ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/IO-AIO/AIO.pm

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.14 by root, Mon Jul 11 02:53:59 2005 UTC vs.
Revision 1.201 by root, Tue Jul 5 09:24:11 2011 UTC

…		…
4		4
5	=head1 SYNOPSIS	5	=head1 SYNOPSIS
6		6
7	use IO::AIO;	7	use IO::AIO;
8		8
9	aio_open "/etc/passwd", O_RDONLY, 0, sub {	9	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
10	my ($fh) = @_;	10	my $fh = shift
		11	or die "/etc/passwd: $!";
11	...	12	...
12	};	13	};
13		14
14	aio_unlink "/tmp/file", sub { };	15	aio_unlink "/tmp/file", sub { };
15		16
16	aio_read $fh, 30000, 1024, $buffer, 0, sub {	17	aio_read $fh, 30000, 1024, $buffer, 0, sub {
17	$_[0] > 0 or die "read error: $!";	18	$_[0] > 0 or die "read error: $!";
18	};	19	};
19		20
20	# Event	21	# version 2+ has request and group objects
21	Event->io (fd => IO::AIO::poll_fileno,	22	use IO::AIO 2;
22	poll => 'r',
23	cb => \&IO::AIO::poll_cb);
24		23
25	# Glib/Gtk2	24	aioreq_pri 4; # give next request a very high priority
26	add_watch Glib::IO IO::AIO::poll_fileno,	25	my $req = aio_unlink "/tmp/file", sub { };
27	\&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
33	# Danga::Socket
34	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
35	\&IO::AIO::poll_cb);
36
37		30
38	=head1 DESCRIPTION	31	=head1 DESCRIPTION
39		32
40	This module implements asynchronous I/O using whatever means your	33	This module implements asynchronous I/O using whatever means your
41	operating system supports.	34	operating system supports. It is implemented as an interface to C<libeio>
		35	(L<http://software.schmorp.de/pkg/libeio.html>).
42		36
		37	Asynchronous means that operations that can normally block your program
		38	(e.g. reading from disk) will be done asynchronously: the operation
		39	will still block, but you can do something else in the meantime. This
		40	is extremely useful for programs that need to stay interactive even
		41	when doing heavy I/O (GUI programs, high performance network servers
		42	etc.), but can also be used to easily do operations in parallel that are
		43	normally done sequentially, e.g. stat'ing many files, which is much faster
		44	on a RAID volume or over NFS when you do a number of stat operations
		45	concurrently.
		46
		47	While most of this works on all types of file descriptors (for
		48	example sockets), using these functions on file descriptors that
		49	support nonblocking operation (again, sockets, pipes etc.) is
		50	very inefficient. Use an event loop for that (such as the L<EV>
		51	module): IO::AIO will naturally fit into such an event loop itself.
		52
43	Currently, a number of threads are started that execute your read/writes	53	In this version, a number of threads are started that execute your
44	and signal their completion. You don't need thread support in your libc or	54	requests and signal their completion. You don't need thread support
45	perl, and the threads created by this module will not be visible to the	55	in perl, and the threads created by this module will not be visible
46	pthreads library. In the future, this module might make use of the native	56	to perl. In the future, this module might make use of the native aio
47	aio functions available on many operating systems. However, they are often	57	functions available on many operating systems. However, they are often
48	not well-supported (Linux doesn't allow them on normal files currently,	58	not well-supported or restricted (GNU/Linux doesn't allow them on normal
49	for example), and they would only support aio_read and aio_write, so the	59	files currently, for example), and they would only support aio_read and
50	remaining functionality would have to be implemented using threads anyway.	60	aio_write, so the remaining functionality would have to be implemented
		61	using threads anyway.
51		62
52	Although the module will work with in the presence of other threads, it is	63	Although the module will work in the presence of other (Perl-) threads,
53	currently not reentrant, so use appropriate locking yourself.	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 Fcntl;
		74	use EV;
		75	use IO::AIO;
		76
		77	# register the IO::AIO callback with EV
		78	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
		79
		80	# queue the request to open /etc/passwd
		81	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
		82	my $fh = shift
		83	or die "error while opening: $!";
		84
		85	# stat'ing filehandles is generally non-blocking
		86	my $size = -s $fh;
		87
		88	# queue a request to read the file
		89	my $contents;
		90	aio_read $fh, 0, $size, $contents, 0, sub {
		91	$_[0] == $size
		92	or die "short read: $!";
		93
		94	close $fh;
		95
		96	# file contents now in $contents
		97	print $contents;
		98
		99	# exit event loop and program
		100	EV::unloop;
		101	};
		102	};
		103
		104	# possibly queue up other requests, or open GUI windows,
		105	# check for sockets etc. etc.
		106
		107	# process events as long as there are some:
		108	EV::loop;
		109
		110	=head1 REQUEST ANATOMY AND LIFETIME
		111
		112	Every C<aio_*> function creates a request. which is a C data structure not
		113	directly visible to Perl.
		114
		115	If called in non-void context, every request function returns a Perl
		116	object representing the request. In void context, nothing is returned,
		117	which saves a bit of memory.
		118
		119	The perl object is a fairly standard ref-to-hash object. The hash contents
		120	are not used by IO::AIO so you are free to store anything you like in it.
		121
		122	During their existance, aio requests travel through the following states,
		123	in order:
		124
		125	=over 4
		126
		127	=item ready
		128
		129	Immediately after a request is created it is put into the ready state,
		130	waiting for a thread to execute it.
		131
		132	=item execute
		133
		134	A thread has accepted the request for processing and is currently
		135	executing it (e.g. blocking in read).
		136
		137	=item pending
		138
		139	The request has been executed and is waiting for result processing.
		140
		141	While request submission and execution is fully asynchronous, result
		142	processing is not and relies on the perl interpreter calling C<poll_cb>
		143	(or another function with the same effect).
		144
		145	=item result
		146
		147	The request results are processed synchronously by C<poll_cb>.
		148
		149	The C<poll_cb> function will process all outstanding aio requests by
		150	calling their callbacks, freeing memory associated with them and managing
		151	any groups they are contained in.
		152
		153	=item done
		154
		155	Request has reached the end of its lifetime and holds no resources anymore
		156	(except possibly for the Perl object, but its connection to the actual
		157	aio request is severed and calling its methods will either do nothing or
		158	result in a runtime error).
		159
		160	=back
54		161
55	=cut	162	=cut
56		163
57	package IO::AIO;	164	package IO::AIO;
58		165
		166	use Carp ();
		167
		168	use common::sense;
		169
59	use base 'Exporter';	170	use base 'Exporter';
60		171
61	use Fcntl ();
62
63	BEGIN {	172	BEGIN {
64	$VERSION = 0.3;	173	our $VERSION = '3.93';
65		174
66	@EXPORT = qw(aio_read aio_write aio_open aio_close aio_stat aio_lstat aio_unlink	175	our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close
67	aio_fsync aio_fdatasync aio_readahead);	176	aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx
68	@EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs);	177	aio_scandir aio_symlink aio_readlink aio_realpath aio_sync aio_fsync
		178	aio_fdatasync aio_sync_file_range aio_pathsync aio_readahead
		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
		185	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice));
		186	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush
		187	min_parallel max_parallel max_idle idle_timeout
		188	nreqs nready npending nthreads
		189	max_poll_time max_poll_reqs
		190	sendfile fadvise madvise
		191	mmap munmap munlock munlockall);
		192
		193	push @AIO_REQ, qw(aio_busy); # not exported
		194
		195	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';
69		196
70	require XSLoader;	197	require XSLoader;
71	XSLoader::load IO::AIO, $VERSION;	198	XSLoader::load ("IO::AIO", $VERSION);
72	}	199	}
73		200
74	=head1 FUNCTIONS	201	=head1 FUNCTIONS
75		202
		203	=head2 QUICK OVERVIEW
		204
		205	This section simply lists the prototypes of the most important functions
		206	for quick reference. See the following sections for function-by-function
		207	documentation.
		208
		209	aio_open $pathname, $flags, $mode, $callback->($fh)
		210	aio_close $fh, $callback->($status)
		211	aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
		212	aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
		213	aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
		214	aio_readahead $fh,$offset,$length, $callback->($retval)
		215	aio_stat $fh_or_path, $callback->($status)
		216	aio_lstat $fh, $callback->($status)
		217	aio_statvfs $fh_or_path, $callback->($statvfs)
		218	aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
		219	aio_chown $fh_or_path, $uid, $gid, $callback->($status)
		220	aio_truncate $fh_or_path, $offset, $callback->($status)
		221	aio_chmod $fh_or_path, $mode, $callback->($status)
		222	aio_unlink $pathname, $callback->($status)
		223	aio_mknod $path, $mode, $dev, $callback->($status)
		224	aio_link $srcpath, $dstpath, $callback->($status)
		225	aio_symlink $srcpath, $dstpath, $callback->($status)
		226	aio_readlink $path, $callback->($link)
		227	aio_realpath $path, $callback->($link)
		228	aio_rename $srcpath, $dstpath, $callback->($status)
		229	aio_mkdir $pathname, $mode, $callback->($status)
		230	aio_rmdir $pathname, $callback->($status)
		231	aio_readdir $pathname, $callback->($entries)
		232	aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		233	IO::AIO::READDIR_DENTS IO::AIO::READDIR_DIRS_FIRST
		234	IO::AIO::READDIR_STAT_ORDER IO::AIO::READDIR_FOUND_UNKNOWN
		235	aio_load $path, $data, $callback->($status)
		236	aio_copy $srcpath, $dstpath, $callback->($status)
		237	aio_move $srcpath, $dstpath, $callback->($status)
		238	aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
		239	aio_rmtree $path, $callback->($status)
		240	aio_sync $callback->($status)
		241	aio_fsync $fh, $callback->($status)
		242	aio_fdatasync $fh, $callback->($status)
		243	aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		244	aio_pathsync $path, $callback->($status)
		245	aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		246	aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		247	aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
		248	aio_mlockall $flags, $callback->($status)
		249	aio_group $callback->(...)
