ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/IO-AIO/AIO.pm

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.70 by root, Tue Oct 24 03:40:38 2006 UTC vs.
Revision 1.272 by root, Fri Jun 23 22:09:50 2017 UTC

1	=head1 NAME	1	=head1 NAME
2		2
3	IO::AIO - Asynchronous Input/Output	3	IO::AIO - Asynchronous/Advanced Input/Output
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
…		…
25	$req->cancel; # cancel request if still in queue	26	$req->cancel; # cancel request if still in queue
26		27
27	my $grp = aio_group sub { print "all stats done\n" };	28	my $grp = aio_group sub { print "all stats done\n" };
28	add $grp aio_stat "..." for ...;	29	add $grp aio_stat "..." for ...;
29		30
30	# AnyEvent integration
31	open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!";
32	my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb });
33
34	# Event integration
35	Event->io (fd => IO::AIO::poll_fileno,
36	poll => 'r',
37	cb => \&IO::AIO::poll_cb);
38
39	# Glib/Gtk2 integration
40	add_watch Glib::IO IO::AIO::poll_fileno,
41	in => sub { IO::AIO::poll_cb; 1 };
42
43	# Tk integration
44	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
45	readable => \&IO::AIO::poll_cb);
46
47	# Danga::Socket integration
48	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
49	\&IO::AIO::poll_cb);
50
51	=head1 DESCRIPTION	31	=head1 DESCRIPTION
52		32
53	This module implements asynchronous I/O using whatever means your	33	This module implements asynchronous I/O using whatever means your
54	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>).
55		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
56	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
57	and signal their completion. You don't need thread support in perl, and	54	requests and signal their completion. You don't need thread support
58	the threads created by this module will not be visible to perl. In the	55	in perl, and the threads created by this module will not be visible
59	future, this module might make use of the native aio functions available	56	to perl. In the future, this module might make use of the native aio
60	on many operating systems. However, they are often not well-supported	57	functions available on many operating systems. However, they are often
61	(Linux doesn't allow them on normal files currently, for example),	58	not well-supported or restricted (GNU/Linux doesn't allow them on normal
62	and they would only support aio_read and aio_write, so the remaining	59	files currently, for example), and they would only support aio_read and
63	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.
64		62
		63	In addition to asynchronous I/O, this module also exports some rather
		64	arcane interfaces, such as C<madvise> or linux's C<splice> system call,
		65	which is why the C<A> in C<AIO> can also mean I<advanced>.
		66
65	Although the module will work with in the presence of other threads,	67	Although the module will work in the presence of other (Perl-) threads,
66	it is currently not reentrant in any way, so use appropriate locking	68	it is currently not reentrant in any way, so use appropriate locking
67	yourself, always call C<poll_cb> from within the same thread, or never	69	yourself, always call C<poll_cb> from within the same thread, or never
68	call C<poll_cb> (or other C<aio_> functions) recursively.	70	call C<poll_cb> (or other C<aio_> functions) recursively.
69		71
		72	=head2 EXAMPLE
		73
		74	This is a simple example that uses the EV module and loads
		75	F</etc/passwd> asynchronously:
		76
		77	use EV;
		78	use IO::AIO;
		79
		80	# register the IO::AIO callback with EV
		81	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
		82
		83	# queue the request to open /etc/passwd
		84	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
		85	my $fh = shift
		86	or die "error while opening: $!";
		87
		88	# stat'ing filehandles is generally non-blocking
		89	my $size = -s $fh;
		90
		91	# queue a request to read the file
		92	my $contents;
		93	aio_read $fh, 0, $size, $contents, 0, sub {
		94	$_[0] == $size
		95	or die "short read: $!";
		96
		97	close $fh;
		98
		99	# file contents now in $contents
		100	print $contents;
		101
		102	# exit event loop and program
		103	EV::break;
		104	};
		105	};
		106
		107	# possibly queue up other requests, or open GUI windows,
		108	# check for sockets etc. etc.
		109
		110	# process events as long as there are some:
		111	EV::run;
		112
		113	=head1 REQUEST ANATOMY AND LIFETIME
		114
		115	Every C<aio_*> function creates a request. which is a C data structure not
		116	directly visible to Perl.
		117
		118	If called in non-void context, every request function returns a Perl
		119	object representing the request. In void context, nothing is returned,
		120	which saves a bit of memory.
		121
		122	The perl object is a fairly standard ref-to-hash object. The hash contents
		123	are not used by IO::AIO so you are free to store anything you like in it.
		124
		125	During their existance, aio requests travel through the following states,
		126	in order:
		127
		128	=over 4
		129
		130	=item ready
		131
		132	Immediately after a request is created it is put into the ready state,
		133	waiting for a thread to execute it.
		134
		135	=item execute
		136
		137	A thread has accepted the request for processing and is currently
		138	executing it (e.g. blocking in read).
		139
		140	=item pending
		141
		142	The request has been executed and is waiting for result processing.
		143
		144	While request submission and execution is fully asynchronous, result
		145	processing is not and relies on the perl interpreter calling C<poll_cb>
		146	(or another function with the same effect).
		147
		148	=item result
		149
		150	The request results are processed synchronously by C<poll_cb>.
		151
		152	The C<poll_cb> function will process all outstanding aio requests by
		153	calling their callbacks, freeing memory associated with them and managing
		154	any groups they are contained in.
		155
		156	=item done
		157
		158	Request has reached the end of its lifetime and holds no resources anymore
		159	(except possibly for the Perl object, but its connection to the actual
		160	aio request is severed and calling its methods will either do nothing or
		161	result in a runtime error).
		162
		163	=back
		164
70	=cut	165	=cut
71		166
72	package IO::AIO;	167	package IO::AIO;
73		168
74	no warnings;	169	use Carp ();
75	use strict 'vars';	170
		171	use common::sense;
76		172
77	use base 'Exporter';	173	use base 'Exporter';
78		174
79	BEGIN {	175	BEGIN {
80	our $VERSION = '2.0';	176	our $VERSION = 4.35;
81		177
82	our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat	178	our @AIO_REQ = qw(aio_sendfile aio_seek aio_read aio_write aio_open aio_close
83	aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink	179	aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx
84	aio_fsync aio_fdatasync aio_readahead aio_rename aio_link aio_move	180	aio_scandir aio_symlink aio_readlink aio_realpath aio_fcntl aio_ioctl
		181	aio_sync aio_fsync aio_syncfs aio_fdatasync aio_sync_file_range
		182	aio_pathsync aio_readahead aio_fiemap aio_allocate
		183	aio_rename aio_rename2 aio_link aio_move aio_copy aio_group
		184	aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown
		185	aio_chmod aio_utime aio_truncate
		186	aio_msync aio_mtouch aio_mlock aio_mlockall
		187	aio_statvfs
85	aio_group aio_nop);	188	aio_wd);
		189
86	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice));	190	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice));
87	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush	191	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush
88	min_parallel max_parallel max_outstanding nreqs);	192	min_parallel max_parallel max_idle idle_timeout
		193	nreqs nready npending nthreads
		194	max_poll_time max_poll_reqs
		195	sendfile fadvise madvise
		196	mmap munmap munlock munlockall);
		197
		198	push @AIO_REQ, qw(aio_busy); # not exported
89		199
90	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';	200	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';
91		201
92	require XSLoader;	202	require XSLoader;
93	XSLoader::load ("IO::AIO", $VERSION);	203	XSLoader::load ("IO::AIO", $VERSION);
94	}	204	}
95		205
96	=head1 FUNCTIONS	206	=head1 FUNCTIONS
97		207
98	=head2 AIO FUNCTIONS	208	=head2 QUICK OVERVIEW
		209
		210	This section simply lists the prototypes most of the functions for
		211	quick reference. See the following sections for function-by-function
		212	documentation.
		213
		214	aio_wd $pathname, $callback->($wd)
		215	aio_open $pathname, $flags, $mode, $callback->($fh)
		216	aio_close $fh, $callback->($status)
		217	aio_seek $fh,$offset,$whence, $callback->($offs)
		218	aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
		219	aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
		220	aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
		221	aio_readahead $fh,$offset,$length, $callback->($retval)
		222	aio_stat $fh_or_path, $callback->($status)
		223	aio_lstat $fh, $callback->($status)
		224	aio_statvfs $fh_or_path, $callback->($statvfs)
		225	aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
		226	aio_chown $fh_or_path, $uid, $gid, $callback->($status)
		227	aio_chmod $fh_or_path, $mode, $callback->($status)
		228	aio_truncate $fh_or_path, $offset, $callback->($status)
		229	aio_allocate $fh, $mode, $offset, $len, $callback->($status)
		230	aio_fiemap $fh, $start, $length, $flags, $count, $cb->(\@extents)
		231	aio_unlink $pathname, $callback->($status)
		232	aio_mknod $pathname, $mode, $dev, $callback->($status)
		233	aio_link $srcpath, $dstpath, $callback->($status)
		234	aio_symlink $srcpath, $dstpath, $callback->($status)
		235	aio_readlink $pathname, $callback->($link)
		236	aio_realpath $pathname, $callback->($path)
		237	aio_rename $srcpath, $dstpath, $callback->($status)
		238	aio_rename2 $srcpath, $dstpath, $flags, $callback->($status)
		239	aio_mkdir $pathname, $mode, $callback->($status)
		240	aio_rmdir $pathname, $callback->($status)
		241	aio_readdir $pathname, $callback->($entries)
		242	aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		243	IO::AIO::READDIR_DENTS IO::AIO::READDIR_DIRS_FIRST
		244	IO::AIO::READDIR_STAT_ORDER IO::AIO::READDIR_FOUND_UNKNOWN
		245	aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs)
		246	aio_load $pathname, $data, $callback->($status)
		247	aio_copy $srcpath, $dstpath, $callback->($status)
		248	aio_move $srcpath, $dstpath, $callback->($status)
		249	aio_rmtree $pathname, $callback->($status)
		250	aio_fcntl $fh, $cmd, $arg, $callback->($status)
		251	aio_ioctl $fh, $request, $buf, $callback->($status)
		252	aio_sync $callback->($status)
		253	aio_syncfs $fh, $callback->($status)
		254	aio_fsync $fh, $callback->($status)
		255	aio_fdatasync $fh, $callback->($status)
		256	aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		257	aio_pathsync $pathname, $callback->($status)
		258	aio_msync $scalar, $offset = 0, $length = undef, flags = MS_SYNC, $callback->($status)
		259	aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		260	aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
		261	aio_mlockall $flags, $callback->($status)
		262	aio_group $callback->(...)
