ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/IO-AIO/AIO.pm

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.24 by root, Sun Jul 31 18:45:48 2005 UTC vs.
Revision 1.246 by root, Fri Apr 11 05:19:40 2014 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) = @_;	10	my $fh = shift
		11	or die "/etc/passwd: $!";
11	...	12	...
12	};	13	};
13		14
14	aio_unlink "/tmp/file", sub { };	15	aio_unlink "/tmp/file", sub { };
15		16
16	aio_read $fh, 30000, 1024, $buffer, 0, sub {	17	aio_read $fh, 30000, 1024, $buffer, 0, sub {
17	$_[0] > 0 or die "read error: $!";	18	$_[0] > 0 or die "read error: $!";
18	};	19	};
19		20
20	# Event	21	# version 2+ has request and group objects
21	Event->io (fd => IO::AIO::poll_fileno,	22	use IO::AIO 2;
22	poll => 'r',
23	cb => \&IO::AIO::poll_cb);
24		23
25	# Glib/Gtk2	24	aioreq_pri 4; # give next request a very high priority
26	add_watch Glib::IO IO::AIO::poll_fileno,	25	my $req = aio_unlink "/tmp/file", sub { };
27	in => sub { IO::AIO::poll_cb; 1 };	26	$req->cancel; # cancel request if still in queue
28		27
29	# Tk	28	my $grp = aio_group sub { print "all stats done\n" };
30	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",	29	add $grp aio_stat "..." for ...;
31	readable => \&IO::AIO::poll_cb);
32
33	# Danga::Socket
34	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
35	\&IO::AIO::poll_cb);
36
37		30
38	=head1 DESCRIPTION	31	=head1 DESCRIPTION
39		32
40	This module implements asynchronous I/O using whatever means your	33	This module implements asynchronous I/O using whatever means your
41	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>).
42		36
		37	Asynchronous means that operations that can normally block your program
		38	(e.g. reading from disk) will be done asynchronously: the operation
		39	will still block, but you can do something else in the meantime. This
		40	is extremely useful for programs that need to stay interactive even
		41	when doing heavy I/O (GUI programs, high performance network servers
		42	etc.), but can also be used to easily do operations in parallel that are
		43	normally done sequentially, e.g. stat'ing many files, which is much faster
		44	on a RAID volume or over NFS when you do a number of stat operations
		45	concurrently.
		46
		47	While most of this works on all types of file descriptors (for
		48	example sockets), using these functions on file descriptors that
		49	support nonblocking operation (again, sockets, pipes etc.) is
		50	very inefficient. Use an event loop for that (such as the L<EV>
		51	module): IO::AIO will naturally fit into such an event loop itself.
		52
43	Currently, a number of threads are started that execute your read/writes	53	In this version, a number of threads are started that execute your
44	and signal their completion. You don't need thread support in your libc or	54	requests and signal their completion. You don't need thread support
45	perl, and the threads created by this module will not be visible to the	55	in perl, and the threads created by this module will not be visible
46	pthreads library. In the future, this module might make use of the native	56	to perl. In the future, this module might make use of the native aio
47	aio functions available on many operating systems. However, they are often	57	functions available on many operating systems. However, they are often
48	not well-supported (Linux doesn't allow them on normal files currently,	58	not well-supported or restricted (GNU/Linux doesn't allow them on normal
49	for example), and they would only support aio_read and aio_write, so the	59	files currently, for example), and they would only support aio_read and
50	remaining functionality would have to be implemented using threads anyway.	60	aio_write, so the remaining functionality would have to be implemented
		61	using threads anyway.
51		62
52	Although the module will work with in the presence of other threads, it is	63	Although the module will work in the presence of other (Perl-) threads,
53	currently not reentrant, so use appropriate locking yourself, always call	64	it is currently not reentrant in any way, so use appropriate locking
54	C<poll_cb> from within the same thread, or never call C<poll_cb> (or other	65	yourself, always call C<poll_cb> from within the same thread, or never
55	C<aio_> functions) recursively.	66	call C<poll_cb> (or other C<aio_> functions) recursively.
		67
		68	=head2 EXAMPLE
		69
		70	This is a simple example that uses the EV module and loads
		71	F</etc/passwd> asynchronously:
		72
		73	use EV;
		74	use IO::AIO;
		75
		76	# register the IO::AIO callback with EV
		77	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
		78
		79	# queue the request to open /etc/passwd
		80	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
		81	my $fh = shift
		82	or die "error while opening: $!";
		83
		84	# stat'ing filehandles is generally non-blocking
		85	my $size = -s $fh;
		86
		87	# queue a request to read the file
		88	my $contents;
		89	aio_read $fh, 0, $size, $contents, 0, sub {
		90	$_[0] == $size
		91	or die "short read: $!";
		92
		93	close $fh;
		94
		95	# file contents now in $contents
		96	print $contents;
		97
		98	# exit event loop and program
		99	EV::unloop;
		100	};
		101	};
		102
		103	# possibly queue up other requests, or open GUI windows,
		104	# check for sockets etc. etc.
		105
		106	# process events as long as there are some:
		107	EV::loop;
		108
		109	=head1 REQUEST ANATOMY AND LIFETIME
		110
		111	Every C<aio_*> function creates a request. which is a C data structure not
		112	directly visible to Perl.
		113
		114	If called in non-void context, every request function returns a Perl
		115	object representing the request. In void context, nothing is returned,
		116	which saves a bit of memory.
		117
		118	The perl object is a fairly standard ref-to-hash object. The hash contents
		119	are not used by IO::AIO so you are free to store anything you like in it.
		120
		121	During their existance, aio requests travel through the following states,
		122	in order:
		123
		124	=over 4
		125
		126	=item ready
		127
		128	Immediately after a request is created it is put into the ready state,
		129	waiting for a thread to execute it.
		130
		131	=item execute
		132
		133	A thread has accepted the request for processing and is currently
		134	executing it (e.g. blocking in read).
		135
		136	=item pending
		137
		138	The request has been executed and is waiting for result processing.
		139
		140	While request submission and execution is fully asynchronous, result
		141	processing is not and relies on the perl interpreter calling C<poll_cb>
		142	(or another function with the same effect).
		143
		144	=item result
		145
		146	The request results are processed synchronously by C<poll_cb>.
		147
		148	The C<poll_cb> function will process all outstanding aio requests by
		149	calling their callbacks, freeing memory associated with them and managing
		150	any groups they are contained in.
		151
		152	=item done
		153
		154	Request has reached the end of its lifetime and holds no resources anymore
		155	(except possibly for the Perl object, but its connection to the actual
		156	aio request is severed and calling its methods will either do nothing or
		157	result in a runtime error).
		158
		159	=back
56		160
57	=cut	161	=cut
58		162
59	package IO::AIO;	163	package IO::AIO;
60		164
61	no warnings;	165	use Carp ();
		166
		167	use common::sense;
62		168
63	use base 'Exporter';	169	use base 'Exporter';
64		170
65	use Fcntl ();
66
67	BEGIN {	171	BEGIN {
68	$VERSION = 1.1;	172	our $VERSION = 4.3;
69		173
70	@EXPORT = qw(aio_read aio_write aio_open aio_close aio_stat aio_lstat aio_unlink	174	our @AIO_REQ = qw(aio_sendfile aio_seek aio_read aio_write aio_open aio_close
71	aio_fsync aio_fdatasync aio_readahead);	175	aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx
72	@EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs);	176	aio_scandir aio_symlink aio_readlink aio_realpath aio_sync
		177	aio_fsync aio_syncfs aio_fdatasync aio_sync_file_range aio_allocate
		178	aio_pathsync aio_readahead aio_fiemap
		179	aio_rename aio_link aio_move aio_copy aio_group
		180	aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown
		181	aio_chmod aio_utime aio_truncate
		182	aio_msync aio_mtouch aio_mlock aio_mlockall
		183	aio_statvfs
		184	aio_wd);
		185
		186	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice));
		187	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush
		188	min_parallel max_parallel max_idle idle_timeout
		189	nreqs nready npending nthreads
		190	max_poll_time max_poll_reqs
		191	sendfile fadvise madvise
		192	mmap munmap munlock munlockall);
		193
		194	push @AIO_REQ, qw(aio_busy); # not exported
		195
		196	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';
73		197
74	require XSLoader;	198	require XSLoader;
75	XSLoader::load IO::AIO, $VERSION;	199	XSLoader::load ("IO::AIO", $VERSION);
76	}	200	}
77		201
78	=head1 FUNCTIONS	202	=head1 FUNCTIONS
79		203
80	=head2 AIO 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, $callback->($link)
		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_sync $callback->($status)
		246	aio_syncfs $fh, $callback->($status)
		247	aio_fsync $fh, $callback->($status)
		248	aio_fdatasync $fh, $callback->($status)
		249	aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		250	aio_pathsync $pathname, $callback->($status)
		251	aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		252	aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		253	aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
		254	aio_mlockall $flags, $callback->($status)
		255	aio_group $callback->(...)
		256	aio_nop $callback->()
		257
		258	$prev_pri = aioreq_pri [$pri]
		259	aioreq_nice $pri_adjust
		260
		261	IO::AIO::poll_wait
		262	IO::AIO::poll_cb
		263	IO::AIO::poll
		264	IO::AIO::flush
		265	IO::AIO::max_poll_reqs $nreqs
		266	IO::AIO::max_poll_time $seconds
		267	IO::AIO::min_parallel $nthreads
		268	IO::AIO::max_parallel $nthreads
		269	IO::AIO::max_idle $nthreads
		270	IO::AIO::idle_timeout $seconds
		271	IO::AIO::max_outstanding $maxreqs
		272	IO::AIO::nreqs
		273	IO::AIO::nready
		274	IO::AIO::npending
		275
		276	IO::AIO::sendfile $ofh, $ifh, $offset, $count
		277	IO::AIO::fadvise $fh, $offset, $len, $advice
		278	IO::AIO::mmap $scalar, $length, $prot, $flags[, $fh[, $offset]]
		279	IO::AIO::munmap $scalar
		280	IO::AIO::madvise $scalar, $offset, $length, $advice
		281	IO::AIO::mprotect $scalar, $offset, $length, $protect
		282	IO::AIO::munlock $scalar, $offset = 0, $length = undef
		283	IO::AIO::munlockall
		284
		285	=head2 API NOTES
81		286
82	All the C<aio_*> calls are more or less thin wrappers around the syscall	287	All the C<aio_*> calls are more or less thin wrappers around the syscall
83	with the same name (sans C<aio_>). The arguments are similar or identical,	288	with the same name (sans C<aio_>). The arguments are similar or identical,
84	and they all accept an additional (and optional) C<$callback> argument	289	and they all accept an additional (and optional) C<$callback> argument
85	which must be a code reference. This code reference will get called with	290	which must be a code reference. This code reference will be called after
86	the syscall return code (e.g. most syscalls return C<-1> on error, unlike	291	the syscall has been executed in an asynchronous fashion. The results
87	perl, which usually delivers "false") as it's sole argument when the given	292	of the request will be passed as arguments to the callback (and, if an
88	syscall has been executed asynchronously.	293	error occured, in C<$!>) - for most requests the syscall return code (e.g.
		294	most syscalls return C<-1> on error, unlike perl, which usually delivers
		295	"false").
		296
		297	Some requests (such as C<aio_readdir>) pass the actual results and
		298	communicate failures by passing C<undef>.
89		299
90	All functions expecting a filehandle keep a copy of the filehandle	300	All functions expecting a filehandle keep a copy of the filehandle
91	internally until the request has finished.	301	internally until the request has finished.
92		302
		303	All functions return request objects of type L<IO::AIO::REQ> that allow
		304	further manipulation of those requests while they are in-flight.
		305
93	The filenames you pass to these routines I<must> be absolute. The reason	306	The pathnames you pass to these routines I<should> be absolute. The
94	for this is that at the time the request is being executed, the current	307	reason for this is that at the time the request is being executed, the
95	working directory could have changed. Alternatively, you can make sure	308	current working directory could have changed. Alternatively, you can
96	that you never change the current working directory.	309	make sure that you never change the current working directory anywhere
		310	in the program and then use relative paths. You can also take advantage
		311	of IO::AIOs working directory abstraction, that lets you specify paths
		312	relative to some previously-opened "working directory object" - see the
		313	description of the C<IO::AIO::WD> class later in this document.
