IO::AIO::poll_wait, IO::AIO::poll_cb
		1719
		1720	=item IO::AIO::flush
		1721
		1722	Wait till all outstanding AIO requests have been handled.
		1723
		1724	Strictly equivalent to:
		1725
		1726	IO::AIO::poll_wait, IO::AIO::poll_cb
		1727	while IO::AIO::nreqs;
1088		1728
1089	=item IO::AIO::max_poll_reqs $nreqs	1729	=item IO::AIO::max_poll_reqs $nreqs
1090		1730
1091	=item IO::AIO::max_poll_time $seconds	1731	=item IO::AIO::max_poll_time $seconds
1092		1732
…		…
1117	# use a low priority so other tasks have priority	1757	# use a low priority so other tasks have priority
1118	Event->io (fd => IO::AIO::poll_fileno,	1758	Event->io (fd => IO::AIO::poll_fileno,
1119	poll => 'r', nice => 1,	1759	poll => 'r', nice => 1,
1120	cb => &IO::AIO::poll_cb);	1760	cb => &IO::AIO::poll_cb);
1121		1761
1122	=item IO::AIO::poll_wait
1123
1124	If there are any outstanding requests and none of them in the result
1125	phase, wait till the result filehandle becomes ready for reading (simply
1126	does a C<select> on the filehandle. This is useful if you want to
1127	synchronously wait for some requests to finish).
1128
1129	See C<nreqs> for an example.
1130
1131	=item IO::AIO::poll
1132
1133	Waits until some requests have been handled.
1134
1135	Returns the number of requests processed, but is otherwise strictly
1136	equivalent to:
1137
1138	IO::AIO::poll_wait, IO::AIO::poll_cb
1139
1140	=item IO::AIO::flush
1141
1142	Wait till all outstanding AIO requests have been handled.
1143
1144	Strictly equivalent to:
1145
1146	IO::AIO::poll_wait, IO::AIO::poll_cb
1147	while IO::AIO::nreqs;
1148
1149	=back	1762	=back
1150		1763
1151	=head3 CONTROLLING THE NUMBER OF THREADS	1764	=head3 CONTROLLING THE NUMBER OF THREADS
1152		1765
1153	=over	1766	=over
…		…
1186		1799
1187	Under normal circumstances you don't need to call this function.	1800	Under normal circumstances you don't need to call this function.
1188		1801
1189	=item IO::AIO::max_idle $nthreads	1802	=item IO::AIO::max_idle $nthreads
1190		1803
1191	Limit the number of threads (default: 4) that are allowed to idle (i.e.,	1804	Limit the number of threads (default: 4) that are allowed to idle
1192	threads that did not get a request to process within 10 seconds). That	1805	(i.e., threads that did not get a request to process within the idle
1193	means if a thread becomes idle while C<$nthreads> other threads are also	1806	timeout (default: 10 seconds). That means if a thread becomes idle while
1194	idle, it will free its resources and exit.	1807	C<$nthreads> other threads are also idle, it will free its resources and
		1808	exit.
1195		1809
1196	This is useful when you allow a large number of threads (e.g. 100 or 1000)	1810	This is useful when you allow a large number of threads (e.g. 100 or 1000)
1197	to allow for extremely high load situations, but want to free resources	1811	to allow for extremely high load situations, but want to free resources
1198	under normal circumstances (1000 threads can easily consume 30MB of RAM).	1812	under normal circumstances (1000 threads can easily consume 30MB of RAM).
1199		1813
1200	The default is probably ok in most situations, especially if thread	1814	The default is probably ok in most situations, especially if thread
1201	creation is fast. If thread creation is very slow on your system you might	1815	creation is fast. If thread creation is very slow on your system you might
1202	want to use larger values.	1816	want to use larger values.
1203		1817
		1818	=item IO::AIO::idle_timeout $seconds
		1819
		1820	Sets the minimum idle timeout (default 10) after which worker threads are
		1821	allowed to exit. SEe C<IO::AIO::max_idle>.
