ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/IO-AIO/AIO.pm

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.123 by root, Sat May 10 18:06:41 2008 UTC vs.
Revision 1.241 by root, Fri Dec 28 07:33:41 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 (EV, Event, Glib, Tk, urxvt, pureperl...)
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	# EV integration
36	my $w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
37
38	# Event integration
39	Event->io (fd => IO::AIO::poll_fileno,
40	poll => 'r',
41	cb => \&IO::AIO::poll_cb);
42
43	# Glib/Gtk2 integration
44	add_watch Glib::IO IO::AIO::poll_fileno,
45	in => sub { IO::AIO::poll_cb; 1 };
46
47	# Tk integration
48	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
49	readable => \&IO::AIO::poll_cb);
50
51	# Danga::Socket integration
52	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
53	\&IO::AIO::poll_cb);
54
55	=head1 DESCRIPTION	31	=head1 DESCRIPTION
56		32
57	This module implements asynchronous I/O using whatever means your	33	This module implements asynchronous I/O using whatever means your
58	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>).
59		36
60	Asynchronous means that operations that can normally block your program	37	Asynchronous means that operations that can normally block your program
61	(e.g. reading from disk) will be done asynchronously: the operation	38	(e.g. reading from disk) will be done asynchronously: the operation
62	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
63	is extremely useful for programs that need to stay interactive even	40	is extremely useful for programs that need to stay interactive even
…		…
67	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
68	concurrently.	45	concurrently.
69		46
70	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
71	example sockets), using these functions on file descriptors that	48	example sockets), using these functions on file descriptors that
72	support nonblocking operation (again, sockets, pipes etc.) is very	49	support nonblocking operation (again, sockets, pipes etc.) is
73	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>
74	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.
75		52
76	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
77	requests and signal their completion. You don't need thread support	54	requests and signal their completion. You don't need thread support
78	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
…		…
88	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
89	call C<poll_cb> (or other C<aio_> functions) recursively.	66	call C<poll_cb> (or other C<aio_> functions) recursively.
90		67
91	=head2 EXAMPLE	68	=head2 EXAMPLE
92		69
93	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
94	F</etc/passwd> asynchronously:	71	F</etc/passwd> asynchronously:
95		72
96	use Fcntl;	73	use Fcntl;
97	use Event;	74	use EV;
98	use IO::AIO;	75	use IO::AIO;
99		76
100	# register the IO::AIO callback with Event	77	# register the IO::AIO callback with EV
101	Event->io (fd => IO::AIO::poll_fileno,	78	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
102	poll => 'r',
103	cb => \&IO::AIO::poll_cb);
104		79
105	# queue the request to open /etc/passwd	80	# queue the request to open /etc/passwd
106	aio_open "/etc/passwd", O_RDONLY, 0, sub {	81	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
107	my $fh = shift	82	my $fh = shift
108	or die "error while opening: $!";	83	or die "error while opening: $!";
109		84
110	# stat'ing filehandles is generally non-blocking	85	# stat'ing filehandles is generally non-blocking
111	my $size = -s $fh;	86	my $size = -s $fh;
…		…
120		95
121	# file contents now in $contents	96	# file contents now in $contents
122	print $contents;	97	print $contents;
123		98
124	# exit event loop and program	99	# exit event loop and program
125	Event::unloop;	100	EV::unloop;
126	};	101	};
127	};	102	};
128		103
129	# possibly queue up other requests, or open GUI windows,	104	# possibly queue up other requests, or open GUI windows,
130	# check for sockets etc. etc.	105	# check for sockets etc. etc.
131		106
132	# process events as long as there are some:	107	# process events as long as there are some:
133	Event::loop;	108	EV::loop;
134		109
135	=head1 REQUEST ANATOMY AND LIFETIME	110	=head1 REQUEST ANATOMY AND LIFETIME
136		111
137	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
138	directly visible to Perl.	113	directly visible to Perl.
…		…
188		163
189	package IO::AIO;	164	package IO::AIO;
190		165
191	use Carp ();	166	use Carp ();
192		167
193	no warnings;	168	use common::sense;
194	use strict 'vars';
195		169
196	use base 'Exporter';	170	use base 'Exporter';
197		171
198	BEGIN {	172	BEGIN {
199	our $VERSION = '2.62';	173	our $VERSION = '4.18';
200		174
201	our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close	175	our @AIO_REQ = qw(aio_sendfile aio_seek aio_read aio_write aio_open aio_close
202	aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir	176	aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx
203	aio_scandir aio_symlink aio_readlink aio_sync aio_fsync	177	aio_scandir aio_symlink aio_readlink aio_realpath aio_sync
		178	aio_fsync aio_syncfs aio_fdatasync aio_sync_file_range aio_allocate
204	aio_fdatasync aio_pathsync aio_readahead	179	aio_pathsync aio_readahead aio_fiemap
205	aio_rename aio_link aio_move aio_copy aio_group	180	aio_rename aio_link aio_move aio_copy aio_group
206	aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown	181	aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown
207	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);
208		186
209	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice));	187	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice));
210	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush	188	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush
211	min_parallel max_parallel max_idle	189	min_parallel max_parallel max_idle idle_timeout
212	nreqs nready npending nthreads	190	nreqs nready npending nthreads
213	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
214		196
215	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';	197	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';
216		198
217	require XSLoader;	199	require XSLoader;
218	XSLoader::load ("IO::AIO", $VERSION);	200	XSLoader::load ("IO::AIO", $VERSION);
219	}	201	}
220		202
221	=head1 FUNCTIONS	203	=head1 FUNCTIONS
222		204
223	=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, $length = undef
		284	IO::AIO::munlockall
		285
		286	=head2 API NOTES
224		287
225	All the C<aio_*> calls are more or less thin wrappers around the syscall	288	All the C<aio_*> calls are more or less thin wrappers around the syscall
226	with the same name (sans C<aio_>). The arguments are similar or identical,	289	with the same name (sans C<aio_>). The arguments are similar or identical,
227	and they all accept an additional (and optional) C<$callback> argument	290	and they all accept an additional (and optional) C<$callback> argument
228	which must be a code reference. This code reference will get called with	291	which must be a code reference. This code reference will be called after
229	the syscall return code (e.g. most syscalls return C<-1> on error, unlike	292	the syscall has been executed in an asynchronous fashion. The results
230	perl, which usually delivers "false") as it's sole argument when the given	293	of the request will be passed as arguments to the callback (and, if an
231	syscall has been executed asynchronously.	294	error occured, in C<$!>) - 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>.
232		300
233	All functions expecting a filehandle keep a copy of the filehandle	301	All functions expecting a filehandle keep a copy of the filehandle
234	internally until the request has finished.	302	internally until the request has finished.
235		303
236	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
237	further manipulation of those requests while they are in-flight.	305	further manipulation of those requests while they are in-flight.
238		306
239	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
240	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
241	request is being executed, the current working directory could have	309	current working directory could have changed. Alternatively, you can
242	changed. Alternatively, you can make sure that you never change the	310	make sure that you never change the current working directory anywhere
243	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
244	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.
245		315
246	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
247	in filenames you got from outside (command line, readdir etc.) without	317	in filenames you got from outside (command line, readdir etc.) without
248	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
249	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
250	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
251	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.
252		323
253	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
254	handles correctly wether it is set or not.	325	handles correctly whether it is set or not.
		326
		327	=head2 AIO REQUEST FUNCTIONS
255		328
256	=over 4	329	=over 4
257		330
258	=item $prev_pri = aioreq_pri [$pri]	331	=item $prev_pri = aioreq_pri [$pri]
259		332
…		…
289		362
290		363
291	=item aio_open $pathname, $flags, $mode, $callback->($fh)	364	=item aio_open $pathname, $flags, $mode, $callback->($fh)
292		365
293	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
294	created filehandle for the file.	367	created filehandle for the file (or C<undef> in case of an error).
295		368
296	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,
297	for an explanation.	370	for an explanation.
298		371
299	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
…		…
306	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
307	change the umask.	380	change the umask.
308		381
309	Example:	382	Example:
310		383
311	aio_open "/etc/passwd", O_RDONLY, 0, sub {	384	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
312	if ($_[0]) {	385	if ($_[0]) {
313	print "open successful, fh is $_[0]\n";	386	print "open successful, fh is $_[0]\n";
314	...	387	...
315	} else {	388	} else {
316	die "open failed: $!\n";	389	die "open failed: $!\n";
317	}	390	}
318	};	391	};
319		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
320		402
321	=item aio_close $fh, $callback->($status)	403	=item aio_close $fh, $callback->($status)
322		404
323	Asynchronously close a file and call the callback with the result	405	Asynchronously close a file and call the callback with the result
324	code.	406	code.
…		…
333	Or in other words: the file descriptor will be closed, but it will not be	415	Or in other words: the file descriptor will be closed, but it will not be
334	free for reuse until the perl filehandle is closed.	416	free for reuse until the perl filehandle is closed.
335		417
336	=cut	418	=cut
337		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".
		439
338	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	440	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
339		441
340	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	442	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
341		443
342	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<$fh> and
343	into the scalar given by C<$data> and offset C<$dataoffset> and calls the	445	C<$offset> into the scalar given by C<$data> and offset C<$dataoffset>
344	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
345	like the syscall).	447	error, just like the syscall).
		448
		449	C<aio_read> will, like C<sysread>, shrink or grow the C<$data> scalar to
		450	offset plus the actual number of bytes read.
346		451
347	If C<$offset> is undefined, then the current file descriptor offset will	452	If C<$offset> is undefined, then the current file descriptor offset will
348	be used (and updated), otherwise the file descriptor offset will not be	453	be used (and updated), otherwise the file descriptor offset will not be
349	changed by these calls.	454	changed by these calls.