		314
		315	To encode pathnames as octets, either make sure you either: a) always pass
		316	in filenames you got from outside (command line, readdir etc.) without
		317	tinkering, b) are in your native filesystem encoding, c) use the Encode
		318	module and encode your pathnames to the locale (or other) encoding in
		319	effect in the user environment, d) use Glib::filename_from_unicode on
		320	unicode filenames or e) use something else to ensure your scalar has the
		321	correct contents.
		322
		323	This works, btw. independent of the internal UTF-8 bit, which IO::AIO
		324	handles correctly whether it is set or not.
		325
		326	=head2 AIO REQUEST FUNCTIONS
97		327
98	=over 4	328	=over 4
99		329
		330	=item $prev_pri = aioreq_pri [$pri]
		331
		332	Returns the priority value that would be used for the next request and, if
		333	C<$pri> is given, sets the priority for the next aio request.
		334
		335	The default priority is C<0>, the minimum and maximum priorities are C<-4>
		336	and C<4>, respectively. Requests with higher priority will be serviced
		337	first.
		338
		339	The priority will be reset to C<0> after each call to one of the C<aio_*>
		340	functions.
		341
		342	Example: open a file with low priority, then read something from it with
		343	higher priority so the read request is serviced before other low priority
		344	open requests (potentially spamming the cache):
		345
		346	aioreq_pri -3;
		347	aio_open ..., sub {
		348	return unless $_[0];
		349
		350	aioreq_pri -2;
		351	aio_read $_[0], ..., sub {
		352	...
		353	};
		354	};
		355
		356
		357	=item aioreq_nice $pri_adjust
		358
		359	Similar to C<aioreq_pri>, but subtracts the given value from the current
		360	priority, so the effect is cumulative.
		361
		362
100	=item aio_open $pathname, $flags, $mode, $callback	363	=item aio_open $pathname, $flags, $mode, $callback->($fh)
101		364
102	Asynchronously open or create a file and call the callback with a newly	365	Asynchronously open or create a file and call the callback with a newly
103	created filehandle for the file.	366	created filehandle for the file (or C<undef> in case of an error).
104		367
105	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,	368	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,
106	for an explanation.	369	for an explanation.
107		370
108	The C<$flags> argument is a bitmask. See the C<Fcntl> module for a	371	The C<$flags> argument is a bitmask. See the C<Fcntl> module for a
109	list. They are the same as used by C<sysopen>.	372	list. They are the same as used by C<sysopen>.
110		373
111	Likewise, C<$mode> specifies the mode of the newly created file, if it	374	Likewise, C<$mode> specifies the mode of the newly created file, if it
112	didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,	375	didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,
113	except that it is mandatory (i.e. use C<0> if you don't create new files,	376	except that it is mandatory (i.e. use C<0> if you don't create new files,
114	and C<0666> or C<0777> if you do).	377	and C<0666> or C<0777> if you do). Note that the C<$mode> will be modified
		378	by the umask in effect then the request is being executed, so better never
		379	change the umask.
115		380
116	Example:	381	Example:
117		382
118	aio_open "/etc/passwd", O_RDONLY, 0, sub {	383	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
119	if ($_[0]) {	384	if ($_[0]) {
120	print "open successful, fh is $_[0]\n";	385	print "open successful, fh is $_[0]\n";
121	...	386	...
122	} else {	387	} else {
123	die "open failed: $!\n";	388	die "open failed: $!\n";
124	}	389	}
125	};	390	};
126		391
		392	In addition to all the common open modes/flags (C<O_RDONLY>, C<O_WRONLY>,
		393	C<O_RDWR>, C<O_CREAT>, C<O_TRUNC>, C<O_EXCL> and C<O_APPEND>), the
		394	following POSIX and non-POSIX constants are available (missing ones on
		395	your system are, as usual, C<0>):
		396
		397	C<O_ASYNC>, C<O_DIRECT>, C<O_NOATIME>, C<O_CLOEXEC>, C<O_NOCTTY>, C<O_NOFOLLOW>,
		398	C<O_NONBLOCK>, C<O_EXEC>, C<O_SEARCH>, C<O_DIRECTORY>, C<O_DSYNC>,
		399	C<O_RSYNC>, C<O_SYNC> and C<O_TTY_INIT>.
		400
		401
127	=item aio_close $fh, $callback	402	=item aio_close $fh, $callback->($status)
128		403
129	Asynchronously close a file and call the callback with the result	404	Asynchronously close a file and call the callback with the result
130	code. I<WARNING:> although accepted, you should not pass in a perl	405	code.
131	filehandle here, as perl will likely close the file descriptor another
132	time when the filehandle is destroyed. Normally, you can safely call perls
133	C<close> or just let filehandles go out of scope.
134		406
135	This is supposed to be a bug in the API, so that might change. It's	407	Unfortunately, you can't do this to perl. Perl I<insists> very strongly on
136	therefore best to avoid this function.	408	closing the file descriptor associated with the filehandle itself.
137		409
		410	Therefore, C<aio_close> will not close the filehandle - instead it will
		411	use dup2 to overwrite the file descriptor with the write-end of a pipe
		412	(the pipe fd will be created on demand and will be cached).
		413
		414	Or in other words: the file descriptor will be closed, but it will not be
		415	free for reuse until the perl filehandle is closed.
		416
		417	=cut
		418
		419	=item aio_seek $fh, $offset, $whence, $callback->($offs)
		420
		421	Seeks the filehandle to the new C<$offset>, similarly to perl's
		422	C<sysseek>. The C<$whence> can use the traditional values (C<0> for
		423	C<IO::AIO::SEEK_SET>, C<1> for C<IO::AIO::SEEK_CUR> or C<2> for
		424	C<IO::AIO::SEEK_END>).
		425
		426	The resulting absolute offset will be passed to the callback, or C<-1> in
		427	case of an error.
		428
		429	In theory, the C<$whence> constants could be different than the
		430	corresponding values from L<Fcntl>, but perl guarantees they are the same,
		431	so don't panic.
		432
		433	As a GNU/Linux (and maybe Solaris) extension, also the constants
		434	C<IO::AIO::SEEK_DATA> and C<IO::AIO::SEEK_HOLE> are available, if they
		435	could be found. No guarantees about suitability for use in C<aio_seek> or
		436	Perl's C<sysseek> can be made though, although I would naively assume they
		437	"just work".
		438
138	=item aio_read $fh,$offset,$length, $data,$dataoffset,$callback	439	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
139		440
140	=item aio_write $fh,$offset,$length, $data,$dataoffset,$callback	441	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
141		442
142	Reads or writes C<length> bytes from the specified C<fh> and C<offset>	443	Reads or writes C<$length> bytes from or to the specified C<$fh> and
143	into the scalar given by C<data> and offset C<dataoffset> and calls the	444	C<$offset> into the scalar given by C<$data> and offset C<$dataoffset>
144	callback without the actual number of bytes read (or -1 on error, just	445	and calls the callback without the actual number of bytes read (or -1 on
145	like the syscall).	446	error, just like the syscall).
		447
		448	C<aio_read> will, like C<sysread>, shrink or grow the C<$data> scalar to
		449	offset plus the actual number of bytes read.
		450
		451	If C<$offset> is undefined, then the current file descriptor offset will
		452	be used (and updated), otherwise the file descriptor offset will not be
		453	changed by these calls.
		454
		455	If C<$length> is undefined in C<aio_write>, use the remaining length of
		456	C<$data>.
		457
		458	If C<$dataoffset> is less than zero, it will be counted from the end of
		459	C<$data>.
		460
		461	The C<$data> scalar I<MUST NOT> be modified in any way while the request
		462	is outstanding. Modifying it can result in segfaults or World War III (if
		463	the necessary/optional hardware is installed).
146		464
147	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at	465	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at
148	offset C<0> within the scalar:	466	offset C<0> within the scalar:
149		467
150	aio_read $fh, 7, 15, $buffer, 0, sub {	468	aio_read $fh, 7, 15, $buffer, 0, sub {
151	$_[0] > 0 or die "read error: $!";	469	$_[0] > 0 or die "read error: $!";
152	print "read $_[0] bytes: <$buffer>\n";	470	print "read $_[0] bytes: <$buffer>\n";
153	};	471	};
154		472
		473
		474	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
		475
		476	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
		477	reading at byte offset C<$in_offset>, and starts writing at the current
		478	file offset of C<$out_fh>. Because of that, it is not safe to issue more
		479	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each
		480	other. The same C<$in_fh> works fine though, as this function does not
		481	move or use the file offset of C<$in_fh>.
		482
		483	Please note that C<aio_sendfile> can read more bytes from C<$in_fh> than
		484	are written, and there is no way to find out how many more bytes have been
		485	read from C<aio_sendfile> alone, as C<aio_sendfile> only provides the
		486	number of bytes written to C<$out_fh>. Only if the result value equals
		487	C<$length> one can assume that C<$length> bytes have been read.
		488
		489	Unlike with other C<aio_> functions, it makes a lot of sense to use
		490	C<aio_sendfile> on non-blocking sockets, as long as one end (typically
		491	the C<$in_fh>) is a file - the file I/O will then be asynchronous, while
		492	the socket I/O will be non-blocking. Note, however, that you can run
		493	into a trap where C<aio_sendfile> reads some data with readahead, then
		494	fails to write all data, and when the socket is ready the next time, the
		495	data in the cache is already lost, forcing C<aio_sendfile> to again hit
		496	the disk. Explicit C<aio_read> + C<aio_write> let's you better control
		497	resource usage.
		498
		499	This call tries to make use of a native C<sendfile>-like syscall to
		500	provide zero-copy operation. For this to work, C<$out_fh> should refer to
		501	a socket, and C<$in_fh> should refer to an mmap'able file.
		502
		503	If a native sendfile cannot be found or it fails with C<ENOSYS>,
		504	C<EINVAL>, C<ENOTSUP>, C<EOPNOTSUPP>, C<EAFNOSUPPORT>, C<EPROTOTYPE> or
		505	C<ENOTSOCK>, it will be emulated, so you can call C<aio_sendfile> on any
		506	type of filehandle regardless of the limitations of the operating system.
		507
		508	As native sendfile syscalls (as practically any non-POSIX interface hacked
		509	together in a hurry to improve benchmark numbers) tend to be rather buggy
		510	on many systems, this implementation tries to work around some known bugs
		511	in Linux and FreeBSD kernels (probably others, too), but that might fail,
		512	so you really really should check the return value of C<aio_sendfile> -
		513	fewre bytes than expected might have been transferred.
		514
		515
155	=item aio_readahead $fh,$offset,$length, $callback	516	=item aio_readahead $fh,$offset,$length, $callback->($retval)
156
157	Asynchronously reads the specified byte range into the page cache, using
158	the C<readahead> syscall. If that syscall doesn't exist (likely if your OS
159	isn't Linux) the status will be C<-1> and C<$!> is set to C<ENOSYS>.
160		517
161	C<aio_readahead> populates the page cache with data from a file so that	518	C<aio_readahead> populates the page cache with data from a file so that
162	subsequent reads from that file will not block on disk I/O. The C<$offset>	519	subsequent reads from that file will not block on disk I/O. The C<$offset>
163	argument specifies the starting point from which data is to be read and	520	argument specifies the starting point from which data is to be read and
164	C<$length> specifies the number of bytes to be read. I/O is performed in	521	C<$length> specifies the number of bytes to be read. I/O is performed in
165	whole pages, so that offset is effectively rounded down to a page boundary	522	whole pages, so that offset is effectively rounded down to a page boundary
166	and bytes are read up to the next page boundary greater than or equal to	523	and bytes are read up to the next page boundary greater than or equal to
167	(off-set+length). C<aio_readahead> does not read beyond the end of the	524	(off-set+length). C<aio_readahead> does not read beyond the end of the
168	file. The current file offset of the file is left unchanged.	525	file. The current file offset of the file is left unchanged.
169		526
		527	If that syscall doesn't exist (likely if your OS isn't Linux) it will be
		528	emulated by simply reading the data, which would have a similar effect.