		1822
1204	=item $oldmaxreqs = IO::AIO::max_outstanding $maxreqs	1823	=item IO::AIO::max_outstanding $maxreqs
		1824
		1825	Sets the maximum number of outstanding requests to C<$nreqs>. If
		1826	you do queue up more than this number of requests, the next call to
		1827	C<IO::AIO::poll_cb> (and other functions calling C<poll_cb>, such as
		1828	C<IO::AIO::flush> or C<IO::AIO::poll>) will block until the limit is no
		1829	longer exceeded.
		1830
		1831	In other words, this setting does not enforce a queue limit, but can be
		1832	used to make poll functions block if the limit is exceeded.
1205		1833
1206	This is a very bad function to use in interactive programs because it	1834	This is a very bad function to use in interactive programs because it
1207	blocks, and a bad way to reduce concurrency because it is inexact: Better	1835	blocks, and a bad way to reduce concurrency because it is inexact: Better
1208	use an C<aio_group> together with a feed callback.	1836	use an C<aio_group> together with a feed callback.
1209		1837
1210	Sets the maximum number of outstanding requests to C<$nreqs>. If you	1838	It's main use is in scripts without an event loop - when you want to stat
1211	to queue up more than this number of requests, the next call to the	1839	a lot of files, you can write somehting like this:
1212	C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>)
1213	function will block until the limit is no longer exceeded.
1214		1840
1215	The default value is very large, so there is no practical limit on the	1841	IO::AIO::max_outstanding 32;
1216	number of outstanding requests.
1217		1842
1218	You can still queue as many requests as you want. Therefore,	1843	for my $path (...) {
1219	C<max_oustsanding> is mainly useful in simple scripts (with low values) or	1844	aio_stat $path , ...;
1220	as a stop gap to shield against fatal memory overflow (with large values).	1845	IO::AIO::poll_cb;
		1846	}
		1847
		1848	IO::AIO::flush;
		1849
		1850	The call to C<poll_cb> inside the loop will normally return instantly, but
		1851	as soon as more thna C<32> reqeusts are in-flight, it will block until
		1852	some requests have been handled. This keeps the loop from pushing a large
		1853	number of C<aio_stat> requests onto the queue.
		1854
		1855	The default value for C<max_outstanding> is very large, so there is no
		1856	practical limit on the number of outstanding requests.
1221		1857
1222	=back	1858	=back
1223		1859
1224	=head3 STATISTICAL INFORMATION	1860	=head3 STATISTICAL INFORMATION
1225		1861
…		…
1245	Returns the number of requests currently in the pending state (executed,	1881	Returns the number of requests currently in the pending state (executed,
1246	but not yet processed by poll_cb).	1882	but not yet processed by poll_cb).
1247		1883
1248	=back	1884	=back
1249		1885
		1886	=head3 MISCELLANEOUS FUNCTIONS
		1887
		1888	IO::AIO implements some functions that might be useful, but are not
		1889	asynchronous.
		1890
		1891	=over 4
		1892
		1893	=item IO::AIO::sendfile $ofh, $ifh, $offset, $count
		1894
		1895	Calls the C<eio_sendfile_sync> function, which is like C<aio_sendfile>,
		1896	but is blocking (this makes most sense if you know the input data is
		1897	likely cached already and the output filehandle is set to non-blocking
		1898	operations).
