ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/IO-AIO/AIO.pm

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.147 by root, Wed Jun 3 12:24:49 2009 UTC vs.
Revision 1.262 by root, Thu Jun 9 03:15:37 2016 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, POE, urxvt, pureperl...)
32	use AnyEvent::AIO;
33
34	# EV integration
35	my $w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
36
37	# Event integration
38	Event->io (fd => IO::AIO::poll_fileno,
39	poll => 'r',
40	cb => \&IO::AIO::poll_cb);
41
42	# Glib/Gtk2 integration
43	add_watch Glib::IO IO::AIO::poll_fileno,
44	in => sub { IO::AIO::poll_cb; 1 };
45
46	# Tk integration
47	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
48	readable => \&IO::AIO::poll_cb);
49
50	# Danga::Socket integration
51	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
52	\&IO::AIO::poll_cb);
53
54	=head1 DESCRIPTION	31	=head1 DESCRIPTION
55		32
56	This module implements asynchronous I/O using whatever means your	33	This module implements asynchronous I/O using whatever means your
57	operating system supports.	34	operating system supports. It is implemented as an interface to C<libeio>
		35	(L<http://software.schmorp.de/pkg/libeio.html>).
58		36
59	Asynchronous means that operations that can normally block your program	37	Asynchronous means that operations that can normally block your program
60	(e.g. reading from disk) will be done asynchronously: the operation	38	(e.g. reading from disk) will be done asynchronously: the operation
61	will still block, but you can do something else in the meantime. This	39	will still block, but you can do something else in the meantime. This
62	is extremely useful for programs that need to stay interactive even	40	is extremely useful for programs that need to stay interactive even
…		…
66	on a RAID volume or over NFS when you do a number of stat operations	44	on a RAID volume or over NFS when you do a number of stat operations
67	concurrently.	45	concurrently.
68		46
69	While most of this works on all types of file descriptors (for	47	While most of this works on all types of file descriptors (for
70	example sockets), using these functions on file descriptors that	48	example sockets), using these functions on file descriptors that
71	support nonblocking operation (again, sockets, pipes etc.) is very	49	support nonblocking operation (again, sockets, pipes etc.) is
72	inefficient. Use an event loop for that (such as the L<Event|Event>	50	very inefficient. Use an event loop for that (such as the L<EV>
73	module): IO::AIO will naturally fit into such an event loop itself.	51	module): IO::AIO will naturally fit into such an event loop itself.
74		52
75	In this version, a number of threads are started that execute your	53	In this version, a number of threads are started that execute your
76	requests and signal their completion. You don't need thread support	54	requests and signal their completion. You don't need thread support
77	in perl, and the threads created by this module will not be visible	55	in perl, and the threads created by this module will not be visible
…		…
87	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
88	call C<poll_cb> (or other C<aio_> functions) recursively.	66	call C<poll_cb> (or other C<aio_> functions) recursively.
89		67
90	=head2 EXAMPLE	68	=head2 EXAMPLE
91		69
92	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
93	F</etc/passwd> asynchronously:	71	F</etc/passwd> asynchronously:
94		72
95	use Fcntl;
96	use Event;	73	use EV;
97	use IO::AIO;	74	use IO::AIO;
98		75
99	# register the IO::AIO callback with Event	76	# register the IO::AIO callback with EV
100	Event->io (fd => IO::AIO::poll_fileno,	77	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
101	poll => 'r',
102	cb => \&IO::AIO::poll_cb);
103		78
104	# queue the request to open /etc/passwd	79	# queue the request to open /etc/passwd
105	aio_open "/etc/passwd", O_RDONLY, 0, sub {	80	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
106	my $fh = shift	81	my $fh = shift
107	or die "error while opening: $!";	82	or die "error while opening: $!";
108		83
109	# stat'ing filehandles is generally non-blocking	84	# stat'ing filehandles is generally non-blocking
110	my $size = -s $fh;	85	my $size = -s $fh;
…		…
119		94
120	# file contents now in $contents	95	# file contents now in $contents
121	print $contents;	96	print $contents;
122		97
123	# exit event loop and program	98	# exit event loop and program
124	Event::unloop;	99	EV::break;
125	};	100	};
126	};	101	};
127		102
128	# possibly queue up other requests, or open GUI windows,	103	# possibly queue up other requests, or open GUI windows,
129	# check for sockets etc. etc.	104	# check for sockets etc. etc.
130		105
131	# process events as long as there are some:	106	# process events as long as there are some:
132	Event::loop;	107	EV::run;
133		108
134	=head1 REQUEST ANATOMY AND LIFETIME	109	=head1 REQUEST ANATOMY AND LIFETIME
135		110
136	Every C<aio_*> function creates a request. which is a C data structure not	111	Every C<aio_*> function creates a request. which is a C data structure not
137	directly visible to Perl.	112	directly visible to Perl.
…		…
187		162
188	package IO::AIO;	163	package IO::AIO;
189		164
190	use Carp ();	165	use Carp ();
191		166
192	no warnings;	167	use common::sense;
193	use strict 'vars';
194		168
195	use base 'Exporter';	169	use base 'Exporter';
196		170
197	BEGIN {	171	BEGIN {
198	our $VERSION = '3.19';	172	our $VERSION = 4.34;
199		173
200	our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close	174	our @AIO_REQ = qw(aio_sendfile aio_seek aio_read aio_write aio_open aio_close
201	aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir	175	aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx
202	aio_scandir aio_symlink aio_readlink aio_sync aio_fsync	176	aio_scandir aio_symlink aio_readlink aio_realpath aio_fcntl aio_ioctl
203	aio_fdatasync aio_sync_file_range aio_pathsync aio_readahead	177	aio_sync aio_fsync aio_syncfs aio_fdatasync aio_sync_file_range
		178	aio_pathsync aio_readahead aio_fiemap aio_allocate
204	aio_rename aio_link aio_move aio_copy aio_group	179	aio_rename aio_link aio_move aio_copy aio_group
205	aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown	180	aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown
206	aio_chmod aio_utime aio_truncate);	181	aio_chmod aio_utime aio_truncate
		182	aio_msync aio_mtouch aio_mlock aio_mlockall
		183	aio_statvfs
		184	aio_wd);
207		185
208	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice));	186	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice));
209	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush	187	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush
210	min_parallel max_parallel max_idle	188	min_parallel max_parallel max_idle idle_timeout
211	nreqs nready npending nthreads	189	nreqs nready npending nthreads
212	max_poll_time max_poll_reqs);	190	max_poll_time max_poll_reqs
		191	sendfile fadvise madvise
		192	mmap munmap munlock munlockall);
213		193
214	push @AIO_REQ, qw(aio_busy); # not exported	194	push @AIO_REQ, qw(aio_busy); # not exported
215		195
216	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';	196	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';
217		197
…		…
219	XSLoader::load ("IO::AIO", $VERSION);	199	XSLoader::load ("IO::AIO", $VERSION);
220	}	200	}
221		201
222	=head1 FUNCTIONS	202	=head1 FUNCTIONS
223		203
224	=head2 AIO REQUEST FUNCTIONS	204	=head2 QUICK OVERVIEW
		205
		206	This section simply lists the prototypes most of the functions for
		207	quick reference. See the following sections for function-by-function
		208	documentation.
		209
		210	aio_wd $pathname, $callback->($wd)
		211	aio_open $pathname, $flags, $mode, $callback->($fh)
		212	aio_close $fh, $callback->($status)
		213	aio_seek $fh,$offset,$whence, $callback->($offs)
		214	aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
		215	aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
		216	aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
		217	aio_readahead $fh,$offset,$length, $callback->($retval)
		218	aio_stat $fh_or_path, $callback->($status)
		219	aio_lstat $fh, $callback->($status)
		220	aio_statvfs $fh_or_path, $callback->($statvfs)
		221	aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
		222	aio_chown $fh_or_path, $uid, $gid, $callback->($status)
		223	aio_chmod $fh_or_path, $mode, $callback->($status)
		224	aio_truncate $fh_or_path, $offset, $callback->($status)
		225	aio_allocate $fh, $mode, $offset, $len, $callback->($status)
		226	aio_fiemap $fh, $start, $length, $flags, $count, $cb->(\@extents)
		227	aio_unlink $pathname, $callback->($status)
		228	aio_mknod $pathname, $mode, $dev, $callback->($status)
		229	aio_link $srcpath, $dstpath, $callback->($status)
		230	aio_symlink $srcpath, $dstpath, $callback->($status)
		231	aio_readlink $pathname, $callback->($link)
		232	aio_realpath $pathname, $callback->($path)
		233	aio_rename $srcpath, $dstpath, $callback->($status)
		234	aio_mkdir $pathname, $mode, $callback->($status)
		235	aio_rmdir $pathname, $callback->($status)
		236	aio_readdir $pathname, $callback->($entries)
		237	aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		238	IO::AIO::READDIR_DENTS IO::AIO::READDIR_DIRS_FIRST
		239	IO::AIO::READDIR_STAT_ORDER IO::AIO::READDIR_FOUND_UNKNOWN
		240	aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs)
		241	aio_load $pathname, $data, $callback->($status)
		242	aio_copy $srcpath, $dstpath, $callback->($status)
		243	aio_move $srcpath, $dstpath, $callback->($status)
		244	aio_rmtree $pathname, $callback->($status)
		245	aio_fcntl $fh, $cmd, $arg, $callback->($status)
		246	aio_ioctl $fh, $request, $buf, $callback->($status)
		247	aio_sync $callback->($status)
		248	aio_syncfs $fh, $callback->($status)
		249	aio_fsync $fh, $callback->($status)
		250	aio_fdatasync $fh, $callback->($status)
		251	aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		252	aio_pathsync $pathname, $callback->($status)
		253	aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		254	aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		255	aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
		256	aio_mlockall $flags, $callback->($status)
		257	aio_group $callback->(...)
		258	aio_nop $callback->()
		259
		260	$prev_pri = aioreq_pri [$pri]
		261	aioreq_nice $pri_adjust
		262
		263	IO::AIO::poll_wait
		264	IO::AIO::poll_cb
		265	IO::AIO::poll
		266	IO::AIO::flush
		267	IO::AIO::max_poll_reqs $nreqs
		268	IO::AIO::max_poll_time $seconds
		269	IO::AIO::min_parallel $nthreads
		270	IO::AIO::max_parallel $nthreads
		271	IO::AIO::max_idle $nthreads
		272	IO::AIO::idle_timeout $seconds
		273	IO::AIO::max_outstanding $maxreqs
		274	IO::AIO::nreqs
		275	IO::AIO::nready
		276	IO::AIO::npending
		277
		278	IO::AIO::sendfile $ofh, $ifh, $offset, $count
		279	IO::AIO::fadvise $fh, $offset, $len, $advice
		280	IO::AIO::mmap $scalar, $length, $prot, $flags[, $fh[, $offset]]
		281	IO::AIO::munmap $scalar
		282	IO::AIO::madvise $scalar, $offset, $length, $advice
		283	IO::AIO::mprotect $scalar, $offset, $length, $protect
		284	IO::AIO::munlock $scalar, $offset = 0, $length = undef
		285	IO::AIO::munlockall
		286
		287	=head2 API NOTES
225		288
226	All the C<aio_*> calls are more or less thin wrappers around the syscall	289	All the C<aio_*> calls are more or less thin wrappers around the syscall
227	with the same name (sans C<aio_>). The arguments are similar or identical,	290	with the same name (sans C<aio_>). The arguments are similar or identical,
228	and they all accept an additional (and optional) C<$callback> argument	291	and they all accept an additional (and optional) C<$callback> argument
229	which must be a code reference. This code reference will get called with	292	which must be a code reference. This code reference will be called after
230	the syscall return code (e.g. most syscalls return C<-1> on error, unlike	293	the syscall has been executed in an asynchronous fashion. The results
231	perl, which usually delivers "false") as its sole argument after the given	294	of the request will be passed as arguments to the callback (and, if an
232	syscall has been executed asynchronously.	295	error occured, in C<$!>) - for most requests the syscall return code (e.g.