		529
		530
170	=item aio_stat $fh_or_path, $callback	531	=item aio_stat $fh_or_path, $callback->($status)
171		532
172	=item aio_lstat $fh, $callback	533	=item aio_lstat $fh, $callback->($status)
173		534
174	Works like perl's C<stat> or C<lstat> in void context. The callback will	535	Works like perl's C<stat> or C<lstat> in void context. The callback will
175	be called after the stat and the results will be available using C<stat _>	536	be called after the stat and the results will be available using C<stat _>
176	or C<-s _> etc...	537	or C<-s _> etc...
177		538
…		…
179	for an explanation.	540	for an explanation.
180		541
181	Currently, the stats are always 64-bit-stats, i.e. instead of returning an	542	Currently, the stats are always 64-bit-stats, i.e. instead of returning an
182	error when stat'ing a large file, the results will be silently truncated	543	error when stat'ing a large file, the results will be silently truncated
183	unless perl itself is compiled with large file support.	544	unless perl itself is compiled with large file support.
		545
		546	To help interpret the mode and dev/rdev stat values, IO::AIO offers the
		547	following constants and functions (if not implemented, the constants will
		548	be C<0> and the functions will either C<croak> or fall back on traditional
		549	behaviour).
		550
		551	C<S_IFMT>, C<S_IFIFO>, C<S_IFCHR>, C<S_IFBLK>, C<S_IFLNK>, C<S_IFREG>,
		552	C<S_IFDIR>, C<S_IFWHT>, C<S_IFSOCK>, C<IO::AIO::major $dev_t>,
		553	C<IO::AIO::minor $dev_t>, C<IO::AIO::makedev $major, $minor>.
184		554
185	Example: Print the length of F</etc/passwd>:	555	Example: Print the length of F</etc/passwd>:
186		556
187	aio_stat "/etc/passwd", sub {	557	aio_stat "/etc/passwd", sub {
188	$_[0] and die "stat failed: $!";	558	$_[0] and die "stat failed: $!";
189	print "size is ", -s _, "\n";	559	print "size is ", -s _, "\n";
190	};	560	};
191		561
		562
		563	=item aio_statvfs $fh_or_path, $callback->($statvfs)
		564
		565	Works like the POSIX C<statvfs> or C<fstatvfs> syscalls, depending on
		566	whether a file handle or path was passed.
		567
		568	On success, the callback is passed a hash reference with the following
		569	members: C<bsize>, C<frsize>, C<blocks>, C<bfree>, C<bavail>, C<files>,
		570	C<ffree>, C<favail>, C<fsid>, C<flag> and C<namemax>. On failure, C<undef>
		571	is passed.
		572
		573	The following POSIX IO::AIO::ST_* constants are defined: C<ST_RDONLY> and
		574	C<ST_NOSUID>.
		575
		576	The following non-POSIX IO::AIO::ST_* flag masks are defined to
		577	their correct value when available, or to C<0> on systems that do
		578	not support them: C<ST_NODEV>, C<ST_NOEXEC>, C<ST_SYNCHRONOUS>,
		579	C<ST_MANDLOCK>, C<ST_WRITE>, C<ST_APPEND>, C<ST_IMMUTABLE>, C<ST_NOATIME>,
		580	C<ST_NODIRATIME> and C<ST_RELATIME>.
		581
		582	Example: stat C</wd> and dump out the data if successful.
		583
		584	aio_statvfs "/wd", sub {
		585	my $f = $_[0]
		586	or die "statvfs: $!";
		587
		588	use Data::Dumper;
		589	say Dumper $f;
		590	};
		591
		592	# result:
		593	{
		594	bsize => 1024,
		595	bfree => 4333064312,
		596	blocks => 10253828096,
		597	files => 2050765568,
		598	flag => 4096,
		599	favail => 2042092649,
		600	bavail => 4333064312,
		601	ffree => 2042092649,
		602	namemax => 255,
		603	frsize => 1024,
		604	fsid => 1810
		605	}
		606
		607	Here is a (likely partial - send me updates!) list of fsid values used by
		608	Linux - it is safe to hardcode these when C<$^O> is C<linux>:
		609
		610	0x0000adf5 adfs
		611	0x0000adff affs
		612	0x5346414f afs
		613	0x09041934 anon-inode filesystem
		614	0x00000187 autofs
		615	0x42465331 befs
		616	0x1badface bfs
		617	0x42494e4d binfmt_misc
		618	0x9123683e btrfs
		619	0x0027e0eb cgroupfs
		620	0xff534d42 cifs
		621	0x73757245 coda
		622	0x012ff7b7 coh
		623	0x28cd3d45 cramfs
		624	0x453dcd28 cramfs-wend (wrong endianness)
		625	0x64626720 debugfs
		626	0x00001373 devfs
		627	0x00001cd1 devpts
		628	0x0000f15f ecryptfs
		629	0x00414a53 efs
		630	0x0000137d ext
		631	0x0000ef53 ext2/ext3
		632	0x0000ef51 ext2
		633	0x00004006 fat
		634	0x65735546 fuseblk
		635	0x65735543 fusectl
		636	0x0bad1dea futexfs
		637	0x01161970 gfs2
		638	0x47504653 gpfs
		639	0x00004244 hfs
		640	0xf995e849 hpfs
		641	0x958458f6 hugetlbfs
		642	0x2bad1dea inotifyfs
		643	0x00009660 isofs
		644	0x000072b6 jffs2
		645	0x3153464a jfs
		646	0x6b414653 k-afs
		647	0x0bd00bd0 lustre
		648	0x0000137f minix
		649	0x0000138f minix 30 char names
		650	0x00002468 minix v2
		651	0x00002478 minix v2 30 char names
		652	0x00004d5a minix v3
		653	0x19800202 mqueue
		654	0x00004d44 msdos
		655	0x0000564c novell
		656	0x00006969 nfs
		657	0x6e667364 nfsd
		658	0x00003434 nilfs
		659	0x5346544e ntfs
		660	0x00009fa1 openprom
		661	0x7461636F ocfs2
		662	0x00009fa0 proc
		663	0x6165676c pstorefs
		664	0x0000002f qnx4
		665	0x858458f6 ramfs
		666	0x52654973 reiserfs
		667	0x00007275 romfs
		668	0x67596969 rpc_pipefs
		669	0x73636673 securityfs
		670	0xf97cff8c selinux
		671	0x0000517b smb
		672	0x534f434b sockfs
		673	0x73717368 squashfs
		674	0x62656572 sysfs
		675	0x012ff7b6 sysv2
		676	0x012ff7b5 sysv4
		677	0x01021994 tmpfs
		678	0x15013346 udf
		679	0x00011954 ufs
		680	0x54190100 ufs byteswapped
		681	0x00009fa2 usbdevfs
		682	0x01021997 v9fs
		683	0xa501fcf5 vxfs
		684	0xabba1974 xenfs
		685	0x012ff7b4 xenix
		686	0x58465342 xfs
		687	0x012fd16d xia
		688
		689	=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
		690
		691	Works like perl's C<utime> function (including the special case of $atime
		692	and $mtime being undef). Fractional times are supported if the underlying
		693	syscalls support them.
		694
		695	When called with a pathname, uses utimes(2) if available, otherwise
		696	utime(2). If called on a file descriptor, uses futimes(2) if available,
		697	otherwise returns ENOSYS, so this is not portable.
		698
		699	Examples:
		700
		701	# set atime and mtime to current time (basically touch(1)):
		702	aio_utime "path", undef, undef;
		703	# set atime to current time and mtime to beginning of the epoch:
		704	aio_utime "path", time, undef; # undef==0
		705
		706
		707	=item aio_chown $fh_or_path, $uid, $gid, $callback->($status)
		708
		709	Works like perl's C<chown> function, except that C<undef> for either $uid
		710	or $gid is being interpreted as "do not change" (but -1 can also be used).
		711
		712	Examples:
		713
		714	# same as "chown root path" in the shell:
		715	aio_chown "path", 0, -1;
		716	# same as above:
		717	aio_chown "path", 0, undef;
		718
		719
		720	=item aio_truncate $fh_or_path, $offset, $callback->($status)
		721
		722	Works like truncate(2) or ftruncate(2).
		723
		724
		725	=item aio_allocate $fh, $mode, $offset, $len, $callback->($status)
		726
		727	Allocates or freed disk space according to the C<$mode> argument. See the
		728	linux C<fallocate> docuemntation for details.
		729
		730	C<$mode> can currently be C<0> or C<IO::AIO::FALLOC_FL_KEEP_SIZE>
		731	to allocate space, or C<IO::AIO::FALLOC_FL_PUNCH_HOLE |
		732	IO::AIO::FALLOC_FL_KEEP_SIZE>, to deallocate a file range.
		733
		734	The file system block size used by C<fallocate> is presumably the
		735	C<f_bsize> returned by C<statvfs>.
		736
		737	If C<fallocate> isn't available or cannot be emulated (currently no
		738	emulation will be attempted), passes C<-1> and sets C<$!> to C<ENOSYS>.
		739
		740
		741	=item aio_chmod $fh_or_path, $mode, $callback->($status)
		742
		743	Works like perl's C<chmod> function.
		744
		745
192	=item aio_unlink $pathname, $callback	746	=item aio_unlink $pathname, $callback->($status)
193		747
194	Asynchronously unlink (delete) a file and call the callback with the	748	Asynchronously unlink (delete) a file and call the callback with the
195	result code.	749	result code.
196		750
		751
		752	=item aio_mknod $pathname, $mode, $dev, $callback->($status)
		753
		754	[EXPERIMENTAL]
		755
		756	Asynchronously create a device node (or fifo). See mknod(2).
		757
		758	The only (POSIX-) portable way of calling this function is:
		759
		760	aio_mknod $pathname, IO::AIO::S_IFIFO | $mode, 0, sub { ...
		761
		762	See C<aio_stat> for info about some potentially helpful extra constants
		763	and functions.
		764
		765	=item aio_link $srcpath, $dstpath, $callback->($status)
		766
		767	Asynchronously create a new link to the existing object at C<$srcpath> at
		768	the path C<$dstpath> and call the callback with the result code.
		769
		770
		771	=item aio_symlink $srcpath, $dstpath, $callback->($status)
		772
		773	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at
		774	the path C<$dstpath> and call the callback with the result code.
		775
		776
		777	=item aio_readlink $pathname, $callback->($link)
		778
		779	Asynchronously read the symlink specified by C<$path> and pass it to
		780	the callback. If an error occurs, nothing or undef gets passed to the
		781	callback.
		782
		783
		784	=item aio_realpath $pathname, $callback->($path)
		785
		786	Asynchronously make the path absolute and resolve any symlinks in
		787	C<$path>. The resulting path only consists of directories (same as
		788	L<Cwd::realpath>).
		789
		790	This request can be used to get the absolute path of the current working
		791	directory by passing it a path of F<.> (a single dot).
		792
		793
		794	=item aio_rename $srcpath, $dstpath, $callback->($status)
		795
		796	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as
		797	rename(2) and call the callback with the result code.
		798
		799	On systems that support the AIO::WD working directory abstraction
		800	natively, the case C<[$wd, "."]> as C<$srcpath> is specialcased - instead
		801	of failing, C<rename> is called on the absolute path of C<$wd>.
		802
		803
		804	=item aio_mkdir $pathname, $mode, $callback->($status)
		805
		806	Asynchronously mkdir (create) a directory and call the callback with
		807	the result code. C<$mode> will be modified by the umask at the time the
		808	request is executed, so do not change your umask.
		809
		810
		811	=item aio_rmdir $pathname, $callback->($status)
		812
		813	Asynchronously rmdir (delete) a directory and call the callback with the
		814	result code.
		815
		816	On systems that support the AIO::WD working directory abstraction
		817	natively, the case C<[$wd, "."]> is specialcased - instead of failing,
		818	C<rmdir> is called on the absolute path of C<$wd>.
		819
		820
		821	=item aio_readdir $pathname, $callback->($entries)
		822
		823	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
		824	directory (i.e. opendir + readdir + closedir). The entries will not be
		825	sorted, and will B<NOT> include the C<.> and C<..> entries.
		826
		827	The callback is passed a single argument which is either C<undef> or an
		828	array-ref with the filenames.