350		455
351	If C<$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<$data>.
352		458
353	If C<$dataoffset> is less than zero, it will be counted from the end of	459	If C<$dataoffset> is less than zero, it will be counted from the end of
354	C<$data>.	460	C<$data>.
355		461
356	The C<$data> scalar I<MUST NOT> be modified in any way while the request	462	The C<$data> scalar I<MUST NOT> be modified in any way while the request
…		…
370		476
371	Tries to copy C<$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<$out_fh>. It starts
372	reading at byte offset C<$in_offset>, and starts writing at the current	478	reading at byte offset C<$in_offset>, and starts writing at the current
373	file offset of C<$out_fh>. Because of that, it is not safe to issue more	479	file offset of C<$out_fh>. Because of that, it is not safe to issue more
374	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each	480	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each
375	other.	481	other. The same C<$in_fh> works fine though, as this function does not
		482	move or use the file offset of C<$in_fh>.
376		483
		484	Please note that C<aio_sendfile> can read more bytes from C<$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
377	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
378	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
379	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.
380		503
381	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>,
382	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
383	regardless of the limitations of the operating system.	507	type of filehandle regardless of the limitations of the operating system.
384		508
385	Please note, however, that C<aio_sendfile> can read more bytes from	509	As native sendfile syscalls (as practically any non-POSIX interface hacked
386	C<$in_fh> than are written, and there is no way to find out how many	510	together in a hurry to improve benchmark numbers) tend to be rather buggy
387	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only	511	on many systems, this implementation tries to work around some known bugs
388	provides the number of bytes written to C<$out_fh>. Only if the result	512	in Linux and FreeBSD kernels (probably others, too), but that might fail,
389	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> -
390	read.	514	fewre bytes than expected might have been transferred.
391		515
392		516
393	=item aio_readahead $fh,$offset,$length, $callback->($retval)	517	=item aio_readahead $fh,$offset,$length, $callback->($retval)
394		518
395	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
…		…
418		542
419	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
420	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
421	unless perl itself is compiled with large file support.	545	unless perl itself is compiled with large file support.
422		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
423	Example: Print the length of F</etc/passwd>:	556	Example: Print the length of F</etc/passwd>:
424		557
425	aio_stat "/etc/passwd", sub {	558	aio_stat "/etc/passwd", sub {
426	$_[0] and die "stat failed: $!";	559	$_[0] and die "stat failed: $!";
427	print "size is ", -s _, "\n";	560	print "size is ", -s _, "\n";
428	};	561	};
429		562
430		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	Here is a (likely partial) list of fsid values used by Linux - it is safe
		609	to hardcode these when the $^O is C<linux>:
		610
		611	0x0000adf5 adfs
		612	0x0000adff affs
		613	0x5346414f afs
		614	0x09041934 anon-inode filesystem
		615	0x00000187 autofs
		616	0x42465331 befs
		617	0x1badface bfs
		618	0x42494e4d binfmt_misc
		619	0x9123683e btrfs
		620	0x0027e0eb cgroupfs
		621	0xff534d42 cifs
		622	0x73757245 coda
		623	0x012ff7b7 coh
		624	0x28cd3d45 cramfs
		625	0x453dcd28 cramfs-wend (wrong endianness)
		626	0x64626720 debugfs
		627	0x00001373 devfs
		628	0x00001cd1 devpts
		629	0x0000f15f ecryptfs
		630	0x00414a53 efs
		631	0x0000137d ext
		632	0x0000ef53 ext2/ext3
		633	0x0000ef51 ext2
		634	0x00004006 fat
		635	0x65735546 fuseblk
		636	0x65735543 fusectl
		637	0x0bad1dea futexfs
		638	0x01161970 gfs2
		639	0x47504653 gpfs
		640	0x00004244 hfs
		641	0xf995e849 hpfs
		642	0x958458f6 hugetlbfs
		643	0x2bad1dea inotifyfs
		644	0x00009660 isofs
		645	0x000072b6 jffs2
		646	0x3153464a jfs
		647	0x6b414653 k-afs
		648	0x0bd00bd0 lustre
		649	0x0000137f minix
		650	0x0000138f minix 30 char names
		651	0x00002468 minix v2
		652	0x00002478 minix v2 30 char names
		653	0x00004d5a minix v3
		654	0x19800202 mqueue
		655	0x00004d44 msdos
		656	0x0000564c novell
		657	0x00006969 nfs
		658	0x6e667364 nfsd
		659	0x00003434 nilfs
		660	0x5346544e ntfs
		661	0x00009fa1 openprom
		662	0x7461636F ocfs2
		663	0x00009fa0 proc
		664	0x6165676c pstorefs
		665	0x0000002f qnx4
		666	0x858458f6 ramfs
		667	0x52654973 reiserfs
		668	0x00007275 romfs
		669	0x67596969 rpc_pipefs
		670	0x73636673 securityfs
		671	0xf97cff8c selinux
		672	0x0000517b smb
		673	0x534f434b sockfs
		674	0x73717368 squashfs
		675	0x62656572 sysfs
		676	0x012ff7b6 sysv2
		677	0x012ff7b5 sysv4
		678	0x01021994 tmpfs
		679	0x15013346 udf
		680	0x00011954 ufs
		681	0x54190100 ufs byteswapped
		682	0x00009fa2 usbdevfs
		683	0x01021997 v9fs
		684	0xa501fcf5 vxfs
		685	0xabba1974 xenfs
		686	0x012ff7b4 xenix
		687	0x58465342 xfs
		688	0x012fd16d xia
		689
431	=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)	690	=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
432		691
433	Works like perl's C<utime> function (including the special case of $atime	692	Works like perl's C<utime> function (including the special case of $atime
434	and $mtime being undef). Fractional times are supported if the underlying	693	and $mtime being undef). Fractional times are supported if the underlying
435	syscalls support them.	694	syscalls support them.
…		…
462	=item aio_truncate $fh_or_path, $offset, $callback->($status)	721	=item aio_truncate $fh_or_path, $offset, $callback->($status)
463		722
464	Works like truncate(2) or ftruncate(2).	723	Works like truncate(2) or ftruncate(2).
465		724
466		725
		726	=item aio_allocate $fh, $mode, $offset, $len, $callback->($status)
		727
		728	Allocates or freed disk space according to the C<$mode> argument. See the
		729	linux C<fallocate> docuemntation for details.
		730
		731	C<$mode> can currently be C<0> or C<IO::AIO::FALLOC_FL_KEEP_SIZE>
		732	to allocate space, or C<IO::AIO::FALLOC_FL_PUNCH_HOLE |
		733	IO::AIO::FALLOC_FL_KEEP_SIZE>, to deallocate a file range.
		734
		735	The file system block size used by C<fallocate> is presumably the
		736	C<f_bsize> returned by C<statvfs>.
		737
		738	If C<fallocate> isn't available or cannot be emulated (currently no
		739	emulation will be attempted), passes C<-1> and sets C<$!> to C<ENOSYS>.
		740
		741
467	=item aio_chmod $fh_or_path, $mode, $callback->($status)	742	=item aio_chmod $fh_or_path, $mode, $callback->($status)
468		743
469	Works like perl's C<chmod> function.	744	Works like perl's C<chmod> function.
470		745
471		746
…		…
473		748
474	Asynchronously unlink (delete) a file and call the callback with the	749	Asynchronously unlink (delete) a file and call the callback with the
475	result code.	750	result code.
476		751
477		752
478	=item aio_mknod $path, $mode, $dev, $callback->($status)	753	=item aio_mknod $pathname, $mode, $dev, $callback->($status)
479		754
480	[EXPERIMENTAL]	755	[EXPERIMENTAL]
481		756
482	Asynchronously create a device node (or fifo). See mknod(2).	757	Asynchronously create a device node (or fifo). See mknod(2).
483		758
484	The only (POSIX-) portable way of calling this function is:	759	The only (POSIX-) portable way of calling this function is:
485		760
486	aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ...	761	aio_mknod $pathname, IO::AIO::S_IFIFO | $mode, 0, sub { ...
487		762
		763	See C<aio_stat> for info about some potentially helpful extra constants
		764	and functions.
488		765
489	=item aio_link $srcpath, $dstpath, $callback->($status)	766	=item aio_link $srcpath, $dstpath, $callback->($status)
490		767
491	Asynchronously create a new link to the existing object at C<$srcpath> at	768	Asynchronously create a new link to the existing object at C<$srcpath> at
492	the path C<$dstpath> and call the callback with the result code.	769	the path C<$dstpath> and call the callback with the result code.
…		…
496		773
497	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at	774	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at
498	the path C<$dstpath> and call the callback with the result code.	775	the path C<$dstpath> and call the callback with the result code.
499		776
500		777
501	=item aio_readlink $path, $callback->($link)	778	=item aio_readlink $pathname, $callback->($link)
502		779
503	Asynchronously read the symlink specified by C<$path> and pass it to	780	Asynchronously read the symlink specified by C<$path> and pass it to
504	the callback. If an error occurs, nothing or undef gets passed to the	781	the callback. If an error occurs, nothing or undef gets passed to the
505	callback.	782	callback.
506		783
507		784
		785	=item aio_realpath $pathname, $callback->($path)
		786
		787	Asynchronously make the path absolute and resolve any symlinks in
		788	C<$path>. The resulting path only consists of directories (same as
		789	L<Cwd::realpath>).
		790
		791	This request can be used to get the absolute path of the current working
		792	directory by passing it a path of F<.> (a single dot).
		793
		794
508	=item aio_rename $srcpath, $dstpath, $callback->($status)	795	=item aio_rename $srcpath, $dstpath, $callback->($status)
509		796
510	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as	797	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as
511	rename(2) and call the callback with the result code.	798	rename(2) and call the callback with the result code.
		799
		800	On systems that support the AIO::WD working directory abstraction
		801	natively, the case C<[$wd, "."]> as C<$srcpath> is specialcased - instead
		802	of failing, C<rename> is called on the absolute path of C<$wd>.