		250	aio_nop $callback->()
		251
		252	$prev_pri = aioreq_pri [$pri]
		253	aioreq_nice $pri_adjust
		254
		255	IO::AIO::poll_wait
		256	IO::AIO::poll_cb
		257	IO::AIO::poll
		258	IO::AIO::flush
		259	IO::AIO::max_poll_reqs $nreqs
		260	IO::AIO::max_poll_time $seconds
		261	IO::AIO::min_parallel $nthreads
		262	IO::AIO::max_parallel $nthreads
		263	IO::AIO::max_idle $nthreads
		264	IO::AIO::idle_timeout $seconds
		265	IO::AIO::max_outstanding $maxreqs
		266	IO::AIO::nreqs
		267	IO::AIO::nready
		268	IO::AIO::npending
		269
		270	IO::AIO::sendfile $ofh, $ifh, $offset, $count
		271	IO::AIO::fadvise $fh, $offset, $len, $advice
		272	IO::AIO::madvise $scalar, $offset, $length, $advice
		273	IO::AIO::mprotect $scalar, $offset, $length, $protect
		274	IO::AIO::munlock $scalar, $offset = 0, $length = undef
		275	IO::AIO::munlockall
		276
76	=head2 AIO FUNCTIONS	277	=head2 AIO REQUEST FUNCTIONS
77		278
78	All the C<aio_*> calls are more or less thin wrappers around the syscall	279	All the C<aio_*> calls are more or less thin wrappers around the syscall
79	with the same name (sans C<aio_>). The arguments are similar or identical,	280	with the same name (sans C<aio_>). The arguments are similar or identical,
80	and they all accept an additional (and optional) C<$callback> argument	281	and they all accept an additional (and optional) C<$callback> argument
81	which must be a code reference. This code reference will get called with	282	which must be a code reference. This code reference will get called with
82	the syscall return code (e.g. most syscalls return C<-1> on error, unlike	283	the syscall return code (e.g. most syscalls return C<-1> on error, unlike
83	perl, which usually delivers "false") as it's sole argument when the given	284	perl, which usually delivers "false") as its sole argument after the given
84	syscall has been executed asynchronously.	285	syscall has been executed asynchronously.
85		286
86	All functions that expect a filehandle will also accept a file descriptor.	287	All functions expecting a filehandle keep a copy of the filehandle
		288	internally until the request has finished.
87		289
		290	All functions return request objects of type L<IO::AIO::REQ> that allow
		291	further manipulation of those requests while they are in-flight.
		292
88	The filenames you pass to these routines I<must> be absolute. The reason	293	The pathnames you pass to these routines I<must> be absolute and
89	is that at the time the request is being executed, the current working	294	encoded as octets. The reason for the former is that at the time the
90	directory could have changed. Alternatively, you can make sure that you	295	request is being executed, the current working directory could have
91	never change the current working directory.	296	changed. Alternatively, you can make sure that you never change the
		297	current working directory anywhere in the program and then use relative
		298	paths.
		299
		300	To encode pathnames as octets, either make sure you either: a) always pass
		301	in filenames you got from outside (command line, readdir etc.) without
		302	tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module and encode
		303	your pathnames to the locale (or other) encoding in effect in the user
		304	environment, d) use Glib::filename_from_unicode on unicode filenames or e)
		305	use something else to ensure your scalar has the correct contents.
		306
		307	This works, btw. independent of the internal UTF-8 bit, which IO::AIO
		308	handles correctly whether it is set or not.
92		309
93	=over 4	310	=over 4
94		311
		312	=item $prev_pri = aioreq_pri [$pri]
		313
		314	Returns the priority value that would be used for the next request and, if
		315	C<$pri> is given, sets the priority for the next aio request.
		316
		317	The default priority is C<0>, the minimum and maximum priorities are C<-4>
		318	and C<4>, respectively. Requests with higher priority will be serviced
		319	first.
		320
		321	The priority will be reset to C<0> after each call to one of the C<aio_*>
		322	functions.
		323
		324	Example: open a file with low priority, then read something from it with
		325	higher priority so the read request is serviced before other low priority
		326	open requests (potentially spamming the cache):
		327
		328	aioreq_pri -3;
		329	aio_open ..., sub {
		330	return unless $_[0];
		331
		332	aioreq_pri -2;
		333	aio_read $_[0], ..., sub {
		334	...
		335	};
		336	};
		337
		338
		339	=item aioreq_nice $pri_adjust
		340
		341	Similar to C<aioreq_pri>, but subtracts the given value from the current
		342	priority, so the effect is cumulative.
		343
		344
95	=item aio_open $pathname, $flags, $mode, $callback	345	=item aio_open $pathname, $flags, $mode, $callback->($fh)
96		346
97	Asynchronously open or create a file and call the callback with a newly	347	Asynchronously open or create a file and call the callback with a newly
98	created filehandle for the file.	348	created filehandle for the file.
99		349
100	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,	350	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,
101	for an explanation.	351	for an explanation.
102		352
103	The C<$mode> argument is a bitmask. See the C<Fcntl> module for a	353	The C<$flags> argument is a bitmask. See the C<Fcntl> module for a
104	list. They are the same as used in C<sysopen>.	354	list. They are the same as used by C<sysopen>.
		355
		356	Likewise, C<$mode> specifies the mode of the newly created file, if it
		357	didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,
		358	except that it is mandatory (i.e. use C<0> if you don't create new files,
		359	and C<0666> or C<0777> if you do). Note that the C<$mode> will be modified
		360	by the umask in effect then the request is being executed, so better never
		361	change the umask.
105		362
106	Example:	363	Example:
107		364
108	aio_open "/etc/passwd", O_RDONLY, 0, sub {	365	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
109	if ($_[0]) {	366	if ($_[0]) {
110	print "open successful, fh is $_[0]\n";	367	print "open successful, fh is $_[0]\n";
111	...	368	...
112	} else {	369	} else {
113	die "open failed: $!\n";	370	die "open failed: $!\n";
114	}	371	}
115	};	372	};
116		373
		374	In addition to all the common open modes/flags (C<O_RDONLY>, C<O_WRONLY>,
		375	C<O_RDWR>, C<O_CREAT>, C<O_TRUNC>, C<O_EXCL> and C<O_APPEND>), the
		376	following POSIX and non-POSIX constants are available (missing ones on
		377	your system are, as usual, C<0>):
		378
		379	C<O_ASYNC>, C<O_DIRECT>, C<O_NOATIME>, C<O_CLOEXEC>, C<O_NOCTTY>, C<O_NOFOLLOW>,
		380	C<O_NONBLOCK>, C<O_EXEC>, C<O_SEARCH>, C<O_DIRECTORY>, C<O_DSYNC>,
		381	C<O_RSYNC>, C<O_SYNC> and C<O_TTY_INIT>.
		382
		383
117	=item aio_close $fh, $callback	384	=item aio_close $fh, $callback->($status)
118		385
119	Asynchronously close a file and call the callback with the result	386	Asynchronously close a file and call the callback with the result
120	code. I<WARNING:> although accepted, you should not pass in a perl	387	code.
121	filehandle here, as perl will likely close the file descriptor itself when
122	the filehandle is destroyed. Normally, you can safely call perls C<close>
123	or just let filehandles go out of scope.
124		388
		389	Unfortunately, you can't do this to perl. Perl I<insists> very strongly on
		390	closing the file descriptor associated with the filehandle itself.
		391
		392	Therefore, C<aio_close> will not close the filehandle - instead it will
		393	use dup2 to overwrite the file descriptor with the write-end of a pipe
		394	(the pipe fd will be created on demand and will be cached).
		395
		396	Or in other words: the file descriptor will be closed, but it will not be
		397	free for reuse until the perl filehandle is closed.
		398
		399	=cut
		400
125	=item aio_read $fh,$offset,$length, $data,$dataoffset,$callback	401	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
126		402
127	=item aio_write $fh,$offset,$length, $data,$dataoffset,$callback	403	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
128		404
129	Reads or writes C<length> bytes from the specified C<fh> and C<offset>	405	Reads or writes C<$length> bytes from or to the specified C<$fh> and
130	into the scalar given by C<data> and offset C<dataoffset> and calls the	406	C<$offset> into the scalar given by C<$data> and offset C<$dataoffset>
131	callback without the actual number of bytes read (or -1 on error, just	407	and calls the callback without the actual number of bytes read (or -1 on
132	like the syscall).	408	error, just like the syscall).
133		409
		410	C<aio_read> will, like C<sysread>, shrink or grow the C<$data> scalar to
		411	offset plus the actual number of bytes read.
		412
		413	If C<$offset> is undefined, then the current file descriptor offset will
		414	be used (and updated), otherwise the file descriptor offset will not be
		415	changed by these calls.
		416
		417	If C<$length> is undefined in C<aio_write>, use the remaining length of
		418	C<$data>.
		419
		420	If C<$dataoffset> is less than zero, it will be counted from the end of
		421	C<$data>.
		422
		423	The C<$data> scalar I<MUST NOT> be modified in any way while the request
		424	is outstanding. Modifying it can result in segfaults or World War III (if
		425	the necessary/optional hardware is installed).
		426
134	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, strating at	427	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at
135	offset C<0> within the scalar:	428	offset C<0> within the scalar:
136		429
137	aio_read $fh, 7, 15, $buffer, 0, sub {	430	aio_read $fh, 7, 15, $buffer, 0, sub {
138	$_[0] > 0 or die "read error: $!";	431	$_[0] > 0 or die "read error: $!";
139	print "read $_[0] bytes: <$buffer>\n";	432	print "read $_[0] bytes: <$buffer>\n";
140	};	433	};
141		434
		435
		436	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
		437
		438	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
		439	reading at byte offset C<$in_offset>, and starts writing at the current
		440	file offset of C<$out_fh>. Because of that, it is not safe to issue more
		441	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each
		442	other. The same C<$in_fh> works fine though, as this function does not
		443	move or use the file offset of C<$in_fh>.