		829
		830
		831	=item aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		832
		833	Quite similar to C<aio_readdir>, but the C<$flags> argument allows one to
		834	tune behaviour and output format. In case of an error, C<$entries> will be
		835	C<undef>.
		836
		837	The flags are a combination of the following constants, ORed together (the
		838	flags will also be passed to the callback, possibly modified):
		839
		840	=over 4
		841
		842	=item IO::AIO::READDIR_DENTS
		843
		844	When this flag is off, then the callback gets an arrayref consisting of
		845	names only (as with C<aio_readdir>), otherwise it gets an arrayref with
		846	C<[$name, $type, $inode]> arrayrefs, each describing a single directory
		847	entry in more detail.
		848
		849	C<$name> is the name of the entry.
		850
		851	C<$type> is one of the C<IO::AIO::DT_xxx> constants:
		852
		853	C<IO::AIO::DT_UNKNOWN>, C<IO::AIO::DT_FIFO>, C<IO::AIO::DT_CHR>, C<IO::AIO::DT_DIR>,
		854	C<IO::AIO::DT_BLK>, C<IO::AIO::DT_REG>, C<IO::AIO::DT_LNK>, C<IO::AIO::DT_SOCK>,
		855	C<IO::AIO::DT_WHT>.
		856
		857	C<IO::AIO::DT_UNKNOWN> means just that: readdir does not know. If you need to
		858	know, you have to run stat yourself. Also, for speed reasons, the C<$type>
		859	scalars are read-only: you can not modify them.
		860
		861	C<$inode> is the inode number (which might not be exact on systems with 64
		862	bit inode numbers and 32 bit perls). This field has unspecified content on
		863	systems that do not deliver the inode information.
		864
		865	=item IO::AIO::READDIR_DIRS_FIRST
		866
		867	When this flag is set, then the names will be returned in an order where
		868	likely directories come first, in optimal stat order. This is useful when
		869	you need to quickly find directories, or you want to find all directories
		870	while avoiding to stat() each entry.
		871
		872	If the system returns type information in readdir, then this is used
		873	to find directories directly. Otherwise, likely directories are names
		874	beginning with ".", or otherwise names with no dots, of which names with
		875	short names are tried first.
		876
		877	=item IO::AIO::READDIR_STAT_ORDER
		878
		879	When this flag is set, then the names will be returned in an order
		880	suitable for stat()'ing each one. That is, when you plan to stat()
		881	all files in the given directory, then the returned order will likely
		882	be fastest.
		883
		884	If both this flag and C<IO::AIO::READDIR_DIRS_FIRST> are specified, then
		885	the likely dirs come first, resulting in a less optimal stat order.
		886
		887	=item IO::AIO::READDIR_FOUND_UNKNOWN
		888
		889	This flag should not be set when calling C<aio_readdirx>. Instead, it
		890	is being set by C<aio_readdirx>, when any of the C<$type>'s found were
		891	C<IO::AIO::DT_UNKNOWN>. The absence of this flag therefore indicates that all
		892	C<$type>'s are known, which can be used to speed up some algorithms.
		893
		894	=back
		895
		896
		897	=item aio_load $pathname, $data, $callback->($status)
		898
		899	This is a composite request that tries to fully load the given file into
		900	memory. Status is the same as with aio_read.
		901
		902	=cut
		903
		904	sub aio_load($$;$) {
		905	my ($path, undef, $cb) = @_;
		906	my $data = \$_[1];
		907
		908	my $pri = aioreq_pri;
		909	my $grp = aio_group $cb;
		910
		911	aioreq_pri $pri;
		912	add $grp aio_open $path, O_RDONLY, 0, sub {
		913	my $fh = shift
		914	or return $grp->result (-1);
		915
		916	aioreq_pri $pri;
		917	add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub {
		918	$grp->result ($_[0]);
		919	};
		920	};
		921
		922	$grp
		923	}
		924
		925	=item aio_copy $srcpath, $dstpath, $callback->($status)
		926
		927	Try to copy the I<file> (directories not supported as either source or
		928	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		929	a status of C<0> (ok) or C<-1> (error, see C<$!>).
		930
		931	This is a composite request that creates the destination file with
		932	mode 0200 and copies the contents of the source file into it using
		933	C<aio_sendfile>, followed by restoring atime, mtime, access mode and
		934	uid/gid, in that order.
		935
		936	If an error occurs, the partial destination file will be unlinked, if
		937	possible, except when setting atime, mtime, access mode and uid/gid, where
		938	errors are being ignored.
		939
		940	=cut
		941
		942	sub aio_copy($$;$) {
		943	my ($src, $dst, $cb) = @_;
		944
		945	my $pri = aioreq_pri;
		946	my $grp = aio_group $cb;
		947
		948	aioreq_pri $pri;
		949	add $grp aio_open $src, O_RDONLY, 0, sub {
		950	if (my $src_fh = $_[0]) {
		951	my @stat = stat $src_fh; # hmm, might block over nfs?
		952
		953	aioreq_pri $pri;
		954	add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {
		955	if (my $dst_fh = $_[0]) {
		956	aioreq_pri $pri;
		957	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
		958	if ($_[0] == $stat[7]) {
		959	$grp->result (0);
		960	close $src_fh;
		961
		962	my $ch = sub {
		963	aioreq_pri $pri;
		964	add $grp aio_chmod $dst_fh, $stat[2] & 07777, sub {
		965	aioreq_pri $pri;
		966	add $grp aio_chown $dst_fh, $stat[4], $stat[5], sub {
		967	aioreq_pri $pri;
		968	add $grp aio_close $dst_fh;
		969	}
		970	};
		971	};
		972
		973	aioreq_pri $pri;
		974	add $grp aio_utime $dst_fh, $stat[8], $stat[9], sub {
		975	if ($_[0] < 0 && $! == ENOSYS) {
		976	aioreq_pri $pri;
		977	add $grp aio_utime $dst, $stat[8], $stat[9], $ch;
		978	} else {
		979	$ch->();
		980	}
		981	};
		982	} else {
		983	$grp->result (-1);
		984	close $src_fh;
		985	close $dst_fh;
		986
		987	aioreq $pri;
		988	add $grp aio_unlink $dst;
		989	}
		990	};
		991	} else {
		992	$grp->result (-1);
		993	}
		994	},
		995
		996	} else {
		997	$grp->result (-1);
		998	}
		999	};
		1000
		1001	$grp
		1002	}
		1003
		1004	=item aio_move $srcpath, $dstpath, $callback->($status)
		1005
		1006	Try to move the I<file> (directories not supported as either source or
		1007	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		1008	a status of C<0> (ok) or C<-1> (error, see C<$!>).
		1009
		1010	This is a composite request that tries to rename(2) the file first; if
		1011	rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if
		1012	that is successful, unlinks the C<$srcpath>.
		1013
		1014	=cut
		1015
		1016	sub aio_move($$;$) {
		1017	my ($src, $dst, $cb) = @_;
		1018
		1019	my $pri = aioreq_pri;
		1020	my $grp = aio_group $cb;
		1021
		1022	aioreq_pri $pri;
		1023	add $grp aio_rename $src, $dst, sub {
		1024	if ($_[0] && $! == EXDEV) {
		1025	aioreq_pri $pri;
		1026	add $grp aio_copy $src, $dst, sub {
		1027	$grp->result ($_[0]);
		1028
		1029	unless ($_[0]) {
		1030	aioreq_pri $pri;
		1031	add $grp aio_unlink $src;
		1032	}
		1033	};
		1034	} else {
		1035	$grp->result ($_[0]);
		1036	}
		1037	};
		1038
		1039	$grp
		1040	}
		1041
		1042	=item aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs)
		1043
		1044	Scans a directory (similar to C<aio_readdir>) but additionally tries to
		1045	efficiently separate the entries of directory C<$path> into two sets of
		1046	names, directories you can recurse into (directories), and ones you cannot
		1047	recurse into (everything else, including symlinks to directories).
		1048
		1049	C<aio_scandir> is a composite request that creates of many sub requests_
		1050	C<$maxreq> specifies the maximum number of outstanding aio requests that
		1051	this function generates. If it is C<< <= 0 >>, then a suitable default
		1052	will be chosen (currently 4).
		1053
		1054	On error, the callback is called without arguments, otherwise it receives
		1055	two array-refs with path-relative entry names.
		1056
		1057	Example:
		1058
		1059	aio_scandir $dir, 0, sub {
		1060	my ($dirs, $nondirs) = @_;
		1061	print "real directories: @$dirs\n";
		1062	print "everything else: @$nondirs\n";
		1063	};
		1064
		1065	Implementation notes.
		1066
		1067	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.
		1068
		1069	If readdir returns file type information, then this is used directly to
		1070	find directories.
		1071
		1072	Otherwise, after reading the directory, the modification time, size etc.
		1073	of the directory before and after the readdir is checked, and if they
		1074	match (and isn't the current time), the link count will be used to decide
		1075	how many entries are directories (if >= 2). Otherwise, no knowledge of the
		1076	number of subdirectories will be assumed.
		1077
		1078	Then entries will be sorted into likely directories a non-initial dot
		1079	currently) and likely non-directories (see C<aio_readdirx>). Then every
		1080	entry plus an appended C</.> will be C<stat>'ed, likely directories first,
		1081	in order of their inode numbers. If that succeeds, it assumes that the
		1082	entry is a directory or a symlink to directory (which will be checked
		1083	separately). This is often faster than stat'ing the entry itself because
		1084	filesystems might detect the type of the entry without reading the inode
		1085	data (e.g. ext2fs filetype feature), even on systems that cannot return
		1086	the filetype information on readdir.
		1087
		1088	If the known number of directories (link count - 2) has been reached, the
		1089	rest of the entries is assumed to be non-directories.
		1090
		1091	This only works with certainty on POSIX (= UNIX) filesystems, which
		1092	fortunately are the vast majority of filesystems around.
		1093
		1094	It will also likely work on non-POSIX filesystems with reduced efficiency
		1095	as those tend to return 0 or 1 as link counts, which disables the
		1096	directory counting heuristic.
		1097
		1098	=cut
		1099
		1100	sub aio_scandir($$;$) {
		1101	my ($path, $maxreq, $cb) = @_;
		1102
		1103	my $pri = aioreq_pri;
		1104
		1105	my $grp = aio_group $cb;
		1106
		1107	$maxreq = 4 if $maxreq <= 0;
		1108
		1109	# get a wd object
		1110	aioreq_pri $pri;
		1111	add $grp aio_wd $path, sub {
		1112	$_[0]
		1113	or return $grp->result ();
		1114
		1115	my $wd = [shift, "."];
		1116
		1117	# stat once
		1118	aioreq_pri $pri;
		1119	add $grp aio_stat $wd, sub {
		1120	return $grp->result () if $_[0];
		1121	my $now = time;
		1122	my $hash1 = join ":", (stat _)[0,1,3,7,9];
		1123
		1124	# read the directory entries
		1125	aioreq_pri $pri;
		1126	add $grp aio_readdirx $wd, READDIR_DIRS_FIRST, sub {
		1127	my $entries = shift
		1128	or return $grp->result ();
		1129
		1130	# stat the dir another time
		1131	aioreq_pri $pri;
		1132	add $grp aio_stat $wd, sub {
		1133	my $hash2 = join ":", (stat _)[0,1,3,7,9];
		1134
		1135	my $ndirs;
		1136
		1137	# take the slow route if anything looks fishy
		1138	if ($hash1 ne $hash2 or (stat _)[9] == $now) {
		1139	$ndirs = -1;
		1140	} else {
		1141	# if nlink == 2, we are finished
		1142	# for non-posix-fs's, we rely on nlink < 2
		1143	$ndirs = (stat _)[3] - 2
		1144	or return $grp->result ([], $entries);
		1145	}
		1146
		1147	my (@dirs, @nondirs);
		1148
		1149	my $statgrp = add $grp aio_group sub {
		1150	$grp->result (\@dirs, \@nondirs);
		1151	};
		1152
		1153	limit $statgrp $maxreq;
		1154	feed $statgrp sub {
		1155	return unless @$entries;
		1156	my $entry = shift @$entries;
		1157
		1158	aioreq_pri $pri;
		1159	$wd->[1] = "$entry/.";
		1160	add $statgrp aio_stat $wd, sub {
		1161	if ($_[0] < 0) {
		1162	push @nondirs, $entry;
		1163	} else {
		1164	# need to check for real directory
		1165	aioreq_pri $pri;
		1166	$wd->[1] = $entry;
		1167	add $statgrp aio_lstat $wd, sub {
		1168	if (-d _) {
		1169	push @dirs, $entry;
		1170
		1171	unless (--$ndirs) {
		1172	push @nondirs, @$entries;
		1173	feed $statgrp;
		1174	}
		1175	} else {
		1176	push @nondirs, $entry;
		1177	}
		1178	}
		1179	}
		1180	};
		1181	};
		1182	};
		1183	};
		1184	};
		1185	};
		1186
		1187	$grp
		1188	}
		1189
		1190	=item aio_rmtree $pathname, $callback->($status)
		1191
		1192	Delete a directory tree starting (and including) C<$path>, return the
		1193	status of the final C<rmdir> only. This is a composite request that
		1194	uses C<aio_scandir> to recurse into and rmdir directories, and unlink
		1195	everything else.
