ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/IO-AIO/AIO.pm

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.6 by root, Sun Jul 10 22:19:48 2005 UTC vs.
Revision 1.257 by root, Mon Jan 18 11:53:09 2016 UTC

…		…
4		4
5	=head1 SYNOPSIS	5	=head1 SYNOPSIS
6		6
7	use IO::AIO;	7	use IO::AIO;
8		8
9	aio_open "/etc/passwd", O_RDONLY, 0, sub {	9	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
10	my ($fh) = @_;	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', async => 1,
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	\&IO::AIO::poll_cb;	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		30
33	=head1 DESCRIPTION	31	=head1 DESCRIPTION
34		32
35	This module implements asynchronous I/O using whatever means your	33	This module implements asynchronous I/O using whatever means your
36	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>).
37		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
38	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
39	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
40	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
41	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
42	aio functions available on many operating systems. However, they are often	57	functions available on many operating systems. However, they are often
43	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
44	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
45	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.
46		62
47	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,
48	currently not reentrant, so use appropriate locking yourself.	64	it is currently not reentrant in any way, so use appropriate locking
		65	yourself, always call C<poll_cb> from within the same thread, or never
		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::break;
		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::run;
		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
49		160
50	=cut	161	=cut
51		162
52	package IO::AIO;	163	package IO::AIO;
53		164
		165	use Carp ();
		166
		167	use common::sense;
		168
54	use base 'Exporter';	169	use base 'Exporter';
55		170
56	use Fcntl ();
57
58	BEGIN {	171	BEGIN {
59	$VERSION = 0.2;	172	our $VERSION = 4.33;
60		173
61	@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
62	aio_fsync aio_fdatasync aio_readahead);	175	aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx
63	@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';
64		197
65	require XSLoader;	198	require XSLoader;
66	XSLoader::load IO::AIO, $VERSION;	199	XSLoader::load ("IO::AIO", $VERSION);
67	}	200	}
68		201
69	=head1 FUNCTIONS	202	=head1 FUNCTIONS
70		203
71	=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, $callback->($path)
		233	aio_rename $srcpath, $dstpath, $callback->($status)
		234	aio_mkdir $pathname, $mode, $callback->($status)
		235	aio_rmdir $pathname, $callback->($status)
		236	aio_readdir $pathname, $callback->($entries)
		237	aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		238	IO::AIO::READDIR_DENTS IO::AIO::READDIR_DIRS_FIRST
		239	IO::AIO::READDIR_STAT_ORDER IO::AIO::READDIR_FOUND_UNKNOWN
		240	aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs)
		241	aio_load $pathname, $data, $callback->($status)
		242	aio_copy $srcpath, $dstpath, $callback->($status)
		243	aio_move $srcpath, $dstpath, $callback->($status)
		244	aio_rmtree $pathname, $callback->($status)
		245	aio_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, $length = undef
		283	IO::AIO::munlockall
		284
		285	=head2 API NOTES
72		286
73	All the C<aio_*> calls are more or less thin wrappers around the syscall	287	All the C<aio_*> calls are more or less thin wrappers around the syscall
74	with the same name (sans C<aio_>). The arguments are similar or identical,	288	with the same name (sans C<aio_>). The arguments are similar or identical,
75	and they all accept an additional C<$callback> argument which must be	289	and they all accept an additional (and optional) C<$callback> argument
76	a code reference. This code reference will get called with the syscall	290	which must be a code reference. This code reference will be called after
		291	the syscall has been executed in an asynchronous fashion. The results
		292	of the request will be passed as arguments to the callback (and, if an
		293	error occured, in C<$!>) - for most requests the syscall return code (e.g.
77	return code (e.g. most syscalls return C<-1> on error, unlike perl, which	294	most syscalls return C<-1> on error, unlike perl, which usually delivers
78	usually delivers "false") as it's sole argument when the given syscall has	295	"false").
79	been executed asynchronously.
80		296
81	All functions that expect a filehandle will also accept a file descriptor.	297	Some requests (such as C<aio_readdir>) pass the actual results and
		298	communicate failures by passing C<undef>.
82		299
		300	All functions expecting a filehandle keep a copy of the filehandle
		301	internally until the request has finished.
		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
83	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
84	is that at the time the request is being executed, the current working	307	reason for this is that at the time the request is being executed, the
85	directory could have changed. Alternatively, you can make sure that you	308	current working directory could have changed. Alternatively, you can
86	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
87		327
88	=over 4	328	=over 4
89		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
90	=item aio_open $pathname, $flags, $mode, $callback	363	=item aio_open $pathname, $flags, $mode, $callback->($fh)
91		364
92	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
93	created filehandle for the file.	366	created filehandle for the file (or C<undef> in case of an error).
94		367
95	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,
96	for an explanation.	369	for an explanation.
97		370
98	The C<$mode> argument is a bitmask. See the C<Fcntl> module for a	371	The C<$flags> argument is a bitmask. See the C<Fcntl> module for a
99	list. They are the same as used in C<sysopen>.	372	list. They are the same as used by C<sysopen>.
		373
		374	Likewise, C<$mode> specifies the mode of the newly created file, if it
		375	didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,
		376	except that it is mandatory (i.e. use C<0> if you don't create new files,
		377	and C<0666> or C<0777> if you do). Note that the C<$mode> will be modified
		378	by the umask in effect then the request is being executed, so better never
		379	change the umask.
100		380
101	Example:	381	Example:
102		382
103	aio_open "/etc/passwd", O_RDONLY, 0, sub {	383	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
104	if ($_[0]) {	384	if ($_[0]) {
105	print "open successful, fh is $_[0]\n";	385	print "open successful, fh is $_[0]\n";
106	...	386	...
107	} else {	387	} else {
108	die "open failed: $!\n";	388	die "open failed: $!\n";
109	}	389	}
110	};	390	};
111		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>, C<O_PATH>, C<O_TMPFILE>, and C<O_TTY_INIT>.
		400
		401
112	=item aio_close $fh, $callback	402	=item aio_close $fh, $callback->($status)
113		403
114	Asynchronously close a file and call the callback with the result	404	Asynchronously close a file and call the callback with the result
115	code. I<WARNING:> although accepted, you should not pass in a perl	405	code.
116	filehandle here, as perl will likely close the file descriptor itself when
117	the filehandle is destroyed. Normally, you can safely call perls C<close>
118	or just let filehandles go out of scope.
119		406
		407	Unfortunately, you can't do this to perl. Perl I<insists> very strongly on
		408	closing the file descriptor associated with the filehandle itself.
		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
120	=item aio_read $fh,$offset,$length, $data,$dataoffset,$callback	439	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
121		440
122	=item aio_write $fh,$offset,$length, $data,$dataoffset,$callback	441	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
123		442
124	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
125	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<$dataoffset>
126	callback without the actual number of bytes read (or -1 on error, just	445	and calls the callback without the actual number of bytes read (or -1 on
127	like the syscall).	446	error, just like the syscall).
128		447
		448	C<aio_read> will, like C<sysread>, shrink or grow the C<$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).
		464
129	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, strating at	465	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at
130	offset C<0> within the scalar:	466	offset C<0> within the scalar:
131		467
132	aio_read $fh, 7, 15, $buffer, 0, sub {	468	aio_read $fh, 7, 15, $buffer, 0, sub {
133	$_[0] >= 0 or die "read error: $!";	469	$_[0] > 0 or die "read error: $!";
134	print "read <$buffer>\n";	470	print "read $_[0] bytes: <$buffer>\n";
135	};	471	};
136		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
137	=item aio_readahead $fh,$offset,$length, $callback	516	=item aio_readahead $fh,$offset,$length, $callback->($retval)
138		517
139	Asynchronously reads the specified byte range into the page cache, using
140	the C<readahead> syscall. If that syscall doesn't exist the status will be
141	C<-1> and C<$!> is set to ENOSYS.
142
143	readahead() populates the page cache with data from a file so that	518	C<aio_readahead> populates the page cache with data from a file so that
144	subsequent reads from that file will not block on disk I/O. The C<$offset>	519	subsequent reads from that file will not block on disk I/O. The C<$offset>
145	argument specifies the starting point from which data is to be read and	520	argument specifies the starting point from which data is to be read and
146	C<$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
147	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
148	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
149	(off-set+length). 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
150	file. The current file offset of the file is left unchanged.	525	file. The current file offset of the file is left unchanged.
151		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
152	=item aio_stat $fh_or_path, $callback	531	=item aio_stat $fh_or_path, $callback->($status)
153		532
154	=item aio_lstat $fh, $callback	533	=item aio_lstat $fh, $callback->($status)
155		534
156	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
157	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 _>
158	or C<-s _> etc...	537	or C<-s _> etc...
159		538
…		…
161	for an explanation.	540	for an explanation.
162		541
163	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
164	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
165	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>.