		444
		445	Please note that C<aio_sendfile> can read more bytes from C<$in_fh> than
		446	are written, and there is no way to find out how many more bytes have been
		447	read from C<aio_sendfile> alone, as C<aio_sendfile> only provides the
		448	number of bytes written to C<$out_fh>. Only if the result value equals
		449	C<$length> one can assume that C<$length> bytes have been read.
		450
		451	Unlike with other C<aio_> functions, it makes a lot of sense to use
		452	C<aio_sendfile> on non-blocking sockets, as long as one end (typically
		453	the C<$in_fh>) is a file - the file I/O will then be asynchronous, while
		454	the socket I/O will be non-blocking. Note, however, that you can run
		455	into a trap where C<aio_sendfile> reads some data with readahead, then
		456	fails to write all data, and when the socket is ready the next time, the
		457	data in the cache is already lost, forcing C<aio_sendfile> to again hit
		458	the disk. Explicit C<aio_read> + C<aio_write> let's you better control
		459	resource usage.
		460
		461	This call tries to make use of a native C<sendfile>-like syscall to
		462	provide zero-copy operation. For this to work, C<$out_fh> should refer to
		463	a socket, and C<$in_fh> should refer to an mmap'able file.
		464
		465	If a native sendfile cannot be found or it fails with C<ENOSYS>,
		466	C<EINVAL>, C<ENOTSUP>, C<EOPNOTSUPP>, C<EAFNOSUPPORT>, C<EPROTOTYPE> or
		467	C<ENOTSOCK>, it will be emulated, so you can call C<aio_sendfile> on any
		468	type of filehandle regardless of the limitations of the operating system.
		469
		470	As native sendfile syscalls (as practically any non-POSIX interface hacked
		471	together in a hurry to improve benchmark numbers) tend to be rather buggy
		472	on many systems, this implementation tries to work around some known bugs
		473	in Linux and FreeBSD kernels (probably others, too), but that might fail,
		474	so you really really should check the return value of C<aio_sendfile> -
		475	fewre bytes than expected might have been transferred.
		476
		477
142	=item aio_readahead $fh,$offset,$length, $callback	478	=item aio_readahead $fh,$offset,$length, $callback->($retval)
143		479
144	Asynchronously reads the specified byte range into the page cache, using
145	the C<readahead> syscall. If that syscall doesn't exist the status will be
146	C<-1> and C<$!> is set to ENOSYS.
147
148	readahead() populates the page cache with data from a file so that	480	C<aio_readahead> populates the page cache with data from a file so that
149	subsequent reads from that file will not block on disk I/O. The C<$offset>	481	subsequent reads from that file will not block on disk I/O. The C<$offset>
150	argument specifies the starting point from which data is to be read and	482	argument specifies the starting point from which data is to be read and
151	C<$length> specifies the number of bytes to be read. I/O is performed in	483	C<$length> specifies the number of bytes to be read. I/O is performed in
152	whole pages, so that offset is effectively rounded down to a page boundary	484	whole pages, so that offset is effectively rounded down to a page boundary
153	and bytes are read up to the next page boundary greater than or equal to	485	and bytes are read up to the next page boundary greater than or equal to
154	(off-set+length). aio_readahead() does not read beyond the end of the	486	(off-set+length). C<aio_readahead> does not read beyond the end of the
155	file. The current file offset of the file is left unchanged.	487	file. The current file offset of the file is left unchanged.
156		488
		489	If that syscall doesn't exist (likely if your OS isn't Linux) it will be
		490	emulated by simply reading the data, which would have a similar effect.
		491
		492
157	=item aio_stat $fh_or_path, $callback	493	=item aio_stat $fh_or_path, $callback->($status)
158		494
159	=item aio_lstat $fh, $callback	495	=item aio_lstat $fh, $callback->($status)
160		496
161	Works like perl's C<stat> or C<lstat> in void context. The callback will	497	Works like perl's C<stat> or C<lstat> in void context. The callback will
162	be called after the stat and the results will be available using C<stat _>	498	be called after the stat and the results will be available using C<stat _>
163	or C<-s _> etc...	499	or C<-s _> etc...
164		500
…		…
166	for an explanation.	502	for an explanation.
167		503
168	Currently, the stats are always 64-bit-stats, i.e. instead of returning an	504	Currently, the stats are always 64-bit-stats, i.e. instead of returning an
169	error when stat'ing a large file, the results will be silently truncated	505	error when stat'ing a large file, the results will be silently truncated
170	unless perl itself is compiled with large file support.	506	unless perl itself is compiled with large file support.
		507
		508	To help interpret the mode and dev/rdev stat values, IO::AIO offers the
		509	following constants and functions (if not implemented, the constants will
		510	be C<0> and the functions will either C<croak> or fall back on traditional
		511	behaviour).
		512
		513	C<S_IFMT>, C<S_IFIFO>, C<S_IFCHR>, C<S_IFBLK>, C<S_IFLNK>, C<S_IFREG>,
		514	C<S_IFDIR>, C<S_IFWHT>, C<S_IFSOCK>, C<IO::AIO::major $dev_t>,
		515	C<IO::AIO::minor $dev_t>, C<IO::AIO::makedev $major, $minor>.
171		516
172	Example: Print the length of F</etc/passwd>:	517	Example: Print the length of F</etc/passwd>:
173		518
174	aio_stat "/etc/passwd", sub {	519	aio_stat "/etc/passwd", sub {
175	$_[0] and die "stat failed: $!";	520	$_[0] and die "stat failed: $!";
176	print "size is ", -s _, "\n";	521	print "size is ", -s _, "\n";
177	};	522	};
178		523
		524
		525	=item aio_statvfs $fh_or_path, $callback->($statvfs)
		526
		527	Works like the POSIX C<statvfs> or C<fstatvfs> syscalls, depending on
		528	whether a file handle or path was passed.
		529
		530	On success, the callback is passed a hash reference with the following
		531	members: C<bsize>, C<frsize>, C<blocks>, C<bfree>, C<bavail>, C<files>,
		532	C<ffree>, C<favail>, C<fsid>, C<flag> and C<namemax>. On failure, C<undef>
		533	is passed.
		534
		535	The following POSIX IO::AIO::ST_* constants are defined: C<ST_RDONLY> and
		536	C<ST_NOSUID>.
		537
		538	The following non-POSIX IO::AIO::ST_* flag masks are defined to
		539	their correct value when available, or to C<0> on systems that do
		540	not support them: C<ST_NODEV>, C<ST_NOEXEC>, C<ST_SYNCHRONOUS>,
		541	C<ST_MANDLOCK>, C<ST_WRITE>, C<ST_APPEND>, C<ST_IMMUTABLE>, C<ST_NOATIME>,
		542	C<ST_NODIRATIME> and C<ST_RELATIME>.
		543
		544	Example: stat C</wd> and dump out the data if successful.
		545
		546	aio_statvfs "/wd", sub {
		547	my $f = $_[0]
		548	or die "statvfs: $!";
		549
		550	use Data::Dumper;
		551	say Dumper $f;
		552	};
		553
		554	# result:
		555	{
		556	bsize => 1024,
		557	bfree => 4333064312,
		558	blocks => 10253828096,
		559	files => 2050765568,
		560	flag => 4096,
		561	favail => 2042092649,
		562	bavail => 4333064312,
		563	ffree => 2042092649,
		564	namemax => 255,
		565	frsize => 1024,
		566	fsid => 1810
		567	}
		568
		569
		570	=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
		571
		572	Works like perl's C<utime> function (including the special case of $atime
		573	and $mtime being undef). Fractional times are supported if the underlying
		574	syscalls support them.
		575
		576	When called with a pathname, uses utimes(2) if available, otherwise
		577	utime(2). If called on a file descriptor, uses futimes(2) if available,
		578	otherwise returns ENOSYS, so this is not portable.
		579
		580	Examples:
		581
		582	# set atime and mtime to current time (basically touch(1)):
		583	aio_utime "path", undef, undef;
		584	# set atime to current time and mtime to beginning of the epoch:
		585	aio_utime "path", time, undef; # undef==0
		586
		587
		588	=item aio_chown $fh_or_path, $uid, $gid, $callback->($status)
		589
		590	Works like perl's C<chown> function, except that C<undef> for either $uid
		591	or $gid is being interpreted as "do not change" (but -1 can also be used).
		592
		593	Examples:
		594
		595	# same as "chown root path" in the shell:
		596	aio_chown "path", 0, -1;
		597	# same as above:
		598	aio_chown "path", 0, undef;
		599
		600
		601	=item aio_truncate $fh_or_path, $offset, $callback->($status)
		602
		603	Works like truncate(2) or ftruncate(2).
		604
		605
		606	=item aio_chmod $fh_or_path, $mode, $callback->($status)
		607
		608	Works like perl's C<chmod> function.
		609
		610
179	=item aio_unlink $pathname, $callback	611	=item aio_unlink $pathname, $callback->($status)
180		612
181	Asynchronously unlink (delete) a file and call the callback with the	613	Asynchronously unlink (delete) a file and call the callback with the
182	result code.	614	result code.
183		615
		616
		617	=item aio_mknod $path, $mode, $dev, $callback->($status)
		618
		619	[EXPERIMENTAL]
		620
		621	Asynchronously create a device node (or fifo). See mknod(2).
		622
		623	The only (POSIX-) portable way of calling this function is:
		624
		625	aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ...
		626
		627	See C<aio_stat> for info about some potentially helpful extra constants
		628	and functions.
		629
		630	=item aio_link $srcpath, $dstpath, $callback->($status)
		631
		632	Asynchronously create a new link to the existing object at C<$srcpath> at
		633	the path C<$dstpath> and call the callback with the result code.
		634
		635
		636	=item aio_symlink $srcpath, $dstpath, $callback->($status)
		637
		638	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at
		639	the path C<$dstpath> and call the callback with the result code.
		640
		641
		642	=item aio_readlink $path, $callback->($link)
		643
		644	Asynchronously read the symlink specified by C<$path> and pass it to
		645	the callback. If an error occurs, nothing or undef gets passed to the
		646	callback.