		1899
		1900	Returns the number of bytes copied, or C<-1> on error.
		1901
		1902	=item IO::AIO::fadvise $fh, $offset, $len, $advice
		1903
		1904	Simply calls the C<posix_fadvise> function (see its
		1905	manpage for details). The following advice constants are
		1906	available: C<IO::AIO::FADV_NORMAL>, C<IO::AIO::FADV_SEQUENTIAL>,
		1907	C<IO::AIO::FADV_RANDOM>, C<IO::AIO::FADV_NOREUSE>,
		1908	C<IO::AIO::FADV_WILLNEED>, C<IO::AIO::FADV_DONTNEED>.
		1909
		1910	On systems that do not implement C<posix_fadvise>, this function returns
		1911	ENOSYS, otherwise the return value of C<posix_fadvise>.
		1912
		1913	=item IO::AIO::madvise $scalar, $offset, $len, $advice
		1914
		1915	Simply calls the C<posix_madvise> function (see its
		1916	manpage for details). The following advice constants are
		1917	available: C<IO::AIO::MADV_NORMAL>, C<IO::AIO::MADV_SEQUENTIAL>,
		1918	C<IO::AIO::MADV_RANDOM>, C<IO::AIO::MADV_WILLNEED>, C<IO::AIO::MADV_DONTNEED>.
		1919
		1920	On systems that do not implement C<posix_madvise>, this function returns
		1921	ENOSYS, otherwise the return value of C<posix_madvise>.
		1922
		1923	=item IO::AIO::mprotect $scalar, $offset, $len, $protect
		1924
		1925	Simply calls the C<mprotect> function on the preferably AIO::mmap'ed
		1926	$scalar (see its manpage for details). The following protect
		1927	constants are available: C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_READ>,
		1928	C<IO::AIO::PROT_WRITE>, C<IO::AIO::PROT_EXEC>.
		1929
		1930	On systems that do not implement C<mprotect>, this function returns
		1931	ENOSYS, otherwise the return value of C<mprotect>.
		1932
		1933	=item IO::AIO::mmap $scalar, $length, $prot, $flags, $fh[, $offset]
		1934
		1935	Memory-maps a file (or anonymous memory range) and attaches it to the
		1936	given C<$scalar>, which will act like a string scalar. Returns true on
		1937	success, and false otherwise.
		1938
		1939	The only operations allowed on the scalar are C<substr>/C<vec> that don't
		1940	change the string length, and most read-only operations such as copying it
		1941	or searching it with regexes and so on.
		1942
		1943	Anything else is unsafe and will, at best, result in memory leaks.
		1944
		1945	The memory map associated with the C<$scalar> is automatically removed
		1946	when the C<$scalar> is destroyed, or when the C<IO::AIO::mmap> or
		1947	C<IO::AIO::munmap> functions are called.
		1948
		1949	This calls the C<mmap>(2) function internally. See your system's manual
		1950	page for details on the C<$length>, C<$prot> and C<$flags> parameters.
		1951
		1952	The C<$length> must be larger than zero and smaller than the actual
		1953	filesize.
		1954
		1955	C<$prot> is a combination of C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_EXEC>,
		1956	C<IO::AIO::PROT_READ> and/or C<IO::AIO::PROT_WRITE>,
		1957
		1958	C<$flags> can be a combination of C<IO::AIO::MAP_SHARED> or
		1959	C<IO::AIO::MAP_PRIVATE>, or a number of system-specific flags (when
		1960	not available, the are defined as 0): C<IO::AIO::MAP_ANONYMOUS>
		1961	(which is set to C<MAP_ANON> if your system only provides this
		1962	constant), C<IO::AIO::MAP_HUGETLB>, C<IO::AIO::MAP_LOCKED>,
		1963	C<IO::AIO::MAP_NORESERVE>, C<IO::AIO::MAP_POPULATE> or
		1964	C<IO::AIO::MAP_NONBLOCK>
		1965
		1966	If C<$fh> is C<undef>, then a file descriptor of C<-1> is passed.
		1967
		1968	C<$offset> is the offset from the start of the file - it generally must be
		1969	a multiple of C<IO::AIO::PAGESIZE> and defaults to C<0>.