		263	aio_nop $callback->()
		264
		265	$prev_pri = aioreq_pri [$pri]
		266	aioreq_nice $pri_adjust
		267
		268	IO::AIO::poll_wait
		269	IO::AIO::poll_cb
		270	IO::AIO::poll
		271	IO::AIO::flush
		272	IO::AIO::max_poll_reqs $nreqs
		273	IO::AIO::max_poll_time $seconds
		274	IO::AIO::min_parallel $nthreads
		275	IO::AIO::max_parallel $nthreads
		276	IO::AIO::max_idle $nthreads
		277	IO::AIO::idle_timeout $seconds
		278	IO::AIO::max_outstanding $maxreqs
		279	IO::AIO::nreqs
		280	IO::AIO::nready
		281	IO::AIO::npending
		282
		283	IO::AIO::sendfile $ofh, $ifh, $offset, $count
		284	IO::AIO::fadvise $fh, $offset, $len, $advice
		285	IO::AIO::mmap $scalar, $length, $prot, $flags[, $fh[, $offset]]
		286	IO::AIO::munmap $scalar
		287	IO::AIO::madvise $scalar, $offset, $length, $advice
		288	IO::AIO::mprotect $scalar, $offset, $length, $protect
		289	IO::AIO::munlock $scalar, $offset = 0, $length = undef
		290	IO::AIO::munlockall
		291
		292	=head2 API NOTES
99		293
100	All the C<aio_*> calls are more or less thin wrappers around the syscall	294	All the C<aio_*> calls are more or less thin wrappers around the syscall
101	with the same name (sans C<aio_>). The arguments are similar or identical,	295	with the same name (sans C<aio_>). The arguments are similar or identical,
102	and they all accept an additional (and optional) C<$callback> argument	296	and they all accept an additional (and optional) C<$callback> argument
103	which must be a code reference. This code reference will get called with	297	which must be a code reference. This code reference will be called after
104	the syscall return code (e.g. most syscalls return C<-1> on error, unlike	298	the syscall has been executed in an asynchronous fashion. The results
105	perl, which usually delivers "false") as it's sole argument when the given	299	of the request will be passed as arguments to the callback (and, if an
106	syscall has been executed asynchronously.	300	error occured, in C<$!>) - for most requests the syscall return code (e.g.
		301	most syscalls return C<-1> on error, unlike perl, which usually delivers
		302	"false").
		303
		304	Some requests (such as C<aio_readdir>) pass the actual results and
		305	communicate failures by passing C<undef>.
107		306
108	All functions expecting a filehandle keep a copy of the filehandle	307	All functions expecting a filehandle keep a copy of the filehandle
109	internally until the request has finished.	308	internally until the request has finished.
110		309
111	All requests return objects of type L<IO::AIO::REQ> that allow further	310	All functions return request objects of type L<IO::AIO::REQ> that allow
112	manipulation of those requests while they are in-flight.	311	further manipulation of those requests while they are in-flight.
113		312
114	The pathnames you pass to these routines I<must> be absolute and	313	The pathnames you pass to these routines I<should> be absolute. The
115	encoded in byte form. The reason for the former is that at the time the	314	reason for this is that at the time the request is being executed, the
116	request is being executed, the current working directory could have	315	current working directory could have changed. Alternatively, you can
117	changed. Alternatively, you can make sure that you never change the	316	make sure that you never change the current working directory anywhere
118	current working directory.	317	in the program and then use relative paths. You can also take advantage
		318	of IO::AIOs working directory abstraction, that lets you specify paths
		319	relative to some previously-opened "working directory object" - see the
		320	description of the C<IO::AIO::WD> class later in this document.
119		321
120	To encode pathnames to byte form, either make sure you either: a)	322	To encode pathnames as octets, either make sure you either: a) always pass
121	always pass in filenames you got from outside (command line, readdir	323	in filenames you got from outside (command line, readdir etc.) without
122	etc.), b) are ASCII or ISO 8859-1, c) use the Encode module and encode	324	tinkering, b) are in your native filesystem encoding, c) use the Encode
123	your pathnames to the locale (or other) encoding in effect in the user	325	module and encode your pathnames to the locale (or other) encoding in
124	environment, d) use Glib::filename_from_unicode on unicode filenames or e)	326	effect in the user environment, d) use Glib::filename_from_unicode on
125	use something else.	327	unicode filenames or e) use something else to ensure your scalar has the
		328	correct contents.
		329
		330	This works, btw. independent of the internal UTF-8 bit, which IO::AIO
		331	handles correctly whether it is set or not.
		332
		333	=head2 AIO REQUEST FUNCTIONS
126		334
127	=over 4	335	=over 4
128		336
129	=item aioreq_pri $pri	337	=item $prev_pri = aioreq_pri [$pri]
130		338
131	Sets the priority for the next aio request. The default priority	339	Returns the priority value that would be used for the next request and, if
		340	C<$pri> is given, sets the priority for the next aio request.
		341
132	is C<0>, the minimum and maximum priorities are C<-4> and C<4>,	342	The default priority is C<0>, the minimum and maximum priorities are C<-4>
133	respectively. Requests with higher priority will be serviced first.	343	and C<4>, respectively. Requests with higher priority will be serviced
		344	first.
134		345
135	The priority will be reset to C<0> after each call to one of the C<aio_>	346	The priority will be reset to C<0> after each call to one of the C<aio_*>
136	functions.	347	functions.
137		348
138	Example: open a file with low priority, then read something from it with	349	Example: open a file with low priority, then read something from it with
139	higher priority so the read request is serviced before other low priority	350	higher priority so the read request is serviced before other low priority
140	open requests (potentially spamming the cache):	351	open requests (potentially spamming the cache):
…		…
147	aio_read $_[0], ..., sub {	358	aio_read $_[0], ..., sub {
148	...	359	...
149	};	360	};
150	};	361	};
151		362
		363
152	=item aioreq_nice $pri_adjust	364	=item aioreq_nice $pri_adjust
153		365
154	Similar to C<aioreq_pri>, but subtracts the given value from the current	366	Similar to C<aioreq_pri>, but subtracts the given value from the current
155	priority, so effects are cumulative.	367	priority, so the effect is cumulative.
		368
156		369
157	=item aio_open $pathname, $flags, $mode, $callback->($fh)	370	=item aio_open $pathname, $flags, $mode, $callback->($fh)
158		371
159	Asynchronously open or create a file and call the callback with a newly	372	Asynchronously open or create a file and call the callback with a newly
160	created filehandle for the file.	373	created filehandle for the file (or C<undef> in case of an error).
161		374
162	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,	375	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,
163	for an explanation.	376	for an explanation.
164		377
165	The C<$flags> argument is a bitmask. See the C<Fcntl> module for a	378	The C<$flags> argument is a bitmask. See the C<Fcntl> module for a
166	list. They are the same as used by C<sysopen>.	379	list. They are the same as used by C<sysopen>.
167		380
168	Likewise, C<$mode> specifies the mode of the newly created file, if it	381	Likewise, C<$mode> specifies the mode of the newly created file, if it
169	didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,	382	didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,
170	except that it is mandatory (i.e. use C<0> if you don't create new files,	383	except that it is mandatory (i.e. use C<0> if you don't create new files,
171	and C<0666> or C<0777> if you do).	384	and C<0666> or C<0777> if you do). Note that the C<$mode> will be modified
		385	by the umask in effect then the request is being executed, so better never
		386	change the umask.
172		387
173	Example:	388	Example:
174		389
175	aio_open "/etc/passwd", O_RDONLY, 0, sub {	390	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
176	if ($_[0]) {	391	if ($_[0]) {
177	print "open successful, fh is $_[0]\n";	392	print "open successful, fh is $_[0]\n";
178	...	393	...
179	} else {	394	} else {
180	die "open failed: $!\n";	395	die "open failed: $!\n";
181	}	396	}
182	};	397	};
183		398
		399	In addition to all the common open modes/flags (C<O_RDONLY>, C<O_WRONLY>,
		400	C<O_RDWR>, C<O_CREAT>, C<O_TRUNC>, C<O_EXCL> and C<O_APPEND>), the
		401	following POSIX and non-POSIX constants are available (missing ones on
		402	your system are, as usual, C<0>):
		403
		404	C<O_ASYNC>, C<O_DIRECT>, C<O_NOATIME>, C<O_CLOEXEC>, C<O_NOCTTY>, C<O_NOFOLLOW>,
		405	C<O_NONBLOCK>, C<O_EXEC>, C<O_SEARCH>, C<O_DIRECTORY>, C<O_DSYNC>,
		406	C<O_RSYNC>, C<O_SYNC>, C<O_PATH>, C<O_TMPFILE>, and C<O_TTY_INIT>.
		407
		408
184	=item aio_close $fh, $callback->($status)	409	=item aio_close $fh, $callback->($status)
185		410
186	Asynchronously close a file and call the callback with the result	411	Asynchronously close a file and call the callback with the result
187	code. I<WARNING:> although accepted, you should not pass in a perl	412	code.
188	filehandle here, as perl will likely close the file descriptor another
189	time when the filehandle is destroyed. Normally, you can safely call perls
190	C<close> or just let filehandles go out of scope.
191		413
192	This is supposed to be a bug in the API, so that might change. It's	414	Unfortunately, you can't do this to perl. Perl I<insists> very strongly on
193	therefore best to avoid this function.	415	closing the file descriptor associated with the filehandle itself.
		416
		417	Therefore, C<aio_close> will not close the filehandle - instead it will
		418	use dup2 to overwrite the file descriptor with the write-end of a pipe
		419	(the pipe fd will be created on demand and will be cached).
		420
		421	Or in other words: the file descriptor will be closed, but it will not be
		422	free for reuse until the perl filehandle is closed.
		423
		424	=cut
		425
		426	=item aio_seek $fh, $offset, $whence, $callback->($offs)
		427
		428	Seeks the filehandle to the new C<$offset>, similarly to perl's
		429	C<sysseek>. The C<$whence> can use the traditional values (C<0> for
		430	C<IO::AIO::SEEK_SET>, C<1> for C<IO::AIO::SEEK_CUR> or C<2> for
		431	C<IO::AIO::SEEK_END>).
		432
		433	The resulting absolute offset will be passed to the callback, or C<-1> in
		434	case of an error.
		435
		436	In theory, the C<$whence> constants could be different than the
		437	corresponding values from L<Fcntl>, but perl guarantees they are the same,
		438	so don't panic.
		439
		440	As a GNU/Linux (and maybe Solaris) extension, also the constants
		441	C<IO::AIO::SEEK_DATA> and C<IO::AIO::SEEK_HOLE> are available, if they
		442	could be found. No guarantees about suitability for use in C<aio_seek> or
		443	Perl's C<sysseek> can be made though, although I would naively assume they
		444	"just work".
194		445
195	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	446	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
196		447
197	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	448	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
198		449
199	Reads or writes C<length> bytes from the specified C<fh> and C<offset>	450	Reads or writes C<$length> bytes from or to the specified C<$fh> and
200	into the scalar given by C<data> and offset C<dataoffset> and calls the	451	C<$offset> into the scalar given by C<$data> and offset C<$dataoffset> and
201	callback without the actual number of bytes read (or -1 on error, just	452	calls the callback with the actual number of bytes transferred (or -1 on
202	like the syscall).	453	error, just like the syscall).
		454
		455	C<aio_read> will, like C<sysread>, shrink or grow the C<$data> scalar to
		456	offset plus the actual number of bytes read.
		457
		458	If C<$offset> is undefined, then the current file descriptor offset will
		459	be used (and updated), otherwise the file descriptor offset will not be
		460	changed by these calls.
		461
		462	If C<$length> is undefined in C<aio_write>, use the remaining length of
		463	C<$data>.
		464
		465	If C<$dataoffset> is less than zero, it will be counted from the end of
		466	C<$data>.
203		467
204	The C<$data> scalar I<MUST NOT> be modified in any way while the request	468	The C<$data> scalar I<MUST NOT> be modified in any way while the request
205	is outstanding. Modifying it can result in segfaults or WW3 (if the	469	is outstanding. Modifying it can result in segfaults or World War III (if
206	necessary/optional hardware is installed).	470	the necessary/optional hardware is installed).