512		803
513		804
514	=item aio_mkdir $pathname, $mode, $callback->($status)	805	=item aio_mkdir $pathname, $mode, $callback->($status)
515		806
516	Asynchronously mkdir (create) a directory and call the callback with	807	Asynchronously mkdir (create) a directory and call the callback with
…		…
521	=item aio_rmdir $pathname, $callback->($status)	812	=item aio_rmdir $pathname, $callback->($status)
522		813
523	Asynchronously rmdir (delete) a directory and call the callback with the	814	Asynchronously rmdir (delete) a directory and call the callback with the
524	result code.	815	result code.
525		816
		817	On systems that support the AIO::WD working directory abstraction
		818	natively, the case C<[$wd, "."]> is specialcased - instead of failing,
		819	C<rmdir> is called on the absolute path of C<$wd>.
		820
526		821
527	=item aio_readdir $pathname, $callback->($entries)	822	=item aio_readdir $pathname, $callback->($entries)
528		823
529	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire	824	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
530	directory (i.e. opendir + readdir + closedir). The entries will not be	825	directory (i.e. opendir + readdir + closedir). The entries will not be
531	sorted, and will B<NOT> include the C<.> and C<..> entries.	826	sorted, and will B<NOT> include the C<.> and C<..> entries.
532		827
533	The callback a single argument which is either C<undef> or an array-ref	828	The callback is passed a single argument which is either C<undef> or an
534	with the filenames.	829	array-ref with the filenames.
535		830
536		831
		832	=item aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		833
		834	Quite similar to C<aio_readdir>, but the C<$flags> argument allows one to
		835	tune behaviour and output format. In case of an error, C<$entries> will be
		836	C<undef>.
		837
		838	The flags are a combination of the following constants, ORed together (the
		839	flags will also be passed to the callback, possibly modified):
		840
		841	=over 4
		842
		843	=item IO::AIO::READDIR_DENTS
		844
		845	When this flag is off, then the callback gets an arrayref consisting of
		846	names only (as with C<aio_readdir>), otherwise it gets an arrayref with
		847	C<[$name, $type, $inode]> arrayrefs, each describing a single directory
		848	entry in more detail.
		849
		850	C<$name> is the name of the entry.
		851
		852	C<$type> is one of the C<IO::AIO::DT_xxx> constants:
		853
		854	C<IO::AIO::DT_UNKNOWN>, C<IO::AIO::DT_FIFO>, C<IO::AIO::DT_CHR>, C<IO::AIO::DT_DIR>,
		855	C<IO::AIO::DT_BLK>, C<IO::AIO::DT_REG>, C<IO::AIO::DT_LNK>, C<IO::AIO::DT_SOCK>,
		856	C<IO::AIO::DT_WHT>.
		857
		858	C<IO::AIO::DT_UNKNOWN> means just that: readdir does not know. If you need to
		859	know, you have to run stat yourself. Also, for speed reasons, the C<$type>
		860	scalars are read-only: you can not modify them.
		861
		862	C<$inode> is the inode number (which might not be exact on systems with 64
		863	bit inode numbers and 32 bit perls). This field has unspecified content on
		864	systems that do not deliver the inode information.
		865
		866	=item IO::AIO::READDIR_DIRS_FIRST
		867
		868	When this flag is set, then the names will be returned in an order where
		869	likely directories come first, in optimal stat order. This is useful when
		870	you need to quickly find directories, or you want to find all directories
		871	while avoiding to stat() each entry.
		872
		873	If the system returns type information in readdir, then this is used
		874	to find directories directly. Otherwise, likely directories are names
		875	beginning with ".", or otherwise names with no dots, of which names with
		876	short names are tried first.
		877
		878	=item IO::AIO::READDIR_STAT_ORDER
		879
		880	When this flag is set, then the names will be returned in an order
		881	suitable for stat()'ing each one. That is, when you plan to stat()
		882	all files in the given directory, then the returned order will likely
		883	be fastest.
		884
		885	If both this flag and C<IO::AIO::READDIR_DIRS_FIRST> are specified, then
		886	the likely dirs come first, resulting in a less optimal stat order.
		887
		888	=item IO::AIO::READDIR_FOUND_UNKNOWN
		889
		890	This flag should not be set when calling C<aio_readdirx>. Instead, it
		891	is being set by C<aio_readdirx>, when any of the C<$type>'s found were
		892	C<IO::AIO::DT_UNKNOWN>. The absence of this flag therefore indicates that all
		893	C<$type>'s are known, which can be used to speed up some algorithms.
		894
		895	=back
		896
		897
537	=item aio_load $path, $data, $callback->($status)	898	=item aio_load $pathname, $data, $callback->($status)
538		899
539	This is a composite request that tries to fully load the given file into	900	This is a composite request that tries to fully load the given file into
540	memory. Status is the same as with aio_read.	901	memory. Status is the same as with aio_read.
541		902
542	=cut	903	=cut
…		…
564		925
565	=item aio_copy $srcpath, $dstpath, $callback->($status)	926	=item aio_copy $srcpath, $dstpath, $callback->($status)
566		927
567	Try to copy the I<file> (directories not supported as either source or	928	Try to copy the I<file> (directories not supported as either source or
568	destination) from C<$srcpath> to C<$dstpath> and call the callback with	929	destination) from C<$srcpath> to C<$dstpath> and call the callback with
569	the C<0> (error) or C<-1> ok.	930	a status of C<0> (ok) or C<-1> (error, see C<$!>).
570		931
571	This is a composite request that it creates the destination file with	932	This is a composite request that creates the destination file with
572	mode 0200 and copies the contents of the source file into it using	933	mode 0200 and copies the contents of the source file into it using
573	C<aio_sendfile>, followed by restoring atime, mtime, access mode and	934	C<aio_sendfile>, followed by restoring atime, mtime, access mode and
574	uid/gid, in that order.	935	uid/gid, in that order.
575		936
576	If an error occurs, the partial destination file will be unlinked, if	937	If an error occurs, the partial destination file will be unlinked, if
…		…
586	my $grp = aio_group $cb;	947	my $grp = aio_group $cb;
587		948
588	aioreq_pri $pri;	949	aioreq_pri $pri;
589	add $grp aio_open $src, O_RDONLY, 0, sub {	950	add $grp aio_open $src, O_RDONLY, 0, sub {
590	if (my $src_fh = $_[0]) {	951	if (my $src_fh = $_[0]) {
591	my @stat = stat $src_fh;	952	my @stat = stat $src_fh; # hmm, might block over nfs?
592		953
593	aioreq_pri $pri;	954	aioreq_pri $pri;
594	add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {	955	add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {
595	if (my $dst_fh = $_[0]) {	956	if (my $dst_fh = $_[0]) {
596	aioreq_pri $pri;	957	aioreq_pri $pri;
597	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {	958	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
598	if ($_[0] == $stat[7]) {	959	if ($_[0] == $stat[7]) {
599	$grp->result (0);	960	$grp->result (0);
600	close $src_fh;	961	close $src_fh;
601		962
602	# those should not normally block. should. should.	963	my $ch = sub {
603	utime $stat[8], $stat[9], $dst;	964	aioreq_pri $pri;
604	chmod $stat[2] & 07777, $dst_fh;	965	add $grp aio_chmod $dst_fh, $stat[2] & 07777, sub {
605	chown $stat[4], $stat[5], $dst_fh;	966	aioreq_pri $pri;
		967	add $grp aio_chown $dst_fh, $stat[4], $stat[5], sub {
		968	aioreq_pri $pri;
		969	add $grp aio_close $dst_fh;
		970	}
		971	};
		972	};
606		973
607	aioreq_pri $pri;	974	aioreq_pri $pri;
608	add $grp aio_close $dst_fh;	975	add $grp aio_utime $dst_fh, $stat[8], $stat[9], sub {
		976	if ($_[0] < 0 && $! == ENOSYS) {
		977	aioreq_pri $pri;
		978	add $grp aio_utime $dst, $stat[8], $stat[9], $ch;
		979	} else {
		980	$ch->();
		981	}
		982	};
609	} else {	983	} else {
610	$grp->result (-1);	984	$grp->result (-1);
611	close $src_fh;	985	close $src_fh;
612	close $dst_fh;	986	close $dst_fh;
613		987
…		…
630		1004
631	=item aio_move $srcpath, $dstpath, $callback->($status)	1005	=item aio_move $srcpath, $dstpath, $callback->($status)
632		1006
633	Try to move the I<file> (directories not supported as either source or	1007	Try to move the I<file> (directories not supported as either source or
634	destination) from C<$srcpath> to C<$dstpath> and call the callback with	1008	destination) from C<$srcpath> to C<$dstpath> and call the callback with
635	the C<0> (error) or C<-1> ok.	1009	a status of C<0> (ok) or C<-1> (error, see C<$!>).
636		1010
637	This is a composite request that tries to rename(2) the file first. If	1011	This is a composite request that tries to rename(2) the file first; if
638	rename files with C<EXDEV>, it copies the file with C<aio_copy> and, if	1012	rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if
639	that is successful, unlinking the C<$srcpath>.	1013	that is successful, unlinks the C<$srcpath>.
640		1014
641	=cut	1015	=cut
642		1016
643	sub aio_move($$;$) {	1017	sub aio_move($$;$) {
644	my ($src, $dst, $cb) = @_;	1018	my ($src, $dst, $cb) = @_;
…		…
651	if ($_[0] && $! == EXDEV) {	1025	if ($_[0] && $! == EXDEV) {
652	aioreq_pri $pri;	1026	aioreq_pri $pri;
653	add $grp aio_copy $src, $dst, sub {	1027	add $grp aio_copy $src, $dst, sub {
654	$grp->result ($_[0]);	1028	$grp->result ($_[0]);
655		1029
656	if (!$_[0]) {	1030	unless ($_[0]) {
657	aioreq_pri $pri;	1031	aioreq_pri $pri;
658	add $grp aio_unlink $src;	1032	add $grp aio_unlink $src;
659	}	1033	}
660	};	1034	};
661	} else {	1035	} else {
…		…
664	};	1038	};
665		1039
666	$grp	1040	$grp
667	}	1041	}
668		1042
669	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)	1043	=item aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs)
670		1044
671	Scans a directory (similar to C<aio_readdir>) but additionally tries to	1045	Scans a directory (similar to C<aio_readdir>) but additionally tries to
672	efficiently separate the entries of directory C<$path> into two sets of	1046	efficiently separate the entries of directory C<$path> into two sets of
673	names, directories you can recurse into (directories), and ones you cannot	1047	names, directories you can recurse into (directories), and ones you cannot
674	recurse into (everything else, including symlinks to directories).	1048	recurse into (everything else, including symlinks to directories).