		1970
		1971	Example:
		1972
		1973	use Digest::MD5;
		1974	use IO::AIO;
		1975
		1976	open my $fh, "<verybigfile"
		1977	or die "$!";
		1978
		1979	IO::AIO::mmap my $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh
		1980	or die "verybigfile: $!";
		1981
		1982	my $fast_md5 = md5 $data;
		1983
		1984	=item IO::AIO::munmap $scalar
		1985
		1986	Removes a previous mmap and undefines the C<$scalar>.
		1987
		1988	=item IO::AIO::munlock $scalar, $offset = 0, $length = undef
		1989
		1990	Calls the C<munlock> function, undoing the effects of a previous
		1991	C<aio_mlock> call (see its description for details).
		1992
		1993	=item IO::AIO::munlockall
		1994
		1995	Calls the C<munlockall> function.
		1996
		1997	On systems that do not implement C<munlockall>, this function returns
		1998	ENOSYS, otherwise the return value of C<munlockall>.
		1999
		2000	=item IO::AIO::splice $r_fh, $r_off, $w_fh, $w_off, $length, $flags
		2001
		2002	Calls the GNU/Linux C<splice(2)> syscall, if available. If C<$r_off> or
		2003	C<$w_off> are C<undef>, then C<NULL> is passed for these, otherwise they
		2004	should be the file offset.
		2005
		2006	C<$r_fh> and C<$w_fh> should not refer to the same file, as splice might
		2007	silently corrupt the data in this case.
		2008
		2009	The following symbol flag values are available: C<IO::AIO::SPLICE_F_MOVE>,
		2010	C<IO::AIO::SPLICE_F_NONBLOCK>, C<IO::AIO::SPLICE_F_MORE> and
		2011	C<IO::AIO::SPLICE_F_GIFT>.
		2012
		2013	See the C<splice(2)> manpage for details.
		2014
		2015	=item IO::AIO::tee $r_fh, $w_fh, $length, $flags
		2016
		2017	Calls the GNU/Linux C<tee(2)> syscall, see it's manpage and the
		2018	description for C<IO::AIO::splice> above for details.
		2019
		2020	=back
		2021
1250	=cut	2022	=cut
1251		2023
1252	# support function to convert a fd into a perl filehandle
1253	sub _fd2fh {
1254	return undef if $_[0] < 0;
1255
1256	# try to generate nice filehandles
1257	my $sym = "IO::AIO::fd#$_[0]";
1258	local *$sym;
1259
1260	open *$sym, "+<&=$_[0]" # usually works under any unix
1261	or open *$sym, "<&=$_[0]" # cygwin needs this
1262	or open *$sym, ">&=$_[0]" # or this
1263	or return undef;
1264
1265	*$sym
1266	}
1267
1268	min_parallel 8;	2024	min_parallel 8;
1269		2025
1270	END { flush }	2026	END { flush }
1271		2027
1272	1;	2028	1;
1273		2029
		2030	=head1 EVENT LOOP INTEGRATION
		2031
		2032	It is recommended to use L<AnyEvent::AIO> to integrate IO::AIO
		2033	automatically into many event loops:
		2034
		2035	# AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...)
		2036	use AnyEvent::AIO;
		2037
		2038	You can also integrate IO::AIO manually into many event loops, here are
		2039	some examples of how to do this:
		2040
		2041	# EV integration
		2042	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
		2043
		2044	# Event integration
		2045	Event->io (fd => IO::AIO::poll_fileno,
		2046	poll => 'r',
		2047	cb => \&IO::AIO::poll_cb);
		2048
		2049	# Glib/Gtk2 integration
		2050	add_watch Glib::IO IO::AIO::poll_fileno,
		2051	in => sub { IO::AIO::poll_cb; 1 };
		2052
		2053	# Tk integration
		2054	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
		2055	readable => \&IO::AIO::poll_cb);
		2056
		2057	# Danga::Socket integration
		2058	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
		2059	\&IO::AIO::poll_cb);
		2060
1274	=head2 FORK BEHAVIOUR	2061	=head2 FORK BEHAVIOUR
1275		2062
1276	This module should do "the right thing" when the process using it forks:	2063	Usage of pthreads in a program changes the semantics of fork
		2064	considerably. Specifically, only async-safe functions can be called after
		2065	fork. Perl doesn't know about this, so in general, you cannot call fork
		2066	with defined behaviour in perl if pthreads are involved. IO::AIO uses
		2067	pthreads, so this applies, but many other extensions and (for inexplicable
		2068	reasons) perl itself often is linked against pthreads, so this limitation
		2069	applies to quite a lot of perls.
