ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/IO-AIO/AIO.pm

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.62 by root, Sun Oct 22 21:13:47 2006 UTC vs.
Revision 1.263 by root, Tue Jul 12 20:46:33 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
…		…
18	};	19	};
19		20
20	# version 2+ has request and group objects	21	# version 2+ has request and group objects
21	use IO::AIO 2;	22	use IO::AIO 2;
22		23
		24	aioreq_pri 4; # give next request a very high priority
23	my $req = aio_unlink "/tmp/file", sub { };	25	my $req = aio_unlink "/tmp/file", sub { };
24	$req->cancel; # cancel request if still in queue	26	$req->cancel; # cancel request if still in queue
25		27
26	my $grp = aio_group sub { print "all stats done\n" };	28	my $grp = aio_group sub { print "all stats done\n" };
27	add $grp aio_stat "..." for ...;	29	add $grp aio_stat "..." for ...;
28		30
29	# AnyEvent integration
30	open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!";
31	my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb });
32
33	# Event integration
34	Event->io (fd => IO::AIO::poll_fileno,
35	poll => 'r',
36	cb => \&IO::AIO::poll_cb);
37
38	# Glib/Gtk2 integration
39	add_watch Glib::IO IO::AIO::poll_fileno,
40	in => sub { IO::AIO::poll_cb; 1 };
41
42	# Tk integration
43	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
44	readable => \&IO::AIO::poll_cb);
45
46	# Danga::Socket integration
47	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
48	\&IO::AIO::poll_cb);
49
50	=head1 DESCRIPTION	31	=head1 DESCRIPTION
51		32
52	This module implements asynchronous I/O using whatever means your	33	This module implements asynchronous I/O using whatever means your
53	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>).
54		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
55	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
56	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
57	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
58	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
59	aio functions available on many operating systems. However, they are often	57	functions available on many operating systems. However, they are often
60	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
61	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
62	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.
63		62
64	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,
65	currently not reentrant, so use appropriate locking yourself, always call	64	it is currently not reentrant in any way, so use appropriate locking
66	C<poll_cb> from within the same thread, or never call C<poll_cb> (or other	65	yourself, always call C<poll_cb> from within the same thread, or never
67	C<aio_> functions) recursively.	66	call C<poll_cb> (or other C<aio_> functions) recursively.
		67
		68	=head2 EXAMPLE
		69
		70	This is a simple example that uses the EV module and loads
		71	F</etc/passwd> asynchronously:
		72
		73	use EV;
		74	use IO::AIO;
		75
		76	# register the IO::AIO callback with EV
		77	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
		78
		79	# queue the request to open /etc/passwd
		80	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
		81	my $fh = shift
		82	or die "error while opening: $!";
		83
		84	# stat'ing filehandles is generally non-blocking
		85	my $size = -s $fh;
		86
		87	# queue a request to read the file
		88	my $contents;
		89	aio_read $fh, 0, $size, $contents, 0, sub {
		90	$_[0] == $size
		91	or die "short read: $!";
		92
		93	close $fh;
		94
		95	# file contents now in $contents
		96	print $contents;
		97
		98	# exit event loop and program
		99	EV::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
68		160
69	=cut	161	=cut
70		162
71	package IO::AIO;	163	package IO::AIO;
72		164
73	no warnings;	165	use Carp ();
74	use strict 'vars';	166
		167	use common::sense;
75		168
76	use base 'Exporter';	169	use base 'Exporter';
77		170
78	BEGIN {	171	BEGIN {
79	our $VERSION = '2.0';	172	our $VERSION = 4.34;
80		173
81	our @EXPORT = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat	174	our @AIO_REQ = qw(aio_sendfile aio_seek aio_read aio_write aio_open aio_close
82	aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink	175	aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx
83	aio_fsync aio_fdatasync aio_readahead aio_rename aio_link aio_move	176	aio_scandir aio_symlink aio_readlink aio_realpath aio_fcntl aio_ioctl
		177	aio_sync aio_fsync aio_syncfs aio_fdatasync aio_sync_file_range
		178	aio_pathsync aio_readahead aio_fiemap aio_allocate
		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
84	aio_group);	184	aio_wd);
85	our @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs);	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
86		195
87	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';	196	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';
88		197
89	require XSLoader;	198	require XSLoader;
90	XSLoader::load ("IO::AIO", $VERSION);	199	XSLoader::load ("IO::AIO", $VERSION);
91	}	200	}
92		201
93	=head1 FUNCTIONS	202	=head1 FUNCTIONS
94		203
95	=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_fcntl $fh, $cmd, $arg, $callback->($status)
		246	aio_ioctl $fh, $request, $buf, $callback->($status)
		247	aio_sync $callback->($status)
		248	aio_syncfs $fh, $callback->($status)
		249	aio_fsync $fh, $callback->($status)
		250	aio_fdatasync $fh, $callback->($status)
		251	aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		252	aio_pathsync $pathname, $callback->($status)
		253	aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		254	aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		255	aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
		256	aio_mlockall $flags, $callback->($status)
		257	aio_group $callback->(...)
		258	aio_nop $callback->()
		259
		260	$prev_pri = aioreq_pri [$pri]
		261	aioreq_nice $pri_adjust
		262
		263	IO::AIO::poll_wait
		264	IO::AIO::poll_cb
		265	IO::AIO::poll
		266	IO::AIO::flush
		267	IO::AIO::max_poll_reqs $nreqs
		268	IO::AIO::max_poll_time $seconds
		269	IO::AIO::min_parallel $nthreads
		270	IO::AIO::max_parallel $nthreads
		271	IO::AIO::max_idle $nthreads
		272	IO::AIO::idle_timeout $seconds
		273	IO::AIO::max_outstanding $maxreqs
		274	IO::AIO::nreqs
		275	IO::AIO::nready
		276	IO::AIO::npending
		277
		278	IO::AIO::sendfile $ofh, $ifh, $offset, $count
		279	IO::AIO::fadvise $fh, $offset, $len, $advice
		280	IO::AIO::mmap $scalar, $length, $prot, $flags[, $fh[, $offset]]
		281	IO::AIO::munmap $scalar
		282	IO::AIO::madvise $scalar, $offset, $length, $advice
		283	IO::AIO::mprotect $scalar, $offset, $length, $protect
		284	IO::AIO::munlock $scalar, $offset = 0, $length = undef
		285	IO::AIO::munlockall
		286
		287	=head2 API NOTES
96		288
97	All the C<aio_*> calls are more or less thin wrappers around the syscall	289	All the C<aio_*> calls are more or less thin wrappers around the syscall
98	with the same name (sans C<aio_>). The arguments are similar or identical,	290	with the same name (sans C<aio_>). The arguments are similar or identical,
99	and they all accept an additional (and optional) C<$callback> argument	291	and they all accept an additional (and optional) C<$callback> argument
100	which must be a code reference. This code reference will get called with	292	which must be a code reference. This code reference will be called after
101	the syscall return code (e.g. most syscalls return C<-1> on error, unlike	293	the syscall has been executed in an asynchronous fashion. The results
102	perl, which usually delivers "false") as it's sole argument when the given	294	of the request will be passed as arguments to the callback (and, if an
103	syscall has been executed asynchronously.	295	error occured, in C<$!>) - for most requests the syscall return code (e.g.
		296	most syscalls return C<-1> on error, unlike perl, which usually delivers
		297	"false").
		298
		299	Some requests (such as C<aio_readdir>) pass the actual results and
		300	communicate failures by passing C<undef>.
104		301
105	All functions expecting a filehandle keep a copy of the filehandle	302	All functions expecting a filehandle keep a copy of the filehandle
106	internally until the request has finished.	303	internally until the request has finished.
107		304
108	All requests return objects of type L<IO::AIO::REQ> that allow further	305	All functions return request objects of type L<IO::AIO::REQ> that allow
109	manipulation of those requests while they are in-flight.	306	further manipulation of those requests while they are in-flight.
110		307
111	The pathnames you pass to these routines I<must> be absolute and	308	The pathnames you pass to these routines I<should> be absolute. The
112	encoded in byte form. The reason for the former is that at the time the	309	reason for this is that at the time the request is being executed, the
113	request is being executed, the current working directory could have	310	current working directory could have changed. Alternatively, you can
114	changed. Alternatively, you can make sure that you never change the	311	make sure that you never change the current working directory anywhere
115	current working directory.	312	in the program and then use relative paths. You can also take advantage
		313	of IO::AIOs working directory abstraction, that lets you specify paths
		314	relative to some previously-opened "working directory object" - see the
		315	description of the C<IO::AIO::WD> class later in this document.
116		316
117	To encode pathnames to byte form, either make sure you either: a)	317	To encode pathnames as octets, either make sure you either: a) always pass
118	always pass in filenames you got from outside (command line, readdir	318	in filenames you got from outside (command line, readdir etc.) without
119	etc.), b) are ASCII or ISO 8859-1, c) use the Encode module and encode	319	tinkering, b) are in your native filesystem encoding, c) use the Encode
120	your pathnames to the locale (or other) encoding in effect in the user	320	module and encode your pathnames to the locale (or other) encoding in
121	environment, d) use Glib::filename_from_unicode on unicode filenames or e)	321	effect in the user environment, d) use Glib::filename_from_unicode on
122	use something else.	322	unicode filenames or e) use something else to ensure your scalar has the
		323	correct contents.
		324
		325	This works, btw. independent of the internal UTF-8 bit, which IO::AIO
		326	handles correctly whether it is set or not.
		327
		328	=head2 AIO REQUEST FUNCTIONS
123		329
124	=over 4	330	=over 4
125		331
		332	=item $prev_pri = aioreq_pri [$pri]
		333
		334	Returns the priority value that would be used for the next request and, if
		335	C<$pri> is given, sets the priority for the next aio request.
		336
		337	The default priority is C<0>, the minimum and maximum priorities are C<-4>
		338	and C<4>, respectively. Requests with higher priority will be serviced
		339	first.
		340
		341	The priority will be reset to C<0> after each call to one of the C<aio_*>
		342	functions.
		343
		344	Example: open a file with low priority, then read something from it with
		345	higher priority so the read request is serviced before other low priority
		346	open requests (potentially spamming the cache):
		347
		348	aioreq_pri -3;
		349	aio_open ..., sub {
		350	return unless $_[0];
		351
		352	aioreq_pri -2;
		353	aio_read $_[0], ..., sub {
		354	...
		355	};
		356	};
		357
		358
		359	=item aioreq_nice $pri_adjust
		360
		361	Similar to C<aioreq_pri>, but subtracts the given value from the current
		362	priority, so the effect is cumulative.
		363
		364
126	=item aio_open $pathname, $flags, $mode, $callback->($fh)	365	=item aio_open $pathname, $flags, $mode, $callback->($fh)
127		366
128	Asynchronously open or create a file and call the callback with a newly	367	Asynchronously open or create a file and call the callback with a newly
129	created filehandle for the file.	368	created filehandle for the file (or C<undef> in case of an error).
130		369
131	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,	370	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,
132	for an explanation.	371	for an explanation.
133		372
134	The C<$flags> argument is a bitmask. See the C<Fcntl> module for a	373	The C<$flags> argument is a bitmask. See the C<Fcntl> module for a
135	list. They are the same as used by C<sysopen>.	374	list. They are the same as used by C<sysopen>.
136		375
137	Likewise, C<$mode> specifies the mode of the newly created file, if it	376	Likewise, C<$mode> specifies the mode of the newly created file, if it
138	didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,	377	didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,
139	except that it is mandatory (i.e. use C<0> if you don't create new files,	378	except that it is mandatory (i.e. use C<0> if you don't create new files,
140	and C<0666> or C<0777> if you do).	379	and C<0666> or C<0777> if you do). Note that the C<$mode> will be modified
		380	by the umask in effect then the request is being executed, so better never
		381	change the umask.
141		382
142	Example:	383	Example:
143		384
144	aio_open "/etc/passwd", O_RDONLY, 0, sub {	385	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
145	if ($_[0]) {	386	if ($_[0]) {
146	print "open successful, fh is $_[0]\n";	387	print "open successful, fh is $_[0]\n";
147	...	388	...
148	} else {	389	} else {
149	die "open failed: $!\n";	390	die "open failed: $!\n";
150	}	391	}
151	};	392	};
152		393
		394	In addition to all the common open modes/flags (C<O_RDONLY>, C<O_WRONLY>,
		395	C<O_RDWR>, C<O_CREAT>, C<O_TRUNC>, C<O_EXCL> and C<O_APPEND>), the
		396	following POSIX and non-POSIX constants are available (missing ones on
		397	your system are, as usual, C<0>):
		398
		399	C<O_ASYNC>, C<O_DIRECT>, C<O_NOATIME>, C<O_CLOEXEC>, C<O_NOCTTY>, C<O_NOFOLLOW>,
		400	C<O_NONBLOCK>, C<O_EXEC>, C<O_SEARCH>, C<O_DIRECTORY>, C<O_DSYNC>,
		401	C<O_RSYNC>, C<O_SYNC>, C<O_PATH>, C<O_TMPFILE>, and C<O_TTY_INIT>.
		402
		403
153	=item aio_close $fh, $callback->($status)	404	=item aio_close $fh, $callback->($status)
154		405
155	Asynchronously close a file and call the callback with the result	406	Asynchronously close a file and call the callback with the result
156	code. I<WARNING:> although accepted, you should not pass in a perl	407	code.