		1196
		1197	=cut
		1198
		1199	sub aio_rmtree;
		1200	sub aio_rmtree($;$) {
		1201	my ($path, $cb) = @_;
		1202
		1203	my $pri = aioreq_pri;
		1204	my $grp = aio_group $cb;
		1205
		1206	aioreq_pri $pri;
		1207	add $grp aio_scandir $path, 0, sub {
		1208	my ($dirs, $nondirs) = @_;
		1209
		1210	my $dirgrp = aio_group sub {
		1211	add $grp aio_rmdir $path, sub {
		1212	$grp->result ($_[0]);
		1213	};
		1214	};
		1215
		1216	(aioreq_pri $pri), add $dirgrp aio_rmtree "$path/$_" for @$dirs;
		1217	(aioreq_pri $pri), add $dirgrp aio_unlink "$path/$_" for @$nondirs;
		1218
		1219	add $grp $dirgrp;
		1220	};
		1221
		1222	$grp
		1223	}
		1224
		1225	=item aio_sync $callback->($status)
		1226
		1227	Asynchronously call sync and call the callback when finished.
		1228
197	=item aio_fsync $fh, $callback	1229	=item aio_fsync $fh, $callback->($status)
198		1230
199	Asynchronously call fsync on the given filehandle and call the callback	1231	Asynchronously call fsync on the given filehandle and call the callback
200	with the fsync result code.	1232	with the fsync result code.
201		1233
202	=item aio_fdatasync $fh, $callback	1234	=item aio_fdatasync $fh, $callback->($status)
203		1235
204	Asynchronously call fdatasync on the given filehandle and call the	1236	Asynchronously call fdatasync on the given filehandle and call the
205	callback with the fdatasync result code. Might set C<$!> to C<ENOSYS> if	1237	callback with the fdatasync result code.
206	C<fdatasync> is not available.	1238
		1239	If this call isn't available because your OS lacks it or it couldn't be
		1240	detected, it will be emulated by calling C<fsync> instead.
		1241
		1242	=item aio_syncfs $fh, $callback->($status)
		1243
		1244	Asynchronously call the syncfs syscall to sync the filesystem associated
		1245	to the given filehandle and call the callback with the syncfs result
		1246	code. If syncfs is not available, calls sync(), but returns C<-1> and sets
		1247	errno to C<ENOSYS> nevertheless.
		1248
		1249	=item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		1250
		1251	Sync the data portion of the file specified by C<$offset> and C<$length>
		1252	to disk (but NOT the metadata), by calling the Linux-specific
		1253	sync_file_range call. If sync_file_range is not available or it returns
		1254	ENOSYS, then fdatasync or fsync is being substituted.
		1255
		1256	C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>,
		1257	C<IO::AIO::SYNC_FILE_RANGE_WRITE> and
		1258	C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range
		1259	manpage for details.
		1260
		1261	=item aio_pathsync $pathname, $callback->($status)
		1262
		1263	This request tries to open, fsync and close the given path. This is a
		1264	composite request intended to sync directories after directory operations
		1265	(E.g. rename). This might not work on all operating systems or have any
		1266	specific effect, but usually it makes sure that directory changes get
		1267	written to disc. It works for anything that can be opened for read-only,
		1268	not just directories.
		1269
		1270	Future versions of this function might fall back to other methods when
		1271	C<fsync> on the directory fails (such as calling C<sync>).
		1272
		1273	Passes C<0> when everything went ok, and C<-1> on error.
		1274
		1275	=cut
		1276
		1277	sub aio_pathsync($;$) {
		1278	my ($path, $cb) = @_;
		1279
		1280	my $pri = aioreq_pri;
		1281	my $grp = aio_group $cb;
		1282
		1283	aioreq_pri $pri;
		1284	add $grp aio_open $path, O_RDONLY, 0, sub {
		1285	my ($fh) = @_;
		1286	if ($fh) {
		1287	aioreq_pri $pri;
		1288	add $grp aio_fsync $fh, sub {
		1289	$grp->result ($_[0]);
		1290
		1291	aioreq_pri $pri;
		1292	add $grp aio_close $fh;
		1293	};
		1294	} else {
		1295	$grp->result (-1);
		1296	}
		1297	};
		1298
		1299	$grp
		1300	}
		1301
		1302	=item aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		1303
		1304	This is a rather advanced IO::AIO call, which only works on mmap(2)ed
		1305	scalars (see the C<IO::AIO::mmap> function, although it also works on data
		1306	scalars managed by the L<Sys::Mmap> or L<Mmap> modules, note that the
		1307	scalar must only be modified in-place while an aio operation is pending on
		1308	it).
		1309
		1310	It calls the C<msync> function of your OS, if available, with the memory
		1311	area starting at C<$offset> in the string and ending C<$length> bytes
		1312	later. If C<$length> is negative, counts from the end, and if C<$length>
		1313	is C<undef>, then it goes till the end of the string. The flags can be
		1314	a combination of C<IO::AIO::MS_ASYNC>, C<IO::AIO::MS_INVALIDATE> and
		1315	C<IO::AIO::MS_SYNC>.
		1316
		1317	=item aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		1318
		1319	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1320	scalars.
		1321
		1322	It touches (reads or writes) all memory pages in the specified
		1323	range inside the scalar. All caveats and parameters are the same
		1324	as for C<aio_msync>, above, except for flags, which must be either
		1325	C<0> (which reads all pages and ensures they are instantiated) or
		1326	C<IO::AIO::MT_MODIFY>, which modifies the memory pages (by reading and
		1327	writing an octet from it, which dirties the page).
		1328
		1329	=item aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
		1330
		1331	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1332	scalars.
		1333
		1334	It reads in all the pages of the underlying storage into memory (if any)
		1335	and locks them, so they are not getting swapped/paged out or removed.
		1336
		1337	If C<$length> is undefined, then the scalar will be locked till the end.
		1338
		1339	On systems that do not implement C<mlock>, this function returns C<-1>
		1340	and sets errno to C<ENOSYS>.
		1341
		1342	Note that the corresponding C<munlock> is synchronous and is
		1343	documented under L<MISCELLANEOUS FUNCTIONS>.
		1344
		1345	Example: open a file, mmap and mlock it - both will be undone when
		1346	C<$data> gets destroyed.
		1347
		1348	open my $fh, "<", $path or die "$path: $!";
		1349	my $data;
		1350	IO::AIO::mmap $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh;
		1351	aio_mlock $data; # mlock in background
		1352
		1353	=item aio_mlockall $flags, $callback->($status)
		1354
		1355	Calls the C<mlockall> function with the given C<$flags> (a combination of
		1356	C<IO::AIO::MCL_CURRENT> and C<IO::AIO::MCL_FUTURE>).
		1357
		1358	On systems that do not implement C<mlockall>, this function returns C<-1>
		1359	and sets errno to C<ENOSYS>.
		1360
		1361	Note that the corresponding C<munlockall> is synchronous and is
		1362	documented under L<MISCELLANEOUS FUNCTIONS>.
		1363
		1364	Example: asynchronously lock all current and future pages into memory.
		1365
		1366	aio_mlockall IO::AIO::MCL_FUTURE;
		1367
		1368	=item aio_fiemap $fh, $start, $length, $flags, $count, $cb->(\@extents)
		1369
		1370	Queries the extents of the given file (by calling the Linux C<FIEMAP>
		1371	ioctl, see L<http://cvs.schmorp.de/IO-AIO/doc/fiemap.txt> for details). If
		1372	the ioctl is not available on your OS, then this request will fail with
		1373	C<ENOSYS>.
		1374
		1375	C<$start> is the starting offset to query extents for, C<$length> is the
		1376	size of the range to query - if it is C<undef>, then the whole file will
		1377	be queried.
		1378
		1379	C<$flags> is a combination of flags (C<IO::AIO::FIEMAP_FLAG_SYNC> or
		1380	C<IO::AIO::FIEMAP_FLAG_XATTR> - C<IO::AIO::FIEMAP_FLAGS_COMPAT> is also
		1381	exported), and is normally C<0> or C<IO::AIO::FIEMAP_FLAG_SYNC> to query
		1382	the data portion.
		1383
		1384	C<$count> is the maximum number of extent records to return. If it is
		1385	C<undef>, then IO::AIO queries all extents of the range. As a very special
		1386	case, if it is C<0>, then the callback receives the number of extents
		1387	instead of the extents themselves (which is unreliable, see below).
		1388
		1389	If an error occurs, the callback receives no arguments. The special
		1390	C<errno> value C<IO::AIO::EBADR> is available to test for flag errors.
		1391
		1392	Otherwise, the callback receives an array reference with extent
		1393	structures. Each extent structure is an array reference itself, with the
		1394	following members:
		1395
		1396	[$logical, $physical, $length, $flags]
		1397
		1398	Flags is any combination of the following flag values (typically either C<0>
		1399	or C<IO::AIO::FIEMAP_EXTENT_LAST> (1)):
		1400
		1401	C<IO::AIO::FIEMAP_EXTENT_LAST>, C<IO::AIO::FIEMAP_EXTENT_UNKNOWN>,
		1402	C<IO::AIO::FIEMAP_EXTENT_DELALLOC>, C<IO::AIO::FIEMAP_EXTENT_ENCODED>,
		1403	C<IO::AIO::FIEMAP_EXTENT_DATA_ENCRYPTED>, C<IO::AIO::FIEMAP_EXTENT_NOT_ALIGNED>,
		1404	C<IO::AIO::FIEMAP_EXTENT_DATA_INLINE>, C<IO::AIO::FIEMAP_EXTENT_DATA_TAIL>,
		1405	C<IO::AIO::FIEMAP_EXTENT_UNWRITTEN>, C<IO::AIO::FIEMAP_EXTENT_MERGED> or
		1406	C<IO::AIO::FIEMAP_EXTENT_SHARED>.
		1407
		1408	At the time of this writing (Linux 3.2), this requets is unreliable unless
		1409	C<$count> is C<undef>, as the kernel has all sorts of bugs preventing
		1410	it to return all extents of a range for files with large number of
		1411	extents. The code works around all these issues if C<$count> is undef.
		1412
		1413	=item aio_group $callback->(...)
		1414
		1415	This is a very special aio request: Instead of doing something, it is a
		1416	container for other aio requests, which is useful if you want to bundle
		1417	many requests into a single, composite, request with a definite callback
		1418	and the ability to cancel the whole request with its subrequests.
		1419
		1420	Returns an object of class L<IO::AIO::GRP>. See its documentation below
		1421	for more info.
		1422
		1423	Example:
		1424
		1425	my $grp = aio_group sub {
		1426	print "all stats done\n";
		1427	};
		1428
		1429	add $grp
		1430	(aio_stat ...),
		1431	(aio_stat ...),
		1432	...;
		1433
		1434	=item aio_nop $callback->()
		1435
		1436	This is a special request - it does nothing in itself and is only used for
		1437	side effects, such as when you want to add a dummy request to a group so
		1438	that finishing the requests in the group depends on executing the given
		1439	code.