207		471
208	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at	472	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at
209	offset C<0> within the scalar:	473	offset C<0> within the scalar:
210		474
211	aio_read $fh, 7, 15, $buffer, 0, sub {	475	aio_read $fh, 7, 15, $buffer, 0, sub {
212	$_[0] > 0 or die "read error: $!";	476	$_[0] > 0 or die "read error: $!";
213	print "read $_[0] bytes: <$buffer>\n";	477	print "read $_[0] bytes: <$buffer>\n";
214	};	478	};
215		479
216	=item aio_move $srcpath, $dstpath, $callback->($status)
217
218	[EXPERIMENTAL due to internal aio_group use]
219
220	Try to move the I<file> (directories not supported as either source or
221	destination) from C<$srcpath> to C<$dstpath> and call the callback with
222	the C<0> (error) or C<-1> ok.
223
224	This is a composite request that tries to rename(2) the file first. If
225	rename files with C<EXDEV>, it creates the destination file with mode 0200
226	and copies the contents of the source file into it using C<aio_sendfile>,
227	followed by restoring atime, mtime, access mode and uid/gid, in that
228	order, and unlinking the C<$srcpath>.
229
230	If an error occurs, the partial destination file will be unlinked, if
231	possible, except when setting atime, mtime, access mode and uid/gid, where
232	errors are being ignored.
233
234	=cut
235
236	sub aio_move($$$) {
237	my ($src, $dst, $cb) = @_;
238
239	my $grp = aio_group $cb;
240
241	add $grp aio_rename $src, $dst, sub {
242	if ($_[0] && $! == EXDEV) {
243	add $grp aio_open $src, O_RDONLY, 0, sub {
244	if (my $src_fh = $_[0]) {
245	my @stat = stat $src_fh;
246
247	add $grp aio_open $dst, O_WRONLY, 0200, sub {
248	if (my $dst_fh = $_[0]) {
249	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
250	close $src_fh;
251
252	if ($_[0] == $stat[7]) {
253	utime $stat[8], $stat[9], $dst;
254	chmod $stat[2] & 07777, $dst_fh;
255	chown $stat[4], $stat[5], $dst_fh;
256	close $dst_fh;
257
258	add $grp aio_unlink $src, sub {
259	$grp->result ($_[0]);
260	};
261	} else {
262	my $errno = $!;
263	add $grp aio_unlink $dst, sub {
264	$! = $errno;
265	$grp->result (-1);
266	};
267	}
268	};
269	} else {
270	$grp->result (-1);
271	}
272	},
273
274	} else {
275	$grp->result (-1);
276	}
277	};
278	} else {
279	$grp->result ($_[0]);
280	}
281	};
282
283	$grp
284	}
285		480
286	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)	481	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
287		482
288	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts	483	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
289	reading at byte offset C<$in_offset>, and starts writing at the current	484	reading at byte offset C<$in_offset>, and starts writing at the current
290	file offset of C<$out_fh>. Because of that, it is not safe to issue more	485	file offset of C<$out_fh>. Because of that, it is not safe to issue more
291	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each	486	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each
292	other.	487	other. The same C<$in_fh> works fine though, as this function does not
		488	move or use the file offset of C<$in_fh>.
293		489
		490	Please note that C<aio_sendfile> can read more bytes from C<$in_fh> than
		491	are written, and there is no way to find out how many more bytes have been
		492	read from C<aio_sendfile> alone, as C<aio_sendfile> only provides the
		493	number of bytes written to C<$out_fh>. Only if the result value equals
		494	C<$length> one can assume that C<$length> bytes have been read.
		495
		496	Unlike with other C<aio_> functions, it makes a lot of sense to use
		497	C<aio_sendfile> on non-blocking sockets, as long as one end (typically
		498	the C<$in_fh>) is a file - the file I/O will then be asynchronous, while
		499	the socket I/O will be non-blocking. Note, however, that you can run
		500	into a trap where C<aio_sendfile> reads some data with readahead, then
		501	fails to write all data, and when the socket is ready the next time, the
		502	data in the cache is already lost, forcing C<aio_sendfile> to again hit
		503	the disk. Explicit C<aio_read> + C<aio_write> let's you better control
		504	resource usage.
		505
294	This call tries to make use of a native C<sendfile> syscall to provide	506	This call tries to make use of a native C<sendfile>-like syscall to
295	zero-copy operation. For this to work, C<$out_fh> should refer to a	507	provide zero-copy operation. For this to work, C<$out_fh> should refer to
296	socket, and C<$in_fh> should refer to mmap'able file.	508	a socket, and C<$in_fh> should refer to an mmap'able file.
297		509
298	If the native sendfile call fails or is not implemented, it will be	510	If a native sendfile cannot be found or it fails with C<ENOSYS>,
299	emulated, so you can call C<aio_sendfile> on any type of filehandle	511	C<EINVAL>, C<ENOTSUP>, C<EOPNOTSUPP>, C<EAFNOSUPPORT>, C<EPROTOTYPE> or
		512	C<ENOTSOCK>, it will be emulated, so you can call C<aio_sendfile> on any
300	regardless of the limitations of the operating system.	513	type of filehandle regardless of the limitations of the operating system.
301		514
302	Please note, however, that C<aio_sendfile> can read more bytes from	515	As native sendfile syscalls (as practically any non-POSIX interface hacked
303	C<$in_fh> than are written, and there is no way to find out how many	516	together in a hurry to improve benchmark numbers) tend to be rather buggy
304	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only	517	on many systems, this implementation tries to work around some known bugs
305	provides the number of bytes written to C<$out_fh>. Only if the result	518	in Linux and FreeBSD kernels (probably others, too), but that might fail,
306	value equals C<$length> one can assume that C<$length> bytes have been	519	so you really really should check the return value of C<aio_sendfile> -
307	read.	520	fewer bytes than expected might have been transferred.
		521
308		522
309	=item aio_readahead $fh,$offset,$length, $callback->($retval)	523	=item aio_readahead $fh,$offset,$length, $callback->($retval)
310		524
311	C<aio_readahead> populates the page cache with data from a file so that	525	C<aio_readahead> populates the page cache with data from a file so that
312	subsequent reads from that file will not block on disk I/O. The C<$offset>	526	subsequent reads from that file will not block on disk I/O. The C<$offset>
…		…
315	whole pages, so that offset is effectively rounded down to a page boundary	529	whole pages, so that offset is effectively rounded down to a page boundary
316	and bytes are read up to the next page boundary greater than or equal to	530	and bytes are read up to the next page boundary greater than or equal to
317	(off-set+length). C<aio_readahead> does not read beyond the end of the	531	(off-set+length). C<aio_readahead> does not read beyond the end of the
318	file. The current file offset of the file is left unchanged.	532	file. The current file offset of the file is left unchanged.
319		533
320	If that syscall doesn't exist (likely if your OS isn't Linux) it will be	534	If that syscall doesn't exist (likely if your kernel isn't Linux) it will
321	emulated by simply reading the data, which would have a similar effect.	535	be emulated by simply reading the data, which would have a similar effect.
		536
322		537
323	=item aio_stat $fh_or_path, $callback->($status)	538	=item aio_stat $fh_or_path, $callback->($status)
324		539
325	=item aio_lstat $fh, $callback->($status)	540	=item aio_lstat $fh, $callback->($status)
326		541
…		…
332	for an explanation.	547	for an explanation.
333		548
334	Currently, the stats are always 64-bit-stats, i.e. instead of returning an	549	Currently, the stats are always 64-bit-stats, i.e. instead of returning an
335	error when stat'ing a large file, the results will be silently truncated	550	error when stat'ing a large file, the results will be silently truncated
336	unless perl itself is compiled with large file support.	551	unless perl itself is compiled with large file support.
		552
		553	To help interpret the mode and dev/rdev stat values, IO::AIO offers the
		554	following constants and functions (if not implemented, the constants will
		555	be C<0> and the functions will either C<croak> or fall back on traditional
		556	behaviour).
		557
		558	C<S_IFMT>, C<S_IFIFO>, C<S_IFCHR>, C<S_IFBLK>, C<S_IFLNK>, C<S_IFREG>,
		559	C<S_IFDIR>, C<S_IFWHT>, C<S_IFSOCK>, C<IO::AIO::major $dev_t>,
		560	C<IO::AIO::minor $dev_t>, C<IO::AIO::makedev $major, $minor>.
337		561
338	Example: Print the length of F</etc/passwd>:	562	Example: Print the length of F</etc/passwd>:
339		563
340	aio_stat "/etc/passwd", sub {	564	aio_stat "/etc/passwd", sub {
341	$_[0] and die "stat failed: $!";	565	$_[0] and die "stat failed: $!";
342	print "size is ", -s _, "\n";	566	print "size is ", -s _, "\n";
343	};	567	};
344		568
		569
		570	=item aio_statvfs $fh_or_path, $callback->($statvfs)
		571
		572	Works like the POSIX C<statvfs> or C<fstatvfs> syscalls, depending on
		573	whether a file handle or path was passed.
		574
		575	On success, the callback is passed a hash reference with the following
		576	members: C<bsize>, C<frsize>, C<blocks>, C<bfree>, C<bavail>, C<files>,
		577	C<ffree>, C<favail>, C<fsid>, C<flag> and C<namemax>. On failure, C<undef>
		578	is passed.