		296	most syscalls return C<-1> on error, unlike perl, which usually delivers
		297	"false").
		298
		299	Some requests (such as C<aio_readdir>) pass the actual results and
		300	communicate failures by passing C<undef>.
233		301
234	All functions expecting a filehandle keep a copy of the filehandle	302	All functions expecting a filehandle keep a copy of the filehandle
235	internally until the request has finished.	303	internally until the request has finished.
236		304
237	All functions return request objects of type L<IO::AIO::REQ> that allow	305	All functions return request objects of type L<IO::AIO::REQ> that allow
238	further manipulation of those requests while they are in-flight.	306	further manipulation of those requests while they are in-flight.
239		307
240	The pathnames you pass to these routines I<must> be absolute and	308	The pathnames you pass to these routines I<should> be absolute. The
241	encoded as octets. The reason for the former is that at the time the	309	reason for this is that at the time the request is being executed, the
242	request is being executed, the current working directory could have	310	current working directory could have changed. Alternatively, you can
243	changed. Alternatively, you can make sure that you never change the	311	make sure that you never change the current working directory anywhere
244	current working directory anywhere in the program and then use relative	312	in the program and then use relative paths. You can also take advantage
245	paths.	313	of IO::AIOs working directory abstraction, that lets you specify paths
		314	relative to some previously-opened "working directory object" - see the
		315	description of the C<IO::AIO::WD> class later in this document.
246		316
247	To encode pathnames as octets, either make sure you either: a) always pass	317	To encode pathnames as octets, either make sure you either: a) always pass
248	in filenames you got from outside (command line, readdir etc.) without	318	in filenames you got from outside (command line, readdir etc.) without
249	tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module and encode	319	tinkering, b) are in your native filesystem encoding, c) use the Encode
250	your pathnames to the locale (or other) encoding in effect in the user	320	module and encode your pathnames to the locale (or other) encoding in
251	environment, d) use Glib::filename_from_unicode on unicode filenames or e)	321	effect in the user environment, d) use Glib::filename_from_unicode on
252	use something else to ensure your scalar has the correct contents.	322	unicode filenames or e) use something else to ensure your scalar has the
		323	correct contents.
253		324
254	This works, btw. independent of the internal UTF-8 bit, which IO::AIO	325	This works, btw. independent of the internal UTF-8 bit, which IO::AIO
255	handles correctly whether it is set or not.	326	handles correctly whether it is set or not.
		327
		328	=head2 AIO REQUEST FUNCTIONS
256		329
257	=over 4	330	=over 4
258		331
259	=item $prev_pri = aioreq_pri [$pri]	332	=item $prev_pri = aioreq_pri [$pri]
260		333
…		…
290		363
291		364
292	=item aio_open $pathname, $flags, $mode, $callback->($fh)	365	=item aio_open $pathname, $flags, $mode, $callback->($fh)
293		366
294	Asynchronously open or create a file and call the callback with a newly	367	Asynchronously open or create a file and call the callback with a newly
295	created filehandle for the file.	368	created filehandle for the file (or C<undef> in case of an error).
296		369
297	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,	370	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,
298	for an explanation.	371	for an explanation.
299		372
300	The C<$flags> argument is a bitmask. See the C<Fcntl> module for a	373	The C<$flags> argument is a bitmask. See the C<Fcntl> module for a
…		…
307	by the umask in effect then the request is being executed, so better never	380	by the umask in effect then the request is being executed, so better never
308	change the umask.	381	change the umask.
309		382
310	Example:	383	Example:
311		384
312	aio_open "/etc/passwd", O_RDONLY, 0, sub {	385	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
313	if ($_[0]) {	386	if ($_[0]) {
314	print "open successful, fh is $_[0]\n";	387	print "open successful, fh is $_[0]\n";
315	...	388	...
316	} else {	389	} else {
317	die "open failed: $!\n";	390	die "open failed: $!\n";
318	}	391	}
319	};	392	};
320		393
		394	In addition to all the common open modes/flags (C<O_RDONLY>, C<O_WRONLY>,
		395	C<O_RDWR>, C<O_CREAT>, C<O_TRUNC>, C<O_EXCL> and C<O_APPEND>), the
		396	following POSIX and non-POSIX constants are available (missing ones on
		397	your system are, as usual, C<0>):
		398
		399	C<O_ASYNC>, C<O_DIRECT>, C<O_NOATIME>, C<O_CLOEXEC>, C<O_NOCTTY>, C<O_NOFOLLOW>,
		400	C<O_NONBLOCK>, C<O_EXEC>, C<O_SEARCH>, C<O_DIRECTORY>, C<O_DSYNC>,
		401	C<O_RSYNC>, C<O_SYNC>, C<O_PATH>, C<O_TMPFILE>, and C<O_TTY_INIT>.
		402
321		403
322	=item aio_close $fh, $callback->($status)	404	=item aio_close $fh, $callback->($status)
323		405
324	Asynchronously close a file and call the callback with the result	406	Asynchronously close a file and call the callback with the result
325	code.	407	code.
…		…
333		415
334	Or in other words: the file descriptor will be closed, but it will not be	416	Or in other words: the file descriptor will be closed, but it will not be
335	free for reuse until the perl filehandle is closed.	417	free for reuse until the perl filehandle is closed.
336		418
337	=cut	419	=cut
		420
		421	=item aio_seek $fh, $offset, $whence, $callback->($offs)
		422
		423	Seeks the filehandle to the new C<$offset>, similarly to perl's
		424	C<sysseek>. The C<$whence> can use the traditional values (C<0> for
		425	C<IO::AIO::SEEK_SET>, C<1> for C<IO::AIO::SEEK_CUR> or C<2> for
		426	C<IO::AIO::SEEK_END>).
		427
		428	The resulting absolute offset will be passed to the callback, or C<-1> in
		429	case of an error.
		430
		431	In theory, the C<$whence> constants could be different than the
		432	corresponding values from L<Fcntl>, but perl guarantees they are the same,
		433	so don't panic.
		434
		435	As a GNU/Linux (and maybe Solaris) extension, also the constants
		436	C<IO::AIO::SEEK_DATA> and C<IO::AIO::SEEK_HOLE> are available, if they
		437	could be found. No guarantees about suitability for use in C<aio_seek> or
		438	Perl's C<sysseek> can be made though, although I would naively assume they
		439	"just work".
338		440
339	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	441	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
340		442
341	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	443	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
342		444
…		…
375		477
376	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts	478	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
377	reading at byte offset C<$in_offset>, and starts writing at the current	479	reading at byte offset C<$in_offset>, and starts writing at the current
378	file offset of C<$out_fh>. Because of that, it is not safe to issue more	480	file offset of C<$out_fh>. Because of that, it is not safe to issue more
379	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each	481	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each
380	other.	482	other. The same C<$in_fh> works fine though, as this function does not
		483	move or use the file offset of C<$in_fh>.
381		484
		485	Please note that C<aio_sendfile> can read more bytes from C<$in_fh> than
		486	are written, and there is no way to find out how many more bytes have been
		487	read from C<aio_sendfile> alone, as C<aio_sendfile> only provides the
		488	number of bytes written to C<$out_fh>. Only if the result value equals
		489	C<$length> one can assume that C<$length> bytes have been read.
		490
		491	Unlike with other C<aio_> functions, it makes a lot of sense to use
		492	C<aio_sendfile> on non-blocking sockets, as long as one end (typically
		493	the C<$in_fh>) is a file - the file I/O will then be asynchronous, while
		494	the socket I/O will be non-blocking. Note, however, that you can run
		495	into a trap where C<aio_sendfile> reads some data with readahead, then
		496	fails to write all data, and when the socket is ready the next time, the
		497	data in the cache is already lost, forcing C<aio_sendfile> to again hit
		498	the disk. Explicit C<aio_read> + C<aio_write> let's you better control
		499	resource usage.
		500
382	This call tries to make use of a native C<sendfile> syscall to provide	501	This call tries to make use of a native C<sendfile>-like syscall to
383	zero-copy operation. For this to work, C<$out_fh> should refer to a	502	provide zero-copy operation. For this to work, C<$out_fh> should refer to
384	socket, and C<$in_fh> should refer to mmap'able file.	503	a socket, and C<$in_fh> should refer to an mmap'able file.
385		504
386	If the native sendfile call fails or is not implemented, it will be	505	If a native sendfile cannot be found or it fails with C<ENOSYS>,
387	emulated, so you can call C<aio_sendfile> on any type of filehandle	506	C<EINVAL>, C<ENOTSUP>, C<EOPNOTSUPP>, C<EAFNOSUPPORT>, C<EPROTOTYPE> or
		507	C<ENOTSOCK>, it will be emulated, so you can call C<aio_sendfile> on any
388	regardless of the limitations of the operating system.	508	type of filehandle regardless of the limitations of the operating system.
389		509
390	Please note, however, that C<aio_sendfile> can read more bytes from	510	As native sendfile syscalls (as practically any non-POSIX interface hacked
391	C<$in_fh> than are written, and there is no way to find out how many	511	together in a hurry to improve benchmark numbers) tend to be rather buggy
392	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only	512	on many systems, this implementation tries to work around some known bugs
393	provides the number of bytes written to C<$out_fh>. Only if the result	513	in Linux and FreeBSD kernels (probably others, too), but that might fail,
394	value equals C<$length> one can assume that C<$length> bytes have been	514	so you really really should check the return value of C<aio_sendfile> -
395	read.	515	fewer bytes than expected might have been transferred.
396		516
397		517
398	=item aio_readahead $fh,$offset,$length, $callback->($retval)	518	=item aio_readahead $fh,$offset,$length, $callback->($retval)
399		519
400	C<aio_readahead> populates the page cache with data from a file so that	520	C<aio_readahead> populates the page cache with data from a file so that
…		…
404	whole pages, so that offset is effectively rounded down to a page boundary	524	whole pages, so that offset is effectively rounded down to a page boundary
405	and bytes are read up to the next page boundary greater than or equal to	525	and bytes are read up to the next page boundary greater than or equal to
406	(off-set+length). C<aio_readahead> does not read beyond the end of the	526	(off-set+length). C<aio_readahead> does not read beyond the end of the
407	file. The current file offset of the file is left unchanged.	527	file. The current file offset of the file is left unchanged.
408		528
409	If that syscall doesn't exist (likely if your OS isn't Linux) it will be	529	If that syscall doesn't exist (likely if your kernel isn't Linux) it will
410	emulated by simply reading the data, which would have a similar effect.	530	be emulated by simply reading the data, which would have a similar effect.
411		531
412		532
413	=item aio_stat $fh_or_path, $callback->($status)	533	=item aio_stat $fh_or_path, $callback->($status)
414		534
415	=item aio_lstat $fh, $callback->($status)	535	=item aio_lstat $fh, $callback->($status)
…		…
422	for an explanation.	542	for an explanation.