166		554
167	Example: Print the length of F</etc/passwd>:	555	Example: Print the length of F</etc/passwd>:
168		556
169	aio_stat "/etc/passwd", sub {	557	aio_stat "/etc/passwd", sub {
170	$_[0] and die "stat failed: $!";	558	$_[0] and die "stat failed: $!";
171	print "size is ", -s _, "\n";	559	print "size is ", -s _, "\n";
172	};	560	};
173		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/ext4
		632	0x0000ef51 ext2
		633	0xf2f52010 f2fs
		634	0x00004006 fat
		635	0x65735546 fuseblk
		636	0x65735543 fusectl
		637	0x0bad1dea futexfs
		638	0x01161970 gfs2
		639	0x47504653 gpfs
		640	0x00004244 hfs
		641	0xf995e849 hpfs
		642	0x00c0ffee hostfs
		643	0x958458f6 hugetlbfs
		644	0x2bad1dea inotifyfs
		645	0x00009660 isofs
		646	0x000072b6 jffs2
		647	0x3153464a jfs
		648	0x6b414653 k-afs
		649	0x0bd00bd0 lustre
		650	0x0000137f minix
		651	0x0000138f minix 30 char names
		652	0x00002468 minix v2
		653	0x00002478 minix v2 30 char names
		654	0x00004d5a minix v3
		655	0x19800202 mqueue
		656	0x00004d44 msdos
		657	0x0000564c novell
		658	0x00006969 nfs
		659	0x6e667364 nfsd
		660	0x00003434 nilfs
		661	0x5346544e ntfs
		662	0x00009fa1 openprom
		663	0x7461636F ocfs2
		664	0x00009fa0 proc
		665	0x6165676c pstorefs
		666	0x0000002f qnx4
		667	0x68191122 qnx6
		668	0x858458f6 ramfs
		669	0x52654973 reiserfs
		670	0x00007275 romfs
		671	0x67596969 rpc_pipefs
		672	0x73636673 securityfs
		673	0xf97cff8c selinux
		674	0x0000517b smb
		675	0x534f434b sockfs
		676	0x73717368 squashfs
		677	0x62656572 sysfs
		678	0x012ff7b6 sysv2
		679	0x012ff7b5 sysv4
		680	0x01021994 tmpfs
		681	0x15013346 udf
		682	0x00011954 ufs
		683	0x54190100 ufs byteswapped
		684	0x00009fa2 usbdevfs
		685	0x01021997 v9fs
		686	0xa501fcf5 vxfs
		687	0xabba1974 xenfs
		688	0x012ff7b4 xenix
		689	0x58465342 xfs
		690	0x012fd16d xia
		691
		692	=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
		693
		694	Works like perl's C<utime> function (including the special case of $atime
		695	and $mtime being undef). Fractional times are supported if the underlying
		696	syscalls support them.
		697
		698	When called with a pathname, uses utimes(2) if available, otherwise
		699	utime(2). If called on a file descriptor, uses futimes(2) if available,
		700	otherwise returns ENOSYS, so this is not portable.
		701
		702	Examples:
		703
		704	# set atime and mtime to current time (basically touch(1)):
		705	aio_utime "path", undef, undef;
		706	# set atime to current time and mtime to beginning of the epoch:
		707	aio_utime "path", time, undef; # undef==0
		708
		709
		710	=item aio_chown $fh_or_path, $uid, $gid, $callback->($status)
		711
		712	Works like perl's C<chown> function, except that C<undef> for either $uid
		713	or $gid is being interpreted as "do not change" (but -1 can also be used).
		714
		715	Examples:
		716
		717	# same as "chown root path" in the shell:
		718	aio_chown "path", 0, -1;
		719	# same as above:
		720	aio_chown "path", 0, undef;
		721
		722
		723	=item aio_truncate $fh_or_path, $offset, $callback->($status)
		724
		725	Works like truncate(2) or ftruncate(2).
		726
		727
		728	=item aio_allocate $fh, $mode, $offset, $len, $callback->($status)
		729
		730	Allocates or frees disk space according to the C<$mode> argument. See the
		731	linux C<fallocate> documentation for details.
		732
		733	C<$mode> is usually C<0> or C<IO::AIO::FALLOC_FL_KEEP_SIZE> to allocate
		734	space, or C<IO::AIO::FALLOC_FL_PUNCH_HOLE | IO::AIO::FALLOC_FL_KEEP_SIZE>,
		735	to deallocate a file range.
		736
		737	IO::AIO also supports C<FALLOC_FL_COLLAPSE_RANGE>, to remove a range
		738	(without leaving a hole) and C<FALLOC_FL_ZERO_RANGE>, to zero a range (see
		739	your L<fallocate(2)> manpage).
		740
		741	The file system block size used by C<fallocate> is presumably the
		742	C<f_bsize> returned by C<statvfs>.
		743
		744	If C<fallocate> isn't available or cannot be emulated (currently no
		745	emulation will be attempted), passes C<-1> and sets C<$!> to C<ENOSYS>.
		746
		747
		748	=item aio_chmod $fh_or_path, $mode, $callback->($status)
		749
		750	Works like perl's C<chmod> function.
		751
		752
174	=item aio_unlink $pathname, $callback	753	=item aio_unlink $pathname, $callback->($status)
175		754
176	Asynchronously unlink (delete) a file and call the callback with the	755	Asynchronously unlink (delete) a file and call the callback with the
177	result code.	756	result code.
178		757
		758
		759	=item aio_mknod $pathname, $mode, $dev, $callback->($status)
		760
		761	[EXPERIMENTAL]
		762
		763	Asynchronously create a device node (or fifo). See mknod(2).
		764
		765	The only (POSIX-) portable way of calling this function is:
		766
		767	aio_mknod $pathname, IO::AIO::S_IFIFO | $mode, 0, sub { ...
		768
		769	See C<aio_stat> for info about some potentially helpful extra constants
		770	and functions.
		771
		772	=item aio_link $srcpath, $dstpath, $callback->($status)
		773
		774	Asynchronously create a new link to the existing object at C<$srcpath> at
		775	the path C<$dstpath> and call the callback with the result code.
		776
		777
		778	=item aio_symlink $srcpath, $dstpath, $callback->($status)
		779
		780	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at
		781	the path C<$dstpath> and call the callback with the result code.
		782
		783
		784	=item aio_readlink $pathname, $callback->($link)
		785
		786	Asynchronously read the symlink specified by C<$path> and pass it to
		787	the callback. If an error occurs, nothing or undef gets passed to the
		788	callback.
		789
		790
		791	=item aio_realpath $pathname, $callback->($path)
		792
		793	Asynchronously make the path absolute and resolve any symlinks in
		794	C<$path>. The resulting path only consists of directories (same as
		795	L<Cwd::realpath>).
		796
		797	This request can be used to get the absolute path of the current working
		798	directory by passing it a path of F<.> (a single dot).
		799
		800
		801	=item aio_rename $srcpath, $dstpath, $callback->($status)
		802
		803	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as
		804	rename(2) and call the callback with the result code.
		805
		806	On systems that support the AIO::WD working directory abstraction
		807	natively, the case C<[$wd, "."]> as C<$srcpath> is specialcased - instead
		808	of failing, C<rename> is called on the absolute path of C<$wd>.
		809
		810
		811	=item aio_mkdir $pathname, $mode, $callback->($status)
		812
		813	Asynchronously mkdir (create) a directory and call the callback with
		814	the result code. C<$mode> will be modified by the umask at the time the
		815	request is executed, so do not change your umask.
		816
		817
		818	=item aio_rmdir $pathname, $callback->($status)
		819
		820	Asynchronously rmdir (delete) a directory and call the callback with the
		821	result code.
		822
		823	On systems that support the AIO::WD working directory abstraction
		824	natively, the case C<[$wd, "."]> is specialcased - instead of failing,
		825	C<rmdir> is called on the absolute path of C<$wd>.
		826
		827
		828	=item aio_readdir $pathname, $callback->($entries)
		829
		830	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
		831	directory (i.e. opendir + readdir + closedir). The entries will not be
		832	sorted, and will B<NOT> include the C<.> and C<..> entries.
		833
		834	The callback is passed a single argument which is either C<undef> or an
		835	array-ref with the filenames.
		836
		837
		838	=item aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		839
		840	Quite similar to C<aio_readdir>, but the C<$flags> argument allows one to
		841	tune behaviour and output format. In case of an error, C<$entries> will be
		842	C<undef>.
		843
		844	The flags are a combination of the following constants, ORed together (the
		845	flags will also be passed to the callback, possibly modified):
		846
		847	=over 4
		848
		849	=item IO::AIO::READDIR_DENTS
		850
		851	When this flag is off, then the callback gets an arrayref consisting of
		852	names only (as with C<aio_readdir>), otherwise it gets an arrayref with
		853	C<[$name, $type, $inode]> arrayrefs, each describing a single directory
		854	entry in more detail.
		855
		856	C<$name> is the name of the entry.
		857
		858	C<$type> is one of the C<IO::AIO::DT_xxx> constants:
		859
		860	C<IO::AIO::DT_UNKNOWN>, C<IO::AIO::DT_FIFO>, C<IO::AIO::DT_CHR>, C<IO::AIO::DT_DIR>,
		861	C<IO::AIO::DT_BLK>, C<IO::AIO::DT_REG>, C<IO::AIO::DT_LNK>, C<IO::AIO::DT_SOCK>,
		862	C<IO::AIO::DT_WHT>.
		863
		864	C<IO::AIO::DT_UNKNOWN> means just that: readdir does not know. If you need to
		865	know, you have to run stat yourself. Also, for speed reasons, the C<$type>
		866	scalars are read-only: you can not modify them.
		867
		868	C<$inode> is the inode number (which might not be exact on systems with 64
		869	bit inode numbers and 32 bit perls). This field has unspecified content on
		870	systems that do not deliver the inode information.
		871
		872	=item IO::AIO::READDIR_DIRS_FIRST
		873
		874	When this flag is set, then the names will be returned in an order where
		875	likely directories come first, in optimal stat order. This is useful when
		876	you need to quickly find directories, or you want to find all directories
		877	while avoiding to stat() each entry.
		878
		879	If the system returns type information in readdir, then this is used
		880	to find directories directly. Otherwise, likely directories are names
		881	beginning with ".", or otherwise names with no dots, of which names with
		882	short names are tried first.
		883
		884	=item IO::AIO::READDIR_STAT_ORDER
		885
		886	When this flag is set, then the names will be returned in an order
		887	suitable for stat()'ing each one. That is, when you plan to stat()
		888	all files in the given directory, then the returned order will likely
		889	be fastest.
		890
		891	If both this flag and C<IO::AIO::READDIR_DIRS_FIRST> are specified, then
		892	the likely dirs come first, resulting in a less optimal stat order.