157	filehandle here, as perl will likely close the file descriptor another
158	time when the filehandle is destroyed. Normally, you can safely call perls
159	C<close> or just let filehandles go out of scope.
160		408
161	This is supposed to be a bug in the API, so that might change. It's	409	Unfortunately, you can't do this to perl. Perl I<insists> very strongly on
162	therefore best to avoid this function.	410	closing the file descriptor associated with the filehandle itself.
		411
		412	Therefore, C<aio_close> will not close the filehandle - instead it will
		413	use dup2 to overwrite the file descriptor with the write-end of a pipe
		414	(the pipe fd will be created on demand and will be cached).
		415
		416	Or in other words: the file descriptor will be closed, but it will not be
		417	free for reuse until the perl filehandle is closed.
		418
		419	=cut
		420
		421	=item aio_seek $fh, $offset, $whence, $callback->($offs)
		422
		423	Seeks the filehandle to the new C<$offset>, similarly to perl's
		424	C<sysseek>. The C<$whence> can use the traditional values (C<0> for
		425	C<IO::AIO::SEEK_SET>, C<1> for C<IO::AIO::SEEK_CUR> or C<2> for
		426	C<IO::AIO::SEEK_END>).
		427
		428	The resulting absolute offset will be passed to the callback, or C<-1> in
		429	case of an error.
		430
		431	In theory, the C<$whence> constants could be different than the
		432	corresponding values from L<Fcntl>, but perl guarantees they are the same,
		433	so don't panic.
		434
		435	As a GNU/Linux (and maybe Solaris) extension, also the constants
		436	C<IO::AIO::SEEK_DATA> and C<IO::AIO::SEEK_HOLE> are available, if they
		437	could be found. No guarantees about suitability for use in C<aio_seek> or
		438	Perl's C<sysseek> can be made though, although I would naively assume they
		439	"just work".
163		440
164	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	441	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
165		442
166	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	443	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
167		444
168	Reads or writes C<length> bytes from the specified C<fh> and C<offset>	445	Reads or writes C<$length> bytes from or to the specified C<$fh> and
169	into the scalar given by C<data> and offset C<dataoffset> and calls the	446	C<$offset> into the scalar given by C<$data> and offset C<$dataoffset>
170	callback without the actual number of bytes read (or -1 on error, just	447	and calls the callback without the actual number of bytes read (or -1 on
171	like the syscall).	448	error, just like the syscall).
		449
		450	C<aio_read> will, like C<sysread>, shrink or grow the C<$data> scalar to
		451	offset plus the actual number of bytes read.
		452
		453	If C<$offset> is undefined, then the current file descriptor offset will
		454	be used (and updated), otherwise the file descriptor offset will not be
		455	changed by these calls.
		456
		457	If C<$length> is undefined in C<aio_write>, use the remaining length of
		458	C<$data>.
		459
		460	If C<$dataoffset> is less than zero, it will be counted from the end of
		461	C<$data>.
172		462
173	The C<$data> scalar I<MUST NOT> be modified in any way while the request	463	The C<$data> scalar I<MUST NOT> be modified in any way while the request
174	is outstanding. Modifying it can result in segfaults or WW3 (if the	464	is outstanding. Modifying it can result in segfaults or World War III (if
175	necessary/optional hardware is installed).	465	the necessary/optional hardware is installed).
176		466
177	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at	467	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at
178	offset C<0> within the scalar:	468	offset C<0> within the scalar:
179		469
180	aio_read $fh, 7, 15, $buffer, 0, sub {	470	aio_read $fh, 7, 15, $buffer, 0, sub {
181	$_[0] > 0 or die "read error: $!";	471	$_[0] > 0 or die "read error: $!";
182	print "read $_[0] bytes: <$buffer>\n";	472	print "read $_[0] bytes: <$buffer>\n";
183	};	473	};
184		474
185	=item aio_move $srcpath, $dstpath, $callback->($status)
186
187	[EXPERIMENTAL due to internal aio_group use]
188
189	Try to move the I<file> (directories not supported as either source or
190	destination) from C<$srcpath> to C<$dstpath> and call the callback with
191	the C<0> (error) or C<-1> ok.
192
193	This is a composite request that tries to rename(2) the file first. If
194	rename files with C<EXDEV>, it creates the destination file with mode 0200
195	and copies the contents of the source file into it using C<aio_sendfile>,
196	followed by restoring atime, mtime, access mode and uid/gid, in that
197	order, and unlinking the C<$srcpath>.
198
199	If an error occurs, the partial destination file will be unlinked, if
200	possible, except when setting atime, mtime, access mode and uid/gid, where
201	errors are being ignored.
202
203	=cut
204
205	sub aio_move($$$) {
206	my ($src, $dst, $cb) = @_;
207
208	my $grp = aio_group $cb;
209
210	add $grp aio_rename $src, $dst, sub {
211	if ($_[0] && $! == EXDEV) {
212	add $grp aio_open $src, O_RDONLY, 0, sub {
213	if (my $src_fh = $_[0]) {
214	my @stat = stat $src_fh;
215
216	add $grp aio_open $dst, O_WRONLY, 0200, sub {
217	if (my $dst_fh = $_[0]) {
218	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
219	close $src_fh;
220
221	if ($_[0] == $stat[7]) {
222	utime $stat[8], $stat[9], $dst;
223	chmod $stat[2] & 07777, $dst_fh;
224	chown $stat[4], $stat[5], $dst_fh;
225	close $dst_fh;
226
227	add $grp aio_unlink $src, sub {
228	$grp->result ($_[0]);
229	};
230	} else {
231	my $errno = $!;
232	add $grp aio_unlink $dst, sub {
233	$! = $errno;
234	$grp->result (-1);
235	};
236	}
237	};
238	} else {
239	$grp->result (-1);
240	}
241	},
242
243	} else {
244	$grp->result (-1);
245	}
246	};
247	} else {
248	$grp->result ($_[0]);
249	}
250	};
251
252	$grp
253	}
254		475
255	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)	476	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
256		477
257	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts	478	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
258	reading at byte offset C<$in_offset>, and starts writing at the current	479	reading at byte offset C<$in_offset>, and starts writing at the current
259	file offset of C<$out_fh>. Because of that, it is not safe to issue more	480	file offset of C<$out_fh>. Because of that, it is not safe to issue more
260	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each	481	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each
261	other.	482	other. The same C<$in_fh> works fine though, as this function does not
		483	move or use the file offset of C<$in_fh>.
262		484
		485	Please note that C<aio_sendfile> can read more bytes from C<$in_fh> than
		486	are written, and there is no way to find out how many more bytes have been
		487	read from C<aio_sendfile> alone, as C<aio_sendfile> only provides the
		488	number of bytes written to C<$out_fh>. Only if the result value equals
		489	C<$length> one can assume that C<$length> bytes have been read.
		490
		491	Unlike with other C<aio_> functions, it makes a lot of sense to use
		492	C<aio_sendfile> on non-blocking sockets, as long as one end (typically
		493	the C<$in_fh>) is a file - the file I/O will then be asynchronous, while
		494	the socket I/O will be non-blocking. Note, however, that you can run
		495	into a trap where C<aio_sendfile> reads some data with readahead, then
		496	fails to write all data, and when the socket is ready the next time, the
		497	data in the cache is already lost, forcing C<aio_sendfile> to again hit
		498	the disk. Explicit C<aio_read> + C<aio_write> let's you better control
		499	resource usage.
		500
263	This call tries to make use of a native C<sendfile> syscall to provide	501	This call tries to make use of a native C<sendfile>-like syscall to
264	zero-copy operation. For this to work, C<$out_fh> should refer to a	502	provide zero-copy operation. For this to work, C<$out_fh> should refer to
265	socket, and C<$in_fh> should refer to mmap'able file.	503	a socket, and C<$in_fh> should refer to an mmap'able file.
266		504
267	If the native sendfile call fails or is not implemented, it will be	505	If a native sendfile cannot be found or it fails with C<ENOSYS>,
268	emulated, so you can call C<aio_sendfile> on any type of filehandle	506	C<EINVAL>, C<ENOTSUP>, C<EOPNOTSUPP>, C<EAFNOSUPPORT>, C<EPROTOTYPE> or
		507	C<ENOTSOCK>, it will be emulated, so you can call C<aio_sendfile> on any
269	regardless of the limitations of the operating system.	508	type of filehandle regardless of the limitations of the operating system.
270		509
271	Please note, however, that C<aio_sendfile> can read more bytes from	510	As native sendfile syscalls (as practically any non-POSIX interface hacked
272	C<$in_fh> than are written, and there is no way to find out how many	511	together in a hurry to improve benchmark numbers) tend to be rather buggy
273	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only	512	on many systems, this implementation tries to work around some known bugs
274	provides the number of bytes written to C<$out_fh>. Only if the result	513	in Linux and FreeBSD kernels (probably others, too), but that might fail,
275	value equals C<$length> one can assume that C<$length> bytes have been	514	so you really really should check the return value of C<aio_sendfile> -
276	read.	515	fewer bytes than expected might have been transferred.
		516
277		517
278	=item aio_readahead $fh,$offset,$length, $callback->($retval)	518	=item aio_readahead $fh,$offset,$length, $callback->($retval)
279		519
280	C<aio_readahead> populates the page cache with data from a file so that	520	C<aio_readahead> populates the page cache with data from a file so that
281	subsequent reads from that file will not block on disk I/O. The C<$offset>	521	subsequent reads from that file will not block on disk I/O. The C<$offset>
…		…
284	whole pages, so that offset is effectively rounded down to a page boundary	524	whole pages, so that offset is effectively rounded down to a page boundary
285	and bytes are read up to the next page boundary greater than or equal to	525	and bytes are read up to the next page boundary greater than or equal to
286	(off-set+length). C<aio_readahead> does not read beyond the end of the	526	(off-set+length). C<aio_readahead> does not read beyond the end of the
287	file. The current file offset of the file is left unchanged.	527	file. The current file offset of the file is left unchanged.
288		528
289	If that syscall doesn't exist (likely if your OS isn't Linux) it will be	529	If that syscall doesn't exist (likely if your kernel isn't Linux) it will
290	emulated by simply reading the data, which would have a similar effect.	530	be emulated by simply reading the data, which would have a similar effect.
		531
291		532
292	=item aio_stat $fh_or_path, $callback->($status)	533	=item aio_stat $fh_or_path, $callback->($status)
293		534
294	=item aio_lstat $fh, $callback->($status)	535	=item aio_lstat $fh, $callback->($status)
295		536
…		…
301	for an explanation.	542	for an explanation.
302		543
303	Currently, the stats are always 64-bit-stats, i.e. instead of returning an	544	Currently, the stats are always 64-bit-stats, i.e. instead of returning an
304	error when stat'ing a large file, the results will be silently truncated	545	error when stat'ing a large file, the results will be silently truncated
305	unless perl itself is compiled with large file support.	546	unless perl itself is compiled with large file support.
		547
		548	To help interpret the mode and dev/rdev stat values, IO::AIO offers the
		549	following constants and functions (if not implemented, the constants will
		550	be C<0> and the functions will either C<croak> or fall back on traditional
		551	behaviour).
		552
		553	C<S_IFMT>, C<S_IFIFO>, C<S_IFCHR>, C<S_IFBLK>, C<S_IFLNK>, C<S_IFREG>,
		554	C<S_IFDIR>, C<S_IFWHT>, C<S_IFSOCK>, C<IO::AIO::major $dev_t>,
		555	C<IO::AIO::minor $dev_t>, C<IO::AIO::makedev $major, $minor>.
306		556
307	Example: Print the length of F</etc/passwd>:	557	Example: Print the length of F</etc/passwd>:
308		558
309	aio_stat "/etc/passwd", sub {	559	aio_stat "/etc/passwd", sub {
310	$_[0] and die "stat failed: $!";	560	$_[0] and die "stat failed: $!";
311	print "size is ", -s _, "\n";	561	print "size is ", -s _, "\n";
312	};	562	};
313		563
		564
		565	=item aio_statvfs $fh_or_path, $callback->($statvfs)
		566
		567	Works like the POSIX C<statvfs> or C<fstatvfs> syscalls, depending on
		568	whether a file handle or path was passed.
		569
		570	On success, the callback is passed a hash reference with the following
		571	members: C<bsize>, C<frsize>, C<blocks>, C<bfree>, C<bavail>, C<files>,
		572	C<ffree>, C<favail>, C<fsid>, C<flag> and C<namemax>. On failure, C<undef>
		573	is passed.