423		543
424	Currently, the stats are always 64-bit-stats, i.e. instead of returning an	544	Currently, the stats are always 64-bit-stats, i.e. instead of returning an
425	error when stat'ing a large file, the results will be silently truncated	545	error when stat'ing a large file, the results will be silently truncated
426	unless perl itself is compiled with large file support.	546	unless perl itself is compiled with large file support.
		547
		548	To help interpret the mode and dev/rdev stat values, IO::AIO offers the
		549	following constants and functions (if not implemented, the constants will
		550	be C<0> and the functions will either C<croak> or fall back on traditional
		551	behaviour).
		552
		553	C<S_IFMT>, C<S_IFIFO>, C<S_IFCHR>, C<S_IFBLK>, C<S_IFLNK>, C<S_IFREG>,
		554	C<S_IFDIR>, C<S_IFWHT>, C<S_IFSOCK>, C<IO::AIO::major $dev_t>,
		555	C<IO::AIO::minor $dev_t>, C<IO::AIO::makedev $major, $minor>.
427		556
428	Example: Print the length of F</etc/passwd>:	557	Example: Print the length of F</etc/passwd>:
429		558
430	aio_stat "/etc/passwd", sub {	559	aio_stat "/etc/passwd", sub {
431	$_[0] and die "stat failed: $!";	560	$_[0] and die "stat failed: $!";
432	print "size is ", -s _, "\n";	561	print "size is ", -s _, "\n";
433	};	562	};
434		563
435		564
		565	=item aio_statvfs $fh_or_path, $callback->($statvfs)
		566
		567	Works like the POSIX C<statvfs> or C<fstatvfs> syscalls, depending on
		568	whether a file handle or path was passed.
		569
		570	On success, the callback is passed a hash reference with the following
		571	members: C<bsize>, C<frsize>, C<blocks>, C<bfree>, C<bavail>, C<files>,
		572	C<ffree>, C<favail>, C<fsid>, C<flag> and C<namemax>. On failure, C<undef>
		573	is passed.
		574
		575	The following POSIX IO::AIO::ST_* constants are defined: C<ST_RDONLY> and
		576	C<ST_NOSUID>.
		577
		578	The following non-POSIX IO::AIO::ST_* flag masks are defined to
		579	their correct value when available, or to C<0> on systems that do
		580	not support them: C<ST_NODEV>, C<ST_NOEXEC>, C<ST_SYNCHRONOUS>,
		581	C<ST_MANDLOCK>, C<ST_WRITE>, C<ST_APPEND>, C<ST_IMMUTABLE>, C<ST_NOATIME>,
		582	C<ST_NODIRATIME> and C<ST_RELATIME>.
		583
		584	Example: stat C</wd> and dump out the data if successful.
		585
		586	aio_statvfs "/wd", sub {
		587	my $f = $_[0]
		588	or die "statvfs: $!";
		589
		590	use Data::Dumper;
		591	say Dumper $f;
		592	};
		593
		594	# result:
		595	{
		596	bsize => 1024,
		597	bfree => 4333064312,
		598	blocks => 10253828096,
		599	files => 2050765568,
		600	flag => 4096,
		601	favail => 2042092649,
		602	bavail => 4333064312,
		603	ffree => 2042092649,
		604	namemax => 255,
		605	frsize => 1024,
		606	fsid => 1810
		607	}
		608
		609	Here is a (likely partial - send me updates!) list of fsid values used by
		610	Linux - it is safe to hardcode these when C<$^O> is C<linux>:
		611
		612	0x0000adf5 adfs
		613	0x0000adff affs
		614	0x5346414f afs
		615	0x09041934 anon-inode filesystem
		616	0x00000187 autofs
		617	0x42465331 befs
		618	0x1badface bfs
		619	0x42494e4d binfmt_misc
		620	0x9123683e btrfs
		621	0x0027e0eb cgroupfs
		622	0xff534d42 cifs
		623	0x73757245 coda
		624	0x012ff7b7 coh
		625	0x28cd3d45 cramfs
		626	0x453dcd28 cramfs-wend (wrong endianness)
		627	0x64626720 debugfs
		628	0x00001373 devfs
		629	0x00001cd1 devpts
		630	0x0000f15f ecryptfs
		631	0x00414a53 efs
		632	0x0000137d ext
		633	0x0000ef53 ext2/ext3/ext4
		634	0x0000ef51 ext2
		635	0xf2f52010 f2fs
		636	0x00004006 fat
		637	0x65735546 fuseblk
		638	0x65735543 fusectl
		639	0x0bad1dea futexfs
		640	0x01161970 gfs2
		641	0x47504653 gpfs
		642	0x00004244 hfs
		643	0xf995e849 hpfs
		644	0x00c0ffee hostfs
		645	0x958458f6 hugetlbfs
		646	0x2bad1dea inotifyfs
		647	0x00009660 isofs
		648	0x000072b6 jffs2
		649	0x3153464a jfs
		650	0x6b414653 k-afs
		651	0x0bd00bd0 lustre
		652	0x0000137f minix
		653	0x0000138f minix 30 char names
		654	0x00002468 minix v2
		655	0x00002478 minix v2 30 char names
		656	0x00004d5a minix v3
		657	0x19800202 mqueue
		658	0x00004d44 msdos
		659	0x0000564c novell
		660	0x00006969 nfs
		661	0x6e667364 nfsd
		662	0x00003434 nilfs
		663	0x5346544e ntfs
		664	0x00009fa1 openprom
		665	0x7461636F ocfs2
		666	0x00009fa0 proc
		667	0x6165676c pstorefs
		668	0x0000002f qnx4
		669	0x68191122 qnx6
		670	0x858458f6 ramfs
		671	0x52654973 reiserfs
		672	0x00007275 romfs
		673	0x67596969 rpc_pipefs
		674	0x73636673 securityfs
		675	0xf97cff8c selinux
		676	0x0000517b smb
		677	0x534f434b sockfs
		678	0x73717368 squashfs
		679	0x62656572 sysfs
		680	0x012ff7b6 sysv2
		681	0x012ff7b5 sysv4
		682	0x01021994 tmpfs
		683	0x15013346 udf
		684	0x00011954 ufs
		685	0x54190100 ufs byteswapped
		686	0x00009fa2 usbdevfs
		687	0x01021997 v9fs
		688	0xa501fcf5 vxfs
		689	0xabba1974 xenfs
		690	0x012ff7b4 xenix
		691	0x58465342 xfs
		692	0x012fd16d xia
		693
436	=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)	694	=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
437		695
438	Works like perl's C<utime> function (including the special case of $atime	696	Works like perl's C<utime> function (including the special case of $atime
439	and $mtime being undef). Fractional times are supported if the underlying	697	and $mtime being undef). Fractional times are supported if the underlying
440	syscalls support them.	698	syscalls support them.
…		…
467	=item aio_truncate $fh_or_path, $offset, $callback->($status)	725	=item aio_truncate $fh_or_path, $offset, $callback->($status)
468		726
469	Works like truncate(2) or ftruncate(2).	727	Works like truncate(2) or ftruncate(2).
470		728
471		729
		730	=item aio_allocate $fh, $mode, $offset, $len, $callback->($status)
		731
		732	Allocates or frees disk space according to the C<$mode> argument. See the
		733	linux C<fallocate> documentation for details.
		734
		735	C<$mode> is usually C<0> or C<IO::AIO::FALLOC_FL_KEEP_SIZE> to allocate
		736	space, or C<IO::AIO::FALLOC_FL_PUNCH_HOLE | IO::AIO::FALLOC_FL_KEEP_SIZE>,
		737	to deallocate a file range.
		738
		739	IO::AIO also supports C<FALLOC_FL_COLLAPSE_RANGE>, to remove a range
		740	(without leaving a hole) and C<FALLOC_FL_ZERO_RANGE>, to zero a range (see
		741	your L<fallocate(2)> manpage).
		742
		743	The file system block size used by C<fallocate> is presumably the
		744	C<f_bsize> returned by C<statvfs>.
		745
		746	If C<fallocate> isn't available or cannot be emulated (currently no
		747	emulation will be attempted), passes C<-1> and sets C<$!> to C<ENOSYS>.
		748
		749
472	=item aio_chmod $fh_or_path, $mode, $callback->($status)	750	=item aio_chmod $fh_or_path, $mode, $callback->($status)
473		751
474	Works like perl's C<chmod> function.	752	Works like perl's C<chmod> function.
475		753
476		754
…		…
478		756
479	Asynchronously unlink (delete) a file and call the callback with the	757	Asynchronously unlink (delete) a file and call the callback with the
480	result code.	758	result code.
481		759
482		760
483	=item aio_mknod $path, $mode, $dev, $callback->($status)	761	=item aio_mknod $pathname, $mode, $dev, $callback->($status)
484		762
485	[EXPERIMENTAL]	763	[EXPERIMENTAL]
486		764
487	Asynchronously create a device node (or fifo). See mknod(2).	765	Asynchronously create a device node (or fifo). See mknod(2).
488		766
489	The only (POSIX-) portable way of calling this function is:	767	The only (POSIX-) portable way of calling this function is:
490		768
491	aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ...	769	aio_mknod $pathname, IO::AIO::S_IFIFO | $mode, 0, sub { ...
492		770
		771	See C<aio_stat> for info about some potentially helpful extra constants
		772	and functions.
493		773
494	=item aio_link $srcpath, $dstpath, $callback->($status)	774	=item aio_link $srcpath, $dstpath, $callback->($status)
495		775
496	Asynchronously create a new link to the existing object at C<$srcpath> at	776	Asynchronously create a new link to the existing object at C<$srcpath> at
497	the path C<$dstpath> and call the callback with the result code.	777	the path C<$dstpath> and call the callback with the result code.
…		…
501		781
502	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at	782	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at
503	the path C<$dstpath> and call the callback with the result code.	783	the path C<$dstpath> and call the callback with the result code.
504		784
505		785
506	=item aio_readlink $path, $callback->($link)	786	=item aio_readlink $pathname, $callback->($link)
507		787
508	Asynchronously read the symlink specified by C<$path> and pass it to	788	Asynchronously read the symlink specified by C<$path> and pass it to
509	the callback. If an error occurs, nothing or undef gets passed to the	789	the callback. If an error occurs, nothing or undef gets passed to the
510	callback.	790	callback.
511		791
512		792
		793	=item aio_realpath $pathname, $callback->($path)
		794
		795	Asynchronously make the path absolute and resolve any symlinks in
		796	C<$path>. The resulting path only consists of directories (same as
		797	L<Cwd::realpath>).
		798
		799	This request can be used to get the absolute path of the current working
		800	directory by passing it a path of F<.> (a single dot).
		801
		802
513	=item aio_rename $srcpath, $dstpath, $callback->($status)	803	=item aio_rename $srcpath, $dstpath, $callback->($status)
514		804
515	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as	805	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as
516	rename(2) and call the callback with the result code.	806	rename(2) and call the callback with the result code.
		807
		808	On systems that support the AIO::WD working directory abstraction
		809	natively, the case C<[$wd, "."]> as C<$srcpath> is specialcased - instead
		810	of failing, C<rename> is called on the absolute path of C<$wd>.
517		811
518		812
519	=item aio_mkdir $pathname, $mode, $callback->($status)	813	=item aio_mkdir $pathname, $mode, $callback->($status)
520		814
521	Asynchronously mkdir (create) a directory and call the callback with	815	Asynchronously mkdir (create) a directory and call the callback with
…		…
526	=item aio_rmdir $pathname, $callback->($status)	820	=item aio_rmdir $pathname, $callback->($status)
527		821
528	Asynchronously rmdir (delete) a directory and call the callback with the	822	Asynchronously rmdir (delete) a directory and call the callback with the
529	result code.	823	result code.