		893
		894	=item IO::AIO::READDIR_FOUND_UNKNOWN
		895
		896	This flag should not be set when calling C<aio_readdirx>. Instead, it
		897	is being set by C<aio_readdirx>, when any of the C<$type>'s found were
		898	C<IO::AIO::DT_UNKNOWN>. The absence of this flag therefore indicates that all
		899	C<$type>'s are known, which can be used to speed up some algorithms.
		900
		901	=back
		902
		903
		904	=item aio_load $pathname, $data, $callback->($status)
		905
		906	This is a composite request that tries to fully load the given file into
		907	memory. Status is the same as with aio_read.
		908
		909	=cut
		910
		911	sub aio_load($$;$) {
		912	my ($path, undef, $cb) = @_;
		913	my $data = \$_[1];
		914
		915	my $pri = aioreq_pri;
		916	my $grp = aio_group $cb;
		917
		918	aioreq_pri $pri;
		919	add $grp aio_open $path, O_RDONLY, 0, sub {
		920	my $fh = shift
		921	or return $grp->result (-1);
		922
		923	aioreq_pri $pri;
		924	add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub {
		925	$grp->result ($_[0]);
		926	};
		927	};
		928
		929	$grp
		930	}
		931
		932	=item aio_copy $srcpath, $dstpath, $callback->($status)
		933
		934	Try to copy the I<file> (directories not supported as either source or
		935	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		936	a status of C<0> (ok) or C<-1> (error, see C<$!>).
		937
		938	This is a composite request that creates the destination file with
		939	mode 0200 and copies the contents of the source file into it using
		940	C<aio_sendfile>, followed by restoring atime, mtime, access mode and
		941	uid/gid, in that order.
		942
		943	If an error occurs, the partial destination file will be unlinked, if
		944	possible, except when setting atime, mtime, access mode and uid/gid, where
		945	errors are being ignored.
		946
		947	=cut
		948
		949	sub aio_copy($$;$) {
		950	my ($src, $dst, $cb) = @_;
		951
		952	my $pri = aioreq_pri;
		953	my $grp = aio_group $cb;
		954
		955	aioreq_pri $pri;
		956	add $grp aio_open $src, O_RDONLY, 0, sub {
		957	if (my $src_fh = $_[0]) {
		958	my @stat = stat $src_fh; # hmm, might block over nfs?
		959
		960	aioreq_pri $pri;
		961	add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {
		962	if (my $dst_fh = $_[0]) {
		963	aioreq_pri $pri;
		964	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
		965	if ($_[0] == $stat[7]) {
		966	$grp->result (0);
		967	close $src_fh;
		968
		969	my $ch = sub {
		970	aioreq_pri $pri;
		971	add $grp aio_chmod $dst_fh, $stat[2] & 07777, sub {
		972	aioreq_pri $pri;
		973	add $grp aio_chown $dst_fh, $stat[4], $stat[5], sub {
		974	aioreq_pri $pri;
		975	add $grp aio_close $dst_fh;
		976	}
		977	};
		978	};
		979
		980	aioreq_pri $pri;
		981	add $grp aio_utime $dst_fh, $stat[8], $stat[9], sub {
		982	if ($_[0] < 0 && $! == ENOSYS) {
		983	aioreq_pri $pri;
		984	add $grp aio_utime $dst, $stat[8], $stat[9], $ch;
		985	} else {
		986	$ch->();
		987	}
		988	};
		989	} else {
		990	$grp->result (-1);
		991	close $src_fh;
		992	close $dst_fh;
		993
		994	aioreq $pri;
		995	add $grp aio_unlink $dst;
		996	}
		997	};
		998	} else {
		999	$grp->result (-1);
		1000	}
		1001	},
		1002
		1003	} else {
		1004	$grp->result (-1);
		1005	}
		1006	};
		1007
		1008	$grp
		1009	}
		1010
		1011	=item aio_move $srcpath, $dstpath, $callback->($status)
		1012
		1013	Try to move the I<file> (directories not supported as either source or
		1014	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		1015	a status of C<0> (ok) or C<-1> (error, see C<$!>).
		1016
		1017	This is a composite request that tries to rename(2) the file first; if
		1018	rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if
		1019	that is successful, unlinks the C<$srcpath>.
		1020
		1021	=cut
		1022
		1023	sub aio_move($$;$) {
		1024	my ($src, $dst, $cb) = @_;
		1025
		1026	my $pri = aioreq_pri;
		1027	my $grp = aio_group $cb;
		1028
		1029	aioreq_pri $pri;
		1030	add $grp aio_rename $src, $dst, sub {
		1031	if ($_[0] && $! == EXDEV) {
		1032	aioreq_pri $pri;
		1033	add $grp aio_copy $src, $dst, sub {
		1034	$grp->result ($_[0]);
		1035
		1036	unless ($_[0]) {
		1037	aioreq_pri $pri;
		1038	add $grp aio_unlink $src;
		1039	}
		1040	};
		1041	} else {
		1042	$grp->result ($_[0]);
		1043	}
		1044	};
		1045
		1046	$grp
		1047	}
		1048
		1049	=item aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs)
		1050
		1051	Scans a directory (similar to C<aio_readdir>) but additionally tries to
		1052	efficiently separate the entries of directory C<$path> into two sets of
		1053	names, directories you can recurse into (directories), and ones you cannot
		1054	recurse into (everything else, including symlinks to directories).
		1055
		1056	C<aio_scandir> is a composite request that creates of many sub requests_
		1057	C<$maxreq> specifies the maximum number of outstanding aio requests that
		1058	this function generates. If it is C<< <= 0 >>, then a suitable default
		1059	will be chosen (currently 4).
		1060
		1061	On error, the callback is called without arguments, otherwise it receives
		1062	two array-refs with path-relative entry names.
		1063
		1064	Example:
		1065
		1066	aio_scandir $dir, 0, sub {
		1067	my ($dirs, $nondirs) = @_;
		1068	print "real directories: @$dirs\n";
		1069	print "everything else: @$nondirs\n";
		1070	};
		1071
		1072	Implementation notes.
		1073
		1074	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.
		1075
		1076	If readdir returns file type information, then this is used directly to
		1077	find directories.
		1078
		1079	Otherwise, after reading the directory, the modification time, size etc.
		1080	of the directory before and after the readdir is checked, and if they
		1081	match (and isn't the current time), the link count will be used to decide
		1082	how many entries are directories (if >= 2). Otherwise, no knowledge of the
		1083	number of subdirectories will be assumed.
		1084
		1085	Then entries will be sorted into likely directories a non-initial dot
		1086	currently) and likely non-directories (see C<aio_readdirx>). Then every
		1087	entry plus an appended C</.> will be C<stat>'ed, likely directories first,
		1088	in order of their inode numbers. If that succeeds, it assumes that the
		1089	entry is a directory or a symlink to directory (which will be checked
		1090	separately). This is often faster than stat'ing the entry itself because
		1091	filesystems might detect the type of the entry without reading the inode
		1092	data (e.g. ext2fs filetype feature), even on systems that cannot return
		1093	the filetype information on readdir.
		1094
		1095	If the known number of directories (link count - 2) has been reached, the
		1096	rest of the entries is assumed to be non-directories.
		1097
		1098	This only works with certainty on POSIX (= UNIX) filesystems, which
		1099	fortunately are the vast majority of filesystems around.
		1100
		1101	It will also likely work on non-POSIX filesystems with reduced efficiency
		1102	as those tend to return 0 or 1 as link counts, which disables the
		1103	directory counting heuristic.
		1104
		1105	=cut
		1106
		1107	sub aio_scandir($$;$) {
		1108	my ($path, $maxreq, $cb) = @_;
		1109
		1110	my $pri = aioreq_pri;
		1111
		1112	my $grp = aio_group $cb;
		1113
		1114	$maxreq = 4 if $maxreq <= 0;
		1115
		1116	# get a wd object
		1117	aioreq_pri $pri;
		1118	add $grp aio_wd $path, sub {
		1119	$_[0]
		1120	or return $grp->result ();
		1121
		1122	my $wd = [shift, "."];
		1123
		1124	# stat once
		1125	aioreq_pri $pri;
		1126	add $grp aio_stat $wd, sub {
		1127	return $grp->result () if $_[0];
		1128	my $now = time;
		1129	my $hash1 = join ":", (stat _)[0,1,3,7,9];
		1130
		1131	# read the directory entries
		1132	aioreq_pri $pri;
		1133	add $grp aio_readdirx $wd, READDIR_DIRS_FIRST, sub {
		1134	my $entries = shift
		1135	or return $grp->result ();
		1136
		1137	# stat the dir another time
		1138	aioreq_pri $pri;
		1139	add $grp aio_stat $wd, sub {
		1140	my $hash2 = join ":", (stat _)[0,1,3,7,9];
		1141
		1142	my $ndirs;
		1143
		1144	# take the slow route if anything looks fishy
		1145	if ($hash1 ne $hash2 or (stat _)[9] == $now) {
		1146	$ndirs = -1;
		1147	} else {
		1148	# if nlink == 2, we are finished
		1149	# for non-posix-fs's, we rely on nlink < 2
		1150	$ndirs = (stat _)[3] - 2
		1151	or return $grp->result ([], $entries);
		1152	}
		1153
		1154	my (@dirs, @nondirs);
		1155
		1156	my $statgrp = add $grp aio_group sub {
		1157	$grp->result (\@dirs, \@nondirs);
		1158	};
		1159
		1160	limit $statgrp $maxreq;
		1161	feed $statgrp sub {
		1162	return unless @$entries;
		1163	my $entry = shift @$entries;
		1164
		1165	aioreq_pri $pri;
		1166	$wd->[1] = "$entry/.";
		1167	add $statgrp aio_stat $wd, sub {
		1168	if ($_[0] < 0) {
		1169	push @nondirs, $entry;
		1170	} else {
		1171	# need to check for real directory
		1172	aioreq_pri $pri;
		1173	$wd->[1] = $entry;
		1174	add $statgrp aio_lstat $wd, sub {
		1175	if (-d _) {
		1176	push @dirs, $entry;
		1177
		1178	unless (--$ndirs) {
		1179	push @nondirs, @$entries;
		1180	feed $statgrp;
		1181	}
		1182	} else {
		1183	push @nondirs, $entry;
		1184	}
		1185	}
		1186	}
		1187	};
		1188	};
		1189	};
		1190	};
		1191	};
		1192	};
		1193
		1194	$grp
		1195	}
		1196
		1197	=item aio_rmtree $pathname, $callback->($status)
		1198
		1199	Delete a directory tree starting (and including) C<$path>, return the
		1200	status of the final C<rmdir> only. This is a composite request that
		1201	uses C<aio_scandir> to recurse into and rmdir directories, and unlink
		1202	everything else.