…		…
691		1065
692	Implementation notes.	1066	Implementation notes.
693		1067
694	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.	1068	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.
695		1069
		1070	If readdir returns file type information, then this is used directly to
		1071	find directories.
		1072
696	After reading the directory, the modification time, size etc. of the	1073	Otherwise, after reading the directory, the modification time, size etc.
697	directory before and after the readdir is checked, and if they match (and	1074	of the directory before and after the readdir is checked, and if they
698	isn't the current time), the link count will be used to decide how many	1075	match (and isn't the current time), the link count will be used to decide
699	entries are directories (if >= 2). Otherwise, no knowledge of the number	1076	how many entries are directories (if >= 2). Otherwise, no knowledge of the
700	of subdirectories will be assumed.	1077	number of subdirectories will be assumed.
701		1078
702	Then entries will be sorted into likely directories (everything without	1079	Then entries will be sorted into likely directories a non-initial dot
703	a non-initial dot currently) and likely non-directories (everything	1080	currently) and likely non-directories (see C<aio_readdirx>). Then every
704	else). Then every entry plus an appended C</.> will be C<stat>'ed,	1081	entry plus an appended C</.> will be C<stat>'ed, likely directories first,
705	likely directories first. If that succeeds, it assumes that the entry	1082	in order of their inode numbers. If that succeeds, it assumes that the
706	is a directory or a symlink to directory (which will be checked	1083	entry is a directory or a symlink to directory (which will be checked
707	seperately). This is often faster than stat'ing the entry itself because	1084	separately). This is often faster than stat'ing the entry itself because
708	filesystems might detect the type of the entry without reading the inode	1085	filesystems might detect the type of the entry without reading the inode
709	data (e.g. ext2fs filetype feature).	1086	data (e.g. ext2fs filetype feature), even on systems that cannot return
		1087	the filetype information on readdir.
710		1088
711	If the known number of directories (link count - 2) has been reached, the	1089	If the known number of directories (link count - 2) has been reached, the
712	rest of the entries is assumed to be non-directories.	1090	rest of the entries is assumed to be non-directories.
713		1091
714	This only works with certainty on POSIX (= UNIX) filesystems, which	1092	This only works with certainty on POSIX (= UNIX) filesystems, which
…		…
727		1105
728	my $grp = aio_group $cb;	1106	my $grp = aio_group $cb;
729		1107
730	$maxreq = 4 if $maxreq <= 0;	1108	$maxreq = 4 if $maxreq <= 0;
731		1109
732	# stat once	1110	# get a wd object
733	aioreq_pri $pri;	1111	aioreq_pri $pri;
734	add $grp aio_stat $path, sub {	1112	add $grp aio_wd $path, sub {
		1113	$_[0]
735	return $grp->result () if $_[0];	1114	or return $grp->result ();
736	my $now = time;
737	my $hash1 = join ":", (stat _)[0,1,3,7,9];
738		1115
739	# read the directory entries	1116	my $wd = [shift, "."];
		1117
		1118	# stat once
740	aioreq_pri $pri;	1119	aioreq_pri $pri;
741	add $grp aio_readdir $path, sub {	1120	add $grp aio_stat $wd, sub {
742	my $entries = shift
743	or return $grp->result ();	1121	return $grp->result () if $_[0];
		1122	my $now = time;
		1123	my $hash1 = join ":", (stat _)[0,1,3,7,9];
744		1124
745	# stat the dir another time	1125	# read the directory entries
746	aioreq_pri $pri;	1126	aioreq_pri $pri;
		1127	add $grp aio_readdirx $wd, READDIR_DIRS_FIRST, sub {
		1128	my $entries = shift
		1129	or return $grp->result ();
		1130
		1131	# stat the dir another time
		1132	aioreq_pri $pri;
747	add $grp aio_stat $path, sub {	1133	add $grp aio_stat $wd, sub {
748	my $hash2 = join ":", (stat _)[0,1,3,7,9];	1134	my $hash2 = join ":", (stat _)[0,1,3,7,9];
749		1135
750	my $ndirs;	1136	my $ndirs;
751		1137
752	# take the slow route if anything looks fishy	1138	# take the slow route if anything looks fishy
753	if ($hash1 ne $hash2 or (stat _)[9] == $now) {	1139	if ($hash1 ne $hash2 or (stat _)[9] == $now) {
754	$ndirs = -1;	1140	$ndirs = -1;
755	} else {	1141	} else {
756	# if nlink == 2, we are finished	1142	# if nlink == 2, we are finished
757	# on non-posix-fs's, we rely on nlink < 2	1143	# for non-posix-fs's, we rely on nlink < 2
758	$ndirs = (stat _)[3] - 2	1144	$ndirs = (stat _)[3] - 2
759	or return $grp->result ([], $entries);	1145	or return $grp->result ([], $entries);
760	}	1146	}
761		1147
762	# sort into likely dirs and likely nondirs
763	# dirs == files without ".", short entries first
764	$entries = [map $_->[0],
765	sort { $b->[1] cmp $a->[1] }
766	map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],
767	@$entries];
768
769	my (@dirs, @nondirs);	1148	my (@dirs, @nondirs);
770		1149
771	my $statgrp = add $grp aio_group sub {	1150	my $statgrp = add $grp aio_group sub {
772	$grp->result (\@dirs, \@nondirs);	1151	$grp->result (\@dirs, \@nondirs);
773	};	1152	};
774		1153
775	limit $statgrp $maxreq;	1154	limit $statgrp $maxreq;
776	feed $statgrp sub {	1155	feed $statgrp sub {
777	return unless @$entries;	1156	return unless @$entries;
778	my $entry = pop @$entries;	1157	my $entry = shift @$entries;
779		1158
780	aioreq_pri $pri;	1159	aioreq_pri $pri;
		1160	$wd->[1] = "$entry/.";
781	add $statgrp aio_stat "$path/$entry/.", sub {	1161	add $statgrp aio_stat $wd, sub {
782	if ($_[0] < 0) {	1162	if ($_[0] < 0) {
783	push @nondirs, $entry;	1163	push @nondirs, $entry;
784	} else {	1164	} else {
785	# need to check for real directory	1165	# need to check for real directory
786	aioreq_pri $pri;	1166	aioreq_pri $pri;
		1167	$wd->[1] = $entry;
787	add $statgrp aio_lstat "$path/$entry", sub {	1168	add $statgrp aio_lstat $wd, sub {
788	if (-d _) {	1169	if (-d _) {
789	push @dirs, $entry;	1170	push @dirs, $entry;
790		1171
791	unless (--$ndirs) {	1172	unless (--$ndirs) {
792	push @nondirs, @$entries;	1173	push @nondirs, @$entries;
793	feed $statgrp;	1174	feed $statgrp;
		1175	}
		1176	} else {
		1177	push @nondirs, $entry;
794	}	1178	}
795	} else {
796	push @nondirs, $entry;
797	}	1179	}
798	}	1180	}
799	}	1181	};
800	};	1182	};
801	};	1183	};
802	};	1184	};
803	};	1185	};
804	};	1186	};
805		1187
806	$grp	1188	$grp
807	}	1189	}
808		1190
809	=item aio_rmtree $path, $callback->($status)	1191	=item aio_rmtree $pathname, $callback->($status)
810		1192
811	Delete a directory tree starting (and including) C<$path>, return the	1193	Delete a directory tree starting (and including) C<$path>, return the
812	status of the final C<rmdir> only. This is a composite request that	1194	status of the final C<rmdir> only. This is a composite request that
813	uses C<aio_scandir> to recurse into and rmdir directories, and unlink	1195	uses C<aio_scandir> to recurse into and rmdir directories, and unlink
814	everything else.	1196	everything else.
815		1197
816	=cut	1198	=cut
817		1199
…		…
856	callback with the fdatasync result code.	1238	callback with the fdatasync result code.
857		1239
858	If this call isn't available because your OS lacks it or it couldn't be	1240	If this call isn't available because your OS lacks it or it couldn't be
859	detected, it will be emulated by calling C<fsync> instead.	1241	detected, it will be emulated by calling C<fsync> instead.
860		1242
		1243	=item aio_syncfs $fh, $callback->($status)
		1244
		1245	Asynchronously call the syncfs syscall to sync the filesystem associated
		1246	to the given filehandle and call the callback with the syncfs result
		1247	code. If syncfs is not available, calls sync(), but returns C<-1> and sets
		1248	errno to C<ENOSYS> nevertheless.
		1249
		1250	=item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		1251
		1252	Sync the data portion of the file specified by C<$offset> and C<$length>
		1253	to disk (but NOT the metadata), by calling the Linux-specific
		1254	sync_file_range call. If sync_file_range is not available or it returns
		1255	ENOSYS, then fdatasync or fsync is being substituted.
		1256
		1257	C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>,
		1258	C<IO::AIO::SYNC_FILE_RANGE_WRITE> and
		1259	C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range
		1260	manpage for details.