		579
		580	The following POSIX IO::AIO::ST_* constants are defined: C<ST_RDONLY> and
		581	C<ST_NOSUID>.
		582
		583	The following non-POSIX IO::AIO::ST_* flag masks are defined to
		584	their correct value when available, or to C<0> on systems that do
		585	not support them: C<ST_NODEV>, C<ST_NOEXEC>, C<ST_SYNCHRONOUS>,
		586	C<ST_MANDLOCK>, C<ST_WRITE>, C<ST_APPEND>, C<ST_IMMUTABLE>, C<ST_NOATIME>,
		587	C<ST_NODIRATIME> and C<ST_RELATIME>.
		588
		589	Example: stat C</wd> and dump out the data if successful.
		590
		591	aio_statvfs "/wd", sub {
		592	my $f = $_[0]
		593	or die "statvfs: $!";
		594
		595	use Data::Dumper;
		596	say Dumper $f;
		597	};
		598
		599	# result:
		600	{
		601	bsize => 1024,
		602	bfree => 4333064312,
		603	blocks => 10253828096,
		604	files => 2050765568,
		605	flag => 4096,
		606	favail => 2042092649,
		607	bavail => 4333064312,
		608	ffree => 2042092649,
		609	namemax => 255,
		610	frsize => 1024,
		611	fsid => 1810
		612	}
		613
		614	Here is a (likely partial - send me updates!) list of fsid values used by
		615	Linux - it is safe to hardcode these when C<$^O> is C<linux>:
		616
		617	0x0000adf5 adfs
		618	0x0000adff affs
		619	0x5346414f afs
		620	0x09041934 anon-inode filesystem
		621	0x00000187 autofs
		622	0x42465331 befs
		623	0x1badface bfs
		624	0x42494e4d binfmt_misc
		625	0x9123683e btrfs
		626	0x0027e0eb cgroupfs
		627	0xff534d42 cifs
		628	0x73757245 coda
		629	0x012ff7b7 coh
		630	0x28cd3d45 cramfs
		631	0x453dcd28 cramfs-wend (wrong endianness)
		632	0x64626720 debugfs
		633	0x00001373 devfs
		634	0x00001cd1 devpts
		635	0x0000f15f ecryptfs
		636	0x00414a53 efs
		637	0x0000137d ext
		638	0x0000ef53 ext2/ext3/ext4
		639	0x0000ef51 ext2
		640	0xf2f52010 f2fs
		641	0x00004006 fat
		642	0x65735546 fuseblk
		643	0x65735543 fusectl
		644	0x0bad1dea futexfs
		645	0x01161970 gfs2
		646	0x47504653 gpfs
		647	0x00004244 hfs
		648	0xf995e849 hpfs
		649	0x00c0ffee hostfs
		650	0x958458f6 hugetlbfs
		651	0x2bad1dea inotifyfs
		652	0x00009660 isofs
		653	0x000072b6 jffs2
		654	0x3153464a jfs
		655	0x6b414653 k-afs
		656	0x0bd00bd0 lustre
		657	0x0000137f minix
		658	0x0000138f minix 30 char names
		659	0x00002468 minix v2
		660	0x00002478 minix v2 30 char names
		661	0x00004d5a minix v3
		662	0x19800202 mqueue
		663	0x00004d44 msdos
		664	0x0000564c novell
		665	0x00006969 nfs
		666	0x6e667364 nfsd
		667	0x00003434 nilfs
		668	0x5346544e ntfs
		669	0x00009fa1 openprom
		670	0x7461636F ocfs2
		671	0x00009fa0 proc
		672	0x6165676c pstorefs
		673	0x0000002f qnx4
		674	0x68191122 qnx6
		675	0x858458f6 ramfs
		676	0x52654973 reiserfs
		677	0x00007275 romfs
		678	0x67596969 rpc_pipefs
		679	0x73636673 securityfs
		680	0xf97cff8c selinux
		681	0x0000517b smb
		682	0x534f434b sockfs
		683	0x73717368 squashfs
		684	0x62656572 sysfs
		685	0x012ff7b6 sysv2
		686	0x012ff7b5 sysv4
		687	0x01021994 tmpfs
		688	0x15013346 udf
		689	0x00011954 ufs
		690	0x54190100 ufs byteswapped
		691	0x00009fa2 usbdevfs
		692	0x01021997 v9fs
		693	0xa501fcf5 vxfs
		694	0xabba1974 xenfs
		695	0x012ff7b4 xenix
		696	0x58465342 xfs
		697	0x012fd16d xia
		698
		699	=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
		700
		701	Works like perl's C<utime> function (including the special case of $atime
		702	and $mtime being undef). Fractional times are supported if the underlying
		703	syscalls support them.
		704
		705	When called with a pathname, uses utimes(2) if available, otherwise
		706	utime(2). If called on a file descriptor, uses futimes(2) if available,
		707	otherwise returns ENOSYS, so this is not portable.
		708
		709	Examples:
		710
		711	# set atime and mtime to current time (basically touch(1)):
		712	aio_utime "path", undef, undef;
		713	# set atime to current time and mtime to beginning of the epoch:
		714	aio_utime "path", time, undef; # undef==0
		715
		716
		717	=item aio_chown $fh_or_path, $uid, $gid, $callback->($status)
		718
		719	Works like perl's C<chown> function, except that C<undef> for either $uid
		720	or $gid is being interpreted as "do not change" (but -1 can also be used).
		721
		722	Examples:
		723
		724	# same as "chown root path" in the shell:
		725	aio_chown "path", 0, -1;
		726	# same as above:
		727	aio_chown "path", 0, undef;
		728
		729
		730	=item aio_truncate $fh_or_path, $offset, $callback->($status)
		731
		732	Works like truncate(2) or ftruncate(2).
		733
		734
		735	=item aio_allocate $fh, $mode, $offset, $len, $callback->($status)
		736
		737	Allocates or frees disk space according to the C<$mode> argument. See the
		738	linux C<fallocate> documentation for details.
		739
		740	C<$mode> is usually C<0> or C<IO::AIO::FALLOC_FL_KEEP_SIZE> to allocate
		741	space, or C<IO::AIO::FALLOC_FL_PUNCH_HOLE | IO::AIO::FALLOC_FL_KEEP_SIZE>,
		742	to deallocate a file range.
		743
		744	IO::AIO also supports C<FALLOC_FL_COLLAPSE_RANGE>, to remove a range
		745	(without leaving a hole) and C<FALLOC_FL_ZERO_RANGE>, to zero a range (see
		746	your L<fallocate(2)> manpage).
		747
		748	The file system block size used by C<fallocate> is presumably the
		749	C<f_bsize> returned by C<statvfs>.
		750
		751	If C<fallocate> isn't available or cannot be emulated (currently no
		752	emulation will be attempted), passes C<-1> and sets C<$!> to C<ENOSYS>.
		753
		754
		755	=item aio_chmod $fh_or_path, $mode, $callback->($status)
		756
		757	Works like perl's C<chmod> function.
		758
		759
345	=item aio_unlink $pathname, $callback->($status)	760	=item aio_unlink $pathname, $callback->($status)
346		761
347	Asynchronously unlink (delete) a file and call the callback with the	762	Asynchronously unlink (delete) a file and call the callback with the
348	result code.	763	result code.
349		764
		765
		766	=item aio_mknod $pathname, $mode, $dev, $callback->($status)
		767
		768	[EXPERIMENTAL]
		769
		770	Asynchronously create a device node (or fifo). See mknod(2).
		771
		772	The only (POSIX-) portable way of calling this function is:
		773
		774	aio_mknod $pathname, IO::AIO::S_IFIFO | $mode, 0, sub { ...
		775
		776	See C<aio_stat> for info about some potentially helpful extra constants
		777	and functions.
		778
350	=item aio_link $srcpath, $dstpath, $callback->($status)	779	=item aio_link $srcpath, $dstpath, $callback->($status)
351		780
352	Asynchronously create a new link to the existing object at C<$srcpath> at	781	Asynchronously create a new link to the existing object at C<$srcpath> at
353	the path C<$dstpath> and call the callback with the result code.	782	the path C<$dstpath> and call the callback with the result code.
354		783
		784
355	=item aio_symlink $srcpath, $dstpath, $callback->($status)	785	=item aio_symlink $srcpath, $dstpath, $callback->($status)
356		786
357	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at	787	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at
358	the path C<$dstpath> and call the callback with the result code.	788	the path C<$dstpath> and call the callback with the result code.
359		789
		790
		791	=item aio_readlink $pathname, $callback->($link)
		792
		793	Asynchronously read the symlink specified by C<$path> and pass it to
		794	the callback. If an error occurs, nothing or undef gets passed to the
		795	callback.
		796
		797
		798	=item aio_realpath $pathname, $callback->($path)
		799
		800	Asynchronously make the path absolute and resolve any symlinks in
		801	C<$path>. The resulting path only consists of directories (same as
		802	L<Cwd::realpath>).
		803
		804	This request can be used to get the absolute path of the current working
		805	directory by passing it a path of F<.> (a single dot).
		806
		807
360	=item aio_rename $srcpath, $dstpath, $callback->($status)	808	=item aio_rename $srcpath, $dstpath, $callback->($status)
361		809
362	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as	810	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as
363	rename(2) and call the callback with the result code.	811	rename(2) and call the callback with the result code.
364		812
		813	On systems that support the AIO::WD working directory abstraction
		814	natively, the case C<[$wd, "."]> as C<$srcpath> is specialcased - instead
		815	of failing, C<rename> is called on the absolute path of C<$wd>.
		816
		817
		818	=item aio_rename2 $srcpath, $dstpath, $flags, $callback->($status)
		819
		820	Basically a version of C<aio_rename> with an additional C<$flags>
		821	argument. Calling this with C<$flags=0> is the same as calling
		822	C<aio_rename>.
		823
		824	Non-zero flags are currently only supported on GNU/Linux systems that
		825	support renameat2. Other systems fail with C<ENOSYS> in this case.
		826
		827	The following constants are available (missing ones are, as usual C<0>),
		828	see renameat2(2) for details:
		829
		830	C<IO::AIO::RENAME_NOREPLACE>, C<IO::AIO::RENAME_EXCHANGE>
		831	and C<IO::AIO::RENAME_WHITEOUT>.
		832
		833
		834	=item aio_mkdir $pathname, $mode, $callback->($status)
		835
		836	Asynchronously mkdir (create) a directory and call the callback with
		837	the result code. C<$mode> will be modified by the umask at the time the
		838	request is executed, so do not change your umask.
		839
		840
365	=item aio_rmdir $pathname, $callback->($status)	841	=item aio_rmdir $pathname, $callback->($status)
366		842
367	Asynchronously rmdir (delete) a directory and call the callback with the	843	Asynchronously rmdir (delete) a directory and call the callback with the
368	result code.	844	result code.
		845
		846	On systems that support the AIO::WD working directory abstraction
		847	natively, the case C<[$wd, "."]> is specialcased - instead of failing,
		848	C<rmdir> is called on the absolute path of C<$wd>.
		849
369		850
370	=item aio_readdir $pathname, $callback->($entries)	851	=item aio_readdir $pathname, $callback->($entries)
371		852
372	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire	853	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
373	directory (i.e. opendir + readdir + closedir). The entries will not be	854	directory (i.e. opendir + readdir + closedir). The entries will not be
374	sorted, and will B<NOT> include the C<.> and C<..> entries.	855	sorted, and will B<NOT> include the C<.> and C<..> entries.
375		856
376	The callback a single argument which is either C<undef> or an array-ref	857	The callback is passed a single argument which is either C<undef> or an
377	with the filenames.	858	array-ref with the filenames.
378		859
		860
		861	=item aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		862
		863	Quite similar to C<aio_readdir>, but the C<$flags> argument allows one to
		864	tune behaviour and output format. In case of an error, C<$entries> will be
		865	C<undef>.
		866
		867	The flags are a combination of the following constants, ORed together (the
		868	flags will also be passed to the callback, possibly modified):
		869
		870	=over 4
		871
		872	=item IO::AIO::READDIR_DENTS
		873
		874	When this flag is off, then the callback gets an arrayref consisting of
		875	names only (as with C<aio_readdir>), otherwise it gets an arrayref with
		876	C<[$name, $type, $inode]> arrayrefs, each describing a single directory
		877	entry in more detail.
		878
		879	C<$name> is the name of the entry.
		880
		881	C<$type> is one of the C<IO::AIO::DT_xxx> constants:
		882
		883	C<IO::AIO::DT_UNKNOWN>, C<IO::AIO::DT_FIFO>, C<IO::AIO::DT_CHR>, C<IO::AIO::DT_DIR>,
		884	C<IO::AIO::DT_BLK>, C<IO::AIO::DT_REG>, C<IO::AIO::DT_LNK>, C<IO::AIO::DT_SOCK>,
		885	C<IO::AIO::DT_WHT>.
		886
		887	C<IO::AIO::DT_UNKNOWN> means just that: readdir does not know. If you need to
		888	know, you have to run stat yourself. Also, for speed reasons, the C<$type>
		889	scalars are read-only: you can not modify them.
		890
		891	C<$inode> is the inode number (which might not be exact on systems with 64
		892	bit inode numbers and 32 bit perls). This field has unspecified content on
		893	systems that do not deliver the inode information.
		894
		895	=item IO::AIO::READDIR_DIRS_FIRST
		896
		897	When this flag is set, then the names will be returned in an order where
		898	likely directories come first, in optimal stat order. This is useful when
		899	you need to quickly find directories, or you want to find all directories
		900	while avoiding to stat() each entry.