		1440
		1441	While this request does nothing, it still goes through the execution
		1442	phase and still requires a worker thread. Thus, the callback will not
		1443	be executed immediately but only after other requests in the queue have
		1444	entered their execution phase. This can be used to measure request
		1445	latency.
		1446
		1447	=item IO::AIO::aio_busy $fractional_seconds, $callback->() *NOT EXPORTED*
		1448
		1449	Mainly used for debugging and benchmarking, this aio request puts one of
		1450	the request workers to sleep for the given time.
		1451
		1452	While it is theoretically handy to have simple I/O scheduling requests
		1453	like sleep and file handle readable/writable, the overhead this creates is
		1454	immense (it blocks a thread for a long time) so do not use this function
		1455	except to put your application under artificial I/O pressure.
207		1456
208	=back	1457	=back
209		1458
		1459
		1460	=head2 IO::AIO::WD - multiple working directories
		1461
		1462	Your process only has one current working directory, which is used by all
		1463	threads. This makes it hard to use relative paths (some other component
		1464	could call C<chdir> at any time, and it is hard to control when the path
		1465	will be used by IO::AIO).
		1466
		1467	One solution for this is to always use absolute paths. This usually works,
		1468	but can be quite slow (the kernel has to walk the whole path on every
		1469	access), and can also be a hassle to implement.
		1470
		1471	Newer POSIX systems have a number of functions (openat, fdopendir,
		1472	futimensat and so on) that make it possible to specify working directories
		1473	per operation.
		1474
		1475	For portability, and because the clowns who "designed", or shall I write,
		1476	perpetrated this new interface were obviously half-drunk, this abstraction
		1477	cannot be perfect, though.
		1478
		1479	IO::AIO allows you to convert directory paths into a so-called IO::AIO::WD
		1480	object. This object stores the canonicalised, absolute version of the
		1481	path, and on systems that allow it, also a directory file descriptor.
		1482
		1483	Everywhere where a pathname is accepted by IO::AIO (e.g. in C<aio_stat>
		1484	or C<aio_unlink>), one can specify an array reference with an IO::AIO::WD
		1485	object and a pathname instead (or the IO::AIO::WD object alone, which
		1486	gets interpreted as C<[$wd, "."]>). If the pathname is absolute, the
		1487	IO::AIO::WD object is ignored, otherwise the pathname is resolved relative
		1488	to that IO::AIO::WD object.
		1489
		1490	For example, to get a wd object for F</etc> and then stat F<passwd>
		1491	inside, you would write:
		1492
		1493	aio_wd "/etc", sub {
		1494	my $etcdir = shift;
		1495
		1496	# although $etcdir can be undef on error, there is generally no reason
		1497	# to check for errors here, as aio_stat will fail with ENOENT
		1498	# when $etcdir is undef.
		1499
		1500	aio_stat [$etcdir, "passwd"], sub {
		1501	# yay
		1502	};
		1503	};
		1504
		1505	That C<aio_wd> is a request and not a normal function shows that creating
		1506	an IO::AIO::WD object is itself a potentially blocking operation, which is
		1507	why it is done asynchronously.
		1508
		1509	To stat the directory obtained with C<aio_wd> above, one could write
		1510	either of the following three request calls:
		1511
		1512	aio_lstat "/etc" , sub { ... # pathname as normal string
		1513	aio_lstat [$wd, "."], sub { ... # "." relative to $wd (i.e. $wd itself)
		1514	aio_lstat $wd , sub { ... # shorthand for the previous
		1515
		1516	As with normal pathnames, IO::AIO keeps a copy of the working directory
		1517	object and the pathname string, so you could write the following without
		1518	causing any issues due to C<$path> getting reused:
		1519
		1520	my $path = [$wd, undef];
		1521
		1522	for my $name (qw(abc def ghi)) {
		1523	$path->[1] = $name;
		1524	aio_stat $path, sub {
		1525	# ...
		1526	};
		1527	}
		1528
		1529	There are some caveats: when directories get renamed (or deleted), the
		1530	pathname string doesn't change, so will point to the new directory (or
		1531	nowhere at all), while the directory fd, if available on the system,
		1532	will still point to the original directory. Most functions accepting a
		1533	pathname will use the directory fd on newer systems, and the string on
		1534	older systems. Some functions (such as realpath) will always rely on the
		1535	string form of the pathname.
		1536
		1537	So this functionality is mainly useful to get some protection against
		1538	C<chdir>, to easily get an absolute path out of a relative path for future
		1539	reference, and to speed up doing many operations in the same directory
		1540	(e.g. when stat'ing all files in a directory).
		1541
		1542	The following functions implement this working directory abstraction:
		1543
		1544	=over 4
		1545
		1546	=item aio_wd $pathname, $callback->($wd)
		1547
		1548	Asynchonously canonicalise the given pathname and convert it to an
		1549	IO::AIO::WD object representing it. If possible and supported on the
		1550	system, also open a directory fd to speed up pathname resolution relative
		1551	to this working directory.
		1552
		1553	If something goes wrong, then C<undef> is passwd to the callback instead
		1554	of a working directory object and C<$!> is set appropriately. Since
		1555	passing C<undef> as working directory component of a pathname fails the
		1556	request with C<ENOENT>, there is often no need for error checking in the
		1557	C<aio_wd> callback, as future requests using the value will fail in the
		1558	expected way.
		1559
		1560	=item IO::AIO::CWD
		1561
		1562	This is a compiletime constant (object) that represents the process
		1563	current working directory.
		1564
		1565	Specifying this object as working directory object for a pathname is as if
		1566	the pathname would be specified directly, without a directory object. For
		1567	example, these calls are functionally identical:
		1568
		1569	aio_stat "somefile", sub { ... };
		1570	aio_stat [IO::AIO::CWD, "somefile"], sub { ... };
		1571
		1572	=back
		1573
		1574	To recover the path associated with an IO::AIO::WD object, you can use
		1575	C<aio_realpath>:
		1576
		1577	aio_realpath $wd, sub {
		1578	warn "path is $_[0]\n";
		1579	};
		1580
		1581	Currently, C<aio_statvfs> always, and C<aio_rename> and C<aio_rmdir>
		1582	sometimes, fall back to using an absolue path.
		1583
		1584	=head2 IO::AIO::REQ CLASS
		1585
		1586	All non-aggregate C<aio_*> functions return an object of this class when
		1587	called in non-void context.
		1588
		1589	=over 4
		1590
		1591	=item cancel $req
		1592
		1593	Cancels the request, if possible. Has the effect of skipping execution
		1594	when entering the B<execute> state and skipping calling the callback when
		1595	entering the the B<result> state, but will leave the request otherwise
		1596	untouched (with the exception of readdir). That means that requests that
		1597	currently execute will not be stopped and resources held by the request
		1598	will not be freed prematurely.
		1599
		1600	=item cb $req $callback->(...)
		1601
		1602	Replace (or simply set) the callback registered to the request.
		1603
		1604	=back
		1605
		1606	=head2 IO::AIO::GRP CLASS
		1607
		1608	This class is a subclass of L<IO::AIO::REQ>, so all its methods apply to
		1609	objects of this class, too.
		1610
		1611	A IO::AIO::GRP object is a special request that can contain multiple other
		1612	aio requests.
		1613
		1614	You create one by calling the C<aio_group> constructing function with a
		1615	callback that will be called when all contained requests have entered the
		1616	C<done> state:
		1617
		1618	my $grp = aio_group sub {
		1619	print "all requests are done\n";
		1620	};
		1621
		1622	You add requests by calling the C<add> method with one or more
		1623	C<IO::AIO::REQ> objects:
		1624
		1625	$grp->add (aio_unlink "...");
		1626
		1627	add $grp aio_stat "...", sub {
		1628	$_[0] or return $grp->result ("error");
		1629
		1630	# add another request dynamically, if first succeeded
		1631	add $grp aio_open "...", sub {
		1632	$grp->result ("ok");
		1633	};
		1634	};
		1635
		1636	This makes it very easy to create composite requests (see the source of
		1637	C<aio_move> for an application) that work and feel like simple requests.
		1638
		1639	=over 4
		1640
		1641	=item * The IO::AIO::GRP objects will be cleaned up during calls to
		1642	C<IO::AIO::poll_cb>, just like any other request.
		1643
		1644	=item * They can be canceled like any other request. Canceling will cancel not
		1645	only the request itself, but also all requests it contains.
		1646
		1647	=item * They can also can also be added to other IO::AIO::GRP objects.
		1648
		1649	=item * You must not add requests to a group from within the group callback (or
		1650	any later time).
		1651
		1652	=back
		1653
		1654	Their lifetime, simplified, looks like this: when they are empty, they
		1655	will finish very quickly. If they contain only requests that are in the
		1656	C<done> state, they will also finish. Otherwise they will continue to
		1657	exist.
		1658
		1659	That means after creating a group you have some time to add requests
		1660	(precisely before the callback has been invoked, which is only done within
		1661	the C<poll_cb>). And in the callbacks of those requests, you can add
		1662	further requests to the group. And only when all those requests have
		1663	finished will the the group itself finish.
		1664
		1665	=over 4
		1666
		1667	=item add $grp ...
		1668
		1669	=item $grp->add (...)
		1670
		1671	Add one or more requests to the group. Any type of L<IO::AIO::REQ> can
		1672	be added, including other groups, as long as you do not create circular
		1673	dependencies.
		1674
		1675	Returns all its arguments.
		1676
		1677	=item $grp->cancel_subs
		1678
		1679	Cancel all subrequests and clears any feeder, but not the group request
		1680	itself. Useful when you queued a lot of events but got a result early.
		1681
		1682	The group request will finish normally (you cannot add requests to the
		1683	group).
		1684
		1685	=item $grp->result (...)
		1686
		1687	Set the result value(s) that will be passed to the group callback when all
		1688	subrequests have finished and set the groups errno to the current value
		1689	of errno (just like calling C<errno> without an error number). By default,
		1690	no argument will be passed and errno is zero.
		1691
		1692	=item $grp->errno ([$errno])
		1693
		1694	Sets the group errno value to C<$errno>, or the current value of errno
		1695	when the argument is missing.
		1696
		1697	Every aio request has an associated errno value that is restored when
		1698	the callback is invoked. This method lets you change this value from its
		1699	default (0).
		1700
		1701	Calling C<result> will also set errno, so make sure you either set C<$!>
		1702	before the call to C<result>, or call c<errno> after it.
		1703
		1704	=item feed $grp $callback->($grp)
		1705
		1706	Sets a feeder/generator on this group: every group can have an attached
		1707	generator that generates requests if idle. The idea behind this is that,
		1708	although you could just queue as many requests as you want in a group,
		1709	this might starve other requests for a potentially long time. For example,
		1710	C<aio_scandir> might generate hundreds of thousands of C<aio_stat>
		1711	requests, delaying any later requests for a long time.
		1712
		1713	To avoid this, and allow incremental generation of requests, you can
		1714	instead a group and set a feeder on it that generates those requests. The
		1715	feed callback will be called whenever there are few enough (see C<limit>,
		1716	below) requests active in the group itself and is expected to queue more
		1717	requests.
		1718
		1719	The feed callback can queue as many requests as it likes (i.e. C<add> does
		1720	not impose any limits).
		1721
		1722	If the feed does not queue more requests when called, it will be
		1723	automatically removed from the group.
		1724
		1725	If the feed limit is C<0> when this method is called, it will be set to
		1726	C<2> automatically.
		1727
		1728	Example:
		1729
		1730	# stat all files in @files, but only ever use four aio requests concurrently:
		1731
		1732	my $grp = aio_group sub { print "finished\n" };
		1733	limit $grp 4;
		1734	feed $grp sub {
		1735	my $file = pop @files
		1736	or return;
		1737
		1738	add $grp aio_stat $file, sub { ... };
		1739	};
		1740
		1741	=item limit $grp $num
		1742
		1743	Sets the feeder limit for the group: The feeder will be called whenever
		1744	the group contains less than this many requests.
		1745
		1746	Setting the limit to C<0> will pause the feeding process.
		1747
		1748	The default value for the limit is C<0>, but note that setting a feeder
		1749	automatically bumps it up to C<2>.