		574
		575	The following POSIX IO::AIO::ST_* constants are defined: C<ST_RDONLY> and
		576	C<ST_NOSUID>.
		577
		578	The following non-POSIX IO::AIO::ST_* flag masks are defined to
		579	their correct value when available, or to C<0> on systems that do
		580	not support them: C<ST_NODEV>, C<ST_NOEXEC>, C<ST_SYNCHRONOUS>,
		581	C<ST_MANDLOCK>, C<ST_WRITE>, C<ST_APPEND>, C<ST_IMMUTABLE>, C<ST_NOATIME>,
		582	C<ST_NODIRATIME> and C<ST_RELATIME>.
		583
		584	Example: stat C</wd> and dump out the data if successful.
		585
		586	aio_statvfs "/wd", sub {
		587	my $f = $_[0]
		588	or die "statvfs: $!";
		589
		590	use Data::Dumper;
		591	say Dumper $f;
		592	};
		593
		594	# result:
		595	{
		596	bsize => 1024,
		597	bfree => 4333064312,
		598	blocks => 10253828096,
		599	files => 2050765568,
		600	flag => 4096,
		601	favail => 2042092649,
		602	bavail => 4333064312,
		603	ffree => 2042092649,
		604	namemax => 255,
		605	frsize => 1024,
		606	fsid => 1810
		607	}
		608
		609	Here is a (likely partial - send me updates!) list of fsid values used by
		610	Linux - it is safe to hardcode these when C<$^O> is C<linux>:
		611
		612	0x0000adf5 adfs
		613	0x0000adff affs
		614	0x5346414f afs
		615	0x09041934 anon-inode filesystem
		616	0x00000187 autofs
		617	0x42465331 befs
		618	0x1badface bfs
		619	0x42494e4d binfmt_misc
		620	0x9123683e btrfs
		621	0x0027e0eb cgroupfs
		622	0xff534d42 cifs
		623	0x73757245 coda
		624	0x012ff7b7 coh
		625	0x28cd3d45 cramfs
		626	0x453dcd28 cramfs-wend (wrong endianness)
		627	0x64626720 debugfs
		628	0x00001373 devfs
		629	0x00001cd1 devpts
		630	0x0000f15f ecryptfs
		631	0x00414a53 efs
		632	0x0000137d ext
		633	0x0000ef53 ext2/ext3/ext4
		634	0x0000ef51 ext2
		635	0xf2f52010 f2fs
		636	0x00004006 fat
		637	0x65735546 fuseblk
		638	0x65735543 fusectl
		639	0x0bad1dea futexfs
		640	0x01161970 gfs2
		641	0x47504653 gpfs
		642	0x00004244 hfs
		643	0xf995e849 hpfs
		644	0x00c0ffee hostfs
		645	0x958458f6 hugetlbfs
		646	0x2bad1dea inotifyfs
		647	0x00009660 isofs
		648	0x000072b6 jffs2
		649	0x3153464a jfs
		650	0x6b414653 k-afs
		651	0x0bd00bd0 lustre
		652	0x0000137f minix
		653	0x0000138f minix 30 char names
		654	0x00002468 minix v2
		655	0x00002478 minix v2 30 char names
		656	0x00004d5a minix v3
		657	0x19800202 mqueue
		658	0x00004d44 msdos
		659	0x0000564c novell
		660	0x00006969 nfs
		661	0x6e667364 nfsd
		662	0x00003434 nilfs
		663	0x5346544e ntfs
		664	0x00009fa1 openprom
		665	0x7461636F ocfs2
		666	0x00009fa0 proc
		667	0x6165676c pstorefs
		668	0x0000002f qnx4
		669	0x68191122 qnx6
		670	0x858458f6 ramfs
		671	0x52654973 reiserfs
		672	0x00007275 romfs
		673	0x67596969 rpc_pipefs
		674	0x73636673 securityfs
		675	0xf97cff8c selinux
		676	0x0000517b smb
		677	0x534f434b sockfs
		678	0x73717368 squashfs
		679	0x62656572 sysfs
		680	0x012ff7b6 sysv2
		681	0x012ff7b5 sysv4
		682	0x01021994 tmpfs
		683	0x15013346 udf
		684	0x00011954 ufs
		685	0x54190100 ufs byteswapped
		686	0x00009fa2 usbdevfs
		687	0x01021997 v9fs
		688	0xa501fcf5 vxfs
		689	0xabba1974 xenfs
		690	0x012ff7b4 xenix
		691	0x58465342 xfs
		692	0x012fd16d xia
		693
		694	=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
		695
		696	Works like perl's C<utime> function (including the special case of $atime
		697	and $mtime being undef). Fractional times are supported if the underlying
		698	syscalls support them.
		699
		700	When called with a pathname, uses utimes(2) if available, otherwise
		701	utime(2). If called on a file descriptor, uses futimes(2) if available,
		702	otherwise returns ENOSYS, so this is not portable.
		703
		704	Examples:
		705
		706	# set atime and mtime to current time (basically touch(1)):
		707	aio_utime "path", undef, undef;
		708	# set atime to current time and mtime to beginning of the epoch:
		709	aio_utime "path", time, undef; # undef==0
		710
		711
		712	=item aio_chown $fh_or_path, $uid, $gid, $callback->($status)
		713
		714	Works like perl's C<chown> function, except that C<undef> for either $uid
		715	or $gid is being interpreted as "do not change" (but -1 can also be used).
		716
		717	Examples:
		718
		719	# same as "chown root path" in the shell:
		720	aio_chown "path", 0, -1;
		721	# same as above:
		722	aio_chown "path", 0, undef;
		723
		724
		725	=item aio_truncate $fh_or_path, $offset, $callback->($status)
		726
		727	Works like truncate(2) or ftruncate(2).
		728
		729
		730	=item aio_allocate $fh, $mode, $offset, $len, $callback->($status)
		731
		732	Allocates or frees disk space according to the C<$mode> argument. See the
		733	linux C<fallocate> documentation for details.
		734
		735	C<$mode> is usually C<0> or C<IO::AIO::FALLOC_FL_KEEP_SIZE> to allocate
		736	space, or C<IO::AIO::FALLOC_FL_PUNCH_HOLE | IO::AIO::FALLOC_FL_KEEP_SIZE>,
		737	to deallocate a file range.
		738
		739	IO::AIO also supports C<FALLOC_FL_COLLAPSE_RANGE>, to remove a range
		740	(without leaving a hole) and C<FALLOC_FL_ZERO_RANGE>, to zero a range (see
		741	your L<fallocate(2)> manpage).
		742
		743	The file system block size used by C<fallocate> is presumably the
		744	C<f_bsize> returned by C<statvfs>.
		745
		746	If C<fallocate> isn't available or cannot be emulated (currently no
		747	emulation will be attempted), passes C<-1> and sets C<$!> to C<ENOSYS>.
		748
		749
		750	=item aio_chmod $fh_or_path, $mode, $callback->($status)
		751
		752	Works like perl's C<chmod> function.
		753
		754
314	=item aio_unlink $pathname, $callback->($status)	755	=item aio_unlink $pathname, $callback->($status)
315		756
316	Asynchronously unlink (delete) a file and call the callback with the	757	Asynchronously unlink (delete) a file and call the callback with the
317	result code.	758	result code.
318		759
		760
		761	=item aio_mknod $pathname, $mode, $dev, $callback->($status)
		762
		763	[EXPERIMENTAL]
		764
		765	Asynchronously create a device node (or fifo). See mknod(2).
		766
		767	The only (POSIX-) portable way of calling this function is:
		768
		769	aio_mknod $pathname, IO::AIO::S_IFIFO | $mode, 0, sub { ...
		770
		771	See C<aio_stat> for info about some potentially helpful extra constants
		772	and functions.
		773
319	=item aio_link $srcpath, $dstpath, $callback->($status)	774	=item aio_link $srcpath, $dstpath, $callback->($status)
320		775
321	Asynchronously create a new link to the existing object at C<$srcpath> at	776	Asynchronously create a new link to the existing object at C<$srcpath> at
322	the path C<$dstpath> and call the callback with the result code.	777	the path C<$dstpath> and call the callback with the result code.
323		778
		779
324	=item aio_symlink $srcpath, $dstpath, $callback->($status)	780	=item aio_symlink $srcpath, $dstpath, $callback->($status)
325		781
326	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at	782	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at
327	the path C<$dstpath> and call the callback with the result code.	783	the path C<$dstpath> and call the callback with the result code.
328		784
		785
		786	=item aio_readlink $pathname, $callback->($link)
		787
		788	Asynchronously read the symlink specified by C<$path> and pass it to
		789	the callback. If an error occurs, nothing or undef gets passed to the
		790	callback.
		791
		792
		793	=item aio_realpath $pathname, $callback->($path)
		794
		795	Asynchronously make the path absolute and resolve any symlinks in
		796	C<$path>. The resulting path only consists of directories (same as
		797	L<Cwd::realpath>).
		798
		799	This request can be used to get the absolute path of the current working
		800	directory by passing it a path of F<.> (a single dot).
		801
		802
329	=item aio_rename $srcpath, $dstpath, $callback->($status)	803	=item aio_rename $srcpath, $dstpath, $callback->($status)
330		804
331	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as	805	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as
332	rename(2) and call the callback with the result code.	806	rename(2) and call the callback with the result code.
333		807
		808	On systems that support the AIO::WD working directory abstraction
		809	natively, the case C<[$wd, "."]> as C<$srcpath> is specialcased - instead
		810	of failing, C<rename> is called on the absolute path of C<$wd>.
		811
		812
		813	=item aio_mkdir $pathname, $mode, $callback->($status)
		814
		815	Asynchronously mkdir (create) a directory and call the callback with
		816	the result code. C<$mode> will be modified by the umask at the time the
		817	request is executed, so do not change your umask.
		818
		819
334	=item aio_rmdir $pathname, $callback->($status)	820	=item aio_rmdir $pathname, $callback->($status)
335		821
336	Asynchronously rmdir (delete) a directory and call the callback with the	822	Asynchronously rmdir (delete) a directory and call the callback with the
337	result code.	823	result code.
		824
		825	On systems that support the AIO::WD working directory abstraction
		826	natively, the case C<[$wd, "."]> is specialcased - instead of failing,
		827	C<rmdir> is called on the absolute path of C<$wd>.
		828
338		829
339	=item aio_readdir $pathname, $callback->($entries)	830	=item aio_readdir $pathname, $callback->($entries)
340		831
341	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire	832	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
342	directory (i.e. opendir + readdir + closedir). The entries will not be	833	directory (i.e. opendir + readdir + closedir). The entries will not be
343	sorted, and will B<NOT> include the C<.> and C<..> entries.	834	sorted, and will B<NOT> include the C<.> and C<..> entries.
344		835
345	The callback a single argument which is either C<undef> or an array-ref	836	The callback is passed a single argument which is either C<undef> or an
346	with the filenames.	837	array-ref with the filenames.
347		838
		839
		840	=item aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		841
		842	Quite similar to C<aio_readdir>, but the C<$flags> argument allows one to
		843	tune behaviour and output format. In case of an error, C<$entries> will be
		844	C<undef>.
		845
		846	The flags are a combination of the following constants, ORed together (the
		847	flags will also be passed to the callback, possibly modified):
		848
		849	=over 4
		850
		851	=item IO::AIO::READDIR_DENTS
		852
		853	When this flag is off, then the callback gets an arrayref consisting of
		854	names only (as with C<aio_readdir>), otherwise it gets an arrayref with
		855	C<[$name, $type, $inode]> arrayrefs, each describing a single directory
		856	entry in more detail.
		857
		858	C<$name> is the name of the entry.
		859
		860	C<$type> is one of the C<IO::AIO::DT_xxx> constants:
		861
		862	C<IO::AIO::DT_UNKNOWN>, C<IO::AIO::DT_FIFO>, C<IO::AIO::DT_CHR>, C<IO::AIO::DT_DIR>,
		863	C<IO::AIO::DT_BLK>, C<IO::AIO::DT_REG>, C<IO::AIO::DT_LNK>, C<IO::AIO::DT_SOCK>,
		864	C<IO::AIO::DT_WHT>.
		865
		866	C<IO::AIO::DT_UNKNOWN> means just that: readdir does not know. If you need to
		867	know, you have to run stat yourself. Also, for speed reasons, the C<$type>
		868	scalars are read-only: you can not modify them.
		869
		870	C<$inode> is the inode number (which might not be exact on systems with 64
		871	bit inode numbers and 32 bit perls). This field has unspecified content on
		872	systems that do not deliver the inode information.
		873
		874	=item IO::AIO::READDIR_DIRS_FIRST
		875
		876	When this flag is set, then the names will be returned in an order where
		877	likely directories come first, in optimal stat order. This is useful when
		878	you need to quickly find directories, or you want to find all directories
		879	while avoiding to stat() each entry.
		880
		881	If the system returns type information in readdir, then this is used
		882	to find directories directly. Otherwise, likely directories are names
		883	beginning with ".", or otherwise names with no dots, of which names with
		884	short names are tried first.
		885
		886	=item IO::AIO::READDIR_STAT_ORDER
		887
		888	When this flag is set, then the names will be returned in an order
		889	suitable for stat()'ing each one. That is, when you plan to stat()
		890	all files in the given directory, then the returned order will likely
		891	be fastest.
		892
		893	If both this flag and C<IO::AIO::READDIR_DIRS_FIRST> are specified, then
		894	the likely dirs come first, resulting in a less optimal stat order.
		895
		896	=item IO::AIO::READDIR_FOUND_UNKNOWN
		897
		898	This flag should not be set when calling C<aio_readdirx>. Instead, it
		899	is being set by C<aio_readdirx>, when any of the C<$type>'s found were
		900	C<IO::AIO::DT_UNKNOWN>. The absence of this flag therefore indicates that all
		901	C<$type>'s are known, which can be used to speed up some algorithms.
		902
		903	=back
		904
		905
		906	=item aio_load $pathname, $data, $callback->($status)
		907
		908	This is a composite request that tries to fully load the given file into
		909	memory. Status is the same as with aio_read.