		1203
		1204	=cut
		1205
		1206	sub aio_rmtree;
		1207	sub aio_rmtree($;$) {
		1208	my ($path, $cb) = @_;
		1209
		1210	my $pri = aioreq_pri;
		1211	my $grp = aio_group $cb;
		1212
		1213	aioreq_pri $pri;
		1214	add $grp aio_scandir $path, 0, sub {
		1215	my ($dirs, $nondirs) = @_;
		1216
		1217	my $dirgrp = aio_group sub {
		1218	add $grp aio_rmdir $path, sub {
		1219	$grp->result ($_[0]);
		1220	};
		1221	};
		1222
		1223	(aioreq_pri $pri), add $dirgrp aio_rmtree "$path/$_" for @$dirs;
		1224	(aioreq_pri $pri), add $dirgrp aio_unlink "$path/$_" for @$nondirs;
		1225
		1226	add $grp $dirgrp;
		1227	};
		1228
		1229	$grp
		1230	}
		1231
		1232	=item aio_sync $callback->($status)
		1233
		1234	Asynchronously call sync and call the callback when finished.
		1235
179	=item aio_fsync $fh, $callback	1236	=item aio_fsync $fh, $callback->($status)
180		1237
181	Asynchronously call fsync on the given filehandle and call the callback	1238	Asynchronously call fsync on the given filehandle and call the callback
182	with the fsync result code.	1239	with the fsync result code.
183		1240
184	=item aio_fdatasync $fh, $callback	1241	=item aio_fdatasync $fh, $callback->($status)
185		1242
186	Asynchronously call fdatasync on the given filehandle and call the	1243	Asynchronously call fdatasync on the given filehandle and call the
187	callback with the fdatasync result code.	1244	callback with the fdatasync result code.
188		1245
		1246	If this call isn't available because your OS lacks it or it couldn't be
		1247	detected, it will be emulated by calling C<fsync> instead.
		1248
		1249	=item aio_syncfs $fh, $callback->($status)
		1250
		1251	Asynchronously call the syncfs syscall to sync the filesystem associated
		1252	to the given filehandle and call the callback with the syncfs result
		1253	code. If syncfs is not available, calls sync(), but returns C<-1> and sets
		1254	errno to C<ENOSYS> nevertheless.
		1255
		1256	=item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		1257
		1258	Sync the data portion of the file specified by C<$offset> and C<$length>
		1259	to disk (but NOT the metadata), by calling the Linux-specific
		1260	sync_file_range call. If sync_file_range is not available or it returns
		1261	ENOSYS, then fdatasync or fsync is being substituted.
		1262
		1263	C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>,
		1264	C<IO::AIO::SYNC_FILE_RANGE_WRITE> and
		1265	C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range
		1266	manpage for details.
		1267
		1268	=item aio_pathsync $pathname, $callback->($status)
		1269
		1270	This request tries to open, fsync and close the given path. This is a
		1271	composite request intended to sync directories after directory operations
		1272	(E.g. rename). This might not work on all operating systems or have any
		1273	specific effect, but usually it makes sure that directory changes get
		1274	written to disc. It works for anything that can be opened for read-only,
		1275	not just directories.
		1276
		1277	Future versions of this function might fall back to other methods when
		1278	C<fsync> on the directory fails (such as calling C<sync>).
		1279
		1280	Passes C<0> when everything went ok, and C<-1> on error.
		1281
		1282	=cut
		1283
		1284	sub aio_pathsync($;$) {
		1285	my ($path, $cb) = @_;
		1286
		1287	my $pri = aioreq_pri;
		1288	my $grp = aio_group $cb;
		1289
		1290	aioreq_pri $pri;
		1291	add $grp aio_open $path, O_RDONLY, 0, sub {
		1292	my ($fh) = @_;
		1293	if ($fh) {
		1294	aioreq_pri $pri;
		1295	add $grp aio_fsync $fh, sub {
		1296	$grp->result ($_[0]);
		1297
		1298	aioreq_pri $pri;
		1299	add $grp aio_close $fh;
		1300	};
		1301	} else {
		1302	$grp->result (-1);
		1303	}
		1304	};
		1305
		1306	$grp
		1307	}
		1308
		1309	=item aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		1310
		1311	This is a rather advanced IO::AIO call, which only works on mmap(2)ed
		1312	scalars (see the C<IO::AIO::mmap> function, although it also works on data
		1313	scalars managed by the L<Sys::Mmap> or L<Mmap> modules, note that the
		1314	scalar must only be modified in-place while an aio operation is pending on
		1315	it).
		1316
		1317	It calls the C<msync> function of your OS, if available, with the memory
		1318	area starting at C<$offset> in the string and ending C<$length> bytes
		1319	later. If C<$length> is negative, counts from the end, and if C<$length>
		1320	is C<undef>, then it goes till the end of the string. The flags can be
		1321	a combination of C<IO::AIO::MS_ASYNC>, C<IO::AIO::MS_INVALIDATE> and
		1322	C<IO::AIO::MS_SYNC>.
		1323
		1324	=item aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		1325
		1326	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1327	scalars.
		1328
		1329	It touches (reads or writes) all memory pages in the specified
		1330	range inside the scalar. All caveats and parameters are the same
		1331	as for C<aio_msync>, above, except for flags, which must be either
		1332	C<0> (which reads all pages and ensures they are instantiated) or
		1333	C<IO::AIO::MT_MODIFY>, which modifies the memory pages (by reading and
		1334	writing an octet from it, which dirties the page).
		1335
		1336	=item aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
		1337
		1338	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1339	scalars.
		1340
		1341	It reads in all the pages of the underlying storage into memory (if any)
		1342	and locks them, so they are not getting swapped/paged out or removed.
		1343
		1344	If C<$length> is undefined, then the scalar will be locked till the end.
		1345
		1346	On systems that do not implement C<mlock>, this function returns C<-1>
		1347	and sets errno to C<ENOSYS>.
		1348
		1349	Note that the corresponding C<munlock> is synchronous and is
		1350	documented under L<MISCELLANEOUS FUNCTIONS>.
		1351
		1352	Example: open a file, mmap and mlock it - both will be undone when
		1353	C<$data> gets destroyed.
		1354
		1355	open my $fh, "<", $path or die "$path: $!";
		1356	my $data;
		1357	IO::AIO::mmap $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh;
		1358	aio_mlock $data; # mlock in background
		1359
		1360	=item aio_mlockall $flags, $callback->($status)
		1361
		1362	Calls the C<mlockall> function with the given C<$flags> (a combination of
		1363	C<IO::AIO::MCL_CURRENT> and C<IO::AIO::MCL_FUTURE>).
		1364
		1365	On systems that do not implement C<mlockall>, this function returns C<-1>
		1366	and sets errno to C<ENOSYS>.
		1367
		1368	Note that the corresponding C<munlockall> is synchronous and is
		1369	documented under L<MISCELLANEOUS FUNCTIONS>.
		1370
		1371	Example: asynchronously lock all current and future pages into memory.
		1372
		1373	aio_mlockall IO::AIO::MCL_FUTURE;
		1374
		1375	=item aio_fiemap $fh, $start, $length, $flags, $count, $cb->(\@extents)
		1376
		1377	Queries the extents of the given file (by calling the Linux C<FIEMAP>
		1378	ioctl, see L<http://cvs.schmorp.de/IO-AIO/doc/fiemap.txt> for details). If
		1379	the ioctl is not available on your OS, then this request will fail with
		1380	C<ENOSYS>.
		1381
		1382	C<$start> is the starting offset to query extents for, C<$length> is the
		1383	size of the range to query - if it is C<undef>, then the whole file will
		1384	be queried.
		1385
		1386	C<$flags> is a combination of flags (C<IO::AIO::FIEMAP_FLAG_SYNC> or
		1387	C<IO::AIO::FIEMAP_FLAG_XATTR> - C<IO::AIO::FIEMAP_FLAGS_COMPAT> is also
		1388	exported), and is normally C<0> or C<IO::AIO::FIEMAP_FLAG_SYNC> to query
		1389	the data portion.
		1390
		1391	C<$count> is the maximum number of extent records to return. If it is
		1392	C<undef>, then IO::AIO queries all extents of the range. As a very special
		1393	case, if it is C<0>, then the callback receives the number of extents
		1394	instead of the extents themselves (which is unreliable, see below).
		1395
		1396	If an error occurs, the callback receives no arguments. The special
		1397	C<errno> value C<IO::AIO::EBADR> is available to test for flag errors.
		1398
		1399	Otherwise, the callback receives an array reference with extent
		1400	structures. Each extent structure is an array reference itself, with the
		1401	following members:
		1402
		1403	[$logical, $physical, $length, $flags]
		1404
		1405	Flags is any combination of the following flag values (typically either C<0>
		1406	or C<IO::AIO::FIEMAP_EXTENT_LAST> (1)):
		1407
		1408	C<IO::AIO::FIEMAP_EXTENT_LAST>, C<IO::AIO::FIEMAP_EXTENT_UNKNOWN>,
		1409	C<IO::AIO::FIEMAP_EXTENT_DELALLOC>, C<IO::AIO::FIEMAP_EXTENT_ENCODED>,
		1410	C<IO::AIO::FIEMAP_EXTENT_DATA_ENCRYPTED>, C<IO::AIO::FIEMAP_EXTENT_NOT_ALIGNED>,
		1411	C<IO::AIO::FIEMAP_EXTENT_DATA_INLINE>, C<IO::AIO::FIEMAP_EXTENT_DATA_TAIL>,
		1412	C<IO::AIO::FIEMAP_EXTENT_UNWRITTEN>, C<IO::AIO::FIEMAP_EXTENT_MERGED> or
		1413	C<IO::AIO::FIEMAP_EXTENT_SHARED>.
		1414
		1415	At the time of this writing (Linux 3.2), this requets is unreliable unless
		1416	C<$count> is C<undef>, as the kernel has all sorts of bugs preventing
		1417	it to return all extents of a range for files with large number of
		1418	extents. The code works around all these issues if C<$count> is undef.