		647
		648
		649	=item aio_realpath $path, $callback->($path)
		650
		651	Asynchronously make the path absolute and resolve any symlinks in
		652	C<$path>. The resulting path only consists of directories.
		653
		654	This request can be used to get the absolute path of the current working
		655	directory by passing it a path of F<.> (a single dot).
		656
		657
		658	=item aio_rename $srcpath, $dstpath, $callback->($status)
		659
		660	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as
		661	rename(2) and call the callback with the result code.
		662
		663
		664	=item aio_mkdir $pathname, $mode, $callback->($status)
		665
		666	Asynchronously mkdir (create) a directory and call the callback with
		667	the result code. C<$mode> will be modified by the umask at the time the
		668	request is executed, so do not change your umask.
		669
		670
		671	=item aio_rmdir $pathname, $callback->($status)
		672
		673	Asynchronously rmdir (delete) a directory and call the callback with the
		674	result code.
		675
		676
		677	=item aio_readdir $pathname, $callback->($entries)
		678
		679	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
		680	directory (i.e. opendir + readdir + closedir). The entries will not be
		681	sorted, and will B<NOT> include the C<.> and C<..> entries.
		682
		683	The callback is passed a single argument which is either C<undef> or an
		684	array-ref with the filenames.
		685
		686
		687	=item aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		688
		689	Quite similar to C<aio_readdir>, but the C<$flags> argument allows to tune
		690	behaviour and output format. In case of an error, C<$entries> will be
		691	C<undef>.
		692
		693	The flags are a combination of the following constants, ORed together (the
		694	flags will also be passed to the callback, possibly modified):
		695
		696	=over 4
		697
		698	=item IO::AIO::READDIR_DENTS
		699
		700	When this flag is off, then the callback gets an arrayref consisting of
		701	names only (as with C<aio_readdir>), otherwise it gets an arrayref with
		702	C<[$name, $type, $inode]> arrayrefs, each describing a single directory
		703	entry in more detail.
		704
		705	C<$name> is the name of the entry.
		706
		707	C<$type> is one of the C<IO::AIO::DT_xxx> constants:
		708
		709	C<IO::AIO::DT_UNKNOWN>, C<IO::AIO::DT_FIFO>, C<IO::AIO::DT_CHR>, C<IO::AIO::DT_DIR>,
		710	C<IO::AIO::DT_BLK>, C<IO::AIO::DT_REG>, C<IO::AIO::DT_LNK>, C<IO::AIO::DT_SOCK>,
		711	C<IO::AIO::DT_WHT>.
		712
		713	C<IO::AIO::DT_UNKNOWN> means just that: readdir does not know. If you need to
		714	know, you have to run stat yourself. Also, for speed reasons, the C<$type>
		715	scalars are read-only: you can not modify them.
		716
		717	C<$inode> is the inode number (which might not be exact on systems with 64
		718	bit inode numbers and 32 bit perls). This field has unspecified content on
		719	systems that do not deliver the inode information.
		720
		721	=item IO::AIO::READDIR_DIRS_FIRST
		722
		723	When this flag is set, then the names will be returned in an order where
		724	likely directories come first, in optimal stat order. This is useful when
		725	you need to quickly find directories, or you want to find all directories
		726	while avoiding to stat() each entry.
		727
		728	If the system returns type information in readdir, then this is used
		729	to find directories directly. Otherwise, likely directories are names
		730	beginning with ".", or otherwise names with no dots, of which names with
		731	short names are tried first.
		732
		733	=item IO::AIO::READDIR_STAT_ORDER
		734
		735	When this flag is set, then the names will be returned in an order
		736	suitable for stat()'ing each one. That is, when you plan to stat()
		737	all files in the given directory, then the returned order will likely
		738	be fastest.
		739
		740	If both this flag and C<IO::AIO::READDIR_DIRS_FIRST> are specified, then
		741	the likely dirs come first, resulting in a less optimal stat order.
		742
		743	=item IO::AIO::READDIR_FOUND_UNKNOWN
		744
		745	This flag should not be set when calling C<aio_readdirx>. Instead, it
		746	is being set by C<aio_readdirx>, when any of the C<$type>'s found were
		747	C<IO::AIO::DT_UNKNOWN>. The absense of this flag therefore indicates that all
		748	C<$type>'s are known, which can be used to speed up some algorithms.
		749
		750	=back
		751
		752
		753	=item aio_load $path, $data, $callback->($status)
		754
		755	This is a composite request that tries to fully load the given file into
		756	memory. Status is the same as with aio_read.
		757
		758	=cut
		759
		760	sub aio_load($$;$) {
		761	my ($path, undef, $cb) = @_;
		762	my $data = \$_[1];
		763
		764	my $pri = aioreq_pri;
		765	my $grp = aio_group $cb;
		766
		767	aioreq_pri $pri;
		768	add $grp aio_open $path, O_RDONLY, 0, sub {
		769	my $fh = shift
		770	or return $grp->result (-1);
		771
		772	aioreq_pri $pri;
		773	add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub {
		774	$grp->result ($_[0]);
		775	};
		776	};
		777
		778	$grp
		779	}
		780
		781	=item aio_copy $srcpath, $dstpath, $callback->($status)
		782
		783	Try to copy the I<file> (directories not supported as either source or
		784	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		785	a status of C<0> (ok) or C<-1> (error, see C<$!>).
		786
		787	This is a composite request that creates the destination file with
		788	mode 0200 and copies the contents of the source file into it using
		789	C<aio_sendfile>, followed by restoring atime, mtime, access mode and
		790	uid/gid, in that order.
		791
		792	If an error occurs, the partial destination file will be unlinked, if
		793	possible, except when setting atime, mtime, access mode and uid/gid, where
		794	errors are being ignored.
		795
		796	=cut
		797
		798	sub aio_copy($$;$) {
		799	my ($src, $dst, $cb) = @_;
		800
		801	my $pri = aioreq_pri;
		802	my $grp = aio_group $cb;
		803
		804	aioreq_pri $pri;
		805	add $grp aio_open $src, O_RDONLY, 0, sub {
		806	if (my $src_fh = $_[0]) {
		807	my @stat = stat $src_fh; # hmm, might block over nfs?
		808
		809	aioreq_pri $pri;
		810	add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {
		811	if (my $dst_fh = $_[0]) {
		812	aioreq_pri $pri;
		813	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
		814	if ($_[0] == $stat[7]) {
		815	$grp->result (0);
		816	close $src_fh;
		817
		818	my $ch = sub {
		819	aioreq_pri $pri;
		820	add $grp aio_chmod $dst_fh, $stat[2] & 07777, sub {
		821	aioreq_pri $pri;
		822	add $grp aio_chown $dst_fh, $stat[4], $stat[5], sub {
		823	aioreq_pri $pri;
		824	add $grp aio_close $dst_fh;
		825	}
		826	};
		827	};
		828
		829	aioreq_pri $pri;
		830	add $grp aio_utime $dst_fh, $stat[8], $stat[9], sub {
		831	if ($_[0] < 0 && $! == ENOSYS) {
		832	aioreq_pri $pri;
		833	add $grp aio_utime $dst, $stat[8], $stat[9], $ch;
		834	} else {
		835	$ch->();
		836	}
		837	};
		838	} else {
		839	$grp->result (-1);
		840	close $src_fh;
		841	close $dst_fh;
		842
		843	aioreq $pri;
		844	add $grp aio_unlink $dst;
		845	}
		846	};
		847	} else {
		848	$grp->result (-1);
		849	}
		850	},
		851
		852	} else {
		853	$grp->result (-1);
		854	}
		855	};
		856
		857	$grp
		858	}
		859
		860	=item aio_move $srcpath, $dstpath, $callback->($status)
		861
		862	Try to move the I<file> (directories not supported as either source or
		863	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		864	a status of C<0> (ok) or C<-1> (error, see C<$!>).
		865
		866	This is a composite request that tries to rename(2) the file first; if
		867	rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if
		868	that is successful, unlinks the C<$srcpath>.
		869
		870	=cut
		871
		872	sub aio_move($$;$) {
		873	my ($src, $dst, $cb) = @_;
		874
		875	my $pri = aioreq_pri;
		876	my $grp = aio_group $cb;
		877
		878	aioreq_pri $pri;
		879	add $grp aio_rename $src, $dst, sub {
		880	if ($_[0] && $! == EXDEV) {
		881	aioreq_pri $pri;
		882	add $grp aio_copy $src, $dst, sub {
		883	$grp->result ($_[0]);
		884
		885	unless ($_[0]) {
		886	aioreq_pri $pri;
		887	add $grp aio_unlink $src;
		888	}
		889	};
		890	} else {
		891	$grp->result ($_[0]);
		892	}
		893	};
		894
		895	$grp
		896	}
		897
		898	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
		899
		900	Scans a directory (similar to C<aio_readdir>) but additionally tries to
		901	efficiently separate the entries of directory C<$path> into two sets of
		902	names, directories you can recurse into (directories), and ones you cannot
		903	recurse into (everything else, including symlinks to directories).
		904
		905	C<aio_scandir> is a composite request that creates of many sub requests_
		906	C<$maxreq> specifies the maximum number of outstanding aio requests that
		907	this function generates. If it is C<< <= 0 >>, then a suitable default
		908	will be chosen (currently 4).
		909
		910	On error, the callback is called without arguments, otherwise it receives
		911	two array-refs with path-relative entry names.
		912
		913	Example:
		914
		915	aio_scandir $dir, 0, sub {
		916	my ($dirs, $nondirs) = @_;
		917	print "real directories: @$dirs\n";
		918	print "everything else: @$nondirs\n";
		919	};
		920
		921	Implementation notes.
		922
		923	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.
		924
		925	If readdir returns file type information, then this is used directly to
		926	find directories.
		927
		928	Otherwise, after reading the directory, the modification time, size etc.
		929	of the directory before and after the readdir is checked, and if they
		930	match (and isn't the current time), the link count will be used to decide
		931	how many entries are directories (if >= 2). Otherwise, no knowledge of the
		932	number of subdirectories will be assumed.