		910
		911	=cut
		912
		913	sub aio_load($$;$) {
		914	my ($path, undef, $cb) = @_;
		915	my $data = \$_[1];
		916
		917	my $pri = aioreq_pri;
		918	my $grp = aio_group $cb;
		919
		920	aioreq_pri $pri;
		921	add $grp aio_open $path, O_RDONLY, 0, sub {
		922	my $fh = shift
		923	or return $grp->result (-1);
		924
		925	aioreq_pri $pri;
		926	add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub {
		927	$grp->result ($_[0]);
		928	};
		929	};
		930
		931	$grp
		932	}
		933
		934	=item aio_copy $srcpath, $dstpath, $callback->($status)
		935
		936	Try to copy the I<file> (directories not supported as either source or
		937	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		938	a status of C<0> (ok) or C<-1> (error, see C<$!>).
		939
		940	This is a composite request that creates the destination file with
		941	mode 0200 and copies the contents of the source file into it using
		942	C<aio_sendfile>, followed by restoring atime, mtime, access mode and
		943	uid/gid, in that order.
		944
		945	If an error occurs, the partial destination file will be unlinked, if
		946	possible, except when setting atime, mtime, access mode and uid/gid, where
		947	errors are being ignored.
		948
		949	=cut
		950
		951	sub aio_copy($$;$) {
		952	my ($src, $dst, $cb) = @_;
		953
		954	my $pri = aioreq_pri;
		955	my $grp = aio_group $cb;
		956
		957	aioreq_pri $pri;
		958	add $grp aio_open $src, O_RDONLY, 0, sub {
		959	if (my $src_fh = $_[0]) {
		960	my @stat = stat $src_fh; # hmm, might block over nfs?
		961
		962	aioreq_pri $pri;
		963	add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {
		964	if (my $dst_fh = $_[0]) {
		965	aioreq_pri $pri;
		966	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
		967	if ($_[0] == $stat[7]) {
		968	$grp->result (0);
		969	close $src_fh;
		970
		971	my $ch = sub {
		972	aioreq_pri $pri;
		973	add $grp aio_chmod $dst_fh, $stat[2] & 07777, sub {
		974	aioreq_pri $pri;
		975	add $grp aio_chown $dst_fh, $stat[4], $stat[5], sub {
		976	aioreq_pri $pri;
		977	add $grp aio_close $dst_fh;
		978	}
		979	};
		980	};
		981
		982	aioreq_pri $pri;
		983	add $grp aio_utime $dst_fh, $stat[8], $stat[9], sub {
		984	if ($_[0] < 0 && $! == ENOSYS) {
		985	aioreq_pri $pri;
		986	add $grp aio_utime $dst, $stat[8], $stat[9], $ch;
		987	} else {
		988	$ch->();
		989	}
		990	};
		991	} else {
		992	$grp->result (-1);
		993	close $src_fh;
		994	close $dst_fh;
		995
		996	aioreq $pri;
		997	add $grp aio_unlink $dst;
		998	}
		999	};
		1000	} else {
		1001	$grp->result (-1);
		1002	}
		1003	},
		1004
		1005	} else {
		1006	$grp->result (-1);
		1007	}
		1008	};
		1009
		1010	$grp
		1011	}
		1012
		1013	=item aio_move $srcpath, $dstpath, $callback->($status)
		1014
		1015	Try to move the I<file> (directories not supported as either source or
		1016	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		1017	a status of C<0> (ok) or C<-1> (error, see C<$!>).
		1018
		1019	This is a composite request that tries to rename(2) the file first; if
		1020	rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if
		1021	that is successful, unlinks the C<$srcpath>.
		1022
		1023	=cut
		1024
		1025	sub aio_move($$;$) {
		1026	my ($src, $dst, $cb) = @_;
		1027
		1028	my $pri = aioreq_pri;
		1029	my $grp = aio_group $cb;
		1030
		1031	aioreq_pri $pri;
		1032	add $grp aio_rename $src, $dst, sub {
		1033	if ($_[0] && $! == EXDEV) {
		1034	aioreq_pri $pri;
		1035	add $grp aio_copy $src, $dst, sub {
		1036	$grp->result ($_[0]);
		1037
		1038	unless ($_[0]) {
		1039	aioreq_pri $pri;
		1040	add $grp aio_unlink $src;
		1041	}
		1042	};
		1043	} else {
		1044	$grp->result ($_[0]);
		1045	}
		1046	};
		1047
		1048	$grp
		1049	}
		1050
348	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)	1051	=item aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs)
349
350	[EXPERIMENTAL due to internal aio_group use]
351		1052
352	Scans a directory (similar to C<aio_readdir>) but additionally tries to	1053	Scans a directory (similar to C<aio_readdir>) but additionally tries to
353	separate the entries of directory C<$path> into two sets of names, ones	1054	efficiently separate the entries of directory C<$path> into two sets of
354	you can recurse into (directories or links to them), and ones you cannot	1055	names, directories you can recurse into (directories), and ones you cannot
355	recurse into (everything else).	1056	recurse into (everything else, including symlinks to directories).
356		1057
357	C<aio_scandir> is a composite request that creates of many sub requests_	1058	C<aio_scandir> is a composite request that creates of many sub requests_
358	C<$maxreq> specifies the maximum number of outstanding aio requests that	1059	C<$maxreq> specifies the maximum number of outstanding aio requests that
359	this function generates. If it is C<< <= 0 >>, then a suitable default	1060	this function generates. If it is C<< <= 0 >>, then a suitable default
360	will be chosen (currently 6).	1061	will be chosen (currently 4).
361		1062
362	On error, the callback is called without arguments, otherwise it receives	1063	On error, the callback is called without arguments, otherwise it receives
363	two array-refs with path-relative entry names.	1064	two array-refs with path-relative entry names.
364		1065
365	Example:	1066	Example:
…		…
372		1073
373	Implementation notes.	1074	Implementation notes.
374		1075
375	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.	1076	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.
376		1077
		1078	If readdir returns file type information, then this is used directly to
		1079	find directories.
		1080
377	After reading the directory, the modification time, size etc. of the	1081	Otherwise, after reading the directory, the modification time, size etc.
378	directory before and after the readdir is checked, and if they match (and	1082	of the directory before and after the readdir is checked, and if they
379	isn't the current time), the link count will be used to decide how many	1083	match (and isn't the current time), the link count will be used to decide
380	entries are directories (if >= 2). Otherwise, no knowledge of the number	1084	how many entries are directories (if >= 2). Otherwise, no knowledge of the
381	of subdirectories will be assumed.	1085	number of subdirectories will be assumed.
382		1086
383	Then entries will be sorted into likely directories (everything without	1087	Then entries will be sorted into likely directories a non-initial dot
384	a non-initial dot currently) and likely non-directories (everything	1088	currently) and likely non-directories (see C<aio_readdirx>). Then every
385	else). Then every entry plus an appended C</.> will be C<stat>'ed,	1089	entry plus an appended C</.> will be C<stat>'ed, likely directories first,
386	likely directories first. If that succeeds, it assumes that the entry	1090	in order of their inode numbers. If that succeeds, it assumes that the
387	is a directory or a symlink to directory (which will be checked	1091	entry is a directory or a symlink to directory (which will be checked
388	seperately). This is often faster than stat'ing the entry itself because	1092	separately). This is often faster than stat'ing the entry itself because
389	filesystems might detect the type of the entry without reading the inode	1093	filesystems might detect the type of the entry without reading the inode
390	data (e.g. ext2fs filetype feature).	1094	data (e.g. ext2fs filetype feature), even on systems that cannot return
		1095	the filetype information on readdir.
391		1096
392	If the known number of directories (link count - 2) has been reached, the	1097	If the known number of directories (link count - 2) has been reached, the
393	rest of the entries is assumed to be non-directories.	1098	rest of the entries is assumed to be non-directories.
394		1099
395	This only works with certainty on POSIX (= UNIX) filesystems, which	1100	This only works with certainty on POSIX (= UNIX) filesystems, which
…		…
399	as those tend to return 0 or 1 as link counts, which disables the	1104	as those tend to return 0 or 1 as link counts, which disables the
400	directory counting heuristic.	1105	directory counting heuristic.
401		1106
402	=cut	1107	=cut
403		1108
404	sub aio_scandir($$$) {	1109	sub aio_scandir($$;$) {
405	my ($path, $maxreq, $cb) = @_;	1110	my ($path, $maxreq, $cb) = @_;
406		1111
		1112	my $pri = aioreq_pri;
		1113
407	my $grp = aio_group $cb;	1114	my $grp = aio_group $cb;
408		1115
409	$maxreq = 6 if $maxreq <= 0;	1116	$maxreq = 4 if $maxreq <= 0;
410		1117
411	# stat once	1118	# get a wd object
		1119	aioreq_pri $pri;
412	add $grp aio_stat $path, sub {	1120	add $grp aio_wd $path, sub {
		1121	$_[0]
		1122	or return $grp->result ();
		1123
		1124	my $wd = [shift, "."];
		1125
		1126	# stat once
		1127	aioreq_pri $pri;
		1128	add $grp aio_stat $wd, sub {
413	return $grp->result () if $_[0];	1129	return $grp->result () if $_[0];
414	my $now = time;	1130	my $now = time;
415	my $hash1 = join ":", (stat _)[0,1,3,7,9];	1131	my $hash1 = join ":", (stat _)[0,1,3,7,9];
416		1132
417	# read the directory entries	1133	# read the directory entries
418	add $grp aio_readdir $path, sub {	1134	aioreq_pri $pri;
		1135	add $grp aio_readdirx $wd, READDIR_DIRS_FIRST, sub {
419	my $entries = shift	1136	my $entries = shift
420	or return $grp->result ();	1137	or return $grp->result ();
421		1138
422	# stat the dir another time	1139	# stat the dir another time
		1140	aioreq_pri $pri;
423	add $grp aio_stat $path, sub {	1141	add $grp aio_stat $wd, sub {
424	my $hash2 = join ":", (stat _)[0,1,3,7,9];	1142	my $hash2 = join ":", (stat _)[0,1,3,7,9];
425		1143
426	my $ndirs;	1144	my $ndirs;
427		1145
428	# take the slow route if anything looks fishy	1146	# take the slow route if anything looks fishy
429	if ($hash1 ne $hash2 or (stat _)[9] == $now) {	1147	if ($hash1 ne $hash2 or (stat _)[9] == $now) {
430	$ndirs = -1;	1148	$ndirs = -1;
431	} else {	1149	} else {
432	# if nlink == 2, we are finished	1150	# if nlink == 2, we are finished
433	# on non-posix-fs's, we rely on nlink < 2	1151	# for non-posix-fs's, we rely on nlink < 2
434	$ndirs = (stat _)[3] - 2	1152	$ndirs = (stat _)[3] - 2
435	or return $grp->result ([], $entries);	1153	or return $grp->result ([], $entries);
436	}	1154	}
437		1155
438	# sort into likely dirs and likely nondirs
439	# dirs == files without ".", short entries first
440	$entries = [map $_->[0],
441	sort { $b->[1] cmp $a->[1] }
442	map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],
443	@$entries];
444
445	my (@dirs, @nondirs);	1156	my (@dirs, @nondirs);
446		1157
447	my ($statcb, $schedcb);
448	my $nreq = 0;
449
450	my $statgrp = add $grp aio_group;	1158	my $statgrp = add $grp aio_group sub {
451
452	$schedcb = sub {
453	if (@$entries) {
454	if ($nreq < $maxreq) {
455	my $ent = pop @$entries;
456	$nreq++;
457	add $statgrp aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) };
458	}
459	} elsif (!$nreq) {
460	# finished
461	$statgrp->cancel;
462	undef $statcb;
463	undef $schedcb;
464	$grp->result (\@dirs, \@nondirs);	1159	$grp->result (\@dirs, \@nondirs);
465	}	1160	};
		1161
		1162	limit $statgrp $maxreq;
		1163	feed $statgrp sub {
		1164	return unless @$entries;
		1165	my $entry = shift @$entries;
		1166
		1167	aioreq_pri $pri;
		1168	$wd->[1] = "$entry/.";
		1169	add $statgrp aio_stat $wd, sub {
		1170	if ($_[0] < 0) {
		1171	push @nondirs, $entry;
		1172	} else {
		1173	# need to check for real directory
		1174	aioreq_pri $pri;
		1175	$wd->[1] = $entry;
		1176	add $statgrp aio_lstat $wd, sub {
		1177	if (-d _) {
		1178	push @dirs, $entry;
		1179
		1180	unless (--$ndirs) {
		1181	push @nondirs, @$entries;
		1182	feed $statgrp;
		1183	}
		1184	} else {
		1185	push @nondirs, $entry;
		1186	}
		1187	}
		1188	}
		1189	};
		1190	};
466	};	1191	};
467	$statcb = sub {
468	my ($status, $entry) = @_;
469
470	if ($status < 0) {
471	$nreq--;
472	push @nondirs, $entry;
473	&$schedcb;
474	} else {
475	# need to check for real directory
476	add $grp aio_lstat "$path/$entry", sub {
477	$nreq--;
478
479	if (-d _) {
480	push @dirs, $entry;
481
482	if (!--$ndirs) {
483	push @nondirs, @$entries;
484	$entries = [];
485	}
486	} else {
487	push @nondirs, $entry;
488	}
489
490	&$schedcb;
491	}
492	}
493	};
494
495	&$schedcb while @$entries && $nreq < $maxreq;
496	};	1192	};
497	};	1193	};
498	};	1194	};
499		1195
500	$grp	1196	$grp
501	}	1197	}
502		1198
		1199	=item aio_rmtree $pathname, $callback->($status)
		1200
		1201	Delete a directory tree starting (and including) C<$path>, return the
		1202	status of the final C<rmdir> only. This is a composite request that
		1203	uses C<aio_scandir> to recurse into and rmdir directories, and unlink
		1204	everything else.