		1419
		1420	=item aio_group $callback->(...)
		1421
		1422	This is a very special aio request: Instead of doing something, it is a
		1423	container for other aio requests, which is useful if you want to bundle
		1424	many requests into a single, composite, request with a definite callback
		1425	and the ability to cancel the whole request with its subrequests.
		1426
		1427	Returns an object of class L<IO::AIO::GRP>. See its documentation below
		1428	for more info.
		1429
		1430	Example:
		1431
		1432	my $grp = aio_group sub {
		1433	print "all stats done\n";
		1434	};
		1435
		1436	add $grp
		1437	(aio_stat ...),
		1438	(aio_stat ...),
		1439	...;
		1440
		1441	=item aio_nop $callback->()
		1442
		1443	This is a special request - it does nothing in itself and is only used for
		1444	side effects, such as when you want to add a dummy request to a group so
		1445	that finishing the requests in the group depends on executing the given
		1446	code.
		1447
		1448	While this request does nothing, it still goes through the execution
		1449	phase and still requires a worker thread. Thus, the callback will not
		1450	be executed immediately but only after other requests in the queue have
		1451	entered their execution phase. This can be used to measure request
		1452	latency.
		1453
		1454	=item IO::AIO::aio_busy $fractional_seconds, $callback->() *NOT EXPORTED*
		1455
		1456	Mainly used for debugging and benchmarking, this aio request puts one of
		1457	the request workers to sleep for the given time.
		1458
		1459	While it is theoretically handy to have simple I/O scheduling requests
		1460	like sleep and file handle readable/writable, the overhead this creates is
		1461	immense (it blocks a thread for a long time) so do not use this function
		1462	except to put your application under artificial I/O pressure.
		1463
189	=back	1464	=back
190		1465
		1466
		1467	=head2 IO::AIO::WD - multiple working directories
		1468
		1469	Your process only has one current working directory, which is used by all
		1470	threads. This makes it hard to use relative paths (some other component
		1471	could call C<chdir> at any time, and it is hard to control when the path
		1472	will be used by IO::AIO).
		1473
		1474	One solution for this is to always use absolute paths. This usually works,
		1475	but can be quite slow (the kernel has to walk the whole path on every
		1476	access), and can also be a hassle to implement.
		1477
		1478	Newer POSIX systems have a number of functions (openat, fdopendir,
		1479	futimensat and so on) that make it possible to specify working directories
		1480	per operation.
		1481
		1482	For portability, and because the clowns who "designed", or shall I write,
		1483	perpetrated this new interface were obviously half-drunk, this abstraction
		1484	cannot be perfect, though.
		1485
		1486	IO::AIO allows you to convert directory paths into a so-called IO::AIO::WD
		1487	object. This object stores the canonicalised, absolute version of the
		1488	path, and on systems that allow it, also a directory file descriptor.
		1489
		1490	Everywhere where a pathname is accepted by IO::AIO (e.g. in C<aio_stat>
		1491	or C<aio_unlink>), one can specify an array reference with an IO::AIO::WD
		1492	object and a pathname instead (or the IO::AIO::WD object alone, which
		1493	gets interpreted as C<[$wd, "."]>). If the pathname is absolute, the
		1494	IO::AIO::WD object is ignored, otherwise the pathname is resolved relative
		1495	to that IO::AIO::WD object.
		1496
		1497	For example, to get a wd object for F</etc> and then stat F<passwd>
		1498	inside, you would write:
		1499
		1500	aio_wd "/etc", sub {
		1501	my $etcdir = shift;
		1502
		1503	# although $etcdir can be undef on error, there is generally no reason
		1504	# to check for errors here, as aio_stat will fail with ENOENT
		1505	# when $etcdir is undef.
		1506
		1507	aio_stat [$etcdir, "passwd"], sub {
		1508	# yay
		1509	};
		1510	};
		1511
		1512	The fact that C<aio_wd> is a request and not a normal function shows that
		1513	creating an IO::AIO::WD object is itself a potentially blocking operation,
		1514	which is why it is done asynchronously.
		1515
		1516	To stat the directory obtained with C<aio_wd> above, one could write
		1517	either of the following three request calls:
		1518
		1519	aio_lstat "/etc" , sub { ... # pathname as normal string
		1520	aio_lstat [$wd, "."], sub { ... # "." relative to $wd (i.e. $wd itself)
		1521	aio_lstat $wd , sub { ... # shorthand for the previous
		1522
		1523	As with normal pathnames, IO::AIO keeps a copy of the working directory
		1524	object and the pathname string, so you could write the following without
		1525	causing any issues due to C<$path> getting reused:
		1526
		1527	my $path = [$wd, undef];
		1528
		1529	for my $name (qw(abc def ghi)) {
		1530	$path->[1] = $name;
		1531	aio_stat $path, sub {
		1532	# ...
		1533	};
		1534	}
		1535
		1536	There are some caveats: when directories get renamed (or deleted), the
		1537	pathname string doesn't change, so will point to the new directory (or
		1538	nowhere at all), while the directory fd, if available on the system,
		1539	will still point to the original directory. Most functions accepting a
		1540	pathname will use the directory fd on newer systems, and the string on
		1541	older systems. Some functions (such as realpath) will always rely on the
		1542	string form of the pathname.
		1543
		1544	So this functionality is mainly useful to get some protection against
		1545	C<chdir>, to easily get an absolute path out of a relative path for future
		1546	reference, and to speed up doing many operations in the same directory
		1547	(e.g. when stat'ing all files in a directory).
		1548
		1549	The following functions implement this working directory abstraction:
		1550
		1551	=over 4
		1552
		1553	=item aio_wd $pathname, $callback->($wd)
		1554
		1555	Asynchonously canonicalise the given pathname and convert it to an
		1556	IO::AIO::WD object representing it. If possible and supported on the
		1557	system, also open a directory fd to speed up pathname resolution relative
		1558	to this working directory.
		1559
		1560	If something goes wrong, then C<undef> is passwd to the callback instead
		1561	of a working directory object and C<$!> is set appropriately. Since
		1562	passing C<undef> as working directory component of a pathname fails the
		1563	request with C<ENOENT>, there is often no need for error checking in the
		1564	C<aio_wd> callback, as future requests using the value will fail in the
		1565	expected way.
		1566
		1567	=item IO::AIO::CWD
		1568
		1569	This is a compiletime constant (object) that represents the process
		1570	current working directory.
		1571
		1572	Specifying this object as working directory object for a pathname is as if
		1573	the pathname would be specified directly, without a directory object. For
		1574	example, these calls are functionally identical:
		1575
		1576	aio_stat "somefile", sub { ... };
		1577	aio_stat [IO::AIO::CWD, "somefile"], sub { ... };
		1578
		1579	=back
		1580
		1581	To recover the path associated with an IO::AIO::WD object, you can use
		1582	C<aio_realpath>:
		1583
		1584	aio_realpath $wd, sub {
		1585	warn "path is $_[0]\n";
		1586	};
		1587
		1588	Currently, C<aio_statvfs> always, and C<aio_rename> and C<aio_rmdir>
		1589	sometimes, fall back to using an absolue path.
		1590
		1591	=head2 IO::AIO::REQ CLASS
		1592
		1593	All non-aggregate C<aio_*> functions return an object of this class when
		1594	called in non-void context.
		1595
		1596	=over 4
		1597
		1598	=item cancel $req
		1599
		1600	Cancels the request, if possible. Has the effect of skipping execution
		1601	when entering the B<execute> state and skipping calling the callback when
		1602	entering the the B<result> state, but will leave the request otherwise
		1603	untouched (with the exception of readdir). That means that requests that
		1604	currently execute will not be stopped and resources held by the request
		1605	will not be freed prematurely.
		1606
		1607	=item cb $req $callback->(...)
		1608
		1609	Replace (or simply set) the callback registered to the request.
		1610
		1611	=back
		1612
		1613	=head2 IO::AIO::GRP CLASS
		1614
		1615	This class is a subclass of L<IO::AIO::REQ>, so all its methods apply to
		1616	objects of this class, too.
		1617
		1618	A IO::AIO::GRP object is a special request that can contain multiple other
		1619	aio requests.
		1620
		1621	You create one by calling the C<aio_group> constructing function with a
		1622	callback that will be called when all contained requests have entered the
		1623	C<done> state:
		1624
		1625	my $grp = aio_group sub {
		1626	print "all requests are done\n";
		1627	};
		1628
		1629	You add requests by calling the C<add> method with one or more
		1630	C<IO::AIO::REQ> objects:
		1631
		1632	$grp->add (aio_unlink "...");
		1633
		1634	add $grp aio_stat "...", sub {
		1635	$_[0] or return $grp->result ("error");
		1636
		1637	# add another request dynamically, if first succeeded
		1638	add $grp aio_open "...", sub {
		1639	$grp->result ("ok");
		1640	};
		1641	};
		1642
		1643	This makes it very easy to create composite requests (see the source of
		1644	C<aio_move> for an application) that work and feel like simple requests.
		1645
		1646	=over 4
		1647
		1648	=item * The IO::AIO::GRP objects will be cleaned up during calls to
		1649	C<IO::AIO::poll_cb>, just like any other request.
		1650
		1651	=item * They can be canceled like any other request. Canceling will cancel not
		1652	only the request itself, but also all requests it contains.