		1261
861	=item aio_pathsync $path, $callback->($status)	1262	=item aio_pathsync $pathname, $callback->($status)
862		1263
863	This request tries to open, fsync and close the given path. This is a	1264	This request tries to open, fsync and close the given path. This is a
864	composite request intended tosync directories after directory operations	1265	composite request intended to sync directories after directory operations
865	(E.g. rename). This might not work on all operating systems or have any	1266	(E.g. rename). This might not work on all operating systems or have any
866	specific effect, but usually it makes sure that directory changes get	1267	specific effect, but usually it makes sure that directory changes get
867	written to disc. It works for anything that can be opened for read-only,	1268	written to disc. It works for anything that can be opened for read-only,
868	not just directories.	1269	not just directories.
		1270
		1271	Future versions of this function might fall back to other methods when
		1272	C<fsync> on the directory fails (such as calling C<sync>).
869		1273
870	Passes C<0> when everything went ok, and C<-1> on error.	1274	Passes C<0> when everything went ok, and C<-1> on error.
871		1275
872	=cut	1276	=cut
873		1277
…		…
894	};	1298	};
895		1299
896	$grp	1300	$grp
897	}	1301	}
898		1302
		1303	=item aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		1304
		1305	This is a rather advanced IO::AIO call, which only works on mmap(2)ed
		1306	scalars (see the C<IO::AIO::mmap> function, although it also works on data
		1307	scalars managed by the L<Sys::Mmap> or L<Mmap> modules, note that the
		1308	scalar must only be modified in-place while an aio operation is pending on
		1309	it).
		1310
		1311	It calls the C<msync> function of your OS, if available, with the memory
		1312	area starting at C<$offset> in the string and ending C<$length> bytes
		1313	later. If C<$length> is negative, counts from the end, and if C<$length>
		1314	is C<undef>, then it goes till the end of the string. The flags can be
		1315	a combination of C<IO::AIO::MS_ASYNC>, C<IO::AIO::MS_INVALIDATE> and
		1316	C<IO::AIO::MS_SYNC>.
		1317
		1318	=item aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		1319
		1320	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1321	scalars.
		1322
		1323	It touches (reads or writes) all memory pages in the specified
		1324	range inside the scalar. All caveats and parameters are the same
		1325	as for C<aio_msync>, above, except for flags, which must be either
		1326	C<0> (which reads all pages and ensures they are instantiated) or
		1327	C<IO::AIO::MT_MODIFY>, which modifies the memory pages (by reading and
		1328	writing an octet from it, which dirties the page).
		1329
		1330	=item aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
		1331
		1332	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1333	scalars.
		1334
		1335	It reads in all the pages of the underlying storage into memory (if any)
		1336	and locks them, so they are not getting swapped/paged out or removed.
		1337
		1338	If C<$length> is undefined, then the scalar will be locked till the end.
		1339
		1340	On systems that do not implement C<mlock>, this function returns C<-1>
		1341	and sets errno to C<ENOSYS>.
		1342
		1343	Note that the corresponding C<munlock> is synchronous and is
		1344	documented under L<MISCELLANEOUS FUNCTIONS>.
		1345
		1346	Example: open a file, mmap and mlock it - both will be undone when
		1347	C<$data> gets destroyed.
		1348
		1349	open my $fh, "<", $path or die "$path: $!";
		1350	my $data;
		1351	IO::AIO::mmap $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh;
		1352	aio_mlock $data; # mlock in background
		1353
		1354	=item aio_mlockall $flags, $callback->($status)
		1355
		1356	Calls the C<mlockall> function with the given C<$flags> (a combination of
		1357	C<IO::AIO::MCL_CURRENT> and C<IO::AIO::MCL_FUTURE>).
		1358
		1359	On systems that do not implement C<mlockall>, this function returns C<-1>
		1360	and sets errno to C<ENOSYS>.
		1361
		1362	Note that the corresponding C<munlockall> is synchronous and is
		1363	documented under L<MISCELLANEOUS FUNCTIONS>.
		1364
		1365	Example: asynchronously lock all current and future pages into memory.
		1366
		1367	aio_mlockall IO::AIO::MCL_FUTURE;
		1368
		1369	=item aio_fiemap $fh, $start, $length, $flags, $count, $cb->(\@extents)
		1370
		1371	Queries the extents of the given file (by calling the Linux C<FIEMAP>
		1372	ioctl, see L<http://cvs.schmorp.de/IO-AIO/doc/fiemap.txt> for details). If
		1373	the ioctl is not available on your OS, then this request will fail with
		1374	C<ENOSYS>.
		1375
		1376	C<$start> is the starting offset to query extents for, C<$length> is the
		1377	size of the range to query - if it is C<undef>, then the whole file will
		1378	be queried.
		1379
		1380	C<$flags> is a combination of flags (C<IO::AIO::FIEMAP_FLAG_SYNC> or
		1381	C<IO::AIO::FIEMAP_FLAG_XATTR> - C<IO::AIO::FIEMAP_FLAGS_COMPAT> is also
		1382	exported), and is normally C<0> or C<IO::AIO::FIEMAP_FLAG_SYNC> to query
		1383	the data portion.
		1384
		1385	C<$count> is the maximum number of extent records to return. If it is
		1386	C<undef>, then IO::AIO queries all extents of the range. As a very special
		1387	case, if it is C<0>, then the callback receives the number of extents
		1388	instead of the extents themselves (which is unreliable, see below).
		1389
		1390	If an error occurs, the callback receives no arguments. The special
		1391	C<errno> value C<IO::AIO::EBADR> is available to test for flag errors.
		1392
		1393	Otherwise, the callback receives an array reference with extent
		1394	structures. Each extent structure is an array reference itself, with the
		1395	following members:
		1396
		1397	[$logical, $physical, $length, $flags]
		1398
		1399	Flags is any combination of the following flag values (typically either C<0>
		1400	or C<IO::AIO::FIEMAP_EXTENT_LAST> (1)):
		1401
		1402	C<IO::AIO::FIEMAP_EXTENT_LAST>, C<IO::AIO::FIEMAP_EXTENT_UNKNOWN>,
		1403	C<IO::AIO::FIEMAP_EXTENT_DELALLOC>, C<IO::AIO::FIEMAP_EXTENT_ENCODED>,
		1404	C<IO::AIO::FIEMAP_EXTENT_DATA_ENCRYPTED>, C<IO::AIO::FIEMAP_EXTENT_NOT_ALIGNED>,
		1405	C<IO::AIO::FIEMAP_EXTENT_DATA_INLINE>, C<IO::AIO::FIEMAP_EXTENT_DATA_TAIL>,
		1406	C<IO::AIO::FIEMAP_EXTENT_UNWRITTEN>, C<IO::AIO::FIEMAP_EXTENT_MERGED> or
		1407	C<IO::AIO::FIEMAP_EXTENT_SHARED>.
		1408
		1409	At the time of this writing (Linux 3.2), this requets is unreliable unless
		1410	C<$count> is C<undef>, as the kernel has all sorts of bugs preventing
		1411	it to return all extents of a range for files with large number of
		1412	extents. The code works around all these issues if C<$count> is undef.
		1413
899	=item aio_group $callback->(...)	1414	=item aio_group $callback->(...)
900		1415
901	This is a very special aio request: Instead of doing something, it is a	1416	This is a very special aio request: Instead of doing something, it is a
902	container for other aio requests, which is useful if you want to bundle	1417	container for other aio requests, which is useful if you want to bundle
903	many requests into a single, composite, request with a definite callback	1418	many requests into a single, composite, request with a definite callback
…		…
940	immense (it blocks a thread for a long time) so do not use this function	1455	immense (it blocks a thread for a long time) so do not use this function
941	except to put your application under artificial I/O pressure.	1456	except to put your application under artificial I/O pressure.
942		1457
943	=back	1458	=back
944		1459
		1460
		1461	=head2 IO::AIO::WD - multiple working directories
		1462
		1463	Your process only has one current working directory, which is used by all
		1464	threads. This makes it hard to use relative paths (some other component
		1465	could call C<chdir> at any time, and it is hard to control when the path
		1466	will be used by IO::AIO).
		1467
		1468	One solution for this is to always use absolute paths. This usually works,
		1469	but can be quite slow (the kernel has to walk the whole path on every
		1470	access), and can also be a hassle to implement.
		1471
		1472	Newer POSIX systems have a number of functions (openat, fdopendir,
		1473	futimensat and so on) that make it possible to specify working directories
		1474	per operation.
		1475
		1476	For portability, and because the clowns who "designed", or shall I write,
		1477	perpetrated this new interface were obviously half-drunk, this abstraction
		1478	cannot be perfect, though.
		1479
		1480	IO::AIO allows you to convert directory paths into a so-called IO::AIO::WD
		1481	object. This object stores the canonicalised, absolute version of the
		1482	path, and on systems that allow it, also a directory file descriptor.
		1483
		1484	Everywhere where a pathname is accepted by IO::AIO (e.g. in C<aio_stat>
		1485	or C<aio_unlink>), one can specify an array reference with an IO::AIO::WD
		1486	object and a pathname instead (or the IO::AIO::WD object alone, which
		1487	gets interpreted as C<[$wd, "."]>). If the pathname is absolute, the
		1488	IO::AIO::WD object is ignored, otherwise the pathname is resolved relative
		1489	to that IO::AIO::WD object.
		1490
		1491	For example, to get a wd object for F</etc> and then stat F<passwd>
		1492	inside, you would write:
		1493
		1494	aio_wd "/etc", sub {
		1495	my $etcdir = shift;
		1496
		1497	# although $etcdir can be undef on error, there is generally no reason
		1498	# to check for errors here, as aio_stat will fail with ENOENT
		1499	# when $etcdir is undef.
		1500
		1501	aio_stat [$etcdir, "passwd"], sub {
		1502	# yay
		1503	};
		1504	};
		1505
		1506	That C<aio_wd> is a request and not a normal function shows that creating
		1507	an IO::AIO::WD object is itself a potentially blocking operation, which is
		1508	why it is done asynchronously.