		901
		902	If the system returns type information in readdir, then this is used
		903	to find directories directly. Otherwise, likely directories are names
		904	beginning with ".", or otherwise names with no dots, of which names with
		905	short names are tried first.
		906
		907	=item IO::AIO::READDIR_STAT_ORDER
		908
		909	When this flag is set, then the names will be returned in an order
		910	suitable for stat()'ing each one. That is, when you plan to stat()
		911	all files in the given directory, then the returned order will likely
		912	be fastest.
		913
		914	If both this flag and C<IO::AIO::READDIR_DIRS_FIRST> are specified, then
		915	the likely dirs come first, resulting in a less optimal stat order.
		916
		917	=item IO::AIO::READDIR_FOUND_UNKNOWN
		918
		919	This flag should not be set when calling C<aio_readdirx>. Instead, it
		920	is being set by C<aio_readdirx>, when any of the C<$type>'s found were
		921	C<IO::AIO::DT_UNKNOWN>. The absence of this flag therefore indicates that all
		922	C<$type>'s are known, which can be used to speed up some algorithms.
		923
		924	=back
		925
		926
		927	=item aio_load $pathname, $data, $callback->($status)
		928
		929	This is a composite request that tries to fully load the given file into
		930	memory. Status is the same as with aio_read.
		931
		932	=cut
		933
		934	sub aio_load($$;$) {
		935	my ($path, undef, $cb) = @_;
		936	my $data = \$_[1];
		937
		938	my $pri = aioreq_pri;
		939	my $grp = aio_group $cb;
		940
		941	aioreq_pri $pri;
		942	add $grp aio_open $path, O_RDONLY, 0, sub {
		943	my $fh = shift
		944	or return $grp->result (-1);
		945
		946	aioreq_pri $pri;
		947	add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub {
		948	$grp->result ($_[0]);
		949	};
		950	};
		951
		952	$grp
		953	}
		954
		955	=item aio_copy $srcpath, $dstpath, $callback->($status)
		956
		957	Try to copy the I<file> (directories not supported as either source or
		958	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		959	a status of C<0> (ok) or C<-1> (error, see C<$!>).
		960
		961	This is a composite request that creates the destination file with
		962	mode 0200 and copies the contents of the source file into it using
		963	C<aio_sendfile>, followed by restoring atime, mtime, access mode and
		964	uid/gid, in that order.
		965
		966	If an error occurs, the partial destination file will be unlinked, if
		967	possible, except when setting atime, mtime, access mode and uid/gid, where
		968	errors are being ignored.
		969
		970	=cut
		971
		972	sub aio_copy($$;$) {
		973	my ($src, $dst, $cb) = @_;
		974
		975	my $pri = aioreq_pri;
		976	my $grp = aio_group $cb;
		977
		978	aioreq_pri $pri;
		979	add $grp aio_open $src, O_RDONLY, 0, sub {
		980	if (my $src_fh = $_[0]) {
		981	my @stat = stat $src_fh; # hmm, might block over nfs?
		982
		983	aioreq_pri $pri;
		984	add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {
		985	if (my $dst_fh = $_[0]) {
		986	aioreq_pri $pri;
		987	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
		988	if ($_[0] == $stat[7]) {
		989	$grp->result (0);
		990	close $src_fh;
		991
		992	my $ch = sub {
		993	aioreq_pri $pri;
		994	add $grp aio_chmod $dst_fh, $stat[2] & 07777, sub {
		995	aioreq_pri $pri;
		996	add $grp aio_chown $dst_fh, $stat[4], $stat[5], sub {
		997	aioreq_pri $pri;
		998	add $grp aio_close $dst_fh;
		999	}
		1000	};
		1001	};
		1002
		1003	aioreq_pri $pri;
		1004	add $grp aio_utime $dst_fh, $stat[8], $stat[9], sub {
		1005	if ($_[0] < 0 && $! == ENOSYS) {
		1006	aioreq_pri $pri;
		1007	add $grp aio_utime $dst, $stat[8], $stat[9], $ch;
		1008	} else {
		1009	$ch->();
		1010	}
		1011	};
		1012	} else {
		1013	$grp->result (-1);
		1014	close $src_fh;
		1015	close $dst_fh;
		1016
		1017	aioreq $pri;
		1018	add $grp aio_unlink $dst;
		1019	}
		1020	};
		1021	} else {
		1022	$grp->result (-1);
		1023	}
		1024	},
		1025
		1026	} else {
		1027	$grp->result (-1);
		1028	}
		1029	};
		1030
		1031	$grp
		1032	}
		1033
		1034	=item aio_move $srcpath, $dstpath, $callback->($status)
		1035
		1036	Try to move the I<file> (directories not supported as either source or
		1037	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		1038	a status of C<0> (ok) or C<-1> (error, see C<$!>).
		1039
		1040	This is a composite request that tries to rename(2) the file first; if
		1041	rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if
		1042	that is successful, unlinks the C<$srcpath>.
		1043
		1044	=cut
		1045
		1046	sub aio_move($$;$) {
		1047	my ($src, $dst, $cb) = @_;
		1048
		1049	my $pri = aioreq_pri;
		1050	my $grp = aio_group $cb;
		1051
		1052	aioreq_pri $pri;
		1053	add $grp aio_rename $src, $dst, sub {
		1054	if ($_[0] && $! == EXDEV) {
		1055	aioreq_pri $pri;
		1056	add $grp aio_copy $src, $dst, sub {
		1057	$grp->result ($_[0]);
		1058
		1059	unless ($_[0]) {
		1060	aioreq_pri $pri;
		1061	add $grp aio_unlink $src;
		1062	}
		1063	};
		1064	} else {
		1065	$grp->result ($_[0]);
		1066	}
		1067	};
		1068
		1069	$grp
		1070	}
		1071
379	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)	1072	=item aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs)
380
381	[EXPERIMENTAL due to internal aio_group use]
382		1073
383	Scans a directory (similar to C<aio_readdir>) but additionally tries to	1074	Scans a directory (similar to C<aio_readdir>) but additionally tries to
384	separate the entries of directory C<$path> into two sets of names, ones	1075	efficiently separate the entries of directory C<$path> into two sets of
385	you can recurse into (directories or links to them), and ones you cannot	1076	names, directories you can recurse into (directories), and ones you cannot
386	recurse into (everything else).	1077	recurse into (everything else, including symlinks to directories).
387		1078
388	C<aio_scandir> is a composite request that creates of many sub requests_	1079	C<aio_scandir> is a composite request that creates of many sub requests_
389	C<$maxreq> specifies the maximum number of outstanding aio requests that	1080	C<$maxreq> specifies the maximum number of outstanding aio requests that
390	this function generates. If it is C<< <= 0 >>, then a suitable default	1081	this function generates. If it is C<< <= 0 >>, then a suitable default
391	will be chosen (currently 6).	1082	will be chosen (currently 4).
392		1083
393	On error, the callback is called without arguments, otherwise it receives	1084	On error, the callback is called without arguments, otherwise it receives
394	two array-refs with path-relative entry names.	1085	two array-refs with path-relative entry names.
395		1086
396	Example:	1087	Example:
…		…
403		1094
404	Implementation notes.	1095	Implementation notes.
405		1096
406	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.	1097	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.
407		1098
		1099	If readdir returns file type information, then this is used directly to
		1100	find directories.
		1101
408	After reading the directory, the modification time, size etc. of the	1102	Otherwise, after reading the directory, the modification time, size etc.
409	directory before and after the readdir is checked, and if they match (and	1103	of the directory before and after the readdir is checked, and if they
410	isn't the current time), the link count will be used to decide how many	1104	match (and isn't the current time), the link count will be used to decide
411	entries are directories (if >= 2). Otherwise, no knowledge of the number	1105	how many entries are directories (if >= 2). Otherwise, no knowledge of the
412	of subdirectories will be assumed.	1106	number of subdirectories will be assumed.
413		1107
414	Then entries will be sorted into likely directories (everything without	1108	Then entries will be sorted into likely directories a non-initial dot
415	a non-initial dot currently) and likely non-directories (everything	1109	currently) and likely non-directories (see C<aio_readdirx>). Then every
416	else). Then every entry plus an appended C</.> will be C<stat>'ed,	1110	entry plus an appended C</.> will be C<stat>'ed, likely directories first,
417	likely directories first. If that succeeds, it assumes that the entry	1111	in order of their inode numbers. If that succeeds, it assumes that the
418	is a directory or a symlink to directory (which will be checked	1112	entry is a directory or a symlink to directory (which will be checked
419	seperately). This is often faster than stat'ing the entry itself because	1113	separately). This is often faster than stat'ing the entry itself because
420	filesystems might detect the type of the entry without reading the inode	1114	filesystems might detect the type of the entry without reading the inode
421	data (e.g. ext2fs filetype feature).	1115	data (e.g. ext2fs filetype feature), even on systems that cannot return
		1116	the filetype information on readdir.
422		1117
423	If the known number of directories (link count - 2) has been reached, the	1118	If the known number of directories (link count - 2) has been reached, the
424	rest of the entries is assumed to be non-directories.	1119	rest of the entries is assumed to be non-directories.
425		1120
426	This only works with certainty on POSIX (= UNIX) filesystems, which	1121	This only works with certainty on POSIX (= UNIX) filesystems, which
…		…
430	as those tend to return 0 or 1 as link counts, which disables the	1125	as those tend to return 0 or 1 as link counts, which disables the
431	directory counting heuristic.	1126	directory counting heuristic.