		1653
		1654	=item * They can also can also be added to other IO::AIO::GRP objects.
		1655
		1656	=item * You must not add requests to a group from within the group callback (or
		1657	any later time).
		1658
		1659	=back
		1660
		1661	Their lifetime, simplified, looks like this: when they are empty, they
		1662	will finish very quickly. If they contain only requests that are in the
		1663	C<done> state, they will also finish. Otherwise they will continue to
		1664	exist.
		1665
		1666	That means after creating a group you have some time to add requests
		1667	(precisely before the callback has been invoked, which is only done within
		1668	the C<poll_cb>). And in the callbacks of those requests, you can add
		1669	further requests to the group. And only when all those requests have
		1670	finished will the the group itself finish.
		1671
		1672	=over 4
		1673
		1674	=item add $grp ...
		1675
		1676	=item $grp->add (...)
		1677
		1678	Add one or more requests to the group. Any type of L<IO::AIO::REQ> can
		1679	be added, including other groups, as long as you do not create circular
		1680	dependencies.
		1681
		1682	Returns all its arguments.
		1683
		1684	=item $grp->cancel_subs
		1685
		1686	Cancel all subrequests and clears any feeder, but not the group request
		1687	itself. Useful when you queued a lot of events but got a result early.
		1688
		1689	The group request will finish normally (you cannot add requests to the
		1690	group).
		1691
		1692	=item $grp->result (...)
		1693
		1694	Set the result value(s) that will be passed to the group callback when all
		1695	subrequests have finished and set the groups errno to the current value
		1696	of errno (just like calling C<errno> without an error number). By default,
		1697	no argument will be passed and errno is zero.
		1698
		1699	=item $grp->errno ([$errno])
		1700
		1701	Sets the group errno value to C<$errno>, or the current value of errno
		1702	when the argument is missing.
		1703
		1704	Every aio request has an associated errno value that is restored when
		1705	the callback is invoked. This method lets you change this value from its
		1706	default (0).
		1707
		1708	Calling C<result> will also set errno, so make sure you either set C<$!>
		1709	before the call to C<result>, or call c<errno> after it.
		1710
		1711	=item feed $grp $callback->($grp)
		1712
		1713	Sets a feeder/generator on this group: every group can have an attached
		1714	generator that generates requests if idle. The idea behind this is that,
		1715	although you could just queue as many requests as you want in a group,
		1716	this might starve other requests for a potentially long time. For example,
		1717	C<aio_scandir> might generate hundreds of thousands of C<aio_stat>
		1718	requests, delaying any later requests for a long time.
		1719
		1720	To avoid this, and allow incremental generation of requests, you can
		1721	instead a group and set a feeder on it that generates those requests. The
		1722	feed callback will be called whenever there are few enough (see C<limit>,
		1723	below) requests active in the group itself and is expected to queue more
		1724	requests.
		1725
		1726	The feed callback can queue as many requests as it likes (i.e. C<add> does
		1727	not impose any limits).
		1728
		1729	If the feed does not queue more requests when called, it will be
		1730	automatically removed from the group.
		1731
		1732	If the feed limit is C<0> when this method is called, it will be set to
		1733	C<2> automatically.
		1734
		1735	Example:
		1736
		1737	# stat all files in @files, but only ever use four aio requests concurrently:
		1738
		1739	my $grp = aio_group sub { print "finished\n" };
		1740	limit $grp 4;
		1741	feed $grp sub {
		1742	my $file = pop @files
		1743	or return;
		1744
		1745	add $grp aio_stat $file, sub { ... };
		1746	};
		1747
		1748	=item limit $grp $num
		1749
		1750	Sets the feeder limit for the group: The feeder will be called whenever
		1751	the group contains less than this many requests.
		1752
		1753	Setting the limit to C<0> will pause the feeding process.
		1754
		1755	The default value for the limit is C<0>, but note that setting a feeder
		1756	automatically bumps it up to C<2>.
		1757
		1758	=back
		1759
191	=head2 SUPPORT FUNCTIONS	1760	=head2 SUPPORT FUNCTIONS
192		1761
		1762	=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION
		1763
193	=over 4	1764	=over 4
194		1765
195	=item $fileno = IO::AIO::poll_fileno	1766	=item $fileno = IO::AIO::poll_fileno
196		1767
197	Return the I<request result pipe filehandle>. This filehandle must be	1768	Return the I<request result pipe file descriptor>. This filehandle must be
198	polled for reading by some mechanism outside this module (e.g. Event	1769	polled for reading by some mechanism outside this module (e.g. EV, Glib,
199	or select, see below). If the pipe becomes readable you have to call	1770	select and so on, see below or the SYNOPSIS). If the pipe becomes readable
200	C<poll_cb> to check the results.	1771	you have to call C<poll_cb> to check the results.
201		1772
202	See C<poll_cb> for an example.	1773	See C<poll_cb> for an example.
203		1774
204	=item IO::AIO::poll_cb	1775	=item IO::AIO::poll_cb
205		1776
206	Process all outstanding events on the result pipe. You have to call this	1777	Process some requests that have reached the result phase (i.e. they have
207	regularly. Returns the number of events processed. Returns immediately	1778	been executed but the results are not yet reported). You have to call
208	when no events are outstanding.	1779	this "regularly" to finish outstanding requests.
209		1780
210	You can use Event to multiplex, e.g.:	1781	Returns C<0> if all events could be processed (or there were no
		1782	events to process), or C<-1> if it returned earlier for whatever
		1783	reason. Returns immediately when no events are outstanding. The amount
		1784	of events processed depends on the settings of C<IO::AIO::max_poll_req>,
		1785	C<IO::AIO::max_poll_time> and C<IO::AIO::max_outstanding>.
		1786
		1787	If not all requests were processed for whatever reason, the poll file
		1788	descriptor will still be ready when C<poll_cb> returns, so normally you
		1789	don't have to do anything special to have it called later.
		1790
		1791	Apart from calling C<IO::AIO::poll_cb> when the event filehandle becomes
		1792	ready, it can be beneficial to call this function from loops which submit
		1793	a lot of requests, to make sure the results get processed when they become
		1794	available and not just when the loop is finished and the event loop takes
		1795	over again. This function returns very fast when there are no outstanding
		1796	requests.
		1797
		1798	Example: Install an Event watcher that automatically calls
		1799	IO::AIO::poll_cb with high priority (more examples can be found in the
		1800	SYNOPSIS section, at the top of this document):
211		1801
212	Event->io (fd => IO::AIO::poll_fileno,	1802	Event->io (fd => IO::AIO::poll_fileno,
213	poll => 'r', async => 1,	1803	poll => 'r', async => 1,
214	cb => \&IO::AIO::poll_cb);	1804	cb => \&IO::AIO::poll_cb);
215		1805
216	=item IO::AIO::poll_wait	1806	=item IO::AIO::poll_wait
217		1807
218	Wait till the result filehandle becomes ready for reading (simply does a	1808	Wait until either at least one request is in the result phase or no
219	select on the filehandle. This is useful if you want to synchronously wait	1809	requests are outstanding anymore.
220	for some requests to finish).	1810
		1811	This is useful if you want to synchronously wait for some requests to
		1812	become ready, without actually handling them.
221		1813
222	See C<nreqs> for an example.	1814	See C<nreqs> for an example.
223		1815
		1816	=item IO::AIO::poll
		1817
		1818	Waits until some requests have been handled.
		1819
		1820	Returns the number of requests processed, but is otherwise strictly
		1821	equivalent to:
		1822
		1823	IO::AIO::poll_wait, IO::AIO::poll_cb
		1824
224	=item IO::AIO::nreqs	1825	=item IO::AIO::flush
225		1826
226	Returns the number of requests currently outstanding.	1827	Wait till all outstanding AIO requests have been handled.
227		1828
228	Example: wait till there are no outstanding requests anymore:	1829	Strictly equivalent to:
229		1830
230	IO::AIO::poll_wait, IO::AIO::poll_cb	1831	IO::AIO::poll_wait, IO::AIO::poll_cb
231	while IO::AIO::nreqs;	1832	while IO::AIO::nreqs;
232		1833
		1834	=item IO::AIO::max_poll_reqs $nreqs
		1835
		1836	=item IO::AIO::max_poll_time $seconds
		1837
		1838	These set the maximum number of requests (default C<0>, meaning infinity)
		1839	that are being processed by C<IO::AIO::poll_cb> in one call, respectively
		1840	the maximum amount of time (default C<0>, meaning infinity) spent in
		1841	C<IO::AIO::poll_cb> to process requests (more correctly the mininum amount
		1842	of time C<poll_cb> is allowed to use).
		1843
		1844	Setting C<max_poll_time> to a non-zero value creates an overhead of one
		1845	syscall per request processed, which is not normally a problem unless your
		1846	callbacks are really really fast or your OS is really really slow (I am
		1847	not mentioning Solaris here). Using C<max_poll_reqs> incurs no overhead.
		1848
		1849	Setting these is useful if you want to ensure some level of
		1850	interactiveness when perl is not fast enough to process all requests in
		1851	time.
		1852
		1853	For interactive programs, values such as C<0.01> to C<0.1> should be fine.
		1854
		1855	Example: Install an Event watcher that automatically calls
		1856	IO::AIO::poll_cb with low priority, to ensure that other parts of the
		1857	program get the CPU sometimes even under high AIO load.