		933
		934	Then entries will be sorted into likely directories a non-initial dot
		935	currently) and likely non-directories (see C<aio_readdirx>). Then every
		936	entry plus an appended C</.> will be C<stat>'ed, likely directories first,
		937	in order of their inode numbers. If that succeeds, it assumes that the
		938	entry is a directory or a symlink to directory (which will be checked
		939	seperately). This is often faster than stat'ing the entry itself because
		940	filesystems might detect the type of the entry without reading the inode
		941	data (e.g. ext2fs filetype feature), even on systems that cannot return
		942	the filetype information on readdir.
		943
		944	If the known number of directories (link count - 2) has been reached, the
		945	rest of the entries is assumed to be non-directories.
		946
		947	This only works with certainty on POSIX (= UNIX) filesystems, which
		948	fortunately are the vast majority of filesystems around.
		949
		950	It will also likely work on non-POSIX filesystems with reduced efficiency
		951	as those tend to return 0 or 1 as link counts, which disables the
		952	directory counting heuristic.
		953
		954	=cut
		955
		956	sub aio_scandir($$;$) {
		957	my ($path, $maxreq, $cb) = @_;
		958
		959	my $pri = aioreq_pri;
		960
		961	my $grp = aio_group $cb;
		962
		963	$maxreq = 4 if $maxreq <= 0;
		964
		965	# stat once
		966	aioreq_pri $pri;
		967	add $grp aio_stat $path, sub {
		968	return $grp->result () if $_[0];
		969	my $now = time;
		970	my $hash1 = join ":", (stat _)[0,1,3,7,9];
		971
		972	# read the directory entries
		973	aioreq_pri $pri;
		974	add $grp aio_readdirx $path, READDIR_DIRS_FIRST, sub {
		975	my $entries = shift
		976	or return $grp->result ();
		977
		978	# stat the dir another time
		979	aioreq_pri $pri;
		980	add $grp aio_stat $path, sub {
		981	my $hash2 = join ":", (stat _)[0,1,3,7,9];
		982
		983	my $ndirs;
		984
		985	# take the slow route if anything looks fishy
		986	if ($hash1 ne $hash2 or (stat _)[9] == $now) {
		987	$ndirs = -1;
		988	} else {
		989	# if nlink == 2, we are finished
		990	# for non-posix-fs's, we rely on nlink < 2
		991	$ndirs = (stat _)[3] - 2
		992	or return $grp->result ([], $entries);
		993	}
		994
		995	my (@dirs, @nondirs);
		996
		997	my $statgrp = add $grp aio_group sub {
		998	$grp->result (\@dirs, \@nondirs);
		999	};
		1000
		1001	limit $statgrp $maxreq;
		1002	feed $statgrp sub {
		1003	return unless @$entries;
		1004	my $entry = shift @$entries;
		1005
		1006	aioreq_pri $pri;
		1007	add $statgrp aio_stat "$path/$entry/.", sub {
		1008	if ($_[0] < 0) {
		1009	push @nondirs, $entry;
		1010	} else {
		1011	# need to check for real directory
		1012	aioreq_pri $pri;
		1013	add $statgrp aio_lstat "$path/$entry", sub {
		1014	if (-d _) {
		1015	push @dirs, $entry;
		1016
		1017	unless (--$ndirs) {
		1018	push @nondirs, @$entries;
		1019	feed $statgrp;
		1020	}
		1021	} else {
		1022	push @nondirs, $entry;
		1023	}
		1024	}
		1025	}
		1026	};
		1027	};
		1028	};
		1029	};
		1030	};
		1031
		1032	$grp
		1033	}
		1034
		1035	=item aio_rmtree $path, $callback->($status)
		1036
		1037	Delete a directory tree starting (and including) C<$path>, return the
		1038	status of the final C<rmdir> only. This is a composite request that
		1039	uses C<aio_scandir> to recurse into and rmdir directories, and unlink
		1040	everything else.
		1041
		1042	=cut
		1043
		1044	sub aio_rmtree;
		1045	sub aio_rmtree($;$) {
		1046	my ($path, $cb) = @_;
		1047
		1048	my $pri = aioreq_pri;
		1049	my $grp = aio_group $cb;
		1050
		1051	aioreq_pri $pri;
		1052	add $grp aio_scandir $path, 0, sub {
		1053	my ($dirs, $nondirs) = @_;
		1054
		1055	my $dirgrp = aio_group sub {
		1056	add $grp aio_rmdir $path, sub {
		1057	$grp->result ($_[0]);
		1058	};
		1059	};
		1060
		1061	(aioreq_pri $pri), add $dirgrp aio_rmtree "$path/$_" for @$dirs;
		1062	(aioreq_pri $pri), add $dirgrp aio_unlink "$path/$_" for @$nondirs;
		1063
		1064	add $grp $dirgrp;
		1065	};
		1066
		1067	$grp
		1068	}
		1069
		1070	=item aio_sync $callback->($status)
		1071
		1072	Asynchronously call sync and call the callback when finished.
		1073
184	=item aio_fsync $fh, $callback	1074	=item aio_fsync $fh, $callback->($status)
185		1075
186	Asynchronously call fsync on the given filehandle and call the callback	1076	Asynchronously call fsync on the given filehandle and call the callback
187	with the fsync result code.	1077	with the fsync result code.
188		1078
189	=item aio_fdatasync $fh, $callback	1079	=item aio_fdatasync $fh, $callback->($status)
190		1080
191	Asynchronously call fdatasync on the given filehandle and call the	1081	Asynchronously call fdatasync on the given filehandle and call the
192	callback with the fdatasync result code.	1082	callback with the fdatasync result code.
193		1083
		1084	If this call isn't available because your OS lacks it or it couldn't be
		1085	detected, it will be emulated by calling C<fsync> instead.
		1086
		1087	=item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		1088
		1089	Sync the data portion of the file specified by C<$offset> and C<$length>
		1090	to disk (but NOT the metadata), by calling the Linux-specific
		1091	sync_file_range call. If sync_file_range is not available or it returns
		1092	ENOSYS, then fdatasync or fsync is being substituted.
		1093
		1094	C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>,
		1095	C<IO::AIO::SYNC_FILE_RANGE_WRITE> and
		1096	C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range
		1097	manpage for details.
		1098
		1099	=item aio_pathsync $path, $callback->($status)
		1100
		1101	This request tries to open, fsync and close the given path. This is a
		1102	composite request intended to sync directories after directory operations
		1103	(E.g. rename). This might not work on all operating systems or have any
		1104	specific effect, but usually it makes sure that directory changes get
		1105	written to disc. It works for anything that can be opened for read-only,
		1106	not just directories.
		1107
		1108	Future versions of this function might fall back to other methods when
		1109	C<fsync> on the directory fails (such as calling C<sync>).
		1110
		1111	Passes C<0> when everything went ok, and C<-1> on error.
		1112
		1113	=cut
		1114
		1115	sub aio_pathsync($;$) {
		1116	my ($path, $cb) = @_;
		1117
		1118	my $pri = aioreq_pri;
		1119	my $grp = aio_group $cb;
		1120
		1121	aioreq_pri $pri;
		1122	add $grp aio_open $path, O_RDONLY, 0, sub {
		1123	my ($fh) = @_;
		1124	if ($fh) {
		1125	aioreq_pri $pri;
		1126	add $grp aio_fsync $fh, sub {
		1127	$grp->result ($_[0]);
		1128
		1129	aioreq_pri $pri;
		1130	add $grp aio_close $fh;
		1131	};
		1132	} else {
		1133	$grp->result (-1);
		1134	}
		1135	};
		1136
		1137	$grp
		1138	}
		1139
		1140	=item aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		1141
		1142	This is a rather advanced IO::AIO call, which only works on mmap(2)ed
		1143	scalars (see the C<IO::AIO::mmap> function, although it also works on data
		1144	scalars managed by the L<Sys::Mmap> or L<Mmap> modules, note that the
		1145	scalar must only be modified in-place while an aio operation is pending on
		1146	it).
		1147
		1148	It calls the C<msync> function of your OS, if available, with the memory
		1149	area starting at C<$offset> in the string and ending C<$length> bytes
		1150	later. If C<$length> is negative, counts from the end, and if C<$length>
		1151	is C<undef>, then it goes till the end of the string. The flags can be
		1152	a combination of C<IO::AIO::MS_ASYNC>, C<IO::AIO::MS_INVALIDATE> and
		1153	C<IO::AIO::MS_SYNC>.
		1154
		1155	=item aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		1156
		1157	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1158	scalars.
		1159
		1160	It touches (reads or writes) all memory pages in the specified
		1161	range inside the scalar. All caveats and parameters are the same
		1162	as for C<aio_msync>, above, except for flags, which must be either
		1163	C<0> (which reads all pages and ensures they are instantiated) or
		1164	C<IO::AIO::MT_MODIFY>, which modifies the memory page s(by reading and
		1165	writing an octet from it, which dirties the page).
		1166
		1167	=item aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
		1168
		1169	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1170	scalars.
		1171
		1172	It reads in all the pages of the underlying storage into memory (if any)
		1173	and locks them, so they are not getting swapped/paged out or removed.
		1174
		1175	If C<$length> is undefined, then the scalar will be locked till the end.
		1176
		1177	On systems that do not implement C<mlock>, this function returns C<-1>
		1178	and sets errno to C<ENOSYS>.
		1179
		1180	Note that the corresponding C<munlock> is synchronous and is
		1181	documented under L<MISCELLANEOUS FUNCTIONS>.
		1182
		1183	Example: open a file, mmap and mlock it - both will be undone when
		1184	C<$data> gets destroyed.
		1185
		1186	open my $fh, "<", $path or die "$path: $!";
		1187	my $data;
		1188	IO::AIO::mmap $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh;
		1189	aio_mlock $data; # mlock in background
		1190
		1191	=item aio_mlockall $flags, $callback->($status)
		1192
		1193	Calls the C<mlockall> function with the given C<$flags> (a combination of
		1194	C<IO::AIO::MCL_CURRENT> and C<IO::AIO::MCL_FUTURE>).
		1195
		1196	On systems that do not implement C<mlockall>, this function returns C<-1>
		1197	and sets errno to C<ENOSYS>.