530		824
		825	On systems that support the AIO::WD working directory abstraction
		826	natively, the case C<[$wd, "."]> is specialcased - instead of failing,
		827	C<rmdir> is called on the absolute path of C<$wd>.
		828
531		829
532	=item aio_readdir $pathname, $callback->($entries)	830	=item aio_readdir $pathname, $callback->($entries)
533		831
534	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire	832	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
535	directory (i.e. opendir + readdir + closedir). The entries will not be	833	directory (i.e. opendir + readdir + closedir). The entries will not be
536	sorted, and will B<NOT> include the C<.> and C<..> entries.	834	sorted, and will B<NOT> include the C<.> and C<..> entries.
537		835
538	The callback a single argument which is either C<undef> or an array-ref	836	The callback is passed a single argument which is either C<undef> or an
539	with the filenames.	837	array-ref with the filenames.
540		838
541		839
		840	=item aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		841
		842	Quite similar to C<aio_readdir>, but the C<$flags> argument allows one to
		843	tune behaviour and output format. In case of an error, C<$entries> will be
		844	C<undef>.
		845
		846	The flags are a combination of the following constants, ORed together (the
		847	flags will also be passed to the callback, possibly modified):
		848
		849	=over 4
		850
		851	=item IO::AIO::READDIR_DENTS
		852
		853	When this flag is off, then the callback gets an arrayref consisting of
		854	names only (as with C<aio_readdir>), otherwise it gets an arrayref with
		855	C<[$name, $type, $inode]> arrayrefs, each describing a single directory
		856	entry in more detail.
		857
		858	C<$name> is the name of the entry.
		859
		860	C<$type> is one of the C<IO::AIO::DT_xxx> constants:
		861
		862	C<IO::AIO::DT_UNKNOWN>, C<IO::AIO::DT_FIFO>, C<IO::AIO::DT_CHR>, C<IO::AIO::DT_DIR>,
		863	C<IO::AIO::DT_BLK>, C<IO::AIO::DT_REG>, C<IO::AIO::DT_LNK>, C<IO::AIO::DT_SOCK>,
		864	C<IO::AIO::DT_WHT>.
		865
		866	C<IO::AIO::DT_UNKNOWN> means just that: readdir does not know. If you need to
		867	know, you have to run stat yourself. Also, for speed reasons, the C<$type>
		868	scalars are read-only: you can not modify them.
		869
		870	C<$inode> is the inode number (which might not be exact on systems with 64
		871	bit inode numbers and 32 bit perls). This field has unspecified content on
		872	systems that do not deliver the inode information.
		873
		874	=item IO::AIO::READDIR_DIRS_FIRST
		875
		876	When this flag is set, then the names will be returned in an order where
		877	likely directories come first, in optimal stat order. This is useful when
		878	you need to quickly find directories, or you want to find all directories
		879	while avoiding to stat() each entry.
		880
		881	If the system returns type information in readdir, then this is used
		882	to find directories directly. Otherwise, likely directories are names
		883	beginning with ".", or otherwise names with no dots, of which names with
		884	short names are tried first.
		885
		886	=item IO::AIO::READDIR_STAT_ORDER
		887
		888	When this flag is set, then the names will be returned in an order
		889	suitable for stat()'ing each one. That is, when you plan to stat()
		890	all files in the given directory, then the returned order will likely
		891	be fastest.
		892
		893	If both this flag and C<IO::AIO::READDIR_DIRS_FIRST> are specified, then
		894	the likely dirs come first, resulting in a less optimal stat order.
		895
		896	=item IO::AIO::READDIR_FOUND_UNKNOWN
		897
		898	This flag should not be set when calling C<aio_readdirx>. Instead, it
		899	is being set by C<aio_readdirx>, when any of the C<$type>'s found were
		900	C<IO::AIO::DT_UNKNOWN>. The absence of this flag therefore indicates that all
		901	C<$type>'s are known, which can be used to speed up some algorithms.
		902
		903	=back
		904
		905
542	=item aio_load $path, $data, $callback->($status)	906	=item aio_load $pathname, $data, $callback->($status)
543		907
544	This is a composite request that tries to fully load the given file into	908	This is a composite request that tries to fully load the given file into
545	memory. Status is the same as with aio_read.	909	memory. Status is the same as with aio_read.
546		910
547	=cut	911	=cut
…		…
569		933
570	=item aio_copy $srcpath, $dstpath, $callback->($status)	934	=item aio_copy $srcpath, $dstpath, $callback->($status)
571		935
572	Try to copy the I<file> (directories not supported as either source or	936	Try to copy the I<file> (directories not supported as either source or
573	destination) from C<$srcpath> to C<$dstpath> and call the callback with	937	destination) from C<$srcpath> to C<$dstpath> and call the callback with
574	the C<0> (error) or C<-1> ok.	938	a status of C<0> (ok) or C<-1> (error, see C<$!>).
575		939
576	This is a composite request that creates the destination file with	940	This is a composite request that creates the destination file with
577	mode 0200 and copies the contents of the source file into it using	941	mode 0200 and copies the contents of the source file into it using
578	C<aio_sendfile>, followed by restoring atime, mtime, access mode and	942	C<aio_sendfile>, followed by restoring atime, mtime, access mode and
579	uid/gid, in that order.	943	uid/gid, in that order.
…		…
591	my $grp = aio_group $cb;	955	my $grp = aio_group $cb;
592		956
593	aioreq_pri $pri;	957	aioreq_pri $pri;
594	add $grp aio_open $src, O_RDONLY, 0, sub {	958	add $grp aio_open $src, O_RDONLY, 0, sub {
595	if (my $src_fh = $_[0]) {	959	if (my $src_fh = $_[0]) {
596	my @stat = stat $src_fh; # hmm, might bock over nfs?	960	my @stat = stat $src_fh; # hmm, might block over nfs?
597		961
598	aioreq_pri $pri;	962	aioreq_pri $pri;
599	add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {	963	add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {
600	if (my $dst_fh = $_[0]) {	964	if (my $dst_fh = $_[0]) {
601	aioreq_pri $pri;	965	aioreq_pri $pri;
…		…
648		1012
649	=item aio_move $srcpath, $dstpath, $callback->($status)	1013	=item aio_move $srcpath, $dstpath, $callback->($status)
650		1014
651	Try to move the I<file> (directories not supported as either source or	1015	Try to move the I<file> (directories not supported as either source or
652	destination) from C<$srcpath> to C<$dstpath> and call the callback with	1016	destination) from C<$srcpath> to C<$dstpath> and call the callback with
653	the C<0> (error) or C<-1> ok.	1017	a status of C<0> (ok) or C<-1> (error, see C<$!>).
654		1018
655	This is a composite request that tries to rename(2) the file first; if	1019	This is a composite request that tries to rename(2) the file first; if
656	rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if	1020	rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if
657	that is successful, unlinks the C<$srcpath>.	1021	that is successful, unlinks the C<$srcpath>.
658		1022
…		…
669	if ($_[0] && $! == EXDEV) {	1033	if ($_[0] && $! == EXDEV) {
670	aioreq_pri $pri;	1034	aioreq_pri $pri;
671	add $grp aio_copy $src, $dst, sub {	1035	add $grp aio_copy $src, $dst, sub {
672	$grp->result ($_[0]);	1036	$grp->result ($_[0]);
673		1037
674	if (!$_[0]) {	1038	unless ($_[0]) {
675	aioreq_pri $pri;	1039	aioreq_pri $pri;
676	add $grp aio_unlink $src;	1040	add $grp aio_unlink $src;
677	}	1041	}
678	};	1042	};
679	} else {	1043	} else {
…		…
682	};	1046	};
683		1047
684	$grp	1048	$grp
685	}	1049	}
686		1050
687	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)	1051	=item aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs)
688		1052
689	Scans a directory (similar to C<aio_readdir>) but additionally tries to	1053	Scans a directory (similar to C<aio_readdir>) but additionally tries to
690	efficiently separate the entries of directory C<$path> into two sets of	1054	efficiently separate the entries of directory C<$path> into two sets of
691	names, directories you can recurse into (directories), and ones you cannot	1055	names, directories you can recurse into (directories), and ones you cannot
692	recurse into (everything else, including symlinks to directories).	1056	recurse into (everything else, including symlinks to directories).
…		…
709		1073
710	Implementation notes.	1074	Implementation notes.
711		1075
712	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.	1076	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.
713		1077
		1078	If readdir returns file type information, then this is used directly to
		1079	find directories.
		1080
714	After reading the directory, the modification time, size etc. of the	1081	Otherwise, after reading the directory, the modification time, size etc.
715	directory before and after the readdir is checked, and if they match (and	1082	of the directory before and after the readdir is checked, and if they
716	isn't the current time), the link count will be used to decide how many	1083	match (and isn't the current time), the link count will be used to decide
717	entries are directories (if >= 2). Otherwise, no knowledge of the number	1084	how many entries are directories (if >= 2). Otherwise, no knowledge of the
718	of subdirectories will be assumed.	1085	number of subdirectories will be assumed.
719		1086
720	Then entries will be sorted into likely directories (everything without	1087	Then entries will be sorted into likely directories a non-initial dot
721	a non-initial dot currently) and likely non-directories (everything	1088	currently) and likely non-directories (see C<aio_readdirx>). Then every
722	else). Then every entry plus an appended C</.> will be C<stat>'ed,	1089	entry plus an appended C</.> will be C<stat>'ed, likely directories first,
723	likely directories first. If that succeeds, it assumes that the entry	1090	in order of their inode numbers. If that succeeds, it assumes that the
724	is a directory or a symlink to directory (which will be checked	1091	entry is a directory or a symlink to directory (which will be checked
725	seperately). This is often faster than stat'ing the entry itself because	1092	separately). This is often faster than stat'ing the entry itself because
726	filesystems might detect the type of the entry without reading the inode	1093	filesystems might detect the type of the entry without reading the inode
727	data (e.g. ext2fs filetype feature).	1094	data (e.g. ext2fs filetype feature), even on systems that cannot return
		1095	the filetype information on readdir.
728		1096
729	If the known number of directories (link count - 2) has been reached, the	1097	If the known number of directories (link count - 2) has been reached, the
730	rest of the entries is assumed to be non-directories.	1098	rest of the entries is assumed to be non-directories.