		1750
		1751	=back
		1752
210	=head2 SUPPORT FUNCTIONS	1753	=head2 SUPPORT FUNCTIONS
211		1754
		1755	=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION
		1756
212	=over 4	1757	=over 4
213		1758
214	=item $fileno = IO::AIO::poll_fileno	1759	=item $fileno = IO::AIO::poll_fileno
215		1760
216	Return the I<request result pipe file descriptor>. This filehandle must be	1761	Return the I<request result pipe file descriptor>. This filehandle must be
217	polled for reading by some mechanism outside this module (e.g. Event or	1762	polled for reading by some mechanism outside this module (e.g. EV, Glib,
218	select, see below or the SYNOPSIS). If the pipe becomes readable you have	1763	select and so on, see below or the SYNOPSIS). If the pipe becomes readable
219	to call C<poll_cb> to check the results.	1764	you have to call C<poll_cb> to check the results.
220		1765
221	See C<poll_cb> for an example.	1766	See C<poll_cb> for an example.
222		1767
223	=item IO::AIO::poll_cb	1768	=item IO::AIO::poll_cb
224		1769
225	Process all outstanding events on the result pipe. You have to call this	1770	Process some requests that have reached the result phase (i.e. they have
226	regularly. Returns the number of events processed. Returns immediately	1771	been executed but the results are not yet reported). You have to call
227	when no events are outstanding.	1772	this "regularly" to finish outstanding requests.
		1773
		1774	Returns C<0> if all events could be processed (or there were no
		1775	events to process), or C<-1> if it returned earlier for whatever
		1776	reason. Returns immediately when no events are outstanding. The amount
		1777	of events processed depends on the settings of C<IO::AIO::max_poll_req>,
		1778	C<IO::AIO::max_poll_time> and C<IO::AIO::max_outstanding>.
		1779
		1780	If not all requests were processed for whatever reason, the poll file
		1781	descriptor will still be ready when C<poll_cb> returns, so normally you
		1782	don't have to do anything special to have it called later.
		1783
		1784	Apart from calling C<IO::AIO::poll_cb> when the event filehandle becomes
		1785	ready, it can be beneficial to call this function from loops which submit
		1786	a lot of requests, to make sure the results get processed when they become
		1787	available and not just when the loop is finished and the event loop takes
		1788	over again. This function returns very fast when there are no outstanding
		1789	requests.
228		1790
229	Example: Install an Event watcher that automatically calls	1791	Example: Install an Event watcher that automatically calls
230	IO::AIO::poll_cb with high priority:	1792	IO::AIO::poll_cb with high priority (more examples can be found in the
		1793	SYNOPSIS section, at the top of this document):
231		1794
232	Event->io (fd => IO::AIO::poll_fileno,	1795	Event->io (fd => IO::AIO::poll_fileno,
233	poll => 'r', async => 1,	1796	poll => 'r', async => 1,
234	cb => \&IO::AIO::poll_cb);	1797	cb => \&IO::AIO::poll_cb);
235		1798
236	=item IO::AIO::poll_wait	1799	=item IO::AIO::poll_wait
237		1800
238	Wait till the result filehandle becomes ready for reading (simply does a	1801	Wait until either at least one request is in the result phase or no
239	C<select> on the filehandle. This is useful if you want to synchronously wait	1802	requests are outstanding anymore.
240	for some requests to finish).	1803
		1804	This is useful if you want to synchronously wait for some requests to
		1805	become ready, without actually handling them.
241		1806
242	See C<nreqs> for an example.	1807	See C<nreqs> for an example.
243		1808
		1809	=item IO::AIO::poll
		1810
		1811	Waits until some requests have been handled.
		1812
		1813	Returns the number of requests processed, but is otherwise strictly
		1814	equivalent to:
		1815
		1816	IO::AIO::poll_wait, IO::AIO::poll_cb
		1817
244	=item IO::AIO::nreqs	1818	=item IO::AIO::flush
245		1819
246	Returns the number of requests currently outstanding (i.e. for which their	1820	Wait till all outstanding AIO requests have been handled.
247	callback has not been invoked yet).
248		1821
249	Example: wait till there are no outstanding requests anymore:	1822	Strictly equivalent to:
250		1823
251	IO::AIO::poll_wait, IO::AIO::poll_cb	1824	IO::AIO::poll_wait, IO::AIO::poll_cb
252	while IO::AIO::nreqs;	1825	while IO::AIO::nreqs;
253		1826
		1827	=item IO::AIO::max_poll_reqs $nreqs
		1828
		1829	=item IO::AIO::max_poll_time $seconds
		1830
		1831	These set the maximum number of requests (default C<0>, meaning infinity)
		1832	that are being processed by C<IO::AIO::poll_cb> in one call, respectively
		1833	the maximum amount of time (default C<0>, meaning infinity) spent in
		1834	C<IO::AIO::poll_cb> to process requests (more correctly the mininum amount
		1835	of time C<poll_cb> is allowed to use).
		1836
		1837	Setting C<max_poll_time> to a non-zero value creates an overhead of one
		1838	syscall per request processed, which is not normally a problem unless your
		1839	callbacks are really really fast or your OS is really really slow (I am
		1840	not mentioning Solaris here). Using C<max_poll_reqs> incurs no overhead.
		1841
		1842	Setting these is useful if you want to ensure some level of
		1843	interactiveness when perl is not fast enough to process all requests in
		1844	time.
		1845
		1846	For interactive programs, values such as C<0.01> to C<0.1> should be fine.
		1847
		1848	Example: Install an Event watcher that automatically calls
		1849	IO::AIO::poll_cb with low priority, to ensure that other parts of the
		1850	program get the CPU sometimes even under high AIO load.
		1851
		1852	# try not to spend much more than 0.1s in poll_cb
		1853	IO::AIO::max_poll_time 0.1;
		1854
		1855	# use a low priority so other tasks have priority
		1856	Event->io (fd => IO::AIO::poll_fileno,
		1857	poll => 'r', nice => 1,
		1858	cb => &IO::AIO::poll_cb);
		1859
		1860	=back
		1861
		1862	=head3 CONTROLLING THE NUMBER OF THREADS
		1863
		1864	=over
		1865
		1866	=item IO::AIO::min_parallel $nthreads
		1867
		1868	Set the minimum number of AIO threads to C<$nthreads>. The current
		1869	default is C<8>, which means eight asynchronous operations can execute
		1870	concurrently at any one time (the number of outstanding requests,
		1871	however, is unlimited).
		1872
		1873	IO::AIO starts threads only on demand, when an AIO request is queued and
		1874	no free thread exists. Please note that queueing up a hundred requests can
		1875	create demand for a hundred threads, even if it turns out that everything
		1876	is in the cache and could have been processed faster by a single thread.
		1877
		1878	It is recommended to keep the number of threads relatively low, as some
		1879	Linux kernel versions will scale negatively with the number of threads
		1880	(higher parallelity => MUCH higher latency). With current Linux 2.6
		1881	versions, 4-32 threads should be fine.
		1882
		1883	Under most circumstances you don't need to call this function, as the
		1884	module selects a default that is suitable for low to moderate load.
		1885
		1886	=item IO::AIO::max_parallel $nthreads
		1887
		1888	Sets the maximum number of AIO threads to C<$nthreads>. If more than the
		1889	specified number of threads are currently running, this function kills
		1890	them. This function blocks until the limit is reached.
		1891
		1892	While C<$nthreads> are zero, aio requests get queued but not executed
		1893	until the number of threads has been increased again.
		1894
		1895	This module automatically runs C<max_parallel 0> at program end, to ensure
		1896	that all threads are killed and that there are no outstanding requests.
		1897
		1898	Under normal circumstances you don't need to call this function.
		1899
		1900	=item IO::AIO::max_idle $nthreads
		1901
		1902	Limit the number of threads (default: 4) that are allowed to idle
		1903	(i.e., threads that did not get a request to process within the idle
		1904	timeout (default: 10 seconds). That means if a thread becomes idle while
		1905	C<$nthreads> other threads are also idle, it will free its resources and
		1906	exit.
		1907
		1908	This is useful when you allow a large number of threads (e.g. 100 or 1000)
		1909	to allow for extremely high load situations, but want to free resources
		1910	under normal circumstances (1000 threads can easily consume 30MB of RAM).
		1911
		1912	The default is probably ok in most situations, especially if thread
		1913	creation is fast. If thread creation is very slow on your system you might
		1914	want to use larger values.
		1915
		1916	=item IO::AIO::idle_timeout $seconds
		1917
		1918	Sets the minimum idle timeout (default 10) after which worker threads are
		1919	allowed to exit. SEe C<IO::AIO::max_idle>.
		1920
		1921	=item IO::AIO::max_outstanding $maxreqs
		1922
		1923	Sets the maximum number of outstanding requests to C<$nreqs>. If
		1924	you do queue up more than this number of requests, the next call to
		1925	C<IO::AIO::poll_cb> (and other functions calling C<poll_cb>, such as
		1926	C<IO::AIO::flush> or C<IO::AIO::poll>) will block until the limit is no
		1927	longer exceeded.
		1928
		1929	In other words, this setting does not enforce a queue limit, but can be
		1930	used to make poll functions block if the limit is exceeded.
		1931
		1932	This is a very bad function to use in interactive programs because it
		1933	blocks, and a bad way to reduce concurrency because it is inexact: Better
		1934	use an C<aio_group> together with a feed callback.
		1935
		1936	It's main use is in scripts without an event loop - when you want to stat
		1937	a lot of files, you can write somehting like this:
		1938
		1939	IO::AIO::max_outstanding 32;
		1940
		1941	for my $path (...) {
		1942	aio_stat $path , ...;
		1943	IO::AIO::poll_cb;
		1944	}
		1945
		1946	IO::AIO::flush;
		1947
		1948	The call to C<poll_cb> inside the loop will normally return instantly, but
		1949	as soon as more thna C<32> reqeusts are in-flight, it will block until
		1950	some requests have been handled. This keeps the loop from pushing a large
		1951	number of C<aio_stat> requests onto the queue.
		1952
		1953	The default value for C<max_outstanding> is very large, so there is no
		1954	practical limit on the number of outstanding requests.
		1955
		1956	=back
		1957
		1958	=head3 STATISTICAL INFORMATION
		1959
		1960	=over
		1961
254	=item IO::AIO::flush	1962	=item IO::AIO::nreqs
255		1963
256	Wait till all outstanding AIO requests have been handled.	1964	Returns the number of requests currently in the ready, execute or pending
		1965	states (i.e. for which their callback has not been invoked yet).
257		1966
258	Strictly equivalent to:	1967	Example: wait till there are no outstanding requests anymore:
259		1968
260	IO::AIO::poll_wait, IO::AIO::poll_cb	1969	IO::AIO::poll_wait, IO::AIO::poll_cb
261	while IO::AIO::nreqs;	1970	while IO::AIO::nreqs;
262		1971
		1972	=item IO::AIO::nready
		1973
		1974	Returns the number of requests currently in the ready state (not yet
		1975	executed).
		1976
263	=item IO::AIO::poll	1977	=item IO::AIO::npending
264		1978
265	Waits until some requests have been handled.	1979	Returns the number of requests currently in the pending state (executed,
266		1980	but not yet processed by poll_cb).
267	Strictly equivalent to:
268
269	IO::AIO::poll_wait, IO::AIO::poll_cb
270	if IO::AIO::nreqs;
271
272	=item IO::AIO::min_parallel $nthreads
273
274	Set the minimum number of AIO threads to C<$nthreads>. The default is
275	C<1>, which means a single asynchronous operation can be done at one time
276	(the number of outstanding operations, however, is unlimited).
277
278	It is recommended to keep the number of threads low, as some Linux
279	kernel versions will scale negatively with the number of threads (higher
280	parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32
281	threads should be fine.
282
283	Under normal circumstances you don't need to call this function, as this
284	module automatically starts some threads (the exact number might change,
285	and is currently 4).
286
287	=item IO::AIO::max_parallel $nthreads
288
289	Sets the maximum number of AIO threads to C<$nthreads>. If more than
290	the specified number of threads are currently running, kill them. This
291	function blocks until the limit is reached.
292
293	This module automatically runs C<max_parallel 0> at program end, to ensure
294	that all threads are killed and that there are no outstanding requests.