		1198
		1199	Note that the corresponding C<munlockall> is synchronous and is
		1200	documented under L<MISCELLANEOUS FUNCTIONS>.
		1201
		1202	Example: asynchronously lock all current and future pages into memory.
		1203
		1204	aio_mlockall IO::AIO::MCL_FUTURE;
		1205
		1206	=item aio_group $callback->(...)
		1207
		1208	This is a very special aio request: Instead of doing something, it is a
		1209	container for other aio requests, which is useful if you want to bundle
		1210	many requests into a single, composite, request with a definite callback
		1211	and the ability to cancel the whole request with its subrequests.
		1212
		1213	Returns an object of class L<IO::AIO::GRP>. See its documentation below
		1214	for more info.
		1215
		1216	Example:
		1217
		1218	my $grp = aio_group sub {
		1219	print "all stats done\n";
		1220	};
		1221
		1222	add $grp
		1223	(aio_stat ...),
		1224	(aio_stat ...),
		1225	...;
		1226
		1227	=item aio_nop $callback->()
		1228
		1229	This is a special request - it does nothing in itself and is only used for
		1230	side effects, such as when you want to add a dummy request to a group so
		1231	that finishing the requests in the group depends on executing the given
		1232	code.
		1233
		1234	While this request does nothing, it still goes through the execution
		1235	phase and still requires a worker thread. Thus, the callback will not
		1236	be executed immediately but only after other requests in the queue have
		1237	entered their execution phase. This can be used to measure request
		1238	latency.
		1239
		1240	=item IO::AIO::aio_busy $fractional_seconds, $callback->() *NOT EXPORTED*
		1241
		1242	Mainly used for debugging and benchmarking, this aio request puts one of
		1243	the request workers to sleep for the given time.
		1244
		1245	While it is theoretically handy to have simple I/O scheduling requests
		1246	like sleep and file handle readable/writable, the overhead this creates is
		1247	immense (it blocks a thread for a long time) so do not use this function
		1248	except to put your application under artificial I/O pressure.
		1249
194	=back	1250	=back
195		1251
		1252	=head2 IO::AIO::REQ CLASS
		1253
		1254	All non-aggregate C<aio_*> functions return an object of this class when
		1255	called in non-void context.
		1256
		1257	=over 4
		1258
		1259	=item cancel $req
		1260
		1261	Cancels the request, if possible. Has the effect of skipping execution
		1262	when entering the B<execute> state and skipping calling the callback when
		1263	entering the the B<result> state, but will leave the request otherwise
		1264	untouched (with the exception of readdir). That means that requests that
		1265	currently execute will not be stopped and resources held by the request
		1266	will not be freed prematurely.
		1267
		1268	=item cb $req $callback->(...)
		1269
		1270	Replace (or simply set) the callback registered to the request.
		1271
		1272	=back
		1273
		1274	=head2 IO::AIO::GRP CLASS
		1275
		1276	This class is a subclass of L<IO::AIO::REQ>, so all its methods apply to
		1277	objects of this class, too.
		1278
		1279	A IO::AIO::GRP object is a special request that can contain multiple other
		1280	aio requests.
		1281
		1282	You create one by calling the C<aio_group> constructing function with a
		1283	callback that will be called when all contained requests have entered the
		1284	C<done> state:
		1285
		1286	my $grp = aio_group sub {
		1287	print "all requests are done\n";
		1288	};
		1289
		1290	You add requests by calling the C<add> method with one or more
		1291	C<IO::AIO::REQ> objects:
		1292
		1293	$grp->add (aio_unlink "...");
		1294
		1295	add $grp aio_stat "...", sub {
		1296	$_[0] or return $grp->result ("error");
		1297
		1298	# add another request dynamically, if first succeeded
		1299	add $grp aio_open "...", sub {
		1300	$grp->result ("ok");
		1301	};
		1302	};
		1303
		1304	This makes it very easy to create composite requests (see the source of
		1305	C<aio_move> for an application) that work and feel like simple requests.
		1306
		1307	=over 4
		1308
		1309	=item * The IO::AIO::GRP objects will be cleaned up during calls to
		1310	C<IO::AIO::poll_cb>, just like any other request.
		1311
		1312	=item * They can be canceled like any other request. Canceling will cancel not
		1313	only the request itself, but also all requests it contains.
		1314
		1315	=item * They can also can also be added to other IO::AIO::GRP objects.
		1316
		1317	=item * You must not add requests to a group from within the group callback (or
		1318	any later time).
		1319
		1320	=back
		1321
		1322	Their lifetime, simplified, looks like this: when they are empty, they
		1323	will finish very quickly. If they contain only requests that are in the
		1324	C<done> state, they will also finish. Otherwise they will continue to
		1325	exist.
		1326
		1327	That means after creating a group you have some time to add requests
		1328	(precisely before the callback has been invoked, which is only done within
		1329	the C<poll_cb>). And in the callbacks of those requests, you can add
		1330	further requests to the group. And only when all those requests have
		1331	finished will the the group itself finish.
		1332
		1333	=over 4
		1334
		1335	=item add $grp ...
		1336
		1337	=item $grp->add (...)
		1338
		1339	Add one or more requests to the group. Any type of L<IO::AIO::REQ> can
		1340	be added, including other groups, as long as you do not create circular
		1341	dependencies.
		1342
		1343	Returns all its arguments.
		1344
		1345	=item $grp->cancel_subs
		1346
		1347	Cancel all subrequests and clears any feeder, but not the group request
		1348	itself. Useful when you queued a lot of events but got a result early.
		1349
		1350	The group request will finish normally (you cannot add requests to the
		1351	group).
		1352
		1353	=item $grp->result (...)
		1354
		1355	Set the result value(s) that will be passed to the group callback when all
		1356	subrequests have finished and set the groups errno to the current value
		1357	of errno (just like calling C<errno> without an error number). By default,
		1358	no argument will be passed and errno is zero.
		1359
		1360	=item $grp->errno ([$errno])
		1361
		1362	Sets the group errno value to C<$errno>, or the current value of errno
		1363	when the argument is missing.
		1364
		1365	Every aio request has an associated errno value that is restored when
		1366	the callback is invoked. This method lets you change this value from its
		1367	default (0).
		1368
		1369	Calling C<result> will also set errno, so make sure you either set C<$!>
		1370	before the call to C<result>, or call c<errno> after it.
		1371
		1372	=item feed $grp $callback->($grp)
		1373
		1374	Sets a feeder/generator on this group: every group can have an attached
		1375	generator that generates requests if idle. The idea behind this is that,
		1376	although you could just queue as many requests as you want in a group,
		1377	this might starve other requests for a potentially long time. For example,
		1378	C<aio_scandir> might generate hundreds of thousands C<aio_stat> requests,
		1379	delaying any later requests for a long time.
		1380
		1381	To avoid this, and allow incremental generation of requests, you can
		1382	instead a group and set a feeder on it that generates those requests. The
		1383	feed callback will be called whenever there are few enough (see C<limit>,
		1384	below) requests active in the group itself and is expected to queue more
		1385	requests.
		1386
		1387	The feed callback can queue as many requests as it likes (i.e. C<add> does
		1388	not impose any limits).
		1389
		1390	If the feed does not queue more requests when called, it will be
		1391	automatically removed from the group.
		1392
		1393	If the feed limit is C<0> when this method is called, it will be set to
		1394	C<2> automatically.
		1395
		1396	Example:
		1397
		1398	# stat all files in @files, but only ever use four aio requests concurrently:
		1399
		1400	my $grp = aio_group sub { print "finished\n" };
		1401	limit $grp 4;
		1402	feed $grp sub {
		1403	my $file = pop @files
		1404	or return;
		1405
		1406	add $grp aio_stat $file, sub { ... };
		1407	};
		1408
		1409	=item limit $grp $num
		1410
		1411	Sets the feeder limit for the group: The feeder will be called whenever
		1412	the group contains less than this many requests.
		1413
		1414	Setting the limit to C<0> will pause the feeding process.
		1415
		1416	The default value for the limit is C<0>, but note that setting a feeder
		1417	automatically bumps it up to C<2>.
		1418
		1419	=back
		1420
196	=head2 SUPPORT FUNCTIONS	1421	=head2 SUPPORT FUNCTIONS
197		1422
		1423	=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION
		1424
198	=over 4	1425	=over 4
199		1426
200	=item $fileno = IO::AIO::poll_fileno	1427	=item $fileno = IO::AIO::poll_fileno
201		1428
202	Return the I<request result pipe filehandle>. This filehandle must be	1429	Return the I<request result pipe file descriptor>. This filehandle must be
203	polled for reading by some mechanism outside this module (e.g. Event	1430	polled for reading by some mechanism outside this module (e.g. EV, Glib,
204	or select, see below). If the pipe becomes readable you have to call	1431	select and so on, see below or the SYNOPSIS). If the pipe becomes readable
205	C<poll_cb> to check the results.	1432	you have to call C<poll_cb> to check the results.
206		1433
207	See C<poll_cb> for an example.	1434	See C<poll_cb> for an example.
208		1435
209	=item IO::AIO::poll_cb	1436	=item IO::AIO::poll_cb
210		1437
211	Process all outstanding events on the result pipe. You have to call this	1438	Process some outstanding events on the result pipe. You have to call
212	regularly. Returns the number of events processed. Returns immediately	1439	this regularly. Returns C<0> if all events could be processed (or there
213	when no events are outstanding.	1440	were no events to process), or C<-1> if it returned earlier for whatever
		1441	reason. Returns immediately when no events are outstanding. The amount of
		1442	events processed depends on the settings of C<IO::AIO::max_poll_req> and
		1443	C<IO::AIO::max_poll_time>.
214		1444
215	You can use Event to multiplex, e.g.:	1445	If not all requests were processed for whatever reason, the filehandle
		1446	will still be ready when C<poll_cb> returns, so normally you don't have to
		1447	do anything special to have it called later.