731		1099
732	This only works with certainty on POSIX (= UNIX) filesystems, which	1100	This only works with certainty on POSIX (= UNIX) filesystems, which
…		…
745		1113
746	my $grp = aio_group $cb;	1114	my $grp = aio_group $cb;
747		1115
748	$maxreq = 4 if $maxreq <= 0;	1116	$maxreq = 4 if $maxreq <= 0;
749		1117
750	# stat once	1118	# get a wd object
751	aioreq_pri $pri;	1119	aioreq_pri $pri;
752	add $grp aio_stat $path, sub {	1120	add $grp aio_wd $path, sub {
		1121	$_[0]
753	return $grp->result () if $_[0];	1122	or return $grp->result ();
754	my $now = time;
755	my $hash1 = join ":", (stat _)[0,1,3,7,9];
756		1123
757	# read the directory entries	1124	my $wd = [shift, "."];
		1125
		1126	# stat once
758	aioreq_pri $pri;	1127	aioreq_pri $pri;
759	add $grp aio_readdir $path, sub {	1128	add $grp aio_stat $wd, sub {
760	my $entries = shift
761	or return $grp->result ();	1129	return $grp->result () if $_[0];
		1130	my $now = time;
		1131	my $hash1 = join ":", (stat _)[0,1,3,7,9];
762		1132
763	# stat the dir another time	1133	# read the directory entries
764	aioreq_pri $pri;	1134	aioreq_pri $pri;
		1135	add $grp aio_readdirx $wd, READDIR_DIRS_FIRST, sub {
		1136	my $entries = shift
		1137	or return $grp->result ();
		1138
		1139	# stat the dir another time
		1140	aioreq_pri $pri;
765	add $grp aio_stat $path, sub {	1141	add $grp aio_stat $wd, sub {
766	my $hash2 = join ":", (stat _)[0,1,3,7,9];	1142	my $hash2 = join ":", (stat _)[0,1,3,7,9];
767		1143
768	my $ndirs;	1144	my $ndirs;
769		1145
770	# take the slow route if anything looks fishy	1146	# take the slow route if anything looks fishy
771	if ($hash1 ne $hash2 or (stat _)[9] == $now) {	1147	if ($hash1 ne $hash2 or (stat _)[9] == $now) {
772	$ndirs = -1;	1148	$ndirs = -1;
773	} else {	1149	} else {
774	# if nlink == 2, we are finished	1150	# if nlink == 2, we are finished
775	# on non-posix-fs's, we rely on nlink < 2	1151	# for non-posix-fs's, we rely on nlink < 2
776	$ndirs = (stat _)[3] - 2	1152	$ndirs = (stat _)[3] - 2
777	or return $grp->result ([], $entries);	1153	or return $grp->result ([], $entries);
778	}	1154	}
779		1155
780	# sort into likely dirs and likely nondirs
781	# dirs == files without ".", short entries first
782	$entries = [map $_->[0],
783	sort { $b->[1] cmp $a->[1] }
784	map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],
785	@$entries];
786
787	my (@dirs, @nondirs);	1156	my (@dirs, @nondirs);
788		1157
789	my $statgrp = add $grp aio_group sub {	1158	my $statgrp = add $grp aio_group sub {
790	$grp->result (\@dirs, \@nondirs);	1159	$grp->result (\@dirs, \@nondirs);
791	};	1160	};
792		1161
793	limit $statgrp $maxreq;	1162	limit $statgrp $maxreq;
794	feed $statgrp sub {	1163	feed $statgrp sub {
795	return unless @$entries;	1164	return unless @$entries;
796	my $entry = pop @$entries;	1165	my $entry = shift @$entries;
797		1166
798	aioreq_pri $pri;	1167	aioreq_pri $pri;
		1168	$wd->[1] = "$entry/.";
799	add $statgrp aio_stat "$path/$entry/.", sub {	1169	add $statgrp aio_stat $wd, sub {
800	if ($_[0] < 0) {	1170	if ($_[0] < 0) {
801	push @nondirs, $entry;	1171	push @nondirs, $entry;
802	} else {	1172	} else {
803	# need to check for real directory	1173	# need to check for real directory
804	aioreq_pri $pri;	1174	aioreq_pri $pri;
		1175	$wd->[1] = $entry;
805	add $statgrp aio_lstat "$path/$entry", sub {	1176	add $statgrp aio_lstat $wd, sub {
806	if (-d _) {	1177	if (-d _) {
807	push @dirs, $entry;	1178	push @dirs, $entry;
808		1179
809	unless (--$ndirs) {	1180	unless (--$ndirs) {
810	push @nondirs, @$entries;	1181	push @nondirs, @$entries;
811	feed $statgrp;	1182	feed $statgrp;
		1183	}
		1184	} else {
		1185	push @nondirs, $entry;
812	}	1186	}
813	} else {
814	push @nondirs, $entry;
815	}	1187	}
816	}	1188	}
817	}	1189	};
818	};	1190	};
819	};	1191	};
820	};	1192	};
821	};	1193	};
822	};	1194	};
823		1195
824	$grp	1196	$grp
825	}	1197	}
826		1198
827	=item aio_rmtree $path, $callback->($status)	1199	=item aio_rmtree $pathname, $callback->($status)
828		1200
829	Delete a directory tree starting (and including) C<$path>, return the	1201	Delete a directory tree starting (and including) C<$path>, return the
830	status of the final C<rmdir> only. This is a composite request that	1202	status of the final C<rmdir> only. This is a composite request that
831	uses C<aio_scandir> to recurse into and rmdir directories, and unlink	1203	uses C<aio_scandir> to recurse into and rmdir directories, and unlink
832	everything else.	1204	everything else.
833		1205
834	=cut	1206	=cut
835		1207
…		…
857	};	1229	};
858		1230
859	$grp	1231	$grp
860	}	1232	}
861		1233
		1234	=item aio_fcntl $fh, $cmd, $arg, $callback->($status)
		1235
		1236	=item aio_ioctl $fh, $request, $buf, $callback->($status)
		1237
		1238	These work just like the C<fcntl> and C<ioctl> built-in functions, except
		1239	they execute asynchronously and pass the return value to the callback.
		1240
		1241	Both calls can be used for a lot of things, some of which make more sense
		1242	to run asynchronously in their own thread, while some others make less
		1243	sense. For example, calls that block waiting for external events, such
		1244	as locking, will also lock down an I/O thread while it is waiting, which
		1245	can deadlock the whole I/O system. At the same time, there might be no
		1246	alternative to using a thread to wait.
		1247
		1248	So in general, you should only use these calls for things that do
		1249	(filesystem) I/O, not for things that wait for other events (network,
		1250	other processes), although if you are careful and know what you are doing,
		1251	you still can.
		1252
862	=item aio_sync $callback->($status)	1253	=item aio_sync $callback->($status)
863		1254
864	Asynchronously call sync and call the callback when finished.	1255	Asynchronously call sync and call the callback when finished.
865		1256
866	=item aio_fsync $fh, $callback->($status)	1257	=item aio_fsync $fh, $callback->($status)
…		…
873	Asynchronously call fdatasync on the given filehandle and call the	1264	Asynchronously call fdatasync on the given filehandle and call the
874	callback with the fdatasync result code.	1265	callback with the fdatasync result code.
875		1266
876	If this call isn't available because your OS lacks it or it couldn't be	1267	If this call isn't available because your OS lacks it or it couldn't be
877	detected, it will be emulated by calling C<fsync> instead.	1268	detected, it will be emulated by calling C<fsync> instead.
		1269
		1270	=item aio_syncfs $fh, $callback->($status)
		1271
		1272	Asynchronously call the syncfs syscall to sync the filesystem associated
		1273	to the given filehandle and call the callback with the syncfs result
		1274	code. If syncfs is not available, calls sync(), but returns C<-1> and sets
		1275	errno to C<ENOSYS> nevertheless.
878		1276
879	=item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)	1277	=item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
880		1278
881	Sync the data portion of the file specified by C<$offset> and C<$length>	1279	Sync the data portion of the file specified by C<$offset> and C<$length>
882	to disk (but NOT the metadata), by calling the Linux-specific	1280	to disk (but NOT the metadata), by calling the Linux-specific
…		…
886	C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>,	1284	C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>,
887	C<IO::AIO::SYNC_FILE_RANGE_WRITE> and	1285	C<IO::AIO::SYNC_FILE_RANGE_WRITE> and
888	C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range	1286	C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range
889	manpage for details.	1287	manpage for details.
890		1288
891	=item aio_pathsync $path, $callback->($status)	1289	=item aio_pathsync $pathname, $callback->($status)
892		1290
893	This request tries to open, fsync and close the given path. This is a	1291	This request tries to open, fsync and close the given path. This is a
894	composite request intended to sync directories after directory operations	1292	composite request intended to sync directories after directory operations
895	(E.g. rename). This might not work on all operating systems or have any	1293	(E.g. rename). This might not work on all operating systems or have any
896	specific effect, but usually it makes sure that directory changes get	1294	specific effect, but usually it makes sure that directory changes get
897	written to disc. It works for anything that can be opened for read-only,	1295	written to disc. It works for anything that can be opened for read-only,
898	not just directories.	1296	not just directories.
		1297
		1298	Future versions of this function might fall back to other methods when
		1299	C<fsync> on the directory fails (such as calling C<sync>).
899		1300
900	Passes C<0> when everything went ok, and C<-1> on error.	1301	Passes C<0> when everything went ok, and C<-1> on error.
901		1302
902	=cut	1303	=cut
903		1304
…		…
924	};	1325	};
925		1326
926	$grp	1327	$grp
927	}	1328	}
928		1329
		1330	=item aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		1331
		1332	This is a rather advanced IO::AIO call, which only works on mmap(2)ed
		1333	scalars (see the C<IO::AIO::mmap> function, although it also works on data
		1334	scalars managed by the L<Sys::Mmap> or L<Mmap> modules, note that the
		1335	scalar must only be modified in-place while an aio operation is pending on
		1336	it).
		1337
		1338	It calls the C<msync> function of your OS, if available, with the memory
		1339	area starting at C<$offset> in the string and ending C<$length> bytes
		1340	later. If C<$length> is negative, counts from the end, and if C<$length>
		1341	is C<undef>, then it goes till the end of the string. The flags can be
		1342	a combination of C<IO::AIO::MS_ASYNC>, C<IO::AIO::MS_INVALIDATE> and
		1343	C<IO::AIO::MS_SYNC>.
		1344
		1345	=item aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		1346
		1347	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1348	scalars.
		1349
		1350	It touches (reads or writes) all memory pages in the specified
		1351	range inside the scalar. All caveats and parameters are the same
		1352	as for C<aio_msync>, above, except for flags, which must be either
		1353	C<0> (which reads all pages and ensures they are instantiated) or
		1354	C<IO::AIO::MT_MODIFY>, which modifies the memory pages (by reading and
		1355	writing an octet from it, which dirties the page).
		1356
		1357	=item aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
		1358
		1359	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1360	scalars.
		1361
		1362	It reads in all the pages of the underlying storage into memory (if any)
		1363	and locks them, so they are not getting swapped/paged out or removed.
		1364
		1365	If C<$length> is undefined, then the scalar will be locked till the end.
		1366
		1367	On systems that do not implement C<mlock>, this function returns C<-1>
		1368	and sets errno to C<ENOSYS>.
		1369
		1370	Note that the corresponding C<munlock> is synchronous and is
		1371	documented under L<MISCELLANEOUS FUNCTIONS>.
		1372
		1373	Example: open a file, mmap and mlock it - both will be undone when
		1374	C<$data> gets destroyed.
		1375
		1376	open my $fh, "<", $path or die "$path: $!";
		1377	my $data;
		1378	IO::AIO::mmap $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh;
		1379	aio_mlock $data; # mlock in background
		1380
		1381	=item aio_mlockall $flags, $callback->($status)
		1382
		1383	Calls the C<mlockall> function with the given C<$flags> (a combination of
		1384	C<IO::AIO::MCL_CURRENT> and C<IO::AIO::MCL_FUTURE>).
		1385
		1386	On systems that do not implement C<mlockall>, this function returns C<-1>
		1387	and sets errno to C<ENOSYS>.
		1388
		1389	Note that the corresponding C<munlockall> is synchronous and is
		1390	documented under L<MISCELLANEOUS FUNCTIONS>.
		1391
		1392	Example: asynchronously lock all current and future pages into memory.
		1393
		1394	aio_mlockall IO::AIO::MCL_FUTURE;
		1395
		1396	=item aio_fiemap $fh, $start, $length, $flags, $count, $cb->(\@extents)
		1397
		1398	Queries the extents of the given file (by calling the Linux C<FIEMAP>
		1399	ioctl, see L<http://cvs.schmorp.de/IO-AIO/doc/fiemap.txt> for details). If
		1400	the ioctl is not available on your OS, then this request will fail with
		1401	C<ENOSYS>.
		1402
		1403	C<$start> is the starting offset to query extents for, C<$length> is the
		1404	size of the range to query - if it is C<undef>, then the whole file will
		1405	be queried.