1277		2070
1278	Before the fork, IO::AIO enters a quiescent state where no requests	2071	This module no longer tries to fight your OS, or POSIX. That means IO::AIO
1279	can be added in other threads and no results will be processed. After	2072	only works in the process that loaded it. Forking is fully supported, but
1280	the fork the parent simply leaves the quiescent state and continues	2073	using IO::AIO in the child is not.
1281	request/result processing, while the child frees the request/result queue
1282	(so that the requests started before the fork will only be handled in the
1283	parent). Threads will be started on demand until the limit set in the
1284	parent process has been reached again.
1285		2074
1286	In short: the parent will, after a short pause, continue as if fork had	2075	You might get around by not I<using> IO::AIO before (or after)
1287	not been called, while the child will act as if IO::AIO has not been used	2076	forking. You could also try to call the L<IO::AIO::reinit> function in the
1288	yet.	2077	child:
		2078
		2079	=over 4
		2080
		2081	=item IO::AIO::reinit
		2082
		2083	Abandons all current requests and I/O threads and simply reinitialises all
		2084	data structures. This is not an operation supported by any standards, but
		2085	happens to work on GNU/Linux and some newer BSD systems.
		2086
		2087	The only reasonable use for this function is to call it after forking, if
		2088	C<IO::AIO> was used in the parent. Calling it while IO::AIO is active in
		2089	the process will result in undefined behaviour. Calling it at any time
		2090	will also result in any undefined (by POSIX) behaviour.
		2091
		2092	=back
1289		2093
1290	=head2 MEMORY USAGE	2094	=head2 MEMORY USAGE
1291		2095
1292	Per-request usage:	2096	Per-request usage:
1293		2097
…		…
1295	bytes of memory. In addition, stat requests need a stat buffer (possibly	2099	bytes of memory. In addition, stat requests need a stat buffer (possibly
1296	a few hundred bytes), readdir requires a result buffer and so on. Perl	2100	a few hundred bytes), readdir requires a result buffer and so on. Perl
1297	scalars and other data passed into aio requests will also be locked and	2101	scalars and other data passed into aio requests will also be locked and
1298	will consume memory till the request has entered the done state.	2102	will consume memory till the request has entered the done state.
1299		2103
1300	This is now awfully much, so queuing lots of requests is not usually a	2104	This is not awfully much, so queuing lots of requests is not usually a
1301	problem.	2105	problem.
1302		2106
1303	Per-thread usage:	2107	Per-thread usage:
1304		2108
1305	In the execution phase, some aio requests require more memory for	2109	In the execution phase, some aio requests require more memory for
…		…
1310		2114
1311	Known bugs will be fixed in the next release.	2115	Known bugs will be fixed in the next release.
1312		2116
1313	=head1 SEE ALSO	2117	=head1 SEE ALSO
1314		2118
1315	L<Coro::AIO>.	2119	L<AnyEvent::AIO> for easy integration into event loops, L<Coro::AIO> for a
		2120	more natural syntax.
1316		2121
1317	=head1 AUTHOR	2122	=head1 AUTHOR
1318		2123
1319	Marc Lehmann <schmorp@schmorp.de>	2124	Marc Lehmann <schmorp@schmorp.de>
1320	http://home.schmorp.de/	2125	http://home.schmorp.de/

Diff Legend

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