432		1127
433	=cut	1128	=cut
434		1129
435	sub aio_scandir($$$) {	1130	sub aio_scandir($$;$) {
436	my ($path, $maxreq, $cb) = @_;	1131	my ($path, $maxreq, $cb) = @_;
437		1132
		1133	my $pri = aioreq_pri;
		1134
438	my $grp = aio_group $cb;	1135	my $grp = aio_group $cb;
439		1136
440	$maxreq = 6 if $maxreq <= 0;	1137	$maxreq = 4 if $maxreq <= 0;
441		1138
442	# stat once	1139	# get a wd object
		1140	aioreq_pri $pri;
443	add $grp aio_stat $path, sub {	1141	add $grp aio_wd $path, sub {
		1142	$_[0]
		1143	or return $grp->result ();
		1144
		1145	my $wd = [shift, "."];
		1146
		1147	# stat once
		1148	aioreq_pri $pri;
		1149	add $grp aio_stat $wd, sub {
444	return $grp->result () if $_[0];	1150	return $grp->result () if $_[0];
445	my $now = time;	1151	my $now = time;
446	my $hash1 = join ":", (stat _)[0,1,3,7,9];	1152	my $hash1 = join ":", (stat _)[0,1,3,7,9];
447		1153
448	# read the directory entries	1154	# read the directory entries
449	add $grp aio_readdir $path, sub {	1155	aioreq_pri $pri;
		1156	add $grp aio_readdirx $wd, READDIR_DIRS_FIRST, sub {
450	my $entries = shift	1157	my $entries = shift
451	or return $grp->result ();	1158	or return $grp->result ();
452		1159
453	# stat the dir another time	1160	# stat the dir another time
		1161	aioreq_pri $pri;
454	add $grp aio_stat $path, sub {	1162	add $grp aio_stat $wd, sub {
455	my $hash2 = join ":", (stat _)[0,1,3,7,9];	1163	my $hash2 = join ":", (stat _)[0,1,3,7,9];
456		1164
457	my $ndirs;	1165	my $ndirs;
458		1166
459	# take the slow route if anything looks fishy	1167	# take the slow route if anything looks fishy
460	if ($hash1 ne $hash2 or (stat _)[9] == $now) {	1168	if ($hash1 ne $hash2 or (stat _)[9] == $now) {
461	$ndirs = -1;	1169	$ndirs = -1;
462	} else {	1170	} else {
463	# if nlink == 2, we are finished	1171	# if nlink == 2, we are finished
464	# on non-posix-fs's, we rely on nlink < 2	1172	# for non-posix-fs's, we rely on nlink < 2
465	$ndirs = (stat _)[3] - 2	1173	$ndirs = (stat _)[3] - 2
466	or return $grp->result ([], $entries);	1174	or return $grp->result ([], $entries);
467	}	1175	}
468		1176
469	# sort into likely dirs and likely nondirs
470	# dirs == files without ".", short entries first
471	$entries = [map $_->[0],
472	sort { $b->[1] cmp $a->[1] }
473	map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],
474	@$entries];
475
476	my (@dirs, @nondirs);	1177	my (@dirs, @nondirs);
477		1178
478	my ($statcb, $schedcb);
479	my $nreq = 0;
480
481	my $statgrp = add $grp aio_group;	1179	my $statgrp = add $grp aio_group sub {
482
483	$schedcb = sub {
484	if (@$entries) {
485	if ($nreq < $maxreq) {
486	my $ent = pop @$entries;
487	$nreq++;
488	add $statgrp aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) };
489	}
490	} elsif (!$nreq) {
491	# finished
492	$statgrp->cancel;
493	undef $statcb;
494	undef $schedcb;
495	$grp->result (\@dirs, \@nondirs);	1180	$grp->result (\@dirs, \@nondirs);
496	}	1181	};
		1182
		1183	limit $statgrp $maxreq;
		1184	feed $statgrp sub {
		1185	return unless @$entries;
		1186	my $entry = shift @$entries;
		1187
		1188	aioreq_pri $pri;
		1189	$wd->[1] = "$entry/.";
		1190	add $statgrp aio_stat $wd, sub {
		1191	if ($_[0] < 0) {
		1192	push @nondirs, $entry;
		1193	} else {
		1194	# need to check for real directory
		1195	aioreq_pri $pri;
		1196	$wd->[1] = $entry;
		1197	add $statgrp aio_lstat $wd, sub {
		1198	if (-d _) {
		1199	push @dirs, $entry;
		1200
		1201	unless (--$ndirs) {
		1202	push @nondirs, @$entries;
		1203	feed $statgrp;
		1204	}
		1205	} else {
		1206	push @nondirs, $entry;
		1207	}
		1208	}
		1209	}
		1210	};
		1211	};
497	};	1212	};
498	$statcb = sub {
499	my ($status, $entry) = @_;
500
501	if ($status < 0) {
502	$nreq--;
503	push @nondirs, $entry;
504	&$schedcb;
505	} else {
506	# need to check for real directory
507	add $grp aio_lstat "$path/$entry", sub {
508	$nreq--;
509
510	if (-d _) {
511	push @dirs, $entry;
512
513	if (!--$ndirs) {
514	push @nondirs, @$entries;
515	$entries = [];
516	}
517	} else {
518	push @nondirs, $entry;
519	}
520
521	&$schedcb;
522	}
523	}
524	};
525
526	&$schedcb while @$entries && $nreq < $maxreq;
527	};	1213	};
528	};	1214	};
529	};	1215	};
530		1216
531	$grp	1217	$grp
532	}	1218	}
533		1219
		1220	=item aio_rmtree $pathname, $callback->($status)
		1221
		1222	Delete a directory tree starting (and including) C<$path>, return the
		1223	status of the final C<rmdir> only. This is a composite request that
		1224	uses C<aio_scandir> to recurse into and rmdir directories, and unlink
		1225	everything else.
		1226
		1227	=cut
		1228
		1229	sub aio_rmtree;
		1230	sub aio_rmtree($;$) {
		1231	my ($path, $cb) = @_;
		1232
		1233	my $pri = aioreq_pri;
		1234	my $grp = aio_group $cb;
		1235
		1236	aioreq_pri $pri;
		1237	add $grp aio_scandir $path, 0, sub {
		1238	my ($dirs, $nondirs) = @_;
		1239
		1240	my $dirgrp = aio_group sub {
		1241	add $grp aio_rmdir $path, sub {
		1242	$grp->result ($_[0]);
		1243	};
		1244	};
		1245
		1246	(aioreq_pri $pri), add $dirgrp aio_rmtree "$path/$_" for @$dirs;
		1247	(aioreq_pri $pri), add $dirgrp aio_unlink "$path/$_" for @$nondirs;
		1248
		1249	add $grp $dirgrp;
		1250	};
		1251
		1252	$grp
		1253	}
		1254
		1255	=item aio_fcntl $fh, $cmd, $arg, $callback->($status)
		1256
		1257	=item aio_ioctl $fh, $request, $buf, $callback->($status)
		1258
		1259	These work just like the C<fcntl> and C<ioctl> built-in functions, except
		1260	they execute asynchronously and pass the return value to the callback.
		1261
		1262	Both calls can be used for a lot of things, some of which make more sense
		1263	to run asynchronously in their own thread, while some others make less
		1264	sense. For example, calls that block waiting for external events, such
		1265	as locking, will also lock down an I/O thread while it is waiting, which
		1266	can deadlock the whole I/O system. At the same time, there might be no
		1267	alternative to using a thread to wait.
		1268
		1269	So in general, you should only use these calls for things that do
		1270	(filesystem) I/O, not for things that wait for other events (network,
		1271	other processes), although if you are careful and know what you are doing,
		1272	you still can.
		1273
		1274	The following constants are available (missing ones are, as usual C<0>):
		1275
		1276	C<F_DUPFD_CLOEXEC>,
		1277
		1278	C<F_OFD_GETLK>, C<F_OFD_SETLK>, C<F_OFD_GETLKW>,
		1279
		1280	C<FIFREEZE>, C<FITHAW>, C<FITRIM>, C<FICLONE>, C<FICLONERANGE>, C<FIDEDUPERANGE>.
		1281
		1282	C<FS_IOC_GETFLAGS>, C<FS_IOC_SETFLAGS>, C<FS_IOC_GETVERSION>, C<FS_IOC_SETVERSION>,
		1283	C<FS_IOC_FIEMAP>.
		1284
		1285	C<FS_IOC_FSGETXATTR>, C<FS_IOC_FSSETXATTR>, C<FS_IOC_SET_ENCRYPTION_POLICY>,
		1286	C<FS_IOC_GET_ENCRYPTION_PWSALT>, C<FS_IOC_GET_ENCRYPTION_POLICY>, C<FS_KEY_DESCRIPTOR_SIZE>.
		1287
		1288	C<FS_SECRM_FL>, C<FS_UNRM_FL>, C<FS_COMPR_FL>, C<FS_SYNC_FL>, C<FS_IMMUTABLE_FL>,
		1289	C<FS_APPEND_FL>, C<FS_NODUMP_FL>, C<FS_NOATIME_FL>, C<FS_DIRTY_FL>,
		1290	C<FS_COMPRBLK_FL>, C<FS_NOCOMP_FL>, C<FS_ENCRYPT_FL>, C<FS_BTREE_FL>,
		1291	C<FS_INDEX_FL>, C<FS_JOURNAL_DATA_FL>, C<FS_NOTAIL_FL>, C<FS_DIRSYNC_FL>, C<FS_TOPDIR_FL>,
		1292	C<FS_FL_USER_MODIFIABLE>.
		1293
		1294	C<FS_XFLAG_REALTIME>, C<FS_XFLAG_PREALLOC>, C<FS_XFLAG_IMMUTABLE>, C<FS_XFLAG_APPEND>,
		1295	C<FS_XFLAG_SYNC>, C<FS_XFLAG_NOATIME>, C<FS_XFLAG_NODUMP>, C<FS_XFLAG_RTINHERIT>,
		1296	C<FS_XFLAG_PROJINHERIT>, C<FS_XFLAG_NOSYMLINKS>, C<FS_XFLAG_EXTSIZE>, C<FS_XFLAG_EXTSZINHERIT>,
		1297	C<FS_XFLAG_NODEFRAG>, C<FS_XFLAG_FILESTREAM>, C<FS_XFLAG_DAX>, C<FS_XFLAG_HASATTR>,
		1298
		1299	=item aio_sync $callback->($status)
		1300
		1301	Asynchronously call sync and call the callback when finished.
		1302
534	=item aio_fsync $fh, $callback->($status)	1303	=item aio_fsync $fh, $callback->($status)
535		1304
536	Asynchronously call fsync on the given filehandle and call the callback	1305	Asynchronously call fsync on the given filehandle and call the callback
537	with the fsync result code.	1306	with the fsync result code.
538		1307
…		…
542	callback with the fdatasync result code.	1311	callback with the fdatasync result code.
543		1312
544	If this call isn't available because your OS lacks it or it couldn't be	1313	If this call isn't available because your OS lacks it or it couldn't be
545	detected, it will be emulated by calling C<fsync> instead.	1314	detected, it will be emulated by calling C<fsync> instead.
546		1315
		1316	=item aio_syncfs $fh, $callback->($status)
		1317
		1318	Asynchronously call the syncfs syscall to sync the filesystem associated
		1319	to the given filehandle and call the callback with the syncfs result
		1320	code. If syncfs is not available, calls sync(), but returns C<-1> and sets
		1321	errno to C<ENOSYS> nevertheless.
		1322
		1323	=item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		1324
		1325	Sync the data portion of the file specified by C<$offset> and C<$length>
		1326	to disk (but NOT the metadata), by calling the Linux-specific
		1327	sync_file_range call. If sync_file_range is not available or it returns
		1328	ENOSYS, then fdatasync or fsync is being substituted.
		1329
		1330	C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>,
		1331	C<IO::AIO::SYNC_FILE_RANGE_WRITE> and
		1332	C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range
		1333	manpage for details.
		1334
		1335	=item aio_pathsync $pathname, $callback->($status)
		1336
		1337	This request tries to open, fsync and close the given path. This is a
		1338	composite request intended to sync directories after directory operations
		1339	(E.g. rename). This might not work on all operating systems or have any
		1340	specific effect, but usually it makes sure that directory changes get
		1341	written to disc. It works for anything that can be opened for read-only,
		1342	not just directories.
		1343
		1344	Future versions of this function might fall back to other methods when
		1345	C<fsync> on the directory fails (such as calling C<sync>).
		1346
		1347	Passes C<0> when everything went ok, and C<-1> on error.
		1348
		1349	=cut
		1350
		1351	sub aio_pathsync($;$) {
		1352	my ($path, $cb) = @_;
		1353
		1354	my $pri = aioreq_pri;
		1355	my $grp = aio_group $cb;
		1356
		1357	aioreq_pri $pri;
		1358	add $grp aio_open $path, O_RDONLY, 0, sub {
		1359	my ($fh) = @_;
		1360	if ($fh) {
		1361	aioreq_pri $pri;
		1362	add $grp aio_fsync $fh, sub {
		1363	$grp->result ($_[0]);
		1364
		1365	aioreq_pri $pri;
		1366	add $grp aio_close $fh;
		1367	};
		1368	} else {
		1369	$grp->result (-1);
		1370	}
		1371	};
		1372
		1373	$grp
		1374	}
		1375
		1376	=item aio_msync $scalar, $offset = 0, $length = undef, flags = MS_SYNC, $callback->($status)
		1377
		1378	This is a rather advanced IO::AIO call, which only works on mmap(2)ed
		1379	scalars (see the C<IO::AIO::mmap> function, although it also works on data
		1380	scalars managed by the L<Sys::Mmap> or L<Mmap> modules, note that the
		1381	scalar must only be modified in-place while an aio operation is pending on
		1382	it).