		1406
		1407	C<$flags> is a combination of flags (C<IO::AIO::FIEMAP_FLAG_SYNC> or
		1408	C<IO::AIO::FIEMAP_FLAG_XATTR> - C<IO::AIO::FIEMAP_FLAGS_COMPAT> is also
		1409	exported), and is normally C<0> or C<IO::AIO::FIEMAP_FLAG_SYNC> to query
		1410	the data portion.
		1411
		1412	C<$count> is the maximum number of extent records to return. If it is
		1413	C<undef>, then IO::AIO queries all extents of the range. As a very special
		1414	case, if it is C<0>, then the callback receives the number of extents
		1415	instead of the extents themselves (which is unreliable, see below).
		1416
		1417	If an error occurs, the callback receives no arguments. The special
		1418	C<errno> value C<IO::AIO::EBADR> is available to test for flag errors.
		1419
		1420	Otherwise, the callback receives an array reference with extent
		1421	structures. Each extent structure is an array reference itself, with the
		1422	following members:
		1423
		1424	[$logical, $physical, $length, $flags]
		1425
		1426	Flags is any combination of the following flag values (typically either C<0>
		1427	or C<IO::AIO::FIEMAP_EXTENT_LAST> (1)):
		1428
		1429	C<IO::AIO::FIEMAP_EXTENT_LAST>, C<IO::AIO::FIEMAP_EXTENT_UNKNOWN>,
		1430	C<IO::AIO::FIEMAP_EXTENT_DELALLOC>, C<IO::AIO::FIEMAP_EXTENT_ENCODED>,
		1431	C<IO::AIO::FIEMAP_EXTENT_DATA_ENCRYPTED>, C<IO::AIO::FIEMAP_EXTENT_NOT_ALIGNED>,
		1432	C<IO::AIO::FIEMAP_EXTENT_DATA_INLINE>, C<IO::AIO::FIEMAP_EXTENT_DATA_TAIL>,
		1433	C<IO::AIO::FIEMAP_EXTENT_UNWRITTEN>, C<IO::AIO::FIEMAP_EXTENT_MERGED> or
		1434	C<IO::AIO::FIEMAP_EXTENT_SHARED>.
		1435
		1436	At the time of this writing (Linux 3.2), this requets is unreliable unless
		1437	C<$count> is C<undef>, as the kernel has all sorts of bugs preventing
		1438	it to return all extents of a range for files with large number of
		1439	extents. The code works around all these issues if C<$count> is undef.
		1440
929	=item aio_group $callback->(...)	1441	=item aio_group $callback->(...)
930		1442
931	This is a very special aio request: Instead of doing something, it is a	1443	This is a very special aio request: Instead of doing something, it is a
932	container for other aio requests, which is useful if you want to bundle	1444	container for other aio requests, which is useful if you want to bundle
933	many requests into a single, composite, request with a definite callback	1445	many requests into a single, composite, request with a definite callback
…		…
970	immense (it blocks a thread for a long time) so do not use this function	1482	immense (it blocks a thread for a long time) so do not use this function
971	except to put your application under artificial I/O pressure.	1483	except to put your application under artificial I/O pressure.
972		1484
973	=back	1485	=back
974		1486
		1487
		1488	=head2 IO::AIO::WD - multiple working directories
		1489
		1490	Your process only has one current working directory, which is used by all
		1491	threads. This makes it hard to use relative paths (some other component
		1492	could call C<chdir> at any time, and it is hard to control when the path
		1493	will be used by IO::AIO).
		1494
		1495	One solution for this is to always use absolute paths. This usually works,
		1496	but can be quite slow (the kernel has to walk the whole path on every
		1497	access), and can also be a hassle to implement.
		1498
		1499	Newer POSIX systems have a number of functions (openat, fdopendir,
		1500	futimensat and so on) that make it possible to specify working directories
		1501	per operation.
		1502
		1503	For portability, and because the clowns who "designed", or shall I write,
		1504	perpetrated this new interface were obviously half-drunk, this abstraction
		1505	cannot be perfect, though.
		1506
		1507	IO::AIO allows you to convert directory paths into a so-called IO::AIO::WD
		1508	object. This object stores the canonicalised, absolute version of the
		1509	path, and on systems that allow it, also a directory file descriptor.
		1510
		1511	Everywhere where a pathname is accepted by IO::AIO (e.g. in C<aio_stat>
		1512	or C<aio_unlink>), one can specify an array reference with an IO::AIO::WD
		1513	object and a pathname instead (or the IO::AIO::WD object alone, which
		1514	gets interpreted as C<[$wd, "."]>). If the pathname is absolute, the
		1515	IO::AIO::WD object is ignored, otherwise the pathname is resolved relative
		1516	to that IO::AIO::WD object.
		1517
		1518	For example, to get a wd object for F</etc> and then stat F<passwd>
		1519	inside, you would write:
		1520
		1521	aio_wd "/etc", sub {
		1522	my $etcdir = shift;
		1523
		1524	# although $etcdir can be undef on error, there is generally no reason
		1525	# to check for errors here, as aio_stat will fail with ENOENT
		1526	# when $etcdir is undef.
		1527
		1528	aio_stat [$etcdir, "passwd"], sub {
		1529	# yay
		1530	};
		1531	};
		1532
		1533	The fact that C<aio_wd> is a request and not a normal function shows that
		1534	creating an IO::AIO::WD object is itself a potentially blocking operation,
		1535	which is why it is done asynchronously.
		1536
		1537	To stat the directory obtained with C<aio_wd> above, one could write
		1538	either of the following three request calls:
		1539
		1540	aio_lstat "/etc" , sub { ... # pathname as normal string
		1541	aio_lstat [$wd, "."], sub { ... # "." relative to $wd (i.e. $wd itself)
		1542	aio_lstat $wd , sub { ... # shorthand for the previous
		1543
		1544	As with normal pathnames, IO::AIO keeps a copy of the working directory
		1545	object and the pathname string, so you could write the following without
		1546	causing any issues due to C<$path> getting reused:
		1547
		1548	my $path = [$wd, undef];
		1549
		1550	for my $name (qw(abc def ghi)) {
		1551	$path->[1] = $name;
		1552	aio_stat $path, sub {
		1553	# ...
		1554	};
		1555	}
		1556
		1557	There are some caveats: when directories get renamed (or deleted), the
		1558	pathname string doesn't change, so will point to the new directory (or
		1559	nowhere at all), while the directory fd, if available on the system,
		1560	will still point to the original directory. Most functions accepting a
		1561	pathname will use the directory fd on newer systems, and the string on
		1562	older systems. Some functions (such as realpath) will always rely on the
		1563	string form of the pathname.
		1564
		1565	So this functionality is mainly useful to get some protection against
		1566	C<chdir>, to easily get an absolute path out of a relative path for future
		1567	reference, and to speed up doing many operations in the same directory
		1568	(e.g. when stat'ing all files in a directory).
		1569
		1570	The following functions implement this working directory abstraction:
		1571
		1572	=over 4
		1573
		1574	=item aio_wd $pathname, $callback->($wd)
		1575
		1576	Asynchonously canonicalise the given pathname and convert it to an
		1577	IO::AIO::WD object representing it. If possible and supported on the
		1578	system, also open a directory fd to speed up pathname resolution relative
		1579	to this working directory.
		1580
		1581	If something goes wrong, then C<undef> is passwd to the callback instead
		1582	of a working directory object and C<$!> is set appropriately. Since
		1583	passing C<undef> as working directory component of a pathname fails the
		1584	request with C<ENOENT>, there is often no need for error checking in the
		1585	C<aio_wd> callback, as future requests using the value will fail in the
		1586	expected way.
		1587
		1588	=item IO::AIO::CWD
		1589
		1590	This is a compiletime constant (object) that represents the process
		1591	current working directory.
		1592
		1593	Specifying this object as working directory object for a pathname is as if
		1594	the pathname would be specified directly, without a directory object. For
		1595	example, these calls are functionally identical:
		1596
		1597	aio_stat "somefile", sub { ... };
		1598	aio_stat [IO::AIO::CWD, "somefile"], sub { ... };
		1599
		1600	=back
		1601
		1602	To recover the path associated with an IO::AIO::WD object, you can use
		1603	C<aio_realpath>:
		1604
		1605	aio_realpath $wd, sub {
		1606	warn "path is $_[0]\n";
		1607	};
		1608
		1609	Currently, C<aio_statvfs> always, and C<aio_rename> and C<aio_rmdir>
		1610	sometimes, fall back to using an absolue path.
		1611
975	=head2 IO::AIO::REQ CLASS	1612	=head2 IO::AIO::REQ CLASS
976		1613
977	All non-aggregate C<aio_*> functions return an object of this class when	1614	All non-aggregate C<aio_*> functions return an object of this class when
978	called in non-void context.	1615	called in non-void context.
979		1616
…		…
982	=item cancel $req	1619	=item cancel $req
983		1620
984	Cancels the request, if possible. Has the effect of skipping execution	1621	Cancels the request, if possible. Has the effect of skipping execution
985	when entering the B<execute> state and skipping calling the callback when	1622	when entering the B<execute> state and skipping calling the callback when
986	entering the the B<result> state, but will leave the request otherwise	1623	entering the the B<result> state, but will leave the request otherwise
987	untouched. That means that requests that currently execute will not be	1624	untouched (with the exception of readdir). That means that requests that
988	stopped and resources held by the request will not be freed prematurely.	1625	currently execute will not be stopped and resources held by the request
		1626	will not be freed prematurely.
989		1627
990	=item cb $req $callback->(...)	1628	=item cb $req $callback->(...)
991		1629
992	Replace (or simply set) the callback registered to the request.	1630	Replace (or simply set) the callback registered to the request.
993		1631
…		…
1067	=item $grp->cancel_subs	1705	=item $grp->cancel_subs
1068		1706
1069	Cancel all subrequests and clears any feeder, but not the group request	1707	Cancel all subrequests and clears any feeder, but not the group request
1070	itself. Useful when you queued a lot of events but got a result early.	1708	itself. Useful when you queued a lot of events but got a result early.
1071		1709
		1710	The group request will finish normally (you cannot add requests to the
		1711	group).
		1712
1072	=item $grp->result (...)	1713	=item $grp->result (...)
1073		1714
1074	Set the result value(s) that will be passed to the group callback when all	1715	Set the result value(s) that will be passed to the group callback when all
1075	subrequests have finished and set the groups errno to the current value	1716	subrequests have finished and set the groups errno to the current value
1076	of errno (just like calling C<errno> without an error number). By default,	1717	of errno (just like calling C<errno> without an error number). By default,
…		…
1092		1733
1093	Sets a feeder/generator on this group: every group can have an attached	1734	Sets a feeder/generator on this group: every group can have an attached
1094	generator that generates requests if idle. The idea behind this is that,	1735	generator that generates requests if idle. The idea behind this is that,
1095	although you could just queue as many requests as you want in a group,	1736	although you could just queue as many requests as you want in a group,
1096	this might starve other requests for a potentially long time. For example,	1737	this might starve other requests for a potentially long time. For example,
1097	C<aio_scandir> might generate hundreds of thousands C<aio_stat> requests,	1738	C<aio_scandir> might generate hundreds of thousands of C<aio_stat>
1098	delaying any later requests for a long time.	1739	requests, delaying any later requests for a long time.