		1858
		1859	# try not to spend much more than 0.1s in poll_cb
		1860	IO::AIO::max_poll_time 0.1;
		1861
		1862	# use a low priority so other tasks have priority
		1863	Event->io (fd => IO::AIO::poll_fileno,
		1864	poll => 'r', nice => 1,
		1865	cb => &IO::AIO::poll_cb);
		1866
		1867	=back
		1868
		1869	=head3 CONTROLLING THE NUMBER OF THREADS
		1870
		1871	=over
		1872
233	=item IO::AIO::min_parallel $nthreads	1873	=item IO::AIO::min_parallel $nthreads
234		1874
235	Set the minimum number of AIO threads to C<$nthreads>. The default is	1875	Set the minimum number of AIO threads to C<$nthreads>. The current
236	C<1>, which means a single asynchronous operation can be done at one time	1876	default is C<8>, which means eight asynchronous operations can execute
237	(the number of outstanding operations, however, is unlimited).	1877	concurrently at any one time (the number of outstanding requests,
		1878	however, is unlimited).
238		1879
		1880	IO::AIO starts threads only on demand, when an AIO request is queued and
		1881	no free thread exists. Please note that queueing up a hundred requests can
		1882	create demand for a hundred threads, even if it turns out that everything
		1883	is in the cache and could have been processed faster by a single thread.
		1884
239	It is recommended to keep the number of threads low, as some Linux	1885	It is recommended to keep the number of threads relatively low, as some
240	kernel versions will scale negatively with the number of threads (higher	1886	Linux kernel versions will scale negatively with the number of threads
241	parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32	1887	(higher parallelity => MUCH higher latency). With current Linux 2.6
242	threads should be fine.	1888	versions, 4-32 threads should be fine.
243		1889
244	Under normal circumstances you don't need to call this function, as this	1890	Under most circumstances you don't need to call this function, as the
245	module automatically starts some threads (the exact number might change,	1891	module selects a default that is suitable for low to moderate load.
246	and is currently 4).
247		1892
248	=item IO::AIO::max_parallel $nthreads	1893	=item IO::AIO::max_parallel $nthreads
249		1894
250	Sets the maximum number of AIO threads to C<$nthreads>. If more than	1895	Sets the maximum number of AIO threads to C<$nthreads>. If more than the
251	the specified number of threads are currently running, kill them. This	1896	specified number of threads are currently running, this function kills
252	function blocks until the limit is reached.	1897	them. This function blocks until the limit is reached.
		1898
		1899	While C<$nthreads> are zero, aio requests get queued but not executed
		1900	until the number of threads has been increased again.
253		1901
254	This module automatically runs C<max_parallel 0> at program end, to ensure	1902	This module automatically runs C<max_parallel 0> at program end, to ensure
255	that all threads are killed and that there are no outstanding requests.	1903	that all threads are killed and that there are no outstanding requests.
256		1904
257	Under normal circumstances you don't need to call this function.	1905	Under normal circumstances you don't need to call this function.
258		1906
		1907	=item IO::AIO::max_idle $nthreads
		1908
		1909	Limit the number of threads (default: 4) that are allowed to idle
		1910	(i.e., threads that did not get a request to process within the idle
		1911	timeout (default: 10 seconds). That means if a thread becomes idle while
		1912	C<$nthreads> other threads are also idle, it will free its resources and
		1913	exit.
		1914
		1915	This is useful when you allow a large number of threads (e.g. 100 or 1000)
		1916	to allow for extremely high load situations, but want to free resources
		1917	under normal circumstances (1000 threads can easily consume 30MB of RAM).
		1918
		1919	The default is probably ok in most situations, especially if thread
		1920	creation is fast. If thread creation is very slow on your system you might
		1921	want to use larger values.
		1922
		1923	=item IO::AIO::idle_timeout $seconds
		1924
		1925	Sets the minimum idle timeout (default 10) after which worker threads are
		1926	allowed to exit. SEe C<IO::AIO::max_idle>.
		1927
259	=item $oldnreqs = IO::AIO::max_outstanding $nreqs	1928	=item IO::AIO::max_outstanding $maxreqs
260		1929
261	Sets the maximum number of outstanding requests to C<$nreqs>. If you	1930	Sets the maximum number of outstanding requests to C<$nreqs>. If
262	try to queue up more than this number of requests, the caller will block until	1931	you do queue up more than this number of requests, the next call to
263	some requests have been handled.	1932	C<IO::AIO::poll_cb> (and other functions calling C<poll_cb>, such as
		1933	C<IO::AIO::flush> or C<IO::AIO::poll>) will block until the limit is no
		1934	longer exceeded.
264		1935
265	The default is very large, so normally there is no practical limit. If you	1936	In other words, this setting does not enforce a queue limit, but can be
266	queue up many requests in a loop it it often improves speed if you set	1937	used to make poll functions block if the limit is exceeded.
267	this to a relatively low number, such as C<100>.
268		1938
269	Under normal circumstances you don't need to call this function.	1939	This is a very bad function to use in interactive programs because it
		1940	blocks, and a bad way to reduce concurrency because it is inexact: Better
		1941	use an C<aio_group> together with a feed callback.
		1942
		1943	Its main use is in scripts without an event loop - when you want to stat
		1944	a lot of files, you can write somehting like this:
		1945
		1946	IO::AIO::max_outstanding 32;
		1947
		1948	for my $path (...) {
		1949	aio_stat $path , ...;
		1950	IO::AIO::poll_cb;
		1951	}
		1952
		1953	IO::AIO::flush;
		1954
		1955	The call to C<poll_cb> inside the loop will normally return instantly, but
		1956	as soon as more thna C<32> reqeusts are in-flight, it will block until
		1957	some requests have been handled. This keeps the loop from pushing a large
		1958	number of C<aio_stat> requests onto the queue.
		1959
		1960	The default value for C<max_outstanding> is very large, so there is no
		1961	practical limit on the number of outstanding requests.
270		1962
271	=back	1963	=back
272		1964
		1965	=head3 STATISTICAL INFORMATION
		1966
		1967	=over
		1968
		1969	=item IO::AIO::nreqs
		1970
		1971	Returns the number of requests currently in the ready, execute or pending
		1972	states (i.e. for which their callback has not been invoked yet).
		1973
		1974	Example: wait till there are no outstanding requests anymore:
		1975
		1976	IO::AIO::poll_wait, IO::AIO::poll_cb
		1977	while IO::AIO::nreqs;
		1978
		1979	=item IO::AIO::nready
		1980
		1981	Returns the number of requests currently in the ready state (not yet
		1982	executed).
		1983
		1984	=item IO::AIO::npending
		1985
		1986	Returns the number of requests currently in the pending state (executed,
		1987	but not yet processed by poll_cb).
		1988
		1989	=back
		1990
		1991	=head3 MISCELLANEOUS FUNCTIONS
		1992
		1993	IO::AIO implements some functions that are useful when you want to use
		1994	some "Advanced I/O" function not available to in Perl, without going the
		1995	"Asynchronous I/O" route. Many of these have an asynchronous C<aio_*>
		1996	counterpart.
		1997
		1998	=over 4
		1999
		2000	=item IO::AIO::sendfile $ofh, $ifh, $offset, $count
		2001
		2002	Calls the C<eio_sendfile_sync> function, which is like C<aio_sendfile>,
		2003	but is blocking (this makes most sense if you know the input data is
		2004	likely cached already and the output filehandle is set to non-blocking
		2005	operations).
		2006
		2007	Returns the number of bytes copied, or C<-1> on error.
		2008
		2009	=item IO::AIO::fadvise $fh, $offset, $len, $advice
		2010
		2011	Simply calls the C<posix_fadvise> function (see its
		2012	manpage for details). The following advice constants are
		2013	available: C<IO::AIO::FADV_NORMAL>, C<IO::AIO::FADV_SEQUENTIAL>,
		2014	C<IO::AIO::FADV_RANDOM>, C<IO::AIO::FADV_NOREUSE>,
		2015	C<IO::AIO::FADV_WILLNEED>, C<IO::AIO::FADV_DONTNEED>.
		2016
		2017	On systems that do not implement C<posix_fadvise>, this function returns
		2018	ENOSYS, otherwise the return value of C<posix_fadvise>.
		2019
		2020	=item IO::AIO::madvise $scalar, $offset, $len, $advice
		2021
		2022	Simply calls the C<posix_madvise> function (see its
		2023	manpage for details). The following advice constants are
		2024	available: C<IO::AIO::MADV_NORMAL>, C<IO::AIO::MADV_SEQUENTIAL>,
		2025	C<IO::AIO::MADV_RANDOM>, C<IO::AIO::MADV_WILLNEED>, C<IO::AIO::MADV_DONTNEED>.
		2026
		2027	On systems that do not implement C<posix_madvise>, this function returns
		2028	ENOSYS, otherwise the return value of C<posix_madvise>.
		2029
		2030	=item IO::AIO::mprotect $scalar, $offset, $len, $protect
		2031
		2032	Simply calls the C<mprotect> function on the preferably AIO::mmap'ed
		2033	$scalar (see its manpage for details). The following protect
		2034	constants are available: C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_READ>,
		2035	C<IO::AIO::PROT_WRITE>, C<IO::AIO::PROT_EXEC>.
		2036
		2037	On systems that do not implement C<mprotect>, this function returns
		2038	ENOSYS, otherwise the return value of C<mprotect>.
		2039
		2040	=item IO::AIO::mmap $scalar, $length, $prot, $flags, $fh[, $offset]
		2041
		2042	Memory-maps a file (or anonymous memory range) and attaches it to the
		2043	given C<$scalar>, which will act like a string scalar. Returns true on
		2044	success, and false otherwise.
		2045
		2046	The only operations allowed on the scalar are C<substr>/C<vec> that don't
		2047	change the string length, and most read-only operations such as copying it
		2048	or searching it with regexes and so on.
		2049
		2050	Anything else is unsafe and will, at best, result in memory leaks.
		2051
		2052	The memory map associated with the C<$scalar> is automatically removed
		2053	when the C<$scalar> is destroyed, or when the C<IO::AIO::mmap> or
		2054	C<IO::AIO::munmap> functions are called.
		2055
		2056	This calls the C<mmap>(2) function internally. See your system's manual
		2057	page for details on the C<$length>, C<$prot> and C<$flags> parameters.