		1205
		1206	=cut
		1207
		1208	sub aio_rmtree;
		1209	sub aio_rmtree($;$) {
		1210	my ($path, $cb) = @_;
		1211
		1212	my $pri = aioreq_pri;
		1213	my $grp = aio_group $cb;
		1214
		1215	aioreq_pri $pri;
		1216	add $grp aio_scandir $path, 0, sub {
		1217	my ($dirs, $nondirs) = @_;
		1218
		1219	my $dirgrp = aio_group sub {
		1220	add $grp aio_rmdir $path, sub {
		1221	$grp->result ($_[0]);
		1222	};
		1223	};
		1224
		1225	(aioreq_pri $pri), add $dirgrp aio_rmtree "$path/$_" for @$dirs;
		1226	(aioreq_pri $pri), add $dirgrp aio_unlink "$path/$_" for @$nondirs;
		1227
		1228	add $grp $dirgrp;
		1229	};
		1230
		1231	$grp
		1232	}
		1233
		1234	=item aio_fcntl $fh, $cmd, $arg, $callback->($status)
		1235
		1236	=item aio_ioctl $fh, $request, $buf, $callback->($status)
		1237
		1238	These work just like the C<fcntl> and C<ioctl> built-in functions, except
		1239	they execute asynchronously and pass the return value to the callback.
		1240
		1241	Both calls can be used for a lot of things, some of which make more sense
		1242	to run asynchronously in their own thread, while some others make less
		1243	sense. For example, calls that block waiting for external events, such
		1244	as locking, will also lock down an I/O thread while it is waiting, which
		1245	can deadlock the whole I/O system. At the same time, there might be no
		1246	alternative to using a thread to wait.
		1247
		1248	So in general, you should only use these calls for things that do
		1249	(filesystem) I/O, not for things that wait for other events (network,
		1250	other processes), although if you are careful and know what you are doing,
		1251	you still can.
		1252
		1253	=item aio_sync $callback->($status)
		1254
		1255	Asynchronously call sync and call the callback when finished.
		1256
503	=item aio_fsync $fh, $callback->($status)	1257	=item aio_fsync $fh, $callback->($status)
504		1258
505	Asynchronously call fsync on the given filehandle and call the callback	1259	Asynchronously call fsync on the given filehandle and call the callback
506	with the fsync result code.	1260	with the fsync result code.
507		1261
…		…
511	callback with the fdatasync result code.	1265	callback with the fdatasync result code.
512		1266
513	If this call isn't available because your OS lacks it or it couldn't be	1267	If this call isn't available because your OS lacks it or it couldn't be
514	detected, it will be emulated by calling C<fsync> instead.	1268	detected, it will be emulated by calling C<fsync> instead.
515		1269
		1270	=item aio_syncfs $fh, $callback->($status)
		1271
		1272	Asynchronously call the syncfs syscall to sync the filesystem associated
		1273	to the given filehandle and call the callback with the syncfs result
		1274	code. If syncfs is not available, calls sync(), but returns C<-1> and sets
		1275	errno to C<ENOSYS> nevertheless.
		1276
		1277	=item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		1278
		1279	Sync the data portion of the file specified by C<$offset> and C<$length>
		1280	to disk (but NOT the metadata), by calling the Linux-specific
		1281	sync_file_range call. If sync_file_range is not available or it returns
		1282	ENOSYS, then fdatasync or fsync is being substituted.
		1283
		1284	C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>,
		1285	C<IO::AIO::SYNC_FILE_RANGE_WRITE> and
		1286	C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range
		1287	manpage for details.
		1288
		1289	=item aio_pathsync $pathname, $callback->($status)
		1290
		1291	This request tries to open, fsync and close the given path. This is a
		1292	composite request intended to sync directories after directory operations
		1293	(E.g. rename). This might not work on all operating systems or have any
		1294	specific effect, but usually it makes sure that directory changes get
		1295	written to disc. It works for anything that can be opened for read-only,
		1296	not just directories.
		1297
		1298	Future versions of this function might fall back to other methods when
		1299	C<fsync> on the directory fails (such as calling C<sync>).
		1300
		1301	Passes C<0> when everything went ok, and C<-1> on error.
		1302
		1303	=cut
		1304
		1305	sub aio_pathsync($;$) {
		1306	my ($path, $cb) = @_;
		1307
		1308	my $pri = aioreq_pri;
		1309	my $grp = aio_group $cb;
		1310
		1311	aioreq_pri $pri;
		1312	add $grp aio_open $path, O_RDONLY, 0, sub {
		1313	my ($fh) = @_;
		1314	if ($fh) {
		1315	aioreq_pri $pri;
		1316	add $grp aio_fsync $fh, sub {
		1317	$grp->result ($_[0]);
		1318
		1319	aioreq_pri $pri;
		1320	add $grp aio_close $fh;
		1321	};
		1322	} else {
		1323	$grp->result (-1);
		1324	}
		1325	};
		1326
		1327	$grp
		1328	}
		1329
		1330	=item aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		1331
		1332	This is a rather advanced IO::AIO call, which only works on mmap(2)ed
		1333	scalars (see the C<IO::AIO::mmap> function, although it also works on data
		1334	scalars managed by the L<Sys::Mmap> or L<Mmap> modules, note that the
		1335	scalar must only be modified in-place while an aio operation is pending on
		1336	it).
		1337
		1338	It calls the C<msync> function of your OS, if available, with the memory
		1339	area starting at C<$offset> in the string and ending C<$length> bytes
		1340	later. If C<$length> is negative, counts from the end, and if C<$length>
		1341	is C<undef>, then it goes till the end of the string. The flags can be
		1342	a combination of C<IO::AIO::MS_ASYNC>, C<IO::AIO::MS_INVALIDATE> and
		1343	C<IO::AIO::MS_SYNC>.
		1344
		1345	=item aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		1346
		1347	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1348	scalars.
		1349
		1350	It touches (reads or writes) all memory pages in the specified
		1351	range inside the scalar. All caveats and parameters are the same
		1352	as for C<aio_msync>, above, except for flags, which must be either
		1353	C<0> (which reads all pages and ensures they are instantiated) or
		1354	C<IO::AIO::MT_MODIFY>, which modifies the memory pages (by reading and
		1355	writing an octet from it, which dirties the page).
		1356
		1357	=item aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
		1358
		1359	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1360	scalars.
		1361
		1362	It reads in all the pages of the underlying storage into memory (if any)
		1363	and locks them, so they are not getting swapped/paged out or removed.
		1364
		1365	If C<$length> is undefined, then the scalar will be locked till the end.
		1366
		1367	On systems that do not implement C<mlock>, this function returns C<-1>
		1368	and sets errno to C<ENOSYS>.
		1369
		1370	Note that the corresponding C<munlock> is synchronous and is
		1371	documented under L<MISCELLANEOUS FUNCTIONS>.
		1372
		1373	Example: open a file, mmap and mlock it - both will be undone when
		1374	C<$data> gets destroyed.
		1375
		1376	open my $fh, "<", $path or die "$path: $!";
		1377	my $data;
		1378	IO::AIO::mmap $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh;
		1379	aio_mlock $data; # mlock in background
		1380
		1381	=item aio_mlockall $flags, $callback->($status)
		1382
		1383	Calls the C<mlockall> function with the given C<$flags> (a combination of
		1384	C<IO::AIO::MCL_CURRENT> and C<IO::AIO::MCL_FUTURE>).
		1385
		1386	On systems that do not implement C<mlockall>, this function returns C<-1>
		1387	and sets errno to C<ENOSYS>.
		1388
		1389	Note that the corresponding C<munlockall> is synchronous and is
		1390	documented under L<MISCELLANEOUS FUNCTIONS>.
		1391
		1392	Example: asynchronously lock all current and future pages into memory.
		1393
		1394	aio_mlockall IO::AIO::MCL_FUTURE;
		1395
		1396	=item aio_fiemap $fh, $start, $length, $flags, $count, $cb->(\@extents)
		1397
		1398	Queries the extents of the given file (by calling the Linux C<FIEMAP>
		1399	ioctl, see L<http://cvs.schmorp.de/IO-AIO/doc/fiemap.txt> for details). If
		1400	the ioctl is not available on your OS, then this request will fail with
		1401	C<ENOSYS>.
		1402
		1403	C<$start> is the starting offset to query extents for, C<$length> is the
		1404	size of the range to query - if it is C<undef>, then the whole file will
		1405	be queried.
		1406
		1407	C<$flags> is a combination of flags (C<IO::AIO::FIEMAP_FLAG_SYNC> or
		1408	C<IO::AIO::FIEMAP_FLAG_XATTR> - C<IO::AIO::FIEMAP_FLAGS_COMPAT> is also
		1409	exported), and is normally C<0> or C<IO::AIO::FIEMAP_FLAG_SYNC> to query
		1410	the data portion.
		1411
		1412	C<$count> is the maximum number of extent records to return. If it is
		1413	C<undef>, then IO::AIO queries all extents of the range. As a very special
		1414	case, if it is C<0>, then the callback receives the number of extents
		1415	instead of the extents themselves (which is unreliable, see below).
		1416
		1417	If an error occurs, the callback receives no arguments. The special
		1418	C<errno> value C<IO::AIO::EBADR> is available to test for flag errors.
		1419
		1420	Otherwise, the callback receives an array reference with extent
		1421	structures. Each extent structure is an array reference itself, with the
		1422	following members:
		1423
		1424	[$logical, $physical, $length, $flags]
		1425
		1426	Flags is any combination of the following flag values (typically either C<0>
		1427	or C<IO::AIO::FIEMAP_EXTENT_LAST> (1)):
		1428
		1429	C<IO::AIO::FIEMAP_EXTENT_LAST>, C<IO::AIO::FIEMAP_EXTENT_UNKNOWN>,
		1430	C<IO::AIO::FIEMAP_EXTENT_DELALLOC>, C<IO::AIO::FIEMAP_EXTENT_ENCODED>,
		1431	C<IO::AIO::FIEMAP_EXTENT_DATA_ENCRYPTED>, C<IO::AIO::FIEMAP_EXTENT_NOT_ALIGNED>,
		1432	C<IO::AIO::FIEMAP_EXTENT_DATA_INLINE>, C<IO::AIO::FIEMAP_EXTENT_DATA_TAIL>,
		1433	C<IO::AIO::FIEMAP_EXTENT_UNWRITTEN>, C<IO::AIO::FIEMAP_EXTENT_MERGED> or
		1434	C<IO::AIO::FIEMAP_EXTENT_SHARED>.
		1435
		1436	At the time of this writing (Linux 3.2), this requets is unreliable unless
		1437	C<$count> is C<undef>, as the kernel has all sorts of bugs preventing
		1438	it to return all extents of a range for files with large number of
		1439	extents. The code works around all these issues if C<$count> is undef.
		1440
516	=item aio_group $callback->(...)	1441	=item aio_group $callback->(...)
517
518	[EXPERIMENTAL]
519		1442
520	This is a very special aio request: Instead of doing something, it is a	1443	This is a very special aio request: Instead of doing something, it is a
521	container for other aio requests, which is useful if you want to bundle	1444	container for other aio requests, which is useful if you want to bundle
522	many requests into a single, composite, request.	1445	many requests into a single, composite, request with a definite callback
		1446	and the ability to cancel the whole request with its subrequests.
523		1447
524	Returns an object of class L<IO::AIO::GRP>. See its documentation below	1448	Returns an object of class L<IO::AIO::GRP>. See its documentation below
525	for more info.	1449	for more info.
526		1450
527	Example:	1451	Example:
…		…
533	add $grp	1457	add $grp
534	(aio_stat ...),	1458	(aio_stat ...),
535	(aio_stat ...),	1459	(aio_stat ...),
536	...;	1460	...;
537		1461
		1462	=item aio_nop $callback->()
		1463
		1464	This is a special request - it does nothing in itself and is only used for
		1465	side effects, such as when you want to add a dummy request to a group so
		1466	that finishing the requests in the group depends on executing the given
		1467	code.
		1468
		1469	While this request does nothing, it still goes through the execution
		1470	phase and still requires a worker thread. Thus, the callback will not
		1471	be executed immediately but only after other requests in the queue have
		1472	entered their execution phase. This can be used to measure request
		1473	latency.
		1474
538	=item IO::AIO::aio_sleep $fractional_seconds, $callback->() *NOT EXPORTED*	1475	=item IO::AIO::aio_busy $fractional_seconds, $callback->() *NOT EXPORTED*
539		1476
540	Mainly used for debugging and benchmarking, this aio request puts one of	1477	Mainly used for debugging and benchmarking, this aio request puts one of
541	the request workers to sleep for the given time.	1478	the request workers to sleep for the given time.
542		1479
543	While it is theoretically handy to have simple I/O scheduling requests	1480	While it is theoretically handy to have simple I/O scheduling requests
544	like sleep and file handle readable/writable, the overhead this creates	1481	like sleep and file handle readable/writable, the overhead this creates is
545	is immense, so do not use this function except to put your application	1482	immense (it blocks a thread for a long time) so do not use this function
546	under artificial I/O pressure.	1483	except to put your application under artificial I/O pressure.