		1383
		1384	It calls the C<msync> function of your OS, if available, with the memory
		1385	area starting at C<$offset> in the string and ending C<$length> bytes
		1386	later. If C<$length> is negative, counts from the end, and if C<$length>
		1387	is C<undef>, then it goes till the end of the string. The flags can be
		1388	either C<IO::AIO::MS_ASYNC> or C<IO::AIO::MS_SYNC>, plus an optional
		1389	C<IO::AIO::MS_INVALIDATE>.
		1390
		1391	=item aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		1392
		1393	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1394	scalars.
		1395
		1396	It touches (reads or writes) all memory pages in the specified
		1397	range inside the scalar. All caveats and parameters are the same
		1398	as for C<aio_msync>, above, except for flags, which must be either
		1399	C<0> (which reads all pages and ensures they are instantiated) or
		1400	C<IO::AIO::MT_MODIFY>, which modifies the memory pages (by reading and
		1401	writing an octet from it, which dirties the page).
		1402
		1403	=item aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
		1404
		1405	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1406	scalars.
		1407
		1408	It reads in all the pages of the underlying storage into memory (if any)
		1409	and locks them, so they are not getting swapped/paged out or removed.
		1410
		1411	If C<$length> is undefined, then the scalar will be locked till the end.
		1412
		1413	On systems that do not implement C<mlock>, this function returns C<-1>
		1414	and sets errno to C<ENOSYS>.
		1415
		1416	Note that the corresponding C<munlock> is synchronous and is
		1417	documented under L<MISCELLANEOUS FUNCTIONS>.
		1418
		1419	Example: open a file, mmap and mlock it - both will be undone when
		1420	C<$data> gets destroyed.
		1421
		1422	open my $fh, "<", $path or die "$path: $!";
		1423	my $data;
		1424	IO::AIO::mmap $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh;
		1425	aio_mlock $data; # mlock in background
		1426
		1427	=item aio_mlockall $flags, $callback->($status)
		1428
		1429	Calls the C<mlockall> function with the given C<$flags> (a combination of
		1430	C<IO::AIO::MCL_CURRENT> and C<IO::AIO::MCL_FUTURE>).
		1431
		1432	On systems that do not implement C<mlockall>, this function returns C<-1>
		1433	and sets errno to C<ENOSYS>.
		1434
		1435	Note that the corresponding C<munlockall> is synchronous and is
		1436	documented under L<MISCELLANEOUS FUNCTIONS>.
		1437
		1438	Example: asynchronously lock all current and future pages into memory.
		1439
		1440	aio_mlockall IO::AIO::MCL_FUTURE;
		1441
		1442	=item aio_fiemap $fh, $start, $length, $flags, $count, $cb->(\@extents)
		1443
		1444	Queries the extents of the given file (by calling the Linux C<FIEMAP>
		1445	ioctl, see L<http://cvs.schmorp.de/IO-AIO/doc/fiemap.txt> for details). If
		1446	the ioctl is not available on your OS, then this request will fail with
		1447	C<ENOSYS>.
		1448
		1449	C<$start> is the starting offset to query extents for, C<$length> is the
		1450	size of the range to query - if it is C<undef>, then the whole file will
		1451	be queried.
		1452
		1453	C<$flags> is a combination of flags (C<IO::AIO::FIEMAP_FLAG_SYNC> or
		1454	C<IO::AIO::FIEMAP_FLAG_XATTR> - C<IO::AIO::FIEMAP_FLAGS_COMPAT> is also
		1455	exported), and is normally C<0> or C<IO::AIO::FIEMAP_FLAG_SYNC> to query
		1456	the data portion.
		1457
		1458	C<$count> is the maximum number of extent records to return. If it is
		1459	C<undef>, then IO::AIO queries all extents of the range. As a very special
		1460	case, if it is C<0>, then the callback receives the number of extents
		1461	instead of the extents themselves (which is unreliable, see below).
		1462
		1463	If an error occurs, the callback receives no arguments. The special
		1464	C<errno> value C<IO::AIO::EBADR> is available to test for flag errors.
		1465
		1466	Otherwise, the callback receives an array reference with extent
		1467	structures. Each extent structure is an array reference itself, with the
		1468	following members:
		1469
		1470	[$logical, $physical, $length, $flags]
		1471
		1472	Flags is any combination of the following flag values (typically either C<0>
		1473	or C<IO::AIO::FIEMAP_EXTENT_LAST> (1)):
		1474
		1475	C<IO::AIO::FIEMAP_EXTENT_LAST>, C<IO::AIO::FIEMAP_EXTENT_UNKNOWN>,
		1476	C<IO::AIO::FIEMAP_EXTENT_DELALLOC>, C<IO::AIO::FIEMAP_EXTENT_ENCODED>,
		1477	C<IO::AIO::FIEMAP_EXTENT_DATA_ENCRYPTED>, C<IO::AIO::FIEMAP_EXTENT_NOT_ALIGNED>,
		1478	C<IO::AIO::FIEMAP_EXTENT_DATA_INLINE>, C<IO::AIO::FIEMAP_EXTENT_DATA_TAIL>,
		1479	C<IO::AIO::FIEMAP_EXTENT_UNWRITTEN>, C<IO::AIO::FIEMAP_EXTENT_MERGED> or
		1480	C<IO::AIO::FIEMAP_EXTENT_SHARED>.
		1481
		1482	At the time of this writing (Linux 3.2), this requets is unreliable unless
		1483	C<$count> is C<undef>, as the kernel has all sorts of bugs preventing
		1484	it to return all extents of a range for files with large number of
		1485	extents. The code works around all these issues if C<$count> is undef.
		1486
547	=item aio_group $callback->(...)	1487	=item aio_group $callback->(...)
548
549	[EXPERIMENTAL]
550		1488
551	This is a very special aio request: Instead of doing something, it is a	1489	This is a very special aio request: Instead of doing something, it is a
552	container for other aio requests, which is useful if you want to bundle	1490	container for other aio requests, which is useful if you want to bundle
553	many requests into a single, composite, request.	1491	many requests into a single, composite, request with a definite callback
		1492	and the ability to cancel the whole request with its subrequests.
554		1493
555	Returns an object of class L<IO::AIO::GRP>. See its documentation below	1494	Returns an object of class L<IO::AIO::GRP>. See its documentation below
556	for more info.	1495	for more info.
557		1496
558	Example:	1497	Example:
…		…
577	phase and still requires a worker thread. Thus, the callback will not	1516	phase and still requires a worker thread. Thus, the callback will not
578	be executed immediately but only after other requests in the queue have	1517	be executed immediately but only after other requests in the queue have
579	entered their execution phase. This can be used to measure request	1518	entered their execution phase. This can be used to measure request
580	latency.	1519	latency.
581		1520
582	=item IO::AIO::aio_sleep $fractional_seconds, $callback->() *NOT EXPORTED*	1521	=item IO::AIO::aio_busy $fractional_seconds, $callback->() *NOT EXPORTED*
583		1522
584	Mainly used for debugging and benchmarking, this aio request puts one of	1523	Mainly used for debugging and benchmarking, this aio request puts one of
585	the request workers to sleep for the given time.	1524	the request workers to sleep for the given time.
586		1525
587	While it is theoretically handy to have simple I/O scheduling requests	1526	While it is theoretically handy to have simple I/O scheduling requests
588	like sleep and file handle readable/writable, the overhead this creates	1527	like sleep and file handle readable/writable, the overhead this creates is
589	is immense, so do not use this function except to put your application	1528	immense (it blocks a thread for a long time) so do not use this function
590	under artificial I/O pressure.	1529	except to put your application under artificial I/O pressure.
591		1530
592	=back	1531	=back
		1532
		1533
		1534	=head2 IO::AIO::WD - multiple working directories
		1535
		1536	Your process only has one current working directory, which is used by all
		1537	threads. This makes it hard to use relative paths (some other component
		1538	could call C<chdir> at any time, and it is hard to control when the path
		1539	will be used by IO::AIO).
		1540
		1541	One solution for this is to always use absolute paths. This usually works,
		1542	but can be quite slow (the kernel has to walk the whole path on every
		1543	access), and can also be a hassle to implement.
		1544
		1545	Newer POSIX systems have a number of functions (openat, fdopendir,
		1546	futimensat and so on) that make it possible to specify working directories
		1547	per operation.
		1548
		1549	For portability, and because the clowns who "designed", or shall I write,
		1550	perpetrated this new interface were obviously half-drunk, this abstraction
		1551	cannot be perfect, though.
		1552
		1553	IO::AIO allows you to convert directory paths into a so-called IO::AIO::WD
		1554	object. This object stores the canonicalised, absolute version of the
		1555	path, and on systems that allow it, also a directory file descriptor.
		1556
		1557	Everywhere where a pathname is accepted by IO::AIO (e.g. in C<aio_stat>
		1558	or C<aio_unlink>), one can specify an array reference with an IO::AIO::WD
		1559	object and a pathname instead (or the IO::AIO::WD object alone, which
		1560	gets interpreted as C<[$wd, "."]>). If the pathname is absolute, the
		1561	IO::AIO::WD object is ignored, otherwise the pathname is resolved relative
		1562	to that IO::AIO::WD object.
		1563
		1564	For example, to get a wd object for F</etc> and then stat F<passwd>
		1565	inside, you would write:
		1566
		1567	aio_wd "/etc", sub {
		1568	my $etcdir = shift;
		1569
		1570	# although $etcdir can be undef on error, there is generally no reason
		1571	# to check for errors here, as aio_stat will fail with ENOENT
		1572	# when $etcdir is undef.
		1573
		1574	aio_stat [$etcdir, "passwd"], sub {
		1575	# yay
		1576	};
		1577	};
		1578
		1579	The fact that C<aio_wd> is a request and not a normal function shows that
		1580	creating an IO::AIO::WD object is itself a potentially blocking operation,
		1581	which is why it is done asynchronously.
		1582
		1583	To stat the directory obtained with C<aio_wd> above, one could write
		1584	either of the following three request calls:
		1585
		1586	aio_lstat "/etc" , sub { ... # pathname as normal string
		1587	aio_lstat [$wd, "."], sub { ... # "." relative to $wd (i.e. $wd itself)
		1588	aio_lstat $wd , sub { ... # shorthand for the previous
		1589
		1590	As with normal pathnames, IO::AIO keeps a copy of the working directory
		1591	object and the pathname string, so you could write the following without
		1592	causing any issues due to C<$path> getting reused:
		1593
		1594	my $path = [$wd, undef];
		1595
		1596	for my $name (qw(abc def ghi)) {
		1597	$path->[1] = $name;
		1598	aio_stat $path, sub {
		1599	# ...
		1600	};
		1601	}
		1602
		1603	There are some caveats: when directories get renamed (or deleted), the
		1604	pathname string doesn't change, so will point to the new directory (or
		1605	nowhere at all), while the directory fd, if available on the system,
		1606	will still point to the original directory. Most functions accepting a
		1607	pathname will use the directory fd on newer systems, and the string on
		1608	older systems. Some functions (such as realpath) will always rely on the
		1609	string form of the pathname.