1099		1740
1100	To avoid this, and allow incremental generation of requests, you can	1741	To avoid this, and allow incremental generation of requests, you can
1101	instead a group and set a feeder on it that generates those requests. The	1742	instead a group and set a feeder on it that generates those requests. The
1102	feed callback will be called whenever there are few enough (see C<limit>,	1743	feed callback will be called whenever there are few enough (see C<limit>,
1103	below) requests active in the group itself and is expected to queue more	1744	below) requests active in the group itself and is expected to queue more
…		…
1144	=over 4	1785	=over 4
1145		1786
1146	=item $fileno = IO::AIO::poll_fileno	1787	=item $fileno = IO::AIO::poll_fileno
1147		1788
1148	Return the I<request result pipe file descriptor>. This filehandle must be	1789	Return the I<request result pipe file descriptor>. This filehandle must be
1149	polled for reading by some mechanism outside this module (e.g. Event or	1790	polled for reading by some mechanism outside this module (e.g. EV, Glib,
1150	select, see below or the SYNOPSIS). If the pipe becomes readable you have	1791	select and so on, see below or the SYNOPSIS). If the pipe becomes readable
1151	to call C<poll_cb> to check the results.	1792	you have to call C<poll_cb> to check the results.
1152		1793
1153	See C<poll_cb> for an example.	1794	See C<poll_cb> for an example.
1154		1795
1155	=item IO::AIO::poll_cb	1796	=item IO::AIO::poll_cb
1156		1797
1157	Process some outstanding events on the result pipe. You have to call this	1798	Process some requests that have reached the result phase (i.e. they have
1158	regularly. Returns C<0> if all events could be processed, or C<-1> if it	1799	been executed but the results are not yet reported). You have to call
1159	returned earlier for whatever reason. Returns immediately when no events	1800	this "regularly" to finish outstanding requests.
1160	are outstanding. The amount of events processed depends on the settings of
1161	C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>.
1162		1801
		1802	Returns C<0> if all events could be processed (or there were no
		1803	events to process), or C<-1> if it returned earlier for whatever
		1804	reason. Returns immediately when no events are outstanding. The amount
		1805	of events processed depends on the settings of C<IO::AIO::max_poll_req>,
		1806	C<IO::AIO::max_poll_time> and C<IO::AIO::max_outstanding>.
		1807
1163	If not all requests were processed for whatever reason, the filehandle	1808	If not all requests were processed for whatever reason, the poll file
1164	will still be ready when C<poll_cb> returns, so normally you don't have to	1809	descriptor will still be ready when C<poll_cb> returns, so normally you
1165	do anything special to have it called later.	1810	don't have to do anything special to have it called later.
		1811
		1812	Apart from calling C<IO::AIO::poll_cb> when the event filehandle becomes
		1813	ready, it can be beneficial to call this function from loops which submit
		1814	a lot of requests, to make sure the results get processed when they become
		1815	available and not just when the loop is finished and the event loop takes
		1816	over again. This function returns very fast when there are no outstanding
		1817	requests.
1166		1818
1167	Example: Install an Event watcher that automatically calls	1819	Example: Install an Event watcher that automatically calls
1168	IO::AIO::poll_cb with high priority:	1820	IO::AIO::poll_cb with high priority (more examples can be found in the
		1821	SYNOPSIS section, at the top of this document):
1169		1822
1170	Event->io (fd => IO::AIO::poll_fileno,	1823	Event->io (fd => IO::AIO::poll_fileno,
1171	poll => 'r', async => 1,	1824	poll => 'r', async => 1,
1172	cb => \&IO::AIO::poll_cb);	1825	cb => \&IO::AIO::poll_cb);
		1826
		1827	=item IO::AIO::poll_wait
		1828
		1829	Wait until either at least one request is in the result phase or no
		1830	requests are outstanding anymore.
		1831
		1832	This is useful if you want to synchronously wait for some requests to
		1833	become ready, without actually handling them.
		1834
		1835	See C<nreqs> for an example.
		1836
		1837	=item IO::AIO::poll
		1838
		1839	Waits until some requests have been handled.
		1840
		1841	Returns the number of requests processed, but is otherwise strictly
		1842	equivalent to:
		1843
		1844	IO::AIO::poll_wait, IO::AIO::poll_cb
		1845
		1846	=item IO::AIO::flush
		1847
		1848	Wait till all outstanding AIO requests have been handled.
		1849
		1850	Strictly equivalent to:
		1851
		1852	IO::AIO::poll_wait, IO::AIO::poll_cb
		1853	while IO::AIO::nreqs;
1173		1854
1174	=item IO::AIO::max_poll_reqs $nreqs	1855	=item IO::AIO::max_poll_reqs $nreqs
1175		1856
1176	=item IO::AIO::max_poll_time $seconds	1857	=item IO::AIO::max_poll_time $seconds
1177		1858
…		…
1202	# use a low priority so other tasks have priority	1883	# use a low priority so other tasks have priority
1203	Event->io (fd => IO::AIO::poll_fileno,	1884	Event->io (fd => IO::AIO::poll_fileno,
1204	poll => 'r', nice => 1,	1885	poll => 'r', nice => 1,
1205	cb => &IO::AIO::poll_cb);	1886	cb => &IO::AIO::poll_cb);
1206		1887
1207	=item IO::AIO::poll_wait
1208
1209	If there are any outstanding requests and none of them in the result
1210	phase, wait till the result filehandle becomes ready for reading (simply
1211	does a C<select> on the filehandle. This is useful if you want to
1212	synchronously wait for some requests to finish).
1213
1214	See C<nreqs> for an example.
1215
1216	=item IO::AIO::poll
1217
1218	Waits until some requests have been handled.
1219
1220	Returns the number of requests processed, but is otherwise strictly
1221	equivalent to:
1222
1223	IO::AIO::poll_wait, IO::AIO::poll_cb
1224
1225	=item IO::AIO::flush
1226
1227	Wait till all outstanding AIO requests have been handled.
1228
1229	Strictly equivalent to:
1230
1231	IO::AIO::poll_wait, IO::AIO::poll_cb
1232	while IO::AIO::nreqs;
1233
1234	=back	1888	=back
1235		1889
1236	=head3 CONTROLLING THE NUMBER OF THREADS	1890	=head3 CONTROLLING THE NUMBER OF THREADS
1237		1891
1238	=over	1892	=over
…		…
1271		1925
1272	Under normal circumstances you don't need to call this function.	1926	Under normal circumstances you don't need to call this function.
1273		1927
1274	=item IO::AIO::max_idle $nthreads	1928	=item IO::AIO::max_idle $nthreads
1275		1929
1276	Limit the number of threads (default: 4) that are allowed to idle (i.e.,	1930	Limit the number of threads (default: 4) that are allowed to idle
1277	threads that did not get a request to process within 10 seconds). That	1931	(i.e., threads that did not get a request to process within the idle
1278	means if a thread becomes idle while C<$nthreads> other threads are also	1932	timeout (default: 10 seconds). That means if a thread becomes idle while
1279	idle, it will free its resources and exit.	1933	C<$nthreads> other threads are also idle, it will free its resources and
		1934	exit.
1280		1935
1281	This is useful when you allow a large number of threads (e.g. 100 or 1000)	1936	This is useful when you allow a large number of threads (e.g. 100 or 1000)
1282	to allow for extremely high load situations, but want to free resources	1937	to allow for extremely high load situations, but want to free resources
1283	under normal circumstances (1000 threads can easily consume 30MB of RAM).	1938	under normal circumstances (1000 threads can easily consume 30MB of RAM).
1284		1939
1285	The default is probably ok in most situations, especially if thread	1940	The default is probably ok in most situations, especially if thread
1286	creation is fast. If thread creation is very slow on your system you might	1941	creation is fast. If thread creation is very slow on your system you might
1287	want to use larger values.	1942	want to use larger values.
1288		1943
		1944	=item IO::AIO::idle_timeout $seconds
		1945
		1946	Sets the minimum idle timeout (default 10) after which worker threads are
		1947	allowed to exit. SEe C<IO::AIO::max_idle>.
		1948
1289	=item IO::AIO::max_outstanding $maxreqs	1949	=item IO::AIO::max_outstanding $maxreqs
		1950
		1951	Sets the maximum number of outstanding requests to C<$nreqs>. If
		1952	you do queue up more than this number of requests, the next call to
		1953	C<IO::AIO::poll_cb> (and other functions calling C<poll_cb>, such as
		1954	C<IO::AIO::flush> or C<IO::AIO::poll>) will block until the limit is no
		1955	longer exceeded.
		1956
		1957	In other words, this setting does not enforce a queue limit, but can be
		1958	used to make poll functions block if the limit is exceeded.
1290		1959
1291	This is a very bad function to use in interactive programs because it	1960	This is a very bad function to use in interactive programs because it
1292	blocks, and a bad way to reduce concurrency because it is inexact: Better	1961	blocks, and a bad way to reduce concurrency because it is inexact: Better
1293	use an C<aio_group> together with a feed callback.	1962	use an C<aio_group> together with a feed callback.
1294		1963
1295	Sets the maximum number of outstanding requests to C<$nreqs>. If you	1964	Its main use is in scripts without an event loop - when you want to stat
1296	do queue up more than this number of requests, the next call to the	1965	a lot of files, you can write somehting like this:
1297	C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>)
1298	function will block until the limit is no longer exceeded.
1299		1966
1300	The default value is very large, so there is no practical limit on the	1967	IO::AIO::max_outstanding 32;
1301	number of outstanding requests.
1302		1968
1303	You can still queue as many requests as you want. Therefore,	1969	for my $path (...) {
1304	C<max_outstanding> is mainly useful in simple scripts (with low values) or	1970	aio_stat $path , ...;
1305	as a stop gap to shield against fatal memory overflow (with large values).	1971	IO::AIO::poll_cb;
		1972	}
		1973
		1974	IO::AIO::flush;
		1975
		1976	The call to C<poll_cb> inside the loop will normally return instantly, but
		1977	as soon as more thna C<32> reqeusts are in-flight, it will block until
		1978	some requests have been handled. This keeps the loop from pushing a large
		1979	number of C<aio_stat> requests onto the queue.
		1980
		1981	The default value for C<max_outstanding> is very large, so there is no
		1982	practical limit on the number of outstanding requests.
1306		1983
1307	=back	1984	=back
1308		1985
1309	=head3 STATISTICAL INFORMATION	1986	=head3 STATISTICAL INFORMATION
1310		1987
…		…
1330	Returns the number of requests currently in the pending state (executed,	2007	Returns the number of requests currently in the pending state (executed,
1331	but not yet processed by poll_cb).	2008	but not yet processed by poll_cb).
1332		2009
1333	=back	2010	=back
1334		2011
		2012	=head3 MISCELLANEOUS FUNCTIONS
		2013
		2014	IO::AIO implements some functions that are useful when you want to use
		2015	some "Advanced I/O" function not available to in Perl, without going the
		2016	"Asynchronous I/O" route. Many of these have an asynchronous C<aio_*>
		2017	counterpart.
		2018
		2019	=over 4
		2020
		2021	=item IO::AIO::sendfile $ofh, $ifh, $offset, $count
		2022
		2023	Calls the C<eio_sendfile_sync> function, which is like C<aio_sendfile>,
		2024	but is blocking (this makes most sense if you know the input data is
		2025	likely cached already and the output filehandle is set to non-blocking
		2026	operations).