547		1484
548	=back	1485	=back
		1486
		1487
		1488	=head2 IO::AIO::WD - multiple working directories
		1489
		1490	Your process only has one current working directory, which is used by all
		1491	threads. This makes it hard to use relative paths (some other component
		1492	could call C<chdir> at any time, and it is hard to control when the path
		1493	will be used by IO::AIO).
		1494
		1495	One solution for this is to always use absolute paths. This usually works,
		1496	but can be quite slow (the kernel has to walk the whole path on every
		1497	access), and can also be a hassle to implement.
		1498
		1499	Newer POSIX systems have a number of functions (openat, fdopendir,
		1500	futimensat and so on) that make it possible to specify working directories
		1501	per operation.
		1502
		1503	For portability, and because the clowns who "designed", or shall I write,
		1504	perpetrated this new interface were obviously half-drunk, this abstraction
		1505	cannot be perfect, though.
		1506
		1507	IO::AIO allows you to convert directory paths into a so-called IO::AIO::WD
		1508	object. This object stores the canonicalised, absolute version of the
		1509	path, and on systems that allow it, also a directory file descriptor.
		1510
		1511	Everywhere where a pathname is accepted by IO::AIO (e.g. in C<aio_stat>
		1512	or C<aio_unlink>), one can specify an array reference with an IO::AIO::WD
		1513	object and a pathname instead (or the IO::AIO::WD object alone, which
		1514	gets interpreted as C<[$wd, "."]>). If the pathname is absolute, the
		1515	IO::AIO::WD object is ignored, otherwise the pathname is resolved relative
		1516	to that IO::AIO::WD object.
		1517
		1518	For example, to get a wd object for F</etc> and then stat F<passwd>
		1519	inside, you would write:
		1520
		1521	aio_wd "/etc", sub {
		1522	my $etcdir = shift;
		1523
		1524	# although $etcdir can be undef on error, there is generally no reason
		1525	# to check for errors here, as aio_stat will fail with ENOENT
		1526	# when $etcdir is undef.
		1527
		1528	aio_stat [$etcdir, "passwd"], sub {
		1529	# yay
		1530	};
		1531	};
		1532
		1533	The fact that C<aio_wd> is a request and not a normal function shows that
		1534	creating an IO::AIO::WD object is itself a potentially blocking operation,
		1535	which is why it is done asynchronously.
		1536
		1537	To stat the directory obtained with C<aio_wd> above, one could write
		1538	either of the following three request calls:
		1539
		1540	aio_lstat "/etc" , sub { ... # pathname as normal string
		1541	aio_lstat [$wd, "."], sub { ... # "." relative to $wd (i.e. $wd itself)
		1542	aio_lstat $wd , sub { ... # shorthand for the previous
		1543
		1544	As with normal pathnames, IO::AIO keeps a copy of the working directory
		1545	object and the pathname string, so you could write the following without
		1546	causing any issues due to C<$path> getting reused:
		1547
		1548	my $path = [$wd, undef];
		1549
		1550	for my $name (qw(abc def ghi)) {
		1551	$path->[1] = $name;
		1552	aio_stat $path, sub {
		1553	# ...
		1554	};
		1555	}
		1556
		1557	There are some caveats: when directories get renamed (or deleted), the
		1558	pathname string doesn't change, so will point to the new directory (or
		1559	nowhere at all), while the directory fd, if available on the system,
		1560	will still point to the original directory. Most functions accepting a
		1561	pathname will use the directory fd on newer systems, and the string on
		1562	older systems. Some functions (such as realpath) will always rely on the
		1563	string form of the pathname.
		1564
		1565	So this functionality is mainly useful to get some protection against
		1566	C<chdir>, to easily get an absolute path out of a relative path for future
		1567	reference, and to speed up doing many operations in the same directory
		1568	(e.g. when stat'ing all files in a directory).
		1569
		1570	The following functions implement this working directory abstraction:
		1571
		1572	=over 4
		1573
		1574	=item aio_wd $pathname, $callback->($wd)
		1575
		1576	Asynchonously canonicalise the given pathname and convert it to an
		1577	IO::AIO::WD object representing it. If possible and supported on the
		1578	system, also open a directory fd to speed up pathname resolution relative
		1579	to this working directory.
		1580
		1581	If something goes wrong, then C<undef> is passwd to the callback instead
		1582	of a working directory object and C<$!> is set appropriately. Since
		1583	passing C<undef> as working directory component of a pathname fails the
		1584	request with C<ENOENT>, there is often no need for error checking in the
		1585	C<aio_wd> callback, as future requests using the value will fail in the
		1586	expected way.
		1587
		1588	=item IO::AIO::CWD
		1589
		1590	This is a compiletime constant (object) that represents the process
		1591	current working directory.
		1592
		1593	Specifying this object as working directory object for a pathname is as if
		1594	the pathname would be specified directly, without a directory object. For
		1595	example, these calls are functionally identical:
		1596
		1597	aio_stat "somefile", sub { ... };
		1598	aio_stat [IO::AIO::CWD, "somefile"], sub { ... };
		1599
		1600	=back
		1601
		1602	To recover the path associated with an IO::AIO::WD object, you can use
		1603	C<aio_realpath>:
		1604
		1605	aio_realpath $wd, sub {
		1606	warn "path is $_[0]\n";
		1607	};
		1608
		1609	Currently, C<aio_statvfs> always, and C<aio_rename> and C<aio_rmdir>
		1610	sometimes, fall back to using an absolue path.
549		1611
550	=head2 IO::AIO::REQ CLASS	1612	=head2 IO::AIO::REQ CLASS
551		1613
552	All non-aggregate C<aio_*> functions return an object of this class when	1614	All non-aggregate C<aio_*> functions return an object of this class when
553	called in non-void context.	1615	called in non-void context.
554		1616
555	A request always moves through the following five states in its lifetime,
556	in order: B<ready> (request has been created, but has not been executed
557	yet), B<execute> (request is currently being executed), B<pending>
558	(request has been executed but callback has not been called yet),
559	B<result> (results are being processed synchronously, includes calling the
560	callback) and B<done> (request has reached the end of its lifetime and
561	holds no resources anymore).
562
563	=over 4	1617	=over 4
564		1618
565	=item $req->cancel	1619	=item cancel $req
566		1620
567	Cancels the request, if possible. Has the effect of skipping execution	1621	Cancels the request, if possible. Has the effect of skipping execution
568	when entering the B<execute> state and skipping calling the callback when	1622	when entering the B<execute> state and skipping calling the callback when
569	entering the the B<result> state, but will leave the request otherwise	1623	entering the the B<result> state, but will leave the request otherwise
570	untouched. That means that requests that currently execute will not be	1624	untouched (with the exception of readdir). That means that requests that
571	stopped and resources held by the request will not be freed prematurely.	1625	currently execute will not be stopped and resources held by the request
		1626	will not be freed prematurely.
		1627
		1628	=item cb $req $callback->(...)
		1629
		1630	Replace (or simply set) the callback registered to the request.
572		1631
573	=back	1632	=back
574		1633
575	=head2 IO::AIO::GRP CLASS	1634	=head2 IO::AIO::GRP CLASS
576		1635
…		…
616	=item * They can also can also be added to other IO::AIO::GRP objects.	1675	=item * They can also can also be added to other IO::AIO::GRP objects.
617		1676
618	=item * You must not add requests to a group from within the group callback (or	1677	=item * You must not add requests to a group from within the group callback (or
619	any later time).	1678	any later time).
620		1679
621	=item * This does not harmonise well with C<max_outstanding>, so best do
622	not combine C<aio_group> with it. Groups and feeders are recommended for
623	this kind of concurrency-limiting.
624
625	=back	1680	=back
626		1681
627	Their lifetime, simplified, looks like this: when they are empty, they	1682	Their lifetime, simplified, looks like this: when they are empty, they
628	will finish very quickly. If they contain only requests that are in the	1683	will finish very quickly. If they contain only requests that are in the
629	C<done> state, they will also finish. Otherwise they will continue to	1684	C<done> state, they will also finish. Otherwise they will continue to
630	exist.	1685	exist.
631		1686
632	That means after creating a group you have some time to add requests. And	1687	That means after creating a group you have some time to add requests
633	in the callbacks of those requests, you can add further requests to the	1688	(precisely before the callback has been invoked, which is only done within
634	group. And only when all those requests have finished will the the group	1689	the C<poll_cb>). And in the callbacks of those requests, you can add
635	itself finish.	1690	further requests to the group. And only when all those requests have
		1691	finished will the the group itself finish.
636		1692
637	=over 4	1693	=over 4
638		1694
		1695	=item add $grp ...
		1696
639	=item $grp->add (...)	1697	=item $grp->add (...)
640
641	=item add $grp ...
642		1698
643	Add one or more requests to the group. Any type of L<IO::AIO::REQ> can	1699	Add one or more requests to the group. Any type of L<IO::AIO::REQ> can
644	be added, including other groups, as long as you do not create circular	1700	be added, including other groups, as long as you do not create circular
645	dependencies.	1701	dependencies.
646		1702
647	Returns all its arguments.	1703	Returns all its arguments.
648		1704
		1705	=item $grp->cancel_subs
		1706
		1707	Cancel all subrequests and clears any feeder, but not the group request
		1708	itself. Useful when you queued a lot of events but got a result early.
		1709
		1710	The group request will finish normally (you cannot add requests to the
		1711	group).
		1712
649	=item $grp->result (...)	1713	=item $grp->result (...)
650		1714
651	Set the result value(s) that will be passed to the group callback when all	1715	Set the result value(s) that will be passed to the group callback when all
652	subrequests have finished. By default, no argument will be passed.	1716	subrequests have finished and set the groups errno to the current value
		1717	of errno (just like calling C<errno> without an error number). By default,
		1718	no argument will be passed and errno is zero.
653		1719
654	=item $grp->set_feeder ($callback->($grp))	1720	=item $grp->errno ([$errno])
655		1721
656	[VERY EXPERIMENTAL]	1722	Sets the group errno value to C<$errno>, or the current value of errno
		1723	when the argument is missing.
		1724
		1725	Every aio request has an associated errno value that is restored when
		1726	the callback is invoked. This method lets you change this value from its
		1727	default (0).
		1728
		1729	Calling C<result> will also set errno, so make sure you either set C<$!>
		1730	before the call to C<result>, or call c<errno> after it.
		1731
		1732	=item feed $grp $callback->($grp)
657		1733
658	Sets a feeder/generator on this group: every group can have an attached	1734	Sets a feeder/generator on this group: every group can have an attached
659	generator that generates requests if idle. The idea behind this is that,	1735	generator that generates requests if idle. The idea behind this is that,
660	although you could just queue as many requests as you want in a group,	1736	although you could just queue as many requests as you want in a group,
661	this might starve other requests for a potentially long time. For	1737	this might starve other requests for a potentially long time. For example,
662	example, C<aio_scandir> might generate hundreds of thousands C<aio_stat>	1738	C<aio_scandir> might generate hundreds of thousands of C<aio_stat>
663	requests, delaying any later requests for a long time.	1739	requests, delaying any later requests for a long time.
664		1740
665	To avoid this, and allow incremental generation of requests, you can	1741	To avoid this, and allow incremental generation of requests, you can
666	instead a group and set a feeder on it that generates those requests. The	1742	instead a group and set a feeder on it that generates those requests. The
667	feeder will be called whenever there are few enough (see C<feeder_limit>,	1743	feed callback will be called whenever there are few enough (see C<limit>,
668	below) requests active in the group itself and is expected to queue more	1744	below) requests active in the group itself and is expected to queue more
669	requests.	1745	requests.
670		1746
671	The feeder can queue as many requests as it likes (i.e. C<add> does not	1747	The feed callback can queue as many requests as it likes (i.e. C<add> does
672	impose any limits).	1748	not impose any limits).
673		1749
674	If the feeder does not queue more requests when called, it will be	1750	If the feed does not queue more requests when called, it will be
675	automatically removed from the group.	1751	automatically removed from the group.
676		1752
677	If the feeder limit is C<0>, it will be set to C<2> automatically.	1753	If the feed limit is C<0> when this method is called, it will be set to
		1754	C<2> automatically.
678		1755
679	Example:	1756	Example:
680		1757
681	# stat all files in @files, but only ever use four aio requests concurrently:	1758	# stat all files in @files, but only ever use four aio requests concurrently:
682		1759
683	my $grp = aio_group sub { print "finished\n" };	1760	my $grp = aio_group sub { print "finished\n" };
684	$grp->feeder_limit (4);	1761	limit $grp 4;
685	$grp->set_feeder (sub {	1762	feed $grp sub {
686	my $file = pop @files	1763	my $file = pop @files
687	or return;	1764	or return;
688		1765
689	add $grp aio_stat $file, sub { ... };	1766	add $grp aio_stat $file, sub { ... };
690	});	1767	};
691		1768
692	=item $grp->feeder_limit ($num)	1769	=item limit $grp $num
693		1770
694	Sets the feeder limit for the group: The feeder will be called whenever	1771	Sets the feeder limit for the group: The feeder will be called whenever
695	the group contains less than this many requests.	1772	the group contains less than this many requests.
696		1773
697	Setting the limit to C<0> will pause the feeding process.	1774	Setting the limit to C<0> will pause the feeding process.