		2058
		2059	The C<$length> must be larger than zero and smaller than the actual
		2060	filesize.
		2061
		2062	C<$prot> is a combination of C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_EXEC>,
		2063	C<IO::AIO::PROT_READ> and/or C<IO::AIO::PROT_WRITE>,
		2064
		2065	C<$flags> can be a combination of
		2066	C<IO::AIO::MAP_SHARED> or
		2067	C<IO::AIO::MAP_PRIVATE>,
		2068	or a number of system-specific flags (when not available, the are C<0>):
		2069	C<IO::AIO::MAP_ANONYMOUS> (which is set to C<MAP_ANON> if your system only provides this constant),
		2070	C<IO::AIO::MAP_HUGETLB>,
		2071	C<IO::AIO::MAP_LOCKED>,
		2072	C<IO::AIO::MAP_NORESERVE>,
		2073	C<IO::AIO::MAP_POPULATE>,
		2074	C<IO::AIO::MAP_NONBLOCK>,
		2075	C<IO::AIO::MAP_FIXED>,
		2076	C<IO::AIO::MAP_GROWSDOWN>,
		2077	C<IO::AIO::MAP_32BIT>,
		2078	C<IO::AIO::MAP_HUGETLB> or
		2079	C<IO::AIO::MAP_STACK>.
		2080
		2081	If C<$fh> is C<undef>, then a file descriptor of C<-1> is passed.
		2082
		2083	C<$offset> is the offset from the start of the file - it generally must be
		2084	a multiple of C<IO::AIO::PAGESIZE> and defaults to C<0>.
		2085
		2086	Example:
		2087
		2088	use Digest::MD5;
		2089	use IO::AIO;
		2090
		2091	open my $fh, "<verybigfile"
		2092	or die "$!";
		2093
		2094	IO::AIO::mmap my $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh
		2095	or die "verybigfile: $!";
		2096
		2097	my $fast_md5 = md5 $data;
		2098
		2099	=item IO::AIO::munmap $scalar
		2100
		2101	Removes a previous mmap and undefines the C<$scalar>.
		2102
		2103	=item IO::AIO::munlock $scalar, $offset = 0, $length = undef
		2104
		2105	Calls the C<munlock> function, undoing the effects of a previous
		2106	C<aio_mlock> call (see its description for details).
		2107
		2108	=item IO::AIO::munlockall
		2109
		2110	Calls the C<munlockall> function.
		2111
		2112	On systems that do not implement C<munlockall>, this function returns
		2113	ENOSYS, otherwise the return value of C<munlockall>.
		2114
		2115	=item IO::AIO::splice $r_fh, $r_off, $w_fh, $w_off, $length, $flags
		2116
		2117	Calls the GNU/Linux C<splice(2)> syscall, if available. If C<$r_off> or
		2118	C<$w_off> are C<undef>, then C<NULL> is passed for these, otherwise they
		2119	should be the file offset.
		2120
		2121	C<$r_fh> and C<$w_fh> should not refer to the same file, as splice might
		2122	silently corrupt the data in this case.
		2123
		2124	The following symbol flag values are available: C<IO::AIO::SPLICE_F_MOVE>,
		2125	C<IO::AIO::SPLICE_F_NONBLOCK>, C<IO::AIO::SPLICE_F_MORE> and
		2126	C<IO::AIO::SPLICE_F_GIFT>.
		2127
		2128	See the C<splice(2)> manpage for details.
		2129
		2130	=item IO::AIO::tee $r_fh, $w_fh, $length, $flags
		2131
		2132	Calls the GNU/Linux C<tee(2)> syscall, see its manpage and the
		2133	description for C<IO::AIO::splice> above for details.
		2134
		2135	=item $actual_size = IO::AIO::pipesize $r_fh[, $new_size]
		2136
		2137	Attempts to query or change the pipe buffer size. Obviously works only
		2138	on pipes, and currently works only on GNU/Linux systems, and fails with
		2139	C<-1>/C<ENOSYS> everywhere else. If anybody knows how to influence pipe buffer
		2140	size on other systems, drop me a note.
		2141
		2142	=item ($rfh, $wfh) = IO::AIO::pipe2 [$flags]
		2143
		2144	This is a direct interface to the Linux L<pipe2(2)> system call. If
		2145	C<$flags> is missing or C<0>, then this should be the same as a call to
		2146	perl's built-in C<pipe> function and create a new pipe, and works on
		2147	systems that lack the pipe2 syscall. On win32, this case invokes C<_pipe
		2148	(..., 4096, O_BINARY)>.
		2149
		2150	If C<$flags> is non-zero, it tries to invoke the pipe2 system call with
		2151	the given flags (Linux 2.6.27, glibc 2.9).
		2152
		2153	On success, the read and write file handles are returned.
		2154
		2155	On error, nothing will be returned. If the pipe2 syscall is missing and
		2156	C<$flags> is non-zero, fails with C<ENOSYS>.
		2157
		2158	Please refer to L<pipe2(2)> for more info on the C<$flags>, but at the
		2159	time of this writing, C<IO::AIO::O_CLOEXEC>, C<IO::AIO::O_NONBLOCK> and
		2160	C<IO::AIO::O_DIRECT> (Linux 3.4, for packet-based pipes) were supported.
		2161
		2162	=back
		2163
273	=cut	2164	=cut
274		2165
275	# support function to convert a fd into a perl filehandle
276	sub _fd2fh {
277	return undef if $_[0] < 0;
278
279	# try to be perl5.6-compatible
280	local *AIO_FH;
281	open AIO_FH, "+<&=$_[0]"
282	or return undef;
283
284	*AIO_FH
285	}
286
287	min_parallel 4;	2166	min_parallel 8;
288		2167
289	END {	2168	END { flush }
290	max_parallel 0;
291	}
292		2169
293	1;	2170	1;
294		2171
		2172	=head1 EVENT LOOP INTEGRATION
		2173
		2174	It is recommended to use L<AnyEvent::AIO> to integrate IO::AIO
		2175	automatically into many event loops:
		2176
		2177	# AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...)
		2178	use AnyEvent::AIO;
		2179
		2180	You can also integrate IO::AIO manually into many event loops, here are
		2181	some examples of how to do this:
		2182
		2183	# EV integration
		2184	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
		2185
		2186	# Event integration
		2187	Event->io (fd => IO::AIO::poll_fileno,
		2188	poll => 'r',
		2189	cb => \&IO::AIO::poll_cb);
		2190
		2191	# Glib/Gtk2 integration
		2192	add_watch Glib::IO IO::AIO::poll_fileno,
		2193	in => sub { IO::AIO::poll_cb; 1 };
		2194
		2195	# Tk integration
		2196	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
		2197	readable => \&IO::AIO::poll_cb);
		2198
		2199	# Danga::Socket integration
		2200	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
		2201	\&IO::AIO::poll_cb);
		2202
		2203	=head2 FORK BEHAVIOUR
		2204
		2205	Usage of pthreads in a program changes the semantics of fork
		2206	considerably. Specifically, only async-safe functions can be called after
		2207	fork. Perl doesn't know about this, so in general, you cannot call fork
		2208	with defined behaviour in perl if pthreads are involved. IO::AIO uses
		2209	pthreads, so this applies, but many other extensions and (for inexplicable
		2210	reasons) perl itself often is linked against pthreads, so this limitation
		2211	applies to quite a lot of perls.
		2212
		2213	This module no longer tries to fight your OS, or POSIX. That means IO::AIO
		2214	only works in the process that loaded it. Forking is fully supported, but
		2215	using IO::AIO in the child is not.
		2216
		2217	You might get around by not I<using> IO::AIO before (or after)
		2218	forking. You could also try to call the L<IO::AIO::reinit> function in the
		2219	child:
		2220
		2221	=over 4
		2222
		2223	=item IO::AIO::reinit
		2224
		2225	Abandons all current requests and I/O threads and simply reinitialises all
		2226	data structures. This is not an operation supported by any standards, but
		2227	happens to work on GNU/Linux and some newer BSD systems.
		2228
		2229	The only reasonable use for this function is to call it after forking, if
		2230	C<IO::AIO> was used in the parent. Calling it while IO::AIO is active in
		2231	the process will result in undefined behaviour. Calling it at any time
		2232	will also result in any undefined (by POSIX) behaviour.
		2233
		2234	=back
		2235
		2236	=head2 MEMORY USAGE
		2237
		2238	Per-request usage:
		2239
		2240	Each aio request uses - depending on your architecture - around 100-200
		2241	bytes of memory. In addition, stat requests need a stat buffer (possibly
		2242	a few hundred bytes), readdir requires a result buffer and so on. Perl
		2243	scalars and other data passed into aio requests will also be locked and
		2244	will consume memory till the request has entered the done state.
		2245
		2246	This is not awfully much, so queuing lots of requests is not usually a
		2247	problem.
		2248
		2249	Per-thread usage:
		2250
		2251	In the execution phase, some aio requests require more memory for
		2252	temporary buffers, and each thread requires a stack and other data
		2253	structures (usually around 16k-128k, depending on the OS).
		2254
		2255	=head1 KNOWN BUGS
		2256
		2257	Known bugs will be fixed in the next release.
		2258
295	=head1 SEE ALSO	2259	=head1 SEE ALSO
296		2260
297	L<Coro>, L<Linux::AIO>.	2261	L<AnyEvent::AIO> for easy integration into event loops, L<Coro::AIO> for a
		2262	more natural syntax.
298		2263
299	=head1 AUTHOR	2264	=head1 AUTHOR
300		2265
301	Marc Lehmann <schmorp@schmorp.de>	2266	Marc Lehmann <schmorp@schmorp.de>
302	http://home.schmorp.de/	2267	http://home.schmorp.de/

Diff Legend

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