		1448
		1449	Apart from calling C<IO::AIO::poll_cb> when the event filehandle becomes
		1450	ready, it can be beneficial to call this function from loops which submit
		1451	a lot of requests, to make sure the results get processed when they become
		1452	available and not just when the loop is finished and the event loop takes
		1453	over again. This function returns very fast when there are no outstanding
		1454	requests.
		1455
		1456	Example: Install an Event watcher that automatically calls
		1457	IO::AIO::poll_cb with high priority (more examples can be found in the
		1458	SYNOPSIS section, at the top of this document):
216		1459
217	Event->io (fd => IO::AIO::poll_fileno,	1460	Event->io (fd => IO::AIO::poll_fileno,
218	poll => 'r', async => 1,	1461	poll => 'r', async => 1,
219	cb => \&IO::AIO::poll_cb);	1462	cb => \&IO::AIO::poll_cb);
220		1463
221	=item IO::AIO::poll_wait	1464	=item IO::AIO::poll_wait
222		1465
		1466	If there are any outstanding requests and none of them in the result
223	Wait till the result filehandle becomes ready for reading (simply does a	1467	phase, wait till the result filehandle becomes ready for reading (simply
224	select on the filehandle. This is useful if you want to synchronously wait	1468	does a C<select> on the filehandle. This is useful if you want to
225	for some requests to finish).	1469	synchronously wait for some requests to finish).
226		1470
227	See C<nreqs> for an example.	1471	See C<nreqs> for an example.
228		1472
		1473	=item IO::AIO::poll
		1474
		1475	Waits until some requests have been handled.
		1476
		1477	Returns the number of requests processed, but is otherwise strictly
		1478	equivalent to:
		1479
		1480	IO::AIO::poll_wait, IO::AIO::poll_cb
		1481
229	=item IO::AIO::nreqs	1482	=item IO::AIO::flush
230		1483
231	Returns the number of requests currently outstanding.	1484	Wait till all outstanding AIO requests have been handled.
232		1485
233	Example: wait till there are no outstanding requests anymore:	1486	Strictly equivalent to:
234		1487
235	IO::AIO::poll_wait, IO::AIO::poll_cb	1488	IO::AIO::poll_wait, IO::AIO::poll_cb
236	while IO::AIO::nreqs;	1489	while IO::AIO::nreqs;
237		1490
		1491	=item IO::AIO::max_poll_reqs $nreqs
		1492
		1493	=item IO::AIO::max_poll_time $seconds
		1494
		1495	These set the maximum number of requests (default C<0>, meaning infinity)
		1496	that are being processed by C<IO::AIO::poll_cb> in one call, respectively
		1497	the maximum amount of time (default C<0>, meaning infinity) spent in
		1498	C<IO::AIO::poll_cb> to process requests (more correctly the mininum amount
		1499	of time C<poll_cb> is allowed to use).
		1500
		1501	Setting C<max_poll_time> to a non-zero value creates an overhead of one
		1502	syscall per request processed, which is not normally a problem unless your
		1503	callbacks are really really fast or your OS is really really slow (I am
		1504	not mentioning Solaris here). Using C<max_poll_reqs> incurs no overhead.
		1505
		1506	Setting these is useful if you want to ensure some level of
		1507	interactiveness when perl is not fast enough to process all requests in
		1508	time.
		1509
		1510	For interactive programs, values such as C<0.01> to C<0.1> should be fine.
		1511
		1512	Example: Install an Event watcher that automatically calls
		1513	IO::AIO::poll_cb with low priority, to ensure that other parts of the
		1514	program get the CPU sometimes even under high AIO load.
		1515
		1516	# try not to spend much more than 0.1s in poll_cb
		1517	IO::AIO::max_poll_time 0.1;
		1518
		1519	# use a low priority so other tasks have priority
		1520	Event->io (fd => IO::AIO::poll_fileno,
		1521	poll => 'r', nice => 1,
		1522	cb => &IO::AIO::poll_cb);
		1523
		1524	=back
		1525
		1526	=head3 CONTROLLING THE NUMBER OF THREADS
		1527
		1528	=over
		1529
		1530	=item IO::AIO::min_parallel $nthreads
		1531
		1532	Set the minimum number of AIO threads to C<$nthreads>. The current
		1533	default is C<8>, which means eight asynchronous operations can execute
		1534	concurrently at any one time (the number of outstanding requests,
		1535	however, is unlimited).
		1536
		1537	IO::AIO starts threads only on demand, when an AIO request is queued and
		1538	no free thread exists. Please note that queueing up a hundred requests can
		1539	create demand for a hundred threads, even if it turns out that everything
		1540	is in the cache and could have been processed faster by a single thread.
		1541
		1542	It is recommended to keep the number of threads relatively low, as some
		1543	Linux kernel versions will scale negatively with the number of threads
		1544	(higher parallelity => MUCH higher latency). With current Linux 2.6
		1545	versions, 4-32 threads should be fine.
		1546
		1547	Under most circumstances you don't need to call this function, as the
		1548	module selects a default that is suitable for low to moderate load.
		1549
		1550	=item IO::AIO::max_parallel $nthreads
		1551
		1552	Sets the maximum number of AIO threads to C<$nthreads>. If more than the
		1553	specified number of threads are currently running, this function kills
		1554	them. This function blocks until the limit is reached.
		1555
		1556	While C<$nthreads> are zero, aio requests get queued but not executed
		1557	until the number of threads has been increased again.
		1558
		1559	This module automatically runs C<max_parallel 0> at program end, to ensure
		1560	that all threads are killed and that there are no outstanding requests.
		1561
		1562	Under normal circumstances you don't need to call this function.
		1563
		1564	=item IO::AIO::max_idle $nthreads
		1565
		1566	Limit the number of threads (default: 4) that are allowed to idle
		1567	(i.e., threads that did not get a request to process within the idle
		1568	timeout (default: 10 seconds). That means if a thread becomes idle while
		1569	C<$nthreads> other threads are also idle, it will free its resources and
		1570	exit.
		1571
		1572	This is useful when you allow a large number of threads (e.g. 100 or 1000)
		1573	to allow for extremely high load situations, but want to free resources
		1574	under normal circumstances (1000 threads can easily consume 30MB of RAM).
		1575
		1576	The default is probably ok in most situations, especially if thread
		1577	creation is fast. If thread creation is very slow on your system you might
		1578	want to use larger values.
		1579
		1580	=item IO::AIO::idle_timeout $seconds
		1581
		1582	Sets the minimum idle timeout (default 10) after which worker threads are
		1583	allowed to exit. SEe C<IO::AIO::max_idle>.
		1584
		1585	=item IO::AIO::max_outstanding $maxreqs
		1586
		1587	Sets the maximum number of outstanding requests to C<$nreqs>. If
		1588	you do queue up more than this number of requests, the next call to
		1589	C<IO::AIO::poll_cb> (and other functions calling C<poll_cb>, such as
		1590	C<IO::AIO::flush> or C<IO::AIO::poll>) will block until the limit is no
		1591	longer exceeded.
		1592
		1593	In other words, this setting does not enforce a queue limit, but can be
		1594	used to make poll functions block if the limit is exceeded.
		1595
		1596	This is a very bad function to use in interactive programs because it
		1597	blocks, and a bad way to reduce concurrency because it is inexact: Better
		1598	use an C<aio_group> together with a feed callback.
		1599
		1600	It's main use is in scripts without an event loop - when you want to stat
		1601	a lot of files, you can write somehting like this:
		1602
		1603	IO::AIO::max_outstanding 32;
		1604
		1605	for my $path (...) {
		1606	aio_stat $path , ...;
		1607	IO::AIO::poll_cb;
		1608	}
		1609
		1610	IO::AIO::flush;
		1611
		1612	The call to C<poll_cb> inside the loop will normally return instantly, but
		1613	as soon as more thna C<32> reqeusts are in-flight, it will block until
		1614	some requests have been handled. This keeps the loop from pushing a large
		1615	number of C<aio_stat> requests onto the queue.
		1616
		1617	The default value for C<max_outstanding> is very large, so there is no
		1618	practical limit on the number of outstanding requests.
		1619
		1620	=back
		1621
		1622	=head3 STATISTICAL INFORMATION
		1623
		1624	=over
		1625
238	=item IO::AIO::flush	1626	=item IO::AIO::nreqs
239		1627
240	Wait till all outstanding AIO requests have been handled.	1628	Returns the number of requests currently in the ready, execute or pending
		1629	states (i.e. for which their callback has not been invoked yet).
241		1630
242	Strictly equivalent to:	1631	Example: wait till there are no outstanding requests anymore:
243		1632
244	IO::AIO::poll_wait, IO::AIO::poll_cb	1633	IO::AIO::poll_wait, IO::AIO::poll_cb
245	while IO::AIO::nreqs;	1634	while IO::AIO::nreqs;
246		1635
		1636	=item IO::AIO::nready
		1637
		1638	Returns the number of requests currently in the ready state (not yet
		1639	executed).
		1640
247	=item IO::AIO::poll	1641	=item IO::AIO::npending
248		1642
249	Waits until some requests have been handled.	1643	Returns the number of requests currently in the pending state (executed,
250		1644	but not yet processed by poll_cb).
251	Strictly equivalent to:
252
253	IO::AIO::poll_wait, IO::AIO::poll_cb
254	if IO::AIO::nreqs;
255
256	=item IO::AIO::min_parallel $nthreads
257
258	Set the minimum number of AIO threads to C<$nthreads>. The default is
259	C<1>, which means a single asynchronous operation can be done at one time
260	(the number of outstanding operations, however, is unlimited).
261
262	It is recommended to keep the number of threads low, as some Linux
263	kernel versions will scale negatively with the number of threads (higher
264	parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32
265	threads should be fine.
266
267	Under normal circumstances you don't need to call this function, as this
268	module automatically starts some threads (the exact number might change,
269	and is currently 4).
270
271	=item IO::AIO::max_parallel $nthreads
272
273	Sets the maximum number of AIO threads to C<$nthreads>. If more than
274	the specified number of threads are currently running, kill them. This
275	function blocks until the limit is reached.