698		1775
		1776	The default value for the limit is C<0>, but note that setting a feeder
		1777	automatically bumps it up to C<2>.
		1778
699	=back	1779	=back
700		1780
701	=head2 SUPPORT FUNCTIONS	1781	=head2 SUPPORT FUNCTIONS
702		1782
		1783	=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION
		1784
703	=over 4	1785	=over 4
704		1786
705	=item $fileno = IO::AIO::poll_fileno	1787	=item $fileno = IO::AIO::poll_fileno
706		1788
707	Return the I<request result pipe file descriptor>. This filehandle must be	1789	Return the I<request result pipe file descriptor>. This filehandle must be
708	polled for reading by some mechanism outside this module (e.g. Event or	1790	polled for reading by some mechanism outside this module (e.g. EV, Glib,
709	select, see below or the SYNOPSIS). If the pipe becomes readable you have	1791	select and so on, see below or the SYNOPSIS). If the pipe becomes readable
710	to call C<poll_cb> to check the results.	1792	you have to call C<poll_cb> to check the results.
711		1793
712	See C<poll_cb> for an example.	1794	See C<poll_cb> for an example.
713		1795
714	=item IO::AIO::poll_cb	1796	=item IO::AIO::poll_cb
715		1797
716	Process all outstanding events on the result pipe. You have to call this	1798	Process some requests that have reached the result phase (i.e. they have
717	regularly. Returns the number of events processed. Returns immediately	1799	been executed but the results are not yet reported). You have to call
718	when no events are outstanding.	1800	this "regularly" to finish outstanding requests.
		1801
		1802	Returns C<0> if all events could be processed (or there were no
		1803	events to process), or C<-1> if it returned earlier for whatever
		1804	reason. Returns immediately when no events are outstanding. The amount
		1805	of events processed depends on the settings of C<IO::AIO::max_poll_req>,
		1806	C<IO::AIO::max_poll_time> and C<IO::AIO::max_outstanding>.
		1807
		1808	If not all requests were processed for whatever reason, the poll file
		1809	descriptor will still be ready when C<poll_cb> returns, so normally you
		1810	don't have to do anything special to have it called later.
		1811
		1812	Apart from calling C<IO::AIO::poll_cb> when the event filehandle becomes
		1813	ready, it can be beneficial to call this function from loops which submit
		1814	a lot of requests, to make sure the results get processed when they become
		1815	available and not just when the loop is finished and the event loop takes
		1816	over again. This function returns very fast when there are no outstanding
		1817	requests.
719		1818
720	Example: Install an Event watcher that automatically calls	1819	Example: Install an Event watcher that automatically calls
721	IO::AIO::poll_cb with high priority:	1820	IO::AIO::poll_cb with high priority (more examples can be found in the
		1821	SYNOPSIS section, at the top of this document):
722		1822
723	Event->io (fd => IO::AIO::poll_fileno,	1823	Event->io (fd => IO::AIO::poll_fileno,
724	poll => 'r', async => 1,	1824	poll => 'r', async => 1,
725	cb => \&IO::AIO::poll_cb);	1825	cb => \&IO::AIO::poll_cb);
726		1826
727	=item IO::AIO::poll_wait	1827	=item IO::AIO::poll_wait
728		1828
729	Wait till the result filehandle becomes ready for reading (simply does a	1829	Wait until either at least one request is in the result phase or no
730	C<select> on the filehandle. This is useful if you want to synchronously wait	1830	requests are outstanding anymore.
731	for some requests to finish).	1831
		1832	This is useful if you want to synchronously wait for some requests to
		1833	become ready, without actually handling them.
732		1834
733	See C<nreqs> for an example.	1835	See C<nreqs> for an example.
734		1836
		1837	=item IO::AIO::poll
		1838
		1839	Waits until some requests have been handled.
		1840
		1841	Returns the number of requests processed, but is otherwise strictly
		1842	equivalent to:
		1843
		1844	IO::AIO::poll_wait, IO::AIO::poll_cb
		1845
735	=item IO::AIO::nreqs	1846	=item IO::AIO::flush
736		1847
737	Returns the number of requests currently outstanding (i.e. for which their	1848	Wait till all outstanding AIO requests have been handled.
738	callback has not been invoked yet).
739		1849
740	Example: wait till there are no outstanding requests anymore:	1850	Strictly equivalent to:
741		1851
742	IO::AIO::poll_wait, IO::AIO::poll_cb	1852	IO::AIO::poll_wait, IO::AIO::poll_cb
743	while IO::AIO::nreqs;	1853	while IO::AIO::nreqs;
744		1854
745	=item IO::AIO::flush	1855	=item IO::AIO::max_poll_reqs $nreqs
746		1856
747	Wait till all outstanding AIO requests have been handled.	1857	=item IO::AIO::max_poll_time $seconds
748		1858
749	Strictly equivalent to:	1859	These set the maximum number of requests (default C<0>, meaning infinity)
		1860	that are being processed by C<IO::AIO::poll_cb> in one call, respectively
		1861	the maximum amount of time (default C<0>, meaning infinity) spent in
		1862	C<IO::AIO::poll_cb> to process requests (more correctly the mininum amount
		1863	of time C<poll_cb> is allowed to use).
750		1864
751	IO::AIO::poll_wait, IO::AIO::poll_cb	1865	Setting C<max_poll_time> to a non-zero value creates an overhead of one
752	while IO::AIO::nreqs;	1866	syscall per request processed, which is not normally a problem unless your
		1867	callbacks are really really fast or your OS is really really slow (I am
		1868	not mentioning Solaris here). Using C<max_poll_reqs> incurs no overhead.
753		1869
754	=item IO::AIO::poll	1870	Setting these is useful if you want to ensure some level of
		1871	interactiveness when perl is not fast enough to process all requests in
		1872	time.
755		1873
756	Waits until some requests have been handled.	1874	For interactive programs, values such as C<0.01> to C<0.1> should be fine.
757		1875
758	Strictly equivalent to:	1876	Example: Install an Event watcher that automatically calls
		1877	IO::AIO::poll_cb with low priority, to ensure that other parts of the
		1878	program get the CPU sometimes even under high AIO load.
759		1879
760	IO::AIO::poll_wait, IO::AIO::poll_cb	1880	# try not to spend much more than 0.1s in poll_cb
761	if IO::AIO::nreqs;	1881	IO::AIO::max_poll_time 0.1;
		1882
		1883	# use a low priority so other tasks have priority
		1884	Event->io (fd => IO::AIO::poll_fileno,
		1885	poll => 'r', nice => 1,
		1886	cb => &IO::AIO::poll_cb);
		1887
		1888	=back
		1889
		1890	=head3 CONTROLLING THE NUMBER OF THREADS
		1891
		1892	=over
762		1893
763	=item IO::AIO::min_parallel $nthreads	1894	=item IO::AIO::min_parallel $nthreads
764		1895
765	Set the minimum number of AIO threads to C<$nthreads>. The current	1896	Set the minimum number of AIO threads to C<$nthreads>. The current
766	default is C<8>, which means eight asynchronous operations can execute	1897	default is C<8>, which means eight asynchronous operations can execute
767	concurrently at any one time (the number of outstanding requests,	1898	concurrently at any one time (the number of outstanding requests,
768	however, is unlimited).	1899	however, is unlimited).
769		1900
770	IO::AIO starts threads only on demand, when an AIO request is queued and	1901	IO::AIO starts threads only on demand, when an AIO request is queued and
771	no free thread exists.	1902	no free thread exists. Please note that queueing up a hundred requests can
		1903	create demand for a hundred threads, even if it turns out that everything
		1904	is in the cache and could have been processed faster by a single thread.
772		1905
773	It is recommended to keep the number of threads relatively low, as some	1906	It is recommended to keep the number of threads relatively low, as some
774	Linux kernel versions will scale negatively with the number of threads	1907	Linux kernel versions will scale negatively with the number of threads
775	(higher parallelity => MUCH higher latency). With current Linux 2.6	1908	(higher parallelity => MUCH higher latency). With current Linux 2.6
776	versions, 4-32 threads should be fine.	1909	versions, 4-32 threads should be fine.
…		…
790	This module automatically runs C<max_parallel 0> at program end, to ensure	1923	This module automatically runs C<max_parallel 0> at program end, to ensure
791	that all threads are killed and that there are no outstanding requests.	1924	that all threads are killed and that there are no outstanding requests.
792		1925
793	Under normal circumstances you don't need to call this function.	1926	Under normal circumstances you don't need to call this function.
794		1927
		1928	=item IO::AIO::max_idle $nthreads
		1929
		1930	Limit the number of threads (default: 4) that are allowed to idle
		1931	(i.e., threads that did not get a request to process within the idle
		1932	timeout (default: 10 seconds). That means if a thread becomes idle while
		1933	C<$nthreads> other threads are also idle, it will free its resources and
		1934	exit.
		1935
		1936	This is useful when you allow a large number of threads (e.g. 100 or 1000)
		1937	to allow for extremely high load situations, but want to free resources
		1938	under normal circumstances (1000 threads can easily consume 30MB of RAM).
		1939
		1940	The default is probably ok in most situations, especially if thread
		1941	creation is fast. If thread creation is very slow on your system you might
		1942	want to use larger values.
		1943
		1944	=item IO::AIO::idle_timeout $seconds
		1945
		1946	Sets the minimum idle timeout (default 10) after which worker threads are
		1947	allowed to exit. SEe C<IO::AIO::max_idle>.
		1948
795	=item $oldnreqs = IO::AIO::max_outstanding $nreqs	1949	=item IO::AIO::max_outstanding $maxreqs
796		1950
797	[DEPRECATED]
798
799	Sets the maximum number of outstanding requests to C<$nreqs>. If you	1951	Sets the maximum number of outstanding requests to C<$nreqs>. If
800	try to queue up more than this number of requests, the caller will block until	1952	you do queue up more than this number of requests, the next call to
801	some requests have been handled.	1953	C<IO::AIO::poll_cb> (and other functions calling C<poll_cb>, such as
		1954	C<IO::AIO::flush> or C<IO::AIO::poll>) will block until the limit is no
		1955	longer exceeded.
802		1956
803	The default is very large, so normally there is no practical limit. If you	1957	In other words, this setting does not enforce a queue limit, but can be
804	queue up many requests in a loop it often improves speed if you set	1958	used to make poll functions block if the limit is exceeded.
805	this to a relatively low number, such as C<100>.
806		1959
807	This function does not work well together with C<aio_group>'s, and their	1960	This is a very bad function to use in interactive programs because it
808	feeder interface is better suited to limiting concurrency, so do not use	1961	blocks, and a bad way to reduce concurrency because it is inexact: Better
809	this function.	1962	use an C<aio_group> together with a feed callback.
810		1963
811	Under normal circumstances you don't need to call this function.	1964	Its main use is in scripts without an event loop - when you want to stat
		1965	a lot of files, you can write somehting like this:
		1966
		1967	IO::AIO::max_outstanding 32;
		1968
		1969	for my $path (...) {
		1970	aio_stat $path , ...;
		1971	IO::AIO::poll_cb;
		1972	}
		1973
		1974	IO::AIO::flush;
		1975
		1976	The call to C<poll_cb> inside the loop will normally return instantly, but
		1977	as soon as more thna C<32> reqeusts are in-flight, it will block until
		1978	some requests have been handled. This keeps the loop from pushing a large
		1979	number of C<aio_stat> requests onto the queue.
		1980
		1981	The default value for C<max_outstanding> is very large, so there is no
		1982	practical limit on the number of outstanding requests.
812		1983
813	=back	1984	=back
814		1985
		1986	=head3 STATISTICAL INFORMATION
		1987
		1988	=over
		1989
		1990	=item IO::AIO::nreqs
		1991
		1992	Returns the number of requests currently in the ready, execute or pending
		1993	states (i.e. for which their callback has not been invoked yet).
		1994
		1995	Example: wait till there are no outstanding requests anymore:
		1996
		1997	IO::AIO::poll_wait, IO::AIO::poll_cb
		1998	while IO::AIO::nreqs;
		1999
		2000	=item IO::AIO::nready
		2001
		2002	Returns the number of requests currently in the ready state (not yet
		2003	executed).
		2004
		2005	=item IO::AIO::npending
		2006
		2007	Returns the number of requests currently in the pending state (executed,
		2008	but not yet processed by poll_cb).
		2009
		2010	=back
		2011
		2012	=head3 MISCELLANEOUS FUNCTIONS
		2013
		2014	IO::AIO implements some functions that are useful when you want to use
		2015	some "Advanced I/O" function not available to in Perl, without going the
		2016	"Asynchronous I/O" route. Many of these have an asynchronous C<aio_*>
		2017	counterpart.
		2018
		2019	=over 4
		2020
		2021	=item IO::AIO::sendfile $ofh, $ifh, $offset, $count
		2022
		2023	Calls the C<eio_sendfile_sync> function, which is like C<aio_sendfile>,
		2024	but is blocking (this makes most sense if you know the input data is
		2025	likely cached already and the output filehandle is set to non-blocking
		2026	operations).