		1509
		1510	To stat the directory obtained with C<aio_wd> above, one could write
		1511	either of the following three request calls:
		1512
		1513	aio_lstat "/etc" , sub { ... # pathname as normal string
		1514	aio_lstat [$wd, "."], sub { ... # "." relative to $wd (i.e. $wd itself)
		1515	aio_lstat $wd , sub { ... # shorthand for the previous
		1516
		1517	As with normal pathnames, IO::AIO keeps a copy of the working directory
		1518	object and the pathname string, so you could write the following without
		1519	causing any issues due to C<$path> getting reused:
		1520
		1521	my $path = [$wd, undef];
		1522
		1523	for my $name (qw(abc def ghi)) {
		1524	$path->[1] = $name;
		1525	aio_stat $path, sub {
		1526	# ...
		1527	};
		1528	}
		1529
		1530	There are some caveats: when directories get renamed (or deleted), the
		1531	pathname string doesn't change, so will point to the new directory (or
		1532	nowhere at all), while the directory fd, if available on the system,
		1533	will still point to the original directory. Most functions accepting a
		1534	pathname will use the directory fd on newer systems, and the string on
		1535	older systems. Some functions (such as realpath) will always rely on the
		1536	string form of the pathname.
		1537
		1538	So this functionality is mainly useful to get some protection against
		1539	C<chdir>, to easily get an absolute path out of a relative path for future
		1540	reference, and to speed up doing many operations in the same directory
		1541	(e.g. when stat'ing all files in a directory).
		1542
		1543	The following functions implement this working directory abstraction:
		1544
		1545	=over 4
		1546
		1547	=item aio_wd $pathname, $callback->($wd)
		1548
		1549	Asynchonously canonicalise the given pathname and convert it to an
		1550	IO::AIO::WD object representing it. If possible and supported on the
		1551	system, also open a directory fd to speed up pathname resolution relative
		1552	to this working directory.
		1553
		1554	If something goes wrong, then C<undef> is passwd to the callback instead
		1555	of a working directory object and C<$!> is set appropriately. Since
		1556	passing C<undef> as working directory component of a pathname fails the
		1557	request with C<ENOENT>, there is often no need for error checking in the
		1558	C<aio_wd> callback, as future requests using the value will fail in the
		1559	expected way.
		1560
		1561	If this call isn't available because your OS lacks it or it couldn't be
		1562	detected, it will be emulated by calling C<fsync> instead.
		1563
		1564	=item IO::AIO::CWD
		1565
		1566	This is a compiletime constant (object) that represents the process
		1567	current working directory.
		1568
		1569	Specifying this object as working directory object for a pathname is as if
		1570	the pathname would be specified directly, without a directory object. For
		1571	example, these calls are functionally identical:
		1572
		1573	aio_stat "somefile", sub { ... };
		1574	aio_stat [IO::AIO::CWD, "somefile"], sub { ... };
		1575
		1576	=back
		1577
		1578	To recover the path associated with an IO::AIO::WD object, you can use
		1579	C<aio_realpath>:
		1580
		1581	aio_realpath $wd, sub {
		1582	warn "path is $_[0]\n";
		1583	};
		1584
		1585	Currently, C<aio_statvfs> always, and C<aio_rename> and C<aio_rmdir>
		1586	sometimes, fall back to using an absolue path.
		1587
945	=head2 IO::AIO::REQ CLASS	1588	=head2 IO::AIO::REQ CLASS
946		1589
947	All non-aggregate C<aio_*> functions return an object of this class when	1590	All non-aggregate C<aio_*> functions return an object of this class when
948	called in non-void context.	1591	called in non-void context.
949		1592
…		…
952	=item cancel $req	1595	=item cancel $req
953		1596
954	Cancels the request, if possible. Has the effect of skipping execution	1597	Cancels the request, if possible. Has the effect of skipping execution
955	when entering the B<execute> state and skipping calling the callback when	1598	when entering the B<execute> state and skipping calling the callback when
956	entering the the B<result> state, but will leave the request otherwise	1599	entering the the B<result> state, but will leave the request otherwise
957	untouched. That means that requests that currently execute will not be	1600	untouched (with the exception of readdir). That means that requests that
958	stopped and resources held by the request will not be freed prematurely.	1601	currently execute will not be stopped and resources held by the request
		1602	will not be freed prematurely.
959		1603
960	=item cb $req $callback->(...)	1604	=item cb $req $callback->(...)
961		1605
962	Replace (or simply set) the callback registered to the request.	1606	Replace (or simply set) the callback registered to the request.
963		1607
…		…
1014	Their lifetime, simplified, looks like this: when they are empty, they	1658	Their lifetime, simplified, looks like this: when they are empty, they
1015	will finish very quickly. If they contain only requests that are in the	1659	will finish very quickly. If they contain only requests that are in the
1016	C<done> state, they will also finish. Otherwise they will continue to	1660	C<done> state, they will also finish. Otherwise they will continue to
1017	exist.	1661	exist.
1018		1662
1019	That means after creating a group you have some time to add requests. And	1663	That means after creating a group you have some time to add requests
1020	in the callbacks of those requests, you can add further requests to the	1664	(precisely before the callback has been invoked, which is only done within
1021	group. And only when all those requests have finished will the the group	1665	the C<poll_cb>). And in the callbacks of those requests, you can add
1022	itself finish.	1666	further requests to the group. And only when all those requests have
		1667	finished will the the group itself finish.
1023		1668
1024	=over 4	1669	=over 4
1025		1670
1026	=item add $grp ...	1671	=item add $grp ...
1027		1672
…		…
1035		1680
1036	=item $grp->cancel_subs	1681	=item $grp->cancel_subs
1037		1682
1038	Cancel all subrequests and clears any feeder, but not the group request	1683	Cancel all subrequests and clears any feeder, but not the group request
1039	itself. Useful when you queued a lot of events but got a result early.	1684	itself. Useful when you queued a lot of events but got a result early.
		1685
		1686	The group request will finish normally (you cannot add requests to the
		1687	group).
1040		1688
1041	=item $grp->result (...)	1689	=item $grp->result (...)
1042		1690
1043	Set the result value(s) that will be passed to the group callback when all	1691	Set the result value(s) that will be passed to the group callback when all
1044	subrequests have finished and set the groups errno to the current value	1692	subrequests have finished and set the groups errno to the current value
…		…
1060	=item feed $grp $callback->($grp)	1708	=item feed $grp $callback->($grp)
1061		1709
1062	Sets a feeder/generator on this group: every group can have an attached	1710	Sets a feeder/generator on this group: every group can have an attached
1063	generator that generates requests if idle. The idea behind this is that,	1711	generator that generates requests if idle. The idea behind this is that,
1064	although you could just queue as many requests as you want in a group,	1712	although you could just queue as many requests as you want in a group,
1065	this might starve other requests for a potentially long time. For	1713	this might starve other requests for a potentially long time. For example,
1066	example, C<aio_scandir> might generate hundreds of thousands C<aio_stat>	1714	C<aio_scandir> might generate hundreds of thousands of C<aio_stat>
1067	requests, delaying any later requests for a long time.	1715	requests, delaying any later requests for a long time.
1068		1716
1069	To avoid this, and allow incremental generation of requests, you can	1717	To avoid this, and allow incremental generation of requests, you can
1070	instead a group and set a feeder on it that generates those requests. The	1718	instead a group and set a feeder on it that generates those requests. The
1071	feed callback will be called whenever there are few enough (see C<limit>,	1719	feed callback will be called whenever there are few enough (see C<limit>,
…		…
1076	not impose any limits).	1724	not impose any limits).
1077		1725
1078	If the feed does not queue more requests when called, it will be	1726	If the feed does not queue more requests when called, it will be
1079	automatically removed from the group.	1727	automatically removed from the group.
1080		1728
1081	If the feed limit is C<0>, it will be set to C<2> automatically.	1729	If the feed limit is C<0> when this method is called, it will be set to
		1730	C<2> automatically.
1082		1731
1083	Example:	1732	Example:
1084		1733
1085	# stat all files in @files, but only ever use four aio requests concurrently:	1734	# stat all files in @files, but only ever use four aio requests concurrently:
1086		1735
…		…
1098	Sets the feeder limit for the group: The feeder will be called whenever	1747	Sets the feeder limit for the group: The feeder will be called whenever
1099	the group contains less than this many requests.	1748	the group contains less than this many requests.
1100		1749
1101	Setting the limit to C<0> will pause the feeding process.	1750	Setting the limit to C<0> will pause the feeding process.
1102		1751
		1752	The default value for the limit is C<0>, but note that setting a feeder
		1753	automatically bumps it up to C<2>.
		1754
1103	=back	1755	=back
1104		1756
1105	=head2 SUPPORT FUNCTIONS	1757	=head2 SUPPORT FUNCTIONS
1106		1758
1107	=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION	1759	=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION
…		…
1109	=over 4	1761	=over 4
1110		1762
1111	=item $fileno = IO::AIO::poll_fileno	1763	=item $fileno = IO::AIO::poll_fileno
1112		1764
1113	Return the I<request result pipe file descriptor>. This filehandle must be	1765	Return the I<request result pipe file descriptor>. This filehandle must be
1114	polled for reading by some mechanism outside this module (e.g. Event or	1766	polled for reading by some mechanism outside this module (e.g. EV, Glib,
1115	select, see below or the SYNOPSIS). If the pipe becomes readable you have	1767	select and so on, see below or the SYNOPSIS). If the pipe becomes readable
1116	to call C<poll_cb> to check the results.	1768	you have to call C<poll_cb> to check the results.
1117		1769
1118	See C<poll_cb> for an example.	1770	See C<poll_cb> for an example.
1119		1771
1120	=item IO::AIO::poll_cb	1772	=item IO::AIO::poll_cb
1121		1773
1122	Process some outstanding events on the result pipe. You have to call this	1774	Process some requests that have reached the result phase (i.e. they have
1123	regularly. Returns the number of events processed. Returns immediately	1775	been executed but the results are not yet reported). You have to call
1124	when no events are outstanding. The amount of events processed depends on	1776	this "regularly" to finish outstanding requests.