295
296	Under normal circumstances you don't need to call this function.
297
298	=item $oldnreqs = IO::AIO::max_outstanding $nreqs
299
300	Sets the maximum number of outstanding requests to C<$nreqs>. If you
301	try to queue up more than this number of requests, the caller will block until
302	some requests have been handled.
303
304	The default is very large, so normally there is no practical limit. If you
305	queue up many requests in a loop it it often improves speed if you set
306	this to a relatively low number, such as C<100>.
307
308	Under normal circumstances you don't need to call this function.
309		1981
310	=back	1982	=back
311		1983
		1984	=head3 MISCELLANEOUS FUNCTIONS
		1985
		1986	IO::AIO implements some functions that might be useful, but are not
		1987	asynchronous.
		1988
		1989	=over 4
		1990
		1991	=item IO::AIO::sendfile $ofh, $ifh, $offset, $count
		1992
		1993	Calls the C<eio_sendfile_sync> function, which is like C<aio_sendfile>,
		1994	but is blocking (this makes most sense if you know the input data is
		1995	likely cached already and the output filehandle is set to non-blocking
		1996	operations).
		1997
		1998	Returns the number of bytes copied, or C<-1> on error.
		1999
		2000	=item IO::AIO::fadvise $fh, $offset, $len, $advice
		2001
		2002	Simply calls the C<posix_fadvise> function (see its
		2003	manpage for details). The following advice constants are
		2004	available: C<IO::AIO::FADV_NORMAL>, C<IO::AIO::FADV_SEQUENTIAL>,
		2005	C<IO::AIO::FADV_RANDOM>, C<IO::AIO::FADV_NOREUSE>,
		2006	C<IO::AIO::FADV_WILLNEED>, C<IO::AIO::FADV_DONTNEED>.
		2007
		2008	On systems that do not implement C<posix_fadvise>, this function returns
		2009	ENOSYS, otherwise the return value of C<posix_fadvise>.
		2010
		2011	=item IO::AIO::madvise $scalar, $offset, $len, $advice
		2012
		2013	Simply calls the C<posix_madvise> function (see its
		2014	manpage for details). The following advice constants are
		2015	available: C<IO::AIO::MADV_NORMAL>, C<IO::AIO::MADV_SEQUENTIAL>,
		2016	C<IO::AIO::MADV_RANDOM>, C<IO::AIO::MADV_WILLNEED>, C<IO::AIO::MADV_DONTNEED>.
		2017
		2018	On systems that do not implement C<posix_madvise>, this function returns
		2019	ENOSYS, otherwise the return value of C<posix_madvise>.
		2020
		2021	=item IO::AIO::mprotect $scalar, $offset, $len, $protect
		2022
		2023	Simply calls the C<mprotect> function on the preferably AIO::mmap'ed
		2024	$scalar (see its manpage for details). The following protect
		2025	constants are available: C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_READ>,
		2026	C<IO::AIO::PROT_WRITE>, C<IO::AIO::PROT_EXEC>.
		2027
		2028	On systems that do not implement C<mprotect>, this function returns
		2029	ENOSYS, otherwise the return value of C<mprotect>.
		2030
		2031	=item IO::AIO::mmap $scalar, $length, $prot, $flags, $fh[, $offset]
		2032
		2033	Memory-maps a file (or anonymous memory range) and attaches it to the
		2034	given C<$scalar>, which will act like a string scalar. Returns true on
		2035	success, and false otherwise.
		2036
		2037	The only operations allowed on the scalar are C<substr>/C<vec> that don't
		2038	change the string length, and most read-only operations such as copying it
		2039	or searching it with regexes and so on.
		2040
		2041	Anything else is unsafe and will, at best, result in memory leaks.
		2042
		2043	The memory map associated with the C<$scalar> is automatically removed
		2044	when the C<$scalar> is destroyed, or when the C<IO::AIO::mmap> or
		2045	C<IO::AIO::munmap> functions are called.
		2046
		2047	This calls the C<mmap>(2) function internally. See your system's manual
		2048	page for details on the C<$length>, C<$prot> and C<$flags> parameters.
		2049
		2050	The C<$length> must be larger than zero and smaller than the actual
		2051	filesize.
		2052
		2053	C<$prot> is a combination of C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_EXEC>,
		2054	C<IO::AIO::PROT_READ> and/or C<IO::AIO::PROT_WRITE>,
		2055
		2056	C<$flags> can be a combination of C<IO::AIO::MAP_SHARED> or
		2057	C<IO::AIO::MAP_PRIVATE>, or a number of system-specific flags (when
		2058	not available, the are defined as 0): C<IO::AIO::MAP_ANONYMOUS>
		2059	(which is set to C<MAP_ANON> if your system only provides this
		2060	constant), C<IO::AIO::MAP_HUGETLB>, C<IO::AIO::MAP_LOCKED>,
		2061	C<IO::AIO::MAP_NORESERVE>, C<IO::AIO::MAP_POPULATE> or
		2062	C<IO::AIO::MAP_NONBLOCK>
		2063
		2064	If C<$fh> is C<undef>, then a file descriptor of C<-1> is passed.
		2065
		2066	C<$offset> is the offset from the start of the file - it generally must be
		2067	a multiple of C<IO::AIO::PAGESIZE> and defaults to C<0>.
		2068
		2069	Example:
		2070
		2071	use Digest::MD5;
		2072	use IO::AIO;
		2073
		2074	open my $fh, "<verybigfile"
		2075	or die "$!";
		2076
		2077	IO::AIO::mmap my $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh
		2078	or die "verybigfile: $!";
		2079
		2080	my $fast_md5 = md5 $data;
		2081
		2082	=item IO::AIO::munmap $scalar
		2083
		2084	Removes a previous mmap and undefines the C<$scalar>.
		2085
		2086	=item IO::AIO::munlock $scalar, $offset = 0, $length = undef
		2087
		2088	Calls the C<munlock> function, undoing the effects of a previous
		2089	C<aio_mlock> call (see its description for details).
		2090
		2091	=item IO::AIO::munlockall
		2092
		2093	Calls the C<munlockall> function.
		2094
		2095	On systems that do not implement C<munlockall>, this function returns
		2096	ENOSYS, otherwise the return value of C<munlockall>.
		2097
		2098	=item IO::AIO::splice $r_fh, $r_off, $w_fh, $w_off, $length, $flags
		2099
		2100	Calls the GNU/Linux C<splice(2)> syscall, if available. If C<$r_off> or
		2101	C<$w_off> are C<undef>, then C<NULL> is passed for these, otherwise they
		2102	should be the file offset.
		2103
		2104	C<$r_fh> and C<$w_fh> should not refer to the same file, as splice might
		2105	silently corrupt the data in this case.
		2106
		2107	The following symbol flag values are available: C<IO::AIO::SPLICE_F_MOVE>,
		2108	C<IO::AIO::SPLICE_F_NONBLOCK>, C<IO::AIO::SPLICE_F_MORE> and
		2109	C<IO::AIO::SPLICE_F_GIFT>.
		2110
		2111	See the C<splice(2)> manpage for details.
		2112
		2113	=item IO::AIO::tee $r_fh, $w_fh, $length, $flags
		2114
		2115	Calls the GNU/Linux C<tee(2)> syscall, see it's manpage and the
		2116	description for C<IO::AIO::splice> above for details.
		2117
		2118	=item $actual_size = IO::AIO::pipesize $r_fh[, $new_size]
		2119
		2120	Attempts to query or change the pipe buffer size. Obviously works only
		2121	on pipes, and currently works only on GNU/Linux systems, and fails with
		2122	C<-1>/C<ENOSYS> everywhere else. If anybody knows how to influence pipe buffer
		2123	size on other systems, drop me a note.
		2124
		2125	=back
		2126
312	=cut	2127	=cut
313		2128
314	# support function to convert a fd into a perl filehandle
315	sub _fd2fh {
316	return undef if $_[0] < 0;
317
318	# try to generate nice filehandles
319	my $sym = "IO::AIO::fd#$_[0]";
320	local *$sym;
321	open *$sym, "+<&=$_[0]"
322	or return undef;
323
324	*$sym
325	}
326
327	min_parallel 4;	2129	min_parallel 8;
328		2130
329	END {	2131	END { flush }
330	max_parallel 0;
331	}
332		2132
333	1;	2133	1;
334		2134
		2135	=head1 EVENT LOOP INTEGRATION
		2136
		2137	It is recommended to use L<AnyEvent::AIO> to integrate IO::AIO
		2138	automatically into many event loops:
		2139
		2140	# AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...)
		2141	use AnyEvent::AIO;
		2142
		2143	You can also integrate IO::AIO manually into many event loops, here are
		2144	some examples of how to do this:
		2145
		2146	# EV integration
		2147	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
		2148
		2149	# Event integration
		2150	Event->io (fd => IO::AIO::poll_fileno,
		2151	poll => 'r',
		2152	cb => \&IO::AIO::poll_cb);
		2153
		2154	# Glib/Gtk2 integration
		2155	add_watch Glib::IO IO::AIO::poll_fileno,
		2156	in => sub { IO::AIO::poll_cb; 1 };
		2157
		2158	# Tk integration
		2159	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
		2160	readable => \&IO::AIO::poll_cb);
		2161
		2162	# Danga::Socket integration
		2163	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
		2164	\&IO::AIO::poll_cb);
		2165
		2166	=head2 FORK BEHAVIOUR
		2167
		2168	Usage of pthreads in a program changes the semantics of fork
		2169	considerably. Specifically, only async-safe functions can be called after
		2170	fork. Perl doesn't know about this, so in general, you cannot call fork
		2171	with defined behaviour in perl if pthreads are involved. IO::AIO uses
		2172	pthreads, so this applies, but many other extensions and (for inexplicable
		2173	reasons) perl itself often is linked against pthreads, so this limitation
		2174	applies to quite a lot of perls.
		2175
		2176	This module no longer tries to fight your OS, or POSIX. That means IO::AIO
		2177	only works in the process that loaded it. Forking is fully supported, but
		2178	using IO::AIO in the child is not.
		2179
		2180	You might get around by not I<using> IO::AIO before (or after)
		2181	forking. You could also try to call the L<IO::AIO::reinit> function in the
		2182	child:
		2183
		2184	=over 4
		2185
		2186	=item IO::AIO::reinit
		2187
		2188	Abandons all current requests and I/O threads and simply reinitialises all
		2189	data structures. This is not an operation supported by any standards, but
		2190	happens to work on GNU/Linux and some newer BSD systems.
		2191
		2192	The only reasonable use for this function is to call it after forking, if
		2193	C<IO::AIO> was used in the parent. Calling it while IO::AIO is active in
		2194	the process will result in undefined behaviour. Calling it at any time
		2195	will also result in any undefined (by POSIX) behaviour.
		2196
		2197	=back
		2198
		2199	=head2 MEMORY USAGE
		2200
		2201	Per-request usage:
		2202
		2203	Each aio request uses - depending on your architecture - around 100-200
		2204	bytes of memory. In addition, stat requests need a stat buffer (possibly
		2205	a few hundred bytes), readdir requires a result buffer and so on. Perl
		2206	scalars and other data passed into aio requests will also be locked and
		2207	will consume memory till the request has entered the done state.
		2208
		2209	This is not awfully much, so queuing lots of requests is not usually a
		2210	problem.
		2211
		2212	Per-thread usage:
		2213
		2214	In the execution phase, some aio requests require more memory for
		2215	temporary buffers, and each thread requires a stack and other data
		2216	structures (usually around 16k-128k, depending on the OS).
		2217
		2218	=head1 KNOWN BUGS
		2219
		2220	Known bugs will be fixed in the next release.
		2221
335	=head1 SEE ALSO	2222	=head1 SEE ALSO
336		2223
337	L<Coro>, L<Linux::AIO>.	2224	L<AnyEvent::AIO> for easy integration into event loops, L<Coro::AIO> for a
		2225	more natural syntax.
338		2226
339	=head1 AUTHOR	2227	=head1 AUTHOR
340		2228
341	Marc Lehmann <schmorp@schmorp.de>	2229	Marc Lehmann <schmorp@schmorp.de>
342	http://home.schmorp.de/	2230	http://home.schmorp.de/

Diff Legend

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