		2027
		2028	Returns the number of bytes copied, or C<-1> on error.
		2029
		2030	=item IO::AIO::fadvise $fh, $offset, $len, $advice
		2031
		2032	Simply calls the C<posix_fadvise> function (see its
		2033	manpage for details). The following advice constants are
		2034	available: C<IO::AIO::FADV_NORMAL>, C<IO::AIO::FADV_SEQUENTIAL>,
		2035	C<IO::AIO::FADV_RANDOM>, C<IO::AIO::FADV_NOREUSE>,
		2036	C<IO::AIO::FADV_WILLNEED>, C<IO::AIO::FADV_DONTNEED>.
		2037
		2038	On systems that do not implement C<posix_fadvise>, this function returns
		2039	ENOSYS, otherwise the return value of C<posix_fadvise>.
		2040
		2041	=item IO::AIO::madvise $scalar, $offset, $len, $advice
		2042
		2043	Simply calls the C<posix_madvise> function (see its
		2044	manpage for details). The following advice constants are
		2045	available: C<IO::AIO::MADV_NORMAL>, C<IO::AIO::MADV_SEQUENTIAL>,
		2046	C<IO::AIO::MADV_RANDOM>, C<IO::AIO::MADV_WILLNEED>, C<IO::AIO::MADV_DONTNEED>,
		2047	C<IO::AIO::MADV_FREE>.
		2048
		2049	On systems that do not implement C<posix_madvise>, this function returns
		2050	ENOSYS, otherwise the return value of C<posix_madvise>.
		2051
		2052	=item IO::AIO::mprotect $scalar, $offset, $len, $protect
		2053
		2054	Simply calls the C<mprotect> function on the preferably AIO::mmap'ed
		2055	$scalar (see its manpage for details). The following protect
		2056	constants are available: C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_READ>,
		2057	C<IO::AIO::PROT_WRITE>, C<IO::AIO::PROT_EXEC>.
		2058
		2059	On systems that do not implement C<mprotect>, this function returns
		2060	ENOSYS, otherwise the return value of C<mprotect>.
		2061
		2062	=item IO::AIO::mmap $scalar, $length, $prot, $flags, $fh[, $offset]
		2063
		2064	Memory-maps a file (or anonymous memory range) and attaches it to the
		2065	given C<$scalar>, which will act like a string scalar. Returns true on
		2066	success, and false otherwise.
		2067
		2068	The only operations allowed on the scalar are C<substr>/C<vec> that don't
		2069	change the string length, and most read-only operations such as copying it
		2070	or searching it with regexes and so on.
		2071
		2072	Anything else is unsafe and will, at best, result in memory leaks.
		2073
		2074	The memory map associated with the C<$scalar> is automatically removed
		2075	when the C<$scalar> is destroyed, or when the C<IO::AIO::mmap> or
		2076	C<IO::AIO::munmap> functions are called.
		2077
		2078	This calls the C<mmap>(2) function internally. See your system's manual
		2079	page for details on the C<$length>, C<$prot> and C<$flags> parameters.
		2080
		2081	The C<$length> must be larger than zero and smaller than the actual
		2082	filesize.
		2083
		2084	C<$prot> is a combination of C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_EXEC>,
		2085	C<IO::AIO::PROT_READ> and/or C<IO::AIO::PROT_WRITE>,
		2086
		2087	C<$flags> can be a combination of
		2088	C<IO::AIO::MAP_SHARED> or
		2089	C<IO::AIO::MAP_PRIVATE>,
		2090	or a number of system-specific flags (when not available, the are C<0>):
		2091	C<IO::AIO::MAP_ANONYMOUS> (which is set to C<MAP_ANON> if your system only provides this constant),
		2092	C<IO::AIO::MAP_LOCKED>,
		2093	C<IO::AIO::MAP_NORESERVE>,
		2094	C<IO::AIO::MAP_POPULATE>,
		2095	C<IO::AIO::MAP_NONBLOCK>,
		2096	C<IO::AIO::MAP_FIXED>,
		2097	C<IO::AIO::MAP_GROWSDOWN>,
		2098	C<IO::AIO::MAP_32BIT>,
		2099	C<IO::AIO::MAP_HUGETLB> or
		2100	C<IO::AIO::MAP_STACK>.
		2101
		2102	If C<$fh> is C<undef>, then a file descriptor of C<-1> is passed.
		2103
		2104	C<$offset> is the offset from the start of the file - it generally must be
		2105	a multiple of C<IO::AIO::PAGESIZE> and defaults to C<0>.
		2106
		2107	Example:
		2108
		2109	use Digest::MD5;
		2110	use IO::AIO;
		2111
		2112	open my $fh, "<verybigfile"
		2113	or die "$!";
		2114
		2115	IO::AIO::mmap my $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh
		2116	or die "verybigfile: $!";
		2117
		2118	my $fast_md5 = md5 $data;
		2119
		2120	=item IO::AIO::munmap $scalar
		2121
		2122	Removes a previous mmap and undefines the C<$scalar>.
		2123
		2124	=item IO::AIO::munlock $scalar, $offset = 0, $length = undef
		2125
		2126	Calls the C<munlock> function, undoing the effects of a previous
		2127	C<aio_mlock> call (see its description for details).
		2128
		2129	=item IO::AIO::munlockall
		2130
		2131	Calls the C<munlockall> function.
		2132
		2133	On systems that do not implement C<munlockall>, this function returns
		2134	ENOSYS, otherwise the return value of C<munlockall>.
		2135
		2136	=item IO::AIO::splice $r_fh, $r_off, $w_fh, $w_off, $length, $flags
		2137
		2138	Calls the GNU/Linux C<splice(2)> syscall, if available. If C<$r_off> or
		2139	C<$w_off> are C<undef>, then C<NULL> is passed for these, otherwise they
		2140	should be the file offset.
		2141
		2142	C<$r_fh> and C<$w_fh> should not refer to the same file, as splice might
		2143	silently corrupt the data in this case.
		2144
		2145	The following symbol flag values are available: C<IO::AIO::SPLICE_F_MOVE>,
		2146	C<IO::AIO::SPLICE_F_NONBLOCK>, C<IO::AIO::SPLICE_F_MORE> and
		2147	C<IO::AIO::SPLICE_F_GIFT>.
		2148
		2149	See the C<splice(2)> manpage for details.
		2150
		2151	=item IO::AIO::tee $r_fh, $w_fh, $length, $flags
		2152
		2153	Calls the GNU/Linux C<tee(2)> syscall, see its manpage and the
		2154	description for C<IO::AIO::splice> above for details.
		2155
		2156	=item $actual_size = IO::AIO::pipesize $r_fh[, $new_size]
		2157
		2158	Attempts to query or change the pipe buffer size. Obviously works only
		2159	on pipes, and currently works only on GNU/Linux systems, and fails with
		2160	C<-1>/C<ENOSYS> everywhere else. If anybody knows how to influence pipe buffer
		2161	size on other systems, drop me a note.
		2162
		2163	=item ($rfh, $wfh) = IO::AIO::pipe2 [$flags]
		2164
		2165	This is a direct interface to the Linux L<pipe2(2)> system call. If
		2166	C<$flags> is missing or C<0>, then this should be the same as a call to
		2167	perl's built-in C<pipe> function and create a new pipe, and works on
		2168	systems that lack the pipe2 syscall. On win32, this case invokes C<_pipe
		2169	(..., 4096, O_BINARY)>.
		2170
		2171	If C<$flags> is non-zero, it tries to invoke the pipe2 system call with
		2172	the given flags (Linux 2.6.27, glibc 2.9).
		2173
		2174	On success, the read and write file handles are returned.
		2175
		2176	On error, nothing will be returned. If the pipe2 syscall is missing and
		2177	C<$flags> is non-zero, fails with C<ENOSYS>.
		2178
		2179	Please refer to L<pipe2(2)> for more info on the C<$flags>, but at the
		2180	time of this writing, C<IO::AIO::O_CLOEXEC>, C<IO::AIO::O_NONBLOCK> and
		2181	C<IO::AIO::O_DIRECT> (Linux 3.4, for packet-based pipes) were supported.
		2182
		2183	=back
		2184
815	=cut	2185	=cut
816		2186
817	# support function to convert a fd into a perl filehandle
818	sub _fd2fh {
819	return undef if $_[0] < 0;
820
821	# try to generate nice filehandles
822	my $sym = "IO::AIO::fd#$_[0]";
823	local *$sym;
824
825	open *$sym, "+<&=$_[0]" # usually works under any unix
826	or open *$sym, "<&=$_[0]" # cygwin needs this
827	or open *$sym, ">&=$_[0]" # or this
828	or return undef;
829
830	*$sym
831	}
832
833	min_parallel 8;	2187	min_parallel 8;
834		2188
835	END {	2189	END { flush }
836	max_parallel 0;
837	}
838		2190
839	1;	2191	1;
840		2192
		2193	=head1 EVENT LOOP INTEGRATION
		2194
		2195	It is recommended to use L<AnyEvent::AIO> to integrate IO::AIO
		2196	automatically into many event loops:
		2197
		2198	# AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...)
		2199	use AnyEvent::AIO;
		2200
		2201	You can also integrate IO::AIO manually into many event loops, here are
		2202	some examples of how to do this:
		2203
		2204	# EV integration
		2205	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
		2206
		2207	# Event integration
		2208	Event->io (fd => IO::AIO::poll_fileno,
		2209	poll => 'r',
		2210	cb => \&IO::AIO::poll_cb);
		2211
		2212	# Glib/Gtk2 integration
		2213	add_watch Glib::IO IO::AIO::poll_fileno,
		2214	in => sub { IO::AIO::poll_cb; 1 };
		2215
		2216	# Tk integration
		2217	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
		2218	readable => \&IO::AIO::poll_cb);
		2219
		2220	# Danga::Socket integration
		2221	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
		2222	\&IO::AIO::poll_cb);
		2223
841	=head2 FORK BEHAVIOUR	2224	=head2 FORK BEHAVIOUR
842		2225
843	This module should do "the right thing" when the process using it forks:	2226	Usage of pthreads in a program changes the semantics of fork
		2227	considerably. Specifically, only async-safe functions can be called after
		2228	fork. Perl doesn't know about this, so in general, you cannot call fork
		2229	with defined behaviour in perl if pthreads are involved. IO::AIO uses
		2230	pthreads, so this applies, but many other extensions and (for inexplicable
		2231	reasons) perl itself often is linked against pthreads, so this limitation
		2232	applies to quite a lot of perls.
844		2233
845	Before the fork, IO::AIO enters a quiescent state where no requests	2234	This module no longer tries to fight your OS, or POSIX. That means IO::AIO
846	can be added in other threads and no results will be processed. After	2235	only works in the process that loaded it. Forking is fully supported, but
847	the fork the parent simply leaves the quiescent state and continues	2236	using IO::AIO in the child is not.
848	request/result processing, while the child clears the request/result
849	queue (so the requests started before the fork will only be handled in
850	the parent). Threads will be started on demand until the limit ste in the
851	parent process has been reached again.
852		2237
853	In short: the parent will, after a short pause, continue as if fork had	2238	You might get around by not I<using> IO::AIO before (or after)
854	not been called, while the child will act as if IO::AIO has not been used	2239	forking. You could also try to call the L<IO::AIO::reinit> function in the
855	yet.	2240	child:
		2241
		2242	=over 4
		2243
		2244	=item IO::AIO::reinit
		2245
		2246	Abandons all current requests and I/O threads and simply reinitialises all
		2247	data structures. This is not an operation supported by any standards, but
		2248	happens to work on GNU/Linux and some newer BSD systems.
		2249
		2250	The only reasonable use for this function is to call it after forking, if
		2251	C<IO::AIO> was used in the parent. Calling it while IO::AIO is active in
		2252	the process will result in undefined behaviour. Calling it at any time
		2253	will also result in any undefined (by POSIX) behaviour.
		2254
		2255	=back
856		2256
857	=head2 MEMORY USAGE	2257	=head2 MEMORY USAGE
858		2258
		2259	Per-request usage:
		2260
859	Each aio request uses - depending on your architecture - around 128 bytes	2261	Each aio request uses - depending on your architecture - around 100-200
860	of memory. In addition, stat requests need a stat buffer (possibly a few	2262	bytes of memory. In addition, stat requests need a stat buffer (possibly
861	hundred bytes). Perl scalars and other data passed into aio requests will	2263	a few hundred bytes), readdir requires a result buffer and so on. Perl
862	also be locked.	2264	scalars and other data passed into aio requests will also be locked and
		2265	will consume memory till the request has entered the done state.
863		2266
864	This is now awfully much, so queuing lots of requests is not usually a	2267	This is not awfully much, so queuing lots of requests is not usually a
865	problem.	2268	problem.
866		2269
867	Each thread needs a stack area which is usually around 16k, sometimes much	2270	Per-thread usage:
868	larger, depending on the OS.	2271
		2272	In the execution phase, some aio requests require more memory for
		2273	temporary buffers, and each thread requires a stack and other data
		2274	structures (usually around 16k-128k, depending on the OS).
		2275
		2276	=head1 KNOWN BUGS
		2277
		2278	Known bugs will be fixed in the next release.
869		2279
870	=head1 SEE ALSO	2280	=head1 SEE ALSO
871		2281
872	L<Coro>, L<Linux::AIO> (obsolete).	2282	L<AnyEvent::AIO> for easy integration into event loops, L<Coro::AIO> for a
		2283	more natural syntax.
873		2284
874	=head1 AUTHOR	2285	=head1 AUTHOR
875		2286
876	Marc Lehmann <schmorp@schmorp.de>	2287	Marc Lehmann <schmorp@schmorp.de>
877	http://home.schmorp.de/	2288	http://home.schmorp.de/

Diff Legend

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