1125	the settings of C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>.
1126		1777
		1778	Returns C<0> if all events could be processed (or there were no
		1779	events to process), or C<-1> if it returned earlier for whatever
		1780	reason. Returns immediately when no events are outstanding. The amount
		1781	of events processed depends on the settings of C<IO::AIO::max_poll_req>,
		1782	C<IO::AIO::max_poll_time> and C<IO::AIO::max_outstanding>.
		1783
1127	If not all requests were processed for whatever reason, the filehandle	1784	If not all requests were processed for whatever reason, the poll file
1128	will still be ready when C<poll_cb> returns.	1785	descriptor will still be ready when C<poll_cb> returns, so normally you
		1786	don't have to do anything special to have it called later.
		1787
		1788	Apart from calling C<IO::AIO::poll_cb> when the event filehandle becomes
		1789	ready, it can be beneficial to call this function from loops which submit
		1790	a lot of requests, to make sure the results get processed when they become
		1791	available and not just when the loop is finished and the event loop takes
		1792	over again. This function returns very fast when there are no outstanding
		1793	requests.
1129		1794
1130	Example: Install an Event watcher that automatically calls	1795	Example: Install an Event watcher that automatically calls
1131	IO::AIO::poll_cb with high priority:	1796	IO::AIO::poll_cb with high priority (more examples can be found in the
		1797	SYNOPSIS section, at the top of this document):
1132		1798
1133	Event->io (fd => IO::AIO::poll_fileno,	1799	Event->io (fd => IO::AIO::poll_fileno,
1134	poll => 'r', async => 1,	1800	poll => 'r', async => 1,
1135	cb => \&IO::AIO::poll_cb);	1801	cb => \&IO::AIO::poll_cb);
		1802
		1803	=item IO::AIO::poll_wait
		1804
		1805	Wait until either at least one request is in the result phase or no
		1806	requests are outstanding anymore.
		1807
		1808	This is useful if you want to synchronously wait for some requests to
		1809	become ready, without actually handling them.
		1810
		1811	See C<nreqs> for an example.
		1812
		1813	=item IO::AIO::poll
		1814
		1815	Waits until some requests have been handled.
		1816
		1817	Returns the number of requests processed, but is otherwise strictly
		1818	equivalent to:
		1819
		1820	IO::AIO::poll_wait, IO::AIO::poll_cb
		1821
		1822	=item IO::AIO::flush
		1823
		1824	Wait till all outstanding AIO requests have been handled.
		1825
		1826	Strictly equivalent to:
		1827
		1828	IO::AIO::poll_wait, IO::AIO::poll_cb
		1829	while IO::AIO::nreqs;
1136		1830
1137	=item IO::AIO::max_poll_reqs $nreqs	1831	=item IO::AIO::max_poll_reqs $nreqs
1138		1832
1139	=item IO::AIO::max_poll_time $seconds	1833	=item IO::AIO::max_poll_time $seconds
1140		1834
…		…
1165	# use a low priority so other tasks have priority	1859	# use a low priority so other tasks have priority
1166	Event->io (fd => IO::AIO::poll_fileno,	1860	Event->io (fd => IO::AIO::poll_fileno,
1167	poll => 'r', nice => 1,	1861	poll => 'r', nice => 1,
1168	cb => &IO::AIO::poll_cb);	1862	cb => &IO::AIO::poll_cb);
1169		1863
1170	=item IO::AIO::poll_wait
1171
1172	If there are any outstanding requests and none of them in the result
1173	phase, wait till the result filehandle becomes ready for reading (simply
1174	does a C<select> on the filehandle. This is useful if you want to
1175	synchronously wait for some requests to finish).
1176
1177	See C<nreqs> for an example.
1178
1179	=item IO::AIO::poll
1180
1181	Waits until some requests have been handled.
1182
1183	Returns the number of requests processed, but is otherwise strictly
1184	equivalent to:
1185
1186	IO::AIO::poll_wait, IO::AIO::poll_cb
1187
1188	=item IO::AIO::flush
1189
1190	Wait till all outstanding AIO requests have been handled.
1191
1192	Strictly equivalent to:
1193
1194	IO::AIO::poll_wait, IO::AIO::poll_cb
1195	while IO::AIO::nreqs;
1196
1197	=back	1864	=back
1198		1865
1199	=head3 CONTROLLING THE NUMBER OF THREADS	1866	=head3 CONTROLLING THE NUMBER OF THREADS
1200		1867
1201	=over	1868	=over
…		…
1234		1901
1235	Under normal circumstances you don't need to call this function.	1902	Under normal circumstances you don't need to call this function.
1236		1903
1237	=item IO::AIO::max_idle $nthreads	1904	=item IO::AIO::max_idle $nthreads
1238		1905
1239	Limit the number of threads (default: 4) that are allowed to idle (i.e.,	1906	Limit the number of threads (default: 4) that are allowed to idle
1240	threads that did not get a request to process within 10 seconds). That	1907	(i.e., threads that did not get a request to process within the idle
1241	means if a thread becomes idle while C<$nthreads> other threads are also	1908	timeout (default: 10 seconds). That means if a thread becomes idle while
1242	idle, it will free its resources and exit.	1909	C<$nthreads> other threads are also idle, it will free its resources and
		1910	exit.
1243		1911
1244	This is useful when you allow a large number of threads (e.g. 100 or 1000)	1912	This is useful when you allow a large number of threads (e.g. 100 or 1000)
1245	to allow for extremely high load situations, but want to free resources	1913	to allow for extremely high load situations, but want to free resources
1246	under normal circumstances (1000 threads can easily consume 30MB of RAM).	1914	under normal circumstances (1000 threads can easily consume 30MB of RAM).
1247		1915
1248	The default is probably ok in most situations, especially if thread	1916	The default is probably ok in most situations, especially if thread
1249	creation is fast. If thread creation is very slow on your system you might	1917	creation is fast. If thread creation is very slow on your system you might
1250	want to use larger values.	1918	want to use larger values.
1251		1919
		1920	=item IO::AIO::idle_timeout $seconds
		1921
		1922	Sets the minimum idle timeout (default 10) after which worker threads are
		1923	allowed to exit. SEe C<IO::AIO::max_idle>.
		1924
1252	=item IO::AIO::max_outstanding $maxreqs	1925	=item IO::AIO::max_outstanding $maxreqs
		1926
		1927	Sets the maximum number of outstanding requests to C<$nreqs>. If
		1928	you do queue up more than this number of requests, the next call to
		1929	C<IO::AIO::poll_cb> (and other functions calling C<poll_cb>, such as
		1930	C<IO::AIO::flush> or C<IO::AIO::poll>) will block until the limit is no
		1931	longer exceeded.
		1932
		1933	In other words, this setting does not enforce a queue limit, but can be
		1934	used to make poll functions block if the limit is exceeded.
1253		1935
1254	This is a very bad function to use in interactive programs because it	1936	This is a very bad function to use in interactive programs because it
1255	blocks, and a bad way to reduce concurrency because it is inexact: Better	1937	blocks, and a bad way to reduce concurrency because it is inexact: Better
1256	use an C<aio_group> together with a feed callback.	1938	use an C<aio_group> together with a feed callback.
1257		1939
1258	Sets the maximum number of outstanding requests to C<$nreqs>. If you	1940	It's main use is in scripts without an event loop - when you want to stat
1259	do queue up more than this number of requests, the next call to the	1941	a lot of files, you can write somehting like this:
1260	C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>)
1261	function will block until the limit is no longer exceeded.
1262		1942
1263	The default value is very large, so there is no practical limit on the	1943	IO::AIO::max_outstanding 32;
1264	number of outstanding requests.
1265		1944
1266	You can still queue as many requests as you want. Therefore,	1945	for my $path (...) {
1267	C<max_outstanding> is mainly useful in simple scripts (with low values) or	1946	aio_stat $path , ...;
1268	as a stop gap to shield against fatal memory overflow (with large values).	1947	IO::AIO::poll_cb;
		1948	}
		1949
		1950	IO::AIO::flush;
		1951
		1952	The call to C<poll_cb> inside the loop will normally return instantly, but
		1953	as soon as more thna C<32> reqeusts are in-flight, it will block until
		1954	some requests have been handled. This keeps the loop from pushing a large
		1955	number of C<aio_stat> requests onto the queue.
		1956
		1957	The default value for C<max_outstanding> is very large, so there is no
		1958	practical limit on the number of outstanding requests.
1269		1959
1270	=back	1960	=back
1271		1961
1272	=head3 STATISTICAL INFORMATION	1962	=head3 STATISTICAL INFORMATION
1273		1963
…		…
1293	Returns the number of requests currently in the pending state (executed,	1983	Returns the number of requests currently in the pending state (executed,
1294	but not yet processed by poll_cb).	1984	but not yet processed by poll_cb).
1295		1985
1296	=back	1986	=back
1297		1987
		1988	=head3 MISCELLANEOUS FUNCTIONS
		1989
		1990	IO::AIO implements some functions that might be useful, but are not
		1991	asynchronous.
		1992
		1993	=over 4
		1994
		1995	=item IO::AIO::sendfile $ofh, $ifh, $offset, $count
		1996
		1997	Calls the C<eio_sendfile_sync> function, which is like C<aio_sendfile>,
		1998	but is blocking (this makes most sense if you know the input data is
		1999	likely cached already and the output filehandle is set to non-blocking
		2000	operations).