276
277	This module automatically runs C<max_parallel 0> at program end, to ensure
278	that all threads are killed and that there are no outstanding requests.
279
280	Under normal circumstances you don't need to call this function.
281
282	=item $oldnreqs = IO::AIO::max_outstanding $nreqs
283
284	Sets the maximum number of outstanding requests to C<$nreqs>. If you
285	try to queue up more than this number of requests, the caller will block until
286	some requests have been handled.
287
288	The default is very large, so normally there is no practical limit. If you
289	queue up many requests in a loop it it often improves speed if you set
290	this to a relatively low number, such as C<100>.
291
292	Under normal circumstances you don't need to call this function.
293		1645
294	=back	1646	=back
295		1647
		1648	=head3 MISCELLANEOUS FUNCTIONS
		1649
		1650	IO::AIO implements some functions that might be useful, but are not
		1651	asynchronous.
		1652
		1653	=over 4
		1654
		1655	=item IO::AIO::sendfile $ofh, $ifh, $offset, $count
		1656
		1657	Calls the C<eio_sendfile_sync> function, which is like C<aio_sendfile>,
		1658	but is blocking (this makes most sense if you know the input data is
		1659	likely cached already and the output filehandle is set to non-blocking
		1660	operations).
		1661
		1662	Returns the number of bytes copied, or C<-1> on error.
		1663
		1664	=item IO::AIO::fadvise $fh, $offset, $len, $advice
		1665
		1666	Simply calls the C<posix_fadvise> function (see its
		1667	manpage for details). The following advice constants are
		1668	avaiable: C<IO::AIO::FADV_NORMAL>, C<IO::AIO::FADV_SEQUENTIAL>,
		1669	C<IO::AIO::FADV_RANDOM>, C<IO::AIO::FADV_NOREUSE>,
		1670	C<IO::AIO::FADV_WILLNEED>, C<IO::AIO::FADV_DONTNEED>.
		1671
		1672	On systems that do not implement C<posix_fadvise>, this function returns
		1673	ENOSYS, otherwise the return value of C<posix_fadvise>.
		1674
		1675	=item IO::AIO::madvise $scalar, $offset, $len, $advice
		1676
		1677	Simply calls the C<posix_madvise> function (see its
		1678	manpage for details). The following advice constants are
		1679	avaiable: C<IO::AIO::MADV_NORMAL>, C<IO::AIO::MADV_SEQUENTIAL>,
		1680	C<IO::AIO::MADV_RANDOM>, C<IO::AIO::MADV_WILLNEED>, C<IO::AIO::MADV_DONTNEED>.
		1681
		1682	On systems that do not implement C<posix_madvise>, this function returns
		1683	ENOSYS, otherwise the return value of C<posix_madvise>.
		1684
		1685	=item IO::AIO::mprotect $scalar, $offset, $len, $protect
		1686
		1687	Simply calls the C<mprotect> function on the preferably AIO::mmap'ed
		1688	$scalar (see its manpage for details). The following protect
		1689	constants are avaiable: C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_READ>,
		1690	C<IO::AIO::PROT_WRITE>, C<IO::AIO::PROT_EXEC>.
		1691
		1692	On systems that do not implement C<mprotect>, this function returns
		1693	ENOSYS, otherwise the return value of C<mprotect>.
		1694
		1695	=item IO::AIO::mmap $scalar, $length, $prot, $flags, $fh[, $offset]
		1696
		1697	Memory-maps a file (or anonymous memory range) and attaches it to the
		1698	given C<$scalar>, which will act like a string scalar.
		1699
		1700	The only operations allowed on the scalar are C<substr>/C<vec> that don't
		1701	change the string length, and most read-only operations such as copying it
		1702	or searching it with regexes and so on.
		1703
		1704	Anything else is unsafe and will, at best, result in memory leaks.
		1705
		1706	The memory map associated with the C<$scalar> is automatically removed
		1707	when the C<$scalar> is destroyed, or when the C<IO::AIO::mmap> or
		1708	C<IO::AIO::munmap> functions are called.
		1709
		1710	This calls the C<mmap>(2) function internally. See your system's manual
		1711	page for details on the C<$length>, C<$prot> and C<$flags> parameters.
		1712
		1713	The C<$length> must be larger than zero and smaller than the actual
		1714	filesize.
		1715
		1716	C<$prot> is a combination of C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_EXEC>,
		1717	C<IO::AIO::PROT_READ> and/or C<IO::AIO::PROT_WRITE>,
		1718
		1719	C<$flags> can be a combination of C<IO::AIO::MAP_SHARED> or
		1720	C<IO::AIO::MAP_PRIVATE>, or a number of system-specific flags (when
		1721	not available, the are defined as 0): C<IO::AIO::MAP_ANONYMOUS>
		1722	(which is set to C<MAP_ANON> if your system only provides this
		1723	constant), C<IO::AIO::MAP_HUGETLB>, C<IO::AIO::MAP_LOCKED>,
		1724	C<IO::AIO::MAP_NORESERVE>, C<IO::AIO::MAP_POPULATE> or
		1725	C<IO::AIO::MAP_NONBLOCK>
		1726
		1727	If C<$fh> is C<undef>, then a file descriptor of C<-1> is passed.
		1728
		1729	C<$offset> is the offset from the start of the file - it generally must be
		1730	a multiple of C<IO::AIO::PAGESIZE> and defaults to C<0>.
		1731
		1732	Example:
		1733
		1734	use Digest::MD5;
		1735	use IO::AIO;
		1736
		1737	open my $fh, "<verybigfile"
		1738	or die "$!";
		1739
		1740	IO::AIO::mmap my $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh
		1741	or die "verybigfile: $!";
		1742
		1743	my $fast_md5 = md5 $data;
		1744
		1745	=item IO::AIO::munmap $scalar
		1746
		1747	Removes a previous mmap and undefines the C<$scalar>.
		1748
		1749	=item IO::AIO::munlock $scalar, $offset = 0, $length = undef
		1750
		1751	Calls the C<munlock> function, undoing the effects of a previous
		1752	C<aio_mlock> call (see its description for details).
		1753
		1754	=item IO::AIO::munlockall
		1755
		1756	Calls the C<munlockall> function.
		1757
		1758	On systems that do not implement C<munlockall>, this function returns
		1759	ENOSYS, otherwise the return value of C<munlockall>.
		1760
		1761	=back
		1762
296	=cut	1763	=cut
297		1764
298	# support function to convert a fd into a perl filehandle
299	sub _fd2fh {
300	return undef if $_[0] < 0;
301
302	# try to be perl5.6-compatible
303	local *AIO_FH;
304	open AIO_FH, "+<&=$_[0]"
305	or return undef;
306
307	*AIO_FH
308	}
309
310	min_parallel 4;	1765	min_parallel 8;
311		1766
312	END {	1767	END { flush }
313	max_parallel 0;
314	}
315		1768
316	1;	1769	1;
317		1770
		1771	=head1 EVENT LOOP INTEGRATION
		1772
		1773	It is recommended to use L<AnyEvent::AIO> to integrate IO::AIO
		1774	automatically into many event loops:
		1775
		1776	# AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...)
		1777	use AnyEvent::AIO;
		1778
		1779	You can also integrate IO::AIO manually into many event loops, here are
		1780	some examples of how to do this:
		1781
		1782	# EV integration
		1783	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
		1784
		1785	# Event integration
		1786	Event->io (fd => IO::AIO::poll_fileno,
		1787	poll => 'r',
		1788	cb => \&IO::AIO::poll_cb);
		1789
		1790	# Glib/Gtk2 integration
		1791	add_watch Glib::IO IO::AIO::poll_fileno,
		1792	in => sub { IO::AIO::poll_cb; 1 };
		1793
		1794	# Tk integration
		1795	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
		1796	readable => \&IO::AIO::poll_cb);
		1797
		1798	# Danga::Socket integration
		1799	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
		1800	\&IO::AIO::poll_cb);
		1801
		1802	=head2 FORK BEHAVIOUR
		1803
		1804	Usage of pthreads in a program changes the semantics of fork
		1805	considerably. Specifically, only async-safe functions can be called after
		1806	fork. Perl doesn't know about this, so in general, you cannot call fork
		1807	with defined behaviour in perl. IO::AIO uses pthreads, so this applies,
		1808	but many other extensions and (for inexplicable reasons) perl itself often
		1809	is linked against pthreads, so this limitation applies.
		1810
		1811	Some operating systems have extensions that allow safe use of fork, and
		1812	this module should do "the right thing" on those, and tries on others. At
		1813	the time of this writing (2011) only GNU/Linux supports these extensions
		1814	to POSIX.
		1815
		1816	=head2 MEMORY USAGE
		1817
		1818	Per-request usage:
		1819
		1820	Each aio request uses - depending on your architecture - around 100-200
		1821	bytes of memory. In addition, stat requests need a stat buffer (possibly
		1822	a few hundred bytes), readdir requires a result buffer and so on. Perl
		1823	scalars and other data passed into aio requests will also be locked and
		1824	will consume memory till the request has entered the done state.
		1825
		1826	This is not awfully much, so queuing lots of requests is not usually a
		1827	problem.
		1828
		1829	Per-thread usage:
		1830
		1831	In the execution phase, some aio requests require more memory for
		1832	temporary buffers, and each thread requires a stack and other data
		1833	structures (usually around 16k-128k, depending on the OS).
		1834
		1835	=head1 KNOWN BUGS
		1836
		1837	Known bugs will be fixed in the next release.
		1838
318	=head1 SEE ALSO	1839	=head1 SEE ALSO
319		1840
320	L<Coro>, L<Linux::AIO>.	1841	L<AnyEvent::AIO> for easy integration into event loops, L<Coro::AIO> for a
		1842	more natural syntax.
321		1843
322	=head1 AUTHOR	1844	=head1 AUTHOR
323		1845
324	Marc Lehmann <schmorp@schmorp.de>	1846	Marc Lehmann <schmorp@schmorp.de>
325	http://home.schmorp.de/	1847	http://home.schmorp.de/

Diff Legend

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