		2027
		2028	Returns the number of bytes copied, or C<-1> on error.
		2029
		2030	=item IO::AIO::fadvise $fh, $offset, $len, $advice
		2031
		2032	Simply calls the C<posix_fadvise> function (see its
		2033	manpage for details). The following advice constants are
		2034	available: C<IO::AIO::FADV_NORMAL>, C<IO::AIO::FADV_SEQUENTIAL>,
		2035	C<IO::AIO::FADV_RANDOM>, C<IO::AIO::FADV_NOREUSE>,
		2036	C<IO::AIO::FADV_WILLNEED>, C<IO::AIO::FADV_DONTNEED>.
		2037
		2038	On systems that do not implement C<posix_fadvise>, this function returns
		2039	ENOSYS, otherwise the return value of C<posix_fadvise>.
		2040
		2041	=item IO::AIO::madvise $scalar, $offset, $len, $advice
		2042
		2043	Simply calls the C<posix_madvise> function (see its
		2044	manpage for details). The following advice constants are
		2045	available: C<IO::AIO::MADV_NORMAL>, C<IO::AIO::MADV_SEQUENTIAL>,
		2046	C<IO::AIO::MADV_RANDOM>, C<IO::AIO::MADV_WILLNEED>, C<IO::AIO::MADV_DONTNEED>.
		2047
		2048	On systems that do not implement C<posix_madvise>, this function returns
		2049	ENOSYS, otherwise the return value of C<posix_madvise>.
		2050
		2051	=item IO::AIO::mprotect $scalar, $offset, $len, $protect
		2052
		2053	Simply calls the C<mprotect> function on the preferably AIO::mmap'ed
		2054	$scalar (see its manpage for details). The following protect
		2055	constants are available: C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_READ>,
		2056	C<IO::AIO::PROT_WRITE>, C<IO::AIO::PROT_EXEC>.
		2057
		2058	On systems that do not implement C<mprotect>, this function returns
		2059	ENOSYS, otherwise the return value of C<mprotect>.
		2060
		2061	=item IO::AIO::mmap $scalar, $length, $prot, $flags, $fh[, $offset]
		2062
		2063	Memory-maps a file (or anonymous memory range) and attaches it to the
		2064	given C<$scalar>, which will act like a string scalar. Returns true on
		2065	success, and false otherwise.
		2066
		2067	The only operations allowed on the scalar are C<substr>/C<vec> that don't
		2068	change the string length, and most read-only operations such as copying it
		2069	or searching it with regexes and so on.
		2070
		2071	Anything else is unsafe and will, at best, result in memory leaks.
		2072
		2073	The memory map associated with the C<$scalar> is automatically removed
		2074	when the C<$scalar> is destroyed, or when the C<IO::AIO::mmap> or
		2075	C<IO::AIO::munmap> functions are called.
		2076
		2077	This calls the C<mmap>(2) function internally. See your system's manual
		2078	page for details on the C<$length>, C<$prot> and C<$flags> parameters.
		2079
		2080	The C<$length> must be larger than zero and smaller than the actual
		2081	filesize.
		2082
		2083	C<$prot> is a combination of C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_EXEC>,
		2084	C<IO::AIO::PROT_READ> and/or C<IO::AIO::PROT_WRITE>,
		2085
		2086	C<$flags> can be a combination of
		2087	C<IO::AIO::MAP_SHARED> or
		2088	C<IO::AIO::MAP_PRIVATE>,
		2089	or a number of system-specific flags (when not available, the are C<0>):
		2090	C<IO::AIO::MAP_ANONYMOUS> (which is set to C<MAP_ANON> if your system only provides this constant),
		2091	C<IO::AIO::MAP_LOCKED>,
		2092	C<IO::AIO::MAP_NORESERVE>,
		2093	C<IO::AIO::MAP_POPULATE>,
		2094	C<IO::AIO::MAP_NONBLOCK>,
		2095	C<IO::AIO::MAP_FIXED>,
		2096	C<IO::AIO::MAP_GROWSDOWN>,
		2097	C<IO::AIO::MAP_32BIT>,
		2098	C<IO::AIO::MAP_HUGETLB> or
		2099	C<IO::AIO::MAP_STACK>.
		2100
		2101	If C<$fh> is C<undef>, then a file descriptor of C<-1> is passed.
		2102
		2103	C<$offset> is the offset from the start of the file - it generally must be
		2104	a multiple of C<IO::AIO::PAGESIZE> and defaults to C<0>.
		2105
		2106	Example:
		2107
		2108	use Digest::MD5;
		2109	use IO::AIO;
		2110
		2111	open my $fh, "<verybigfile"
		2112	or die "$!";
		2113
		2114	IO::AIO::mmap my $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh
		2115	or die "verybigfile: $!";
		2116
		2117	my $fast_md5 = md5 $data;
		2118
		2119	=item IO::AIO::munmap $scalar
		2120
		2121	Removes a previous mmap and undefines the C<$scalar>.
		2122
		2123	=item IO::AIO::munlock $scalar, $offset = 0, $length = undef
		2124
		2125	Calls the C<munlock> function, undoing the effects of a previous
		2126	C<aio_mlock> call (see its description for details).
		2127
		2128	=item IO::AIO::munlockall
		2129
		2130	Calls the C<munlockall> function.
		2131
		2132	On systems that do not implement C<munlockall>, this function returns
		2133	ENOSYS, otherwise the return value of C<munlockall>.
		2134
		2135	=item IO::AIO::splice $r_fh, $r_off, $w_fh, $w_off, $length, $flags
		2136
		2137	Calls the GNU/Linux C<splice(2)> syscall, if available. If C<$r_off> or
		2138	C<$w_off> are C<undef>, then C<NULL> is passed for these, otherwise they
		2139	should be the file offset.
		2140
		2141	C<$r_fh> and C<$w_fh> should not refer to the same file, as splice might
		2142	silently corrupt the data in this case.
		2143
		2144	The following symbol flag values are available: C<IO::AIO::SPLICE_F_MOVE>,
		2145	C<IO::AIO::SPLICE_F_NONBLOCK>, C<IO::AIO::SPLICE_F_MORE> and
		2146	C<IO::AIO::SPLICE_F_GIFT>.
		2147
		2148	See the C<splice(2)> manpage for details.
		2149
		2150	=item IO::AIO::tee $r_fh, $w_fh, $length, $flags
		2151
		2152	Calls the GNU/Linux C<tee(2)> syscall, see its manpage and the
		2153	description for C<IO::AIO::splice> above for details.
		2154
		2155	=item $actual_size = IO::AIO::pipesize $r_fh[, $new_size]
		2156
		2157	Attempts to query or change the pipe buffer size. Obviously works only
		2158	on pipes, and currently works only on GNU/Linux systems, and fails with
		2159	C<-1>/C<ENOSYS> everywhere else. If anybody knows how to influence pipe buffer
		2160	size on other systems, drop me a note.
		2161
		2162	=item ($rfh, $wfh) = IO::AIO::pipe2 [$flags]
		2163
		2164	This is a direct interface to the Linux L<pipe2(2)> system call. If
		2165	C<$flags> is missing or C<0>, then this should be the same as a call to
		2166	perl's built-in C<pipe> function and create a new pipe, and works on
		2167	systems that lack the pipe2 syscall. On win32, this case invokes C<_pipe
		2168	(..., 4096, O_BINARY)>.
		2169
		2170	If C<$flags> is non-zero, it tries to invoke the pipe2 system call with
		2171	the given flags (Linux 2.6.27, glibc 2.9).
		2172
		2173	On success, the read and write file handles are returned.
		2174
		2175	On error, nothing will be returned. If the pipe2 syscall is missing and
		2176	C<$flags> is non-zero, fails with C<ENOSYS>.
		2177
		2178	Please refer to L<pipe2(2)> for more info on the C<$flags>, but at the
		2179	time of this writing, C<IO::AIO::O_CLOEXEC>, C<IO::AIO::O_NONBLOCK> and
		2180	C<IO::AIO::O_DIRECT> (Linux 3.4, for packet-based pipes) were supported.
		2181
		2182	=back
		2183
1335	=cut	2184	=cut
1336		2185
1337	min_parallel 8;	2186	min_parallel 8;
1338		2187
1339	END { flush }	2188	END { flush }
1340		2189
1341	1;	2190	1;
1342		2191
		2192	=head1 EVENT LOOP INTEGRATION
		2193
		2194	It is recommended to use L<AnyEvent::AIO> to integrate IO::AIO
		2195	automatically into many event loops:
		2196
		2197	# AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...)
		2198	use AnyEvent::AIO;
		2199
		2200	You can also integrate IO::AIO manually into many event loops, here are
		2201	some examples of how to do this:
		2202
		2203	# EV integration
		2204	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
		2205
		2206	# Event integration
		2207	Event->io (fd => IO::AIO::poll_fileno,
		2208	poll => 'r',
		2209	cb => \&IO::AIO::poll_cb);
		2210
		2211	# Glib/Gtk2 integration
		2212	add_watch Glib::IO IO::AIO::poll_fileno,
		2213	in => sub { IO::AIO::poll_cb; 1 };
		2214
		2215	# Tk integration
		2216	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
		2217	readable => \&IO::AIO::poll_cb);
		2218
		2219	# Danga::Socket integration
		2220	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
		2221	\&IO::AIO::poll_cb);
		2222
1343	=head2 FORK BEHAVIOUR	2223	=head2 FORK BEHAVIOUR
1344		2224
1345	This module should do "the right thing" when the process using it forks:	2225	Usage of pthreads in a program changes the semantics of fork
		2226	considerably. Specifically, only async-safe functions can be called after
		2227	fork. Perl doesn't know about this, so in general, you cannot call fork
		2228	with defined behaviour in perl if pthreads are involved. IO::AIO uses
		2229	pthreads, so this applies, but many other extensions and (for inexplicable
		2230	reasons) perl itself often is linked against pthreads, so this limitation
		2231	applies to quite a lot of perls.
1346		2232
1347	Before the fork, IO::AIO enters a quiescent state where no requests	2233	This module no longer tries to fight your OS, or POSIX. That means IO::AIO
1348	can be added in other threads and no results will be processed. After	2234	only works in the process that loaded it. Forking is fully supported, but
1349	the fork the parent simply leaves the quiescent state and continues	2235	using IO::AIO in the child is not.
1350	request/result processing, while the child frees the request/result queue
1351	(so that the requests started before the fork will only be handled in the
1352	parent). Threads will be started on demand until the limit set in the
1353	parent process has been reached again.
1354		2236
1355	In short: the parent will, after a short pause, continue as if fork had	2237	You might get around by not I<using> IO::AIO before (or after)
1356	not been called, while the child will act as if IO::AIO has not been used	2238	forking. You could also try to call the L<IO::AIO::reinit> function in the
1357	yet.	2239	child:
		2240
		2241	=over 4
		2242
		2243	=item IO::AIO::reinit
		2244
		2245	Abandons all current requests and I/O threads and simply reinitialises all
		2246	data structures. This is not an operation supported by any standards, but
		2247	happens to work on GNU/Linux and some newer BSD systems.
		2248
		2249	The only reasonable use for this function is to call it after forking, if
		2250	C<IO::AIO> was used in the parent. Calling it while IO::AIO is active in
		2251	the process will result in undefined behaviour. Calling it at any time
		2252	will also result in any undefined (by POSIX) behaviour.
		2253
		2254	=back
1358		2255
1359	=head2 MEMORY USAGE	2256	=head2 MEMORY USAGE
1360		2257
1361	Per-request usage:	2258	Per-request usage:
1362		2259

Diff Legend

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