		2001
		2002	Returns the number of bytes copied, or C<-1> on error.
		2003
		2004	=item IO::AIO::fadvise $fh, $offset, $len, $advice
		2005
		2006	Simply calls the C<posix_fadvise> function (see its
		2007	manpage for details). The following advice constants are
		2008	available: C<IO::AIO::FADV_NORMAL>, C<IO::AIO::FADV_SEQUENTIAL>,
		2009	C<IO::AIO::FADV_RANDOM>, C<IO::AIO::FADV_NOREUSE>,
		2010	C<IO::AIO::FADV_WILLNEED>, C<IO::AIO::FADV_DONTNEED>.
		2011
		2012	On systems that do not implement C<posix_fadvise>, this function returns
		2013	ENOSYS, otherwise the return value of C<posix_fadvise>.
		2014
		2015	=item IO::AIO::madvise $scalar, $offset, $len, $advice
		2016
		2017	Simply calls the C<posix_madvise> function (see its
		2018	manpage for details). The following advice constants are
		2019	available: C<IO::AIO::MADV_NORMAL>, C<IO::AIO::MADV_SEQUENTIAL>,
		2020	C<IO::AIO::MADV_RANDOM>, C<IO::AIO::MADV_WILLNEED>, C<IO::AIO::MADV_DONTNEED>.
		2021
		2022	On systems that do not implement C<posix_madvise>, this function returns
		2023	ENOSYS, otherwise the return value of C<posix_madvise>.
		2024
		2025	=item IO::AIO::mprotect $scalar, $offset, $len, $protect
		2026
		2027	Simply calls the C<mprotect> function on the preferably AIO::mmap'ed
		2028	$scalar (see its manpage for details). The following protect
		2029	constants are available: C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_READ>,
		2030	C<IO::AIO::PROT_WRITE>, C<IO::AIO::PROT_EXEC>.
		2031
		2032	On systems that do not implement C<mprotect>, this function returns
		2033	ENOSYS, otherwise the return value of C<mprotect>.
		2034
		2035	=item IO::AIO::mmap $scalar, $length, $prot, $flags, $fh[, $offset]
		2036
		2037	Memory-maps a file (or anonymous memory range) and attaches it to the
		2038	given C<$scalar>, which will act like a string scalar. Returns true on
		2039	success, and false otherwise.
		2040
		2041	The only operations allowed on the scalar are C<substr>/C<vec> that don't
		2042	change the string length, and most read-only operations such as copying it
		2043	or searching it with regexes and so on.
		2044
		2045	Anything else is unsafe and will, at best, result in memory leaks.
		2046
		2047	The memory map associated with the C<$scalar> is automatically removed
		2048	when the C<$scalar> is destroyed, or when the C<IO::AIO::mmap> or
		2049	C<IO::AIO::munmap> functions are called.
		2050
		2051	This calls the C<mmap>(2) function internally. See your system's manual
		2052	page for details on the C<$length>, C<$prot> and C<$flags> parameters.
		2053
		2054	The C<$length> must be larger than zero and smaller than the actual
		2055	filesize.
		2056
		2057	C<$prot> is a combination of C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_EXEC>,
		2058	C<IO::AIO::PROT_READ> and/or C<IO::AIO::PROT_WRITE>,
		2059
		2060	C<$flags> can be a combination of C<IO::AIO::MAP_SHARED> or
		2061	C<IO::AIO::MAP_PRIVATE>, or a number of system-specific flags (when
		2062	not available, the are defined as 0): C<IO::AIO::MAP_ANONYMOUS>
		2063	(which is set to C<MAP_ANON> if your system only provides this
		2064	constant), C<IO::AIO::MAP_HUGETLB>, C<IO::AIO::MAP_LOCKED>,
		2065	C<IO::AIO::MAP_NORESERVE>, C<IO::AIO::MAP_POPULATE> or
		2066	C<IO::AIO::MAP_NONBLOCK>
		2067
		2068	If C<$fh> is C<undef>, then a file descriptor of C<-1> is passed.
		2069
		2070	C<$offset> is the offset from the start of the file - it generally must be
		2071	a multiple of C<IO::AIO::PAGESIZE> and defaults to C<0>.
		2072
		2073	Example:
		2074
		2075	use Digest::MD5;
		2076	use IO::AIO;
		2077
		2078	open my $fh, "<verybigfile"
		2079	or die "$!";
		2080
		2081	IO::AIO::mmap my $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh
		2082	or die "verybigfile: $!";
		2083
		2084	my $fast_md5 = md5 $data;
		2085
		2086	=item IO::AIO::munmap $scalar
		2087
		2088	Removes a previous mmap and undefines the C<$scalar>.
		2089
		2090	=item IO::AIO::munlock $scalar, $offset = 0, $length = undef
		2091
		2092	Calls the C<munlock> function, undoing the effects of a previous
		2093	C<aio_mlock> call (see its description for details).
		2094
		2095	=item IO::AIO::munlockall
		2096
		2097	Calls the C<munlockall> function.
		2098
		2099	On systems that do not implement C<munlockall>, this function returns
		2100	ENOSYS, otherwise the return value of C<munlockall>.
		2101
		2102	=item IO::AIO::splice $r_fh, $r_off, $w_fh, $w_off, $length, $flags
		2103
		2104	Calls the GNU/Linux C<splice(2)> syscall, if available. If C<$r_off> or
		2105	C<$w_off> are C<undef>, then C<NULL> is passed for these, otherwise they
		2106	should be the file offset.
		2107
		2108	C<$r_fh> and C<$w_fh> should not refer to the same file, as splice might
		2109	silently corrupt the data in this case.
		2110
		2111	The following symbol flag values are available: C<IO::AIO::SPLICE_F_MOVE>,
		2112	C<IO::AIO::SPLICE_F_NONBLOCK>, C<IO::AIO::SPLICE_F_MORE> and
		2113	C<IO::AIO::SPLICE_F_GIFT>.
		2114
		2115	See the C<splice(2)> manpage for details.
		2116
		2117	=item IO::AIO::tee $r_fh, $w_fh, $length, $flags
		2118
		2119	Calls the GNU/Linux C<tee(2)> syscall, see it's manpage and the
		2120	description for C<IO::AIO::splice> above for details.
		2121
		2122	=back
		2123
1298	=cut	2124	=cut
1299		2125
1300	min_parallel 8;	2126	min_parallel 8;
1301		2127
1302	END { flush }	2128	END { flush }
1303		2129
1304	1;	2130	1;
1305		2131
		2132	=head1 EVENT LOOP INTEGRATION
		2133
		2134	It is recommended to use L<AnyEvent::AIO> to integrate IO::AIO
		2135	automatically into many event loops:
		2136
		2137	# AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...)
		2138	use AnyEvent::AIO;
		2139
		2140	You can also integrate IO::AIO manually into many event loops, here are
		2141	some examples of how to do this:
		2142
		2143	# EV integration
		2144	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
		2145
		2146	# Event integration
		2147	Event->io (fd => IO::AIO::poll_fileno,
		2148	poll => 'r',
		2149	cb => \&IO::AIO::poll_cb);
		2150
		2151	# Glib/Gtk2 integration
		2152	add_watch Glib::IO IO::AIO::poll_fileno,
		2153	in => sub { IO::AIO::poll_cb; 1 };
		2154
		2155	# Tk integration
		2156	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
		2157	readable => \&IO::AIO::poll_cb);
		2158
		2159	# Danga::Socket integration
		2160	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
		2161	\&IO::AIO::poll_cb);
		2162
1306	=head2 FORK BEHAVIOUR	2163	=head2 FORK BEHAVIOUR
1307		2164
1308	This module should do "the right thing" when the process using it forks:	2165	Usage of pthreads in a program changes the semantics of fork
		2166	considerably. Specifically, only async-safe functions can be called after
		2167	fork. Perl doesn't know about this, so in general, you cannot call fork
		2168	with defined behaviour in perl if pthreads are involved. IO::AIO uses
		2169	pthreads, so this applies, but many other extensions and (for inexplicable
		2170	reasons) perl itself often is linked against pthreads, so this limitation
		2171	applies to quite a lot of perls.
1309		2172
1310	Before the fork, IO::AIO enters a quiescent state where no requests	2173	This module no longer tries to fight your OS, or POSIX. That means IO::AIO
1311	can be added in other threads and no results will be processed. After	2174	only works in the process that loaded it. Forking is fully supported, but
1312	the fork the parent simply leaves the quiescent state and continues	2175	using IO::AIO in the child is not.
1313	request/result processing, while the child frees the request/result queue
1314	(so that the requests started before the fork will only be handled in the
1315	parent). Threads will be started on demand until the limit set in the
1316	parent process has been reached again.
1317		2176
1318	In short: the parent will, after a short pause, continue as if fork had	2177	You might get around by not I<using> IO::AIO before (or after)
1319	not been called, while the child will act as if IO::AIO has not been used	2178	forking. You could also try to call the L<IO::AIO::reinit> function in the
1320	yet.	2179	child:
		2180
		2181	=over 4
		2182
		2183	=item IO::AIO::reinit
		2184
		2185	Abandons all current requests and I/O threads and simply reinitialises all
		2186	data structures. This is not an operation supported by any standards, but
		2187	happens to work on GNU/Linux and some newer BSD systems.
		2188
		2189	The only reasonable use for this function is to call it after forking, if
		2190	C<IO::AIO> was used in the parent. Calling it while IO::AIO is active in
		2191	the process will result in undefined behaviour. Calling it at any time
		2192	will also result in any undefined (by POSIX) behaviour.
		2193
		2194	=back
1321		2195
1322	=head2 MEMORY USAGE	2196	=head2 MEMORY USAGE
1323		2197
1324	Per-request usage:	2198	Per-request usage:
1325		2199
…		…
1342		2216
1343	Known bugs will be fixed in the next release.	2217	Known bugs will be fixed in the next release.
1344		2218
1345	=head1 SEE ALSO	2219	=head1 SEE ALSO
1346		2220
1347	L<Coro::AIO>.	2221	L<AnyEvent::AIO> for easy integration into event loops, L<Coro::AIO> for a
		2222	more natural syntax.
1348		2223
1349	=head1 AUTHOR	2224	=head1 AUTHOR
1350		2225
1351	Marc Lehmann <schmorp@schmorp.de>	2226	Marc Lehmann <schmorp@schmorp.de>
1352	http://home.schmorp.de/	2227	http://home.schmorp.de/

Diff Legend

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