		1610
		1611	So this functionality is mainly useful to get some protection against
		1612	C<chdir>, to easily get an absolute path out of a relative path for future
		1613	reference, and to speed up doing many operations in the same directory
		1614	(e.g. when stat'ing all files in a directory).
		1615
		1616	The following functions implement this working directory abstraction:
		1617
		1618	=over 4
		1619
		1620	=item aio_wd $pathname, $callback->($wd)
		1621
		1622	Asynchonously canonicalise the given pathname and convert it to an
		1623	IO::AIO::WD object representing it. If possible and supported on the
		1624	system, also open a directory fd to speed up pathname resolution relative
		1625	to this working directory.
		1626
		1627	If something goes wrong, then C<undef> is passwd to the callback instead
		1628	of a working directory object and C<$!> is set appropriately. Since
		1629	passing C<undef> as working directory component of a pathname fails the
		1630	request with C<ENOENT>, there is often no need for error checking in the
		1631	C<aio_wd> callback, as future requests using the value will fail in the
		1632	expected way.
		1633
		1634	=item IO::AIO::CWD
		1635
		1636	This is a compiletime constant (object) that represents the process
		1637	current working directory.
		1638
		1639	Specifying this object as working directory object for a pathname is as if
		1640	the pathname would be specified directly, without a directory object. For
		1641	example, these calls are functionally identical:
		1642
		1643	aio_stat "somefile", sub { ... };
		1644	aio_stat [IO::AIO::CWD, "somefile"], sub { ... };
		1645
		1646	=back
		1647
		1648	To recover the path associated with an IO::AIO::WD object, you can use
		1649	C<aio_realpath>:
		1650
		1651	aio_realpath $wd, sub {
		1652	warn "path is $_[0]\n";
		1653	};
		1654
		1655	Currently, C<aio_statvfs> always, and C<aio_rename> and C<aio_rmdir>
		1656	sometimes, fall back to using an absolue path.
593		1657
594	=head2 IO::AIO::REQ CLASS	1658	=head2 IO::AIO::REQ CLASS
595		1659
596	All non-aggregate C<aio_*> functions return an object of this class when	1660	All non-aggregate C<aio_*> functions return an object of this class when
597	called in non-void context.	1661	called in non-void context.
598
599	A request always moves through the following five states in its lifetime,
600	in order: B<ready> (request has been created, but has not been executed
601	yet), B<execute> (request is currently being executed), B<pending>
602	(request has been executed but callback has not been called yet),
603	B<result> (results are being processed synchronously, includes calling the
604	callback) and B<done> (request has reached the end of its lifetime and
605	holds no resources anymore).
606		1662
607	=over 4	1663	=over 4
608		1664
609	=item cancel $req	1665	=item cancel $req
610		1666
611	Cancels the request, if possible. Has the effect of skipping execution	1667	Cancels the request, if possible. Has the effect of skipping execution
612	when entering the B<execute> state and skipping calling the callback when	1668	when entering the B<execute> state and skipping calling the callback when
613	entering the the B<result> state, but will leave the request otherwise	1669	entering the the B<result> state, but will leave the request otherwise
614	untouched. That means that requests that currently execute will not be	1670	untouched (with the exception of readdir). That means that requests that
615	stopped and resources held by the request will not be freed prematurely.	1671	currently execute will not be stopped and resources held by the request
		1672	will not be freed prematurely.
616		1673
617	=item cb $req $callback->(...)	1674	=item cb $req $callback->(...)
618		1675
619	Replace (or simply set) the callback registered to the request.	1676	Replace (or simply set) the callback registered to the request.
620		1677
…		…
664	=item * They can also can also be added to other IO::AIO::GRP objects.	1721	=item * They can also can also be added to other IO::AIO::GRP objects.
665		1722
666	=item * You must not add requests to a group from within the group callback (or	1723	=item * You must not add requests to a group from within the group callback (or
667	any later time).	1724	any later time).
668		1725
669	=item * This does not harmonise well with C<max_outstanding>, so best do
670	not combine C<aio_group> with it. Groups and feeders are recommended for
671	this kind of concurrency-limiting.
672
673	=back	1726	=back
674		1727
675	Their lifetime, simplified, looks like this: when they are empty, they	1728	Their lifetime, simplified, looks like this: when they are empty, they
676	will finish very quickly. If they contain only requests that are in the	1729	will finish very quickly. If they contain only requests that are in the
677	C<done> state, they will also finish. Otherwise they will continue to	1730	C<done> state, they will also finish. Otherwise they will continue to
678	exist.	1731	exist.
679		1732
680	That means after creating a group you have some time to add requests. And	1733	That means after creating a group you have some time to add requests
681	in the callbacks of those requests, you can add further requests to the	1734	(precisely before the callback has been invoked, which is only done within
682	group. And only when all those requests have finished will the the group	1735	the C<poll_cb>). And in the callbacks of those requests, you can add
683	itself finish.	1736	further requests to the group. And only when all those requests have
		1737	finished will the the group itself finish.
684		1738
685	=over 4	1739	=over 4
686		1740
687	=item add $grp ...	1741	=item add $grp ...
688		1742
…		…
692	be added, including other groups, as long as you do not create circular	1746	be added, including other groups, as long as you do not create circular
693	dependencies.	1747	dependencies.
694		1748
695	Returns all its arguments.	1749	Returns all its arguments.
696		1750
		1751	=item $grp->cancel_subs
		1752
		1753	Cancel all subrequests and clears any feeder, but not the group request
		1754	itself. Useful when you queued a lot of events but got a result early.
		1755
		1756	The group request will finish normally (you cannot add requests to the
		1757	group).
		1758
697	=item $grp->result (...)	1759	=item $grp->result (...)
698		1760
699	Set the result value(s) that will be passed to the group callback when all	1761	Set the result value(s) that will be passed to the group callback when all
700	subrequests have finished. By default, no argument will be passed.	1762	subrequests have finished and set the groups errno to the current value
		1763	of errno (just like calling C<errno> without an error number). By default,
		1764	no argument will be passed and errno is zero.
		1765
		1766	=item $grp->errno ([$errno])
		1767
		1768	Sets the group errno value to C<$errno>, or the current value of errno
		1769	when the argument is missing.
		1770
		1771	Every aio request has an associated errno value that is restored when
		1772	the callback is invoked. This method lets you change this value from its
		1773	default (0).
		1774
		1775	Calling C<result> will also set errno, so make sure you either set C<$!>
		1776	before the call to C<result>, or call c<errno> after it.
701		1777
702	=item feed $grp $callback->($grp)	1778	=item feed $grp $callback->($grp)
703
704	[VERY EXPERIMENTAL]
705		1779
706	Sets a feeder/generator on this group: every group can have an attached	1780	Sets a feeder/generator on this group: every group can have an attached
707	generator that generates requests if idle. The idea behind this is that,	1781	generator that generates requests if idle. The idea behind this is that,
708	although you could just queue as many requests as you want in a group,	1782	although you could just queue as many requests as you want in a group,
709	this might starve other requests for a potentially long time. For	1783	this might starve other requests for a potentially long time. For example,
710	example, C<aio_scandir> might generate hundreds of thousands C<aio_stat>	1784	C<aio_scandir> might generate hundreds of thousands of C<aio_stat>
711	requests, delaying any later requests for a long time.	1785	requests, delaying any later requests for a long time.
712		1786
713	To avoid this, and allow incremental generation of requests, you can	1787	To avoid this, and allow incremental generation of requests, you can
714	instead a group and set a feeder on it that generates those requests. The	1788	instead a group and set a feeder on it that generates those requests. The
715	feed callback will be called whenever there are few enough (see C<limit>,	1789	feed callback will be called whenever there are few enough (see C<limit>,
…		…
720	not impose any limits).	1794	not impose any limits).
721		1795
722	If the feed does not queue more requests when called, it will be	1796	If the feed does not queue more requests when called, it will be
723	automatically removed from the group.	1797	automatically removed from the group.
724		1798
725	If the feed limit is C<0>, it will be set to C<2> automatically.	1799	If the feed limit is C<0> when this method is called, it will be set to
		1800	C<2> automatically.
726		1801
727	Example:	1802	Example:
728		1803
729	# stat all files in @files, but only ever use four aio requests concurrently:	1804	# stat all files in @files, but only ever use four aio requests concurrently:
730		1805
…		…
742	Sets the feeder limit for the group: The feeder will be called whenever	1817	Sets the feeder limit for the group: The feeder will be called whenever
743	the group contains less than this many requests.	1818	the group contains less than this many requests.
744		1819
745	Setting the limit to C<0> will pause the feeding process.	1820	Setting the limit to C<0> will pause the feeding process.
746		1821
		1822	The default value for the limit is C<0>, but note that setting a feeder
		1823	automatically bumps it up to C<2>.
		1824
747	=back	1825	=back
748		1826
749	=head2 SUPPORT FUNCTIONS	1827	=head2 SUPPORT FUNCTIONS
750		1828
		1829	=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION
		1830
751	=over 4	1831	=over 4
752		1832
753	=item $fileno = IO::AIO::poll_fileno	1833	=item $fileno = IO::AIO::poll_fileno
754		1834
755	Return the I<request result pipe file descriptor>. This filehandle must be	1835	Return the I<request result pipe file descriptor>. This filehandle must be
756	polled for reading by some mechanism outside this module (e.g. Event or	1836	polled for reading by some mechanism outside this module (e.g. EV, Glib,
757	select, see below or the SYNOPSIS). If the pipe becomes readable you have	1837	select and so on, see below or the SYNOPSIS). If the pipe becomes readable
758	to call C<poll_cb> to check the results.	1838	you have to call C<poll_cb> to check the results.
759		1839
760	See C<poll_cb> for an example.	1840	See C<poll_cb> for an example.
761		1841
762	=item IO::AIO::poll_cb	1842	=item IO::AIO::poll_cb
763		1843
764	Process all outstanding events on the result pipe. You have to call this	1844	Process some requests that have reached the result phase (i.e. they have
765	regularly. Returns the number of events processed. Returns immediately	1845	been executed but the results are not yet reported). You have to call
766	when no events are outstanding.	1846	this "regularly" to finish outstanding requests.
		1847
		1848	Returns C<0> if all events could be processed (or there were no
		1849	events to process), or C<-1> if it returned earlier for whatever
		1850	reason. Returns immediately when no events are outstanding. The amount
		1851	of events processed depends on the settings of C<IO::AIO::max_poll_req>,
		1852	C<IO::AIO::max_poll_time> and C<IO::AIO::max_outstanding>.
		1853
		1854	If not all requests were processed for whatever reason, the poll file
		1855	descriptor will still be ready when C<poll_cb> returns, so normally you
		1856	don't have to do anything special to have it called later.
		1857
		1858	Apart from calling C<IO::AIO::poll_cb> when the event filehandle becomes
		1859	ready, it can be beneficial to call this function from loops which submit
		1860	a lot of requests, to make sure the results get processed when they become
		1861	available and not just when the loop is finished and the event loop takes
		1862	over again. This function returns very fast when there are no outstanding
		1863	requests.
767		1864
768	Example: Install an Event watcher that automatically calls	1865	Example: Install an Event watcher that automatically calls
769	IO::AIO::poll_cb with high priority:	1866	IO::AIO::poll_cb with high priority (more examples can be found in the
		1867	SYNOPSIS section, at the top of this document):
770		1868
771	Event->io (fd => IO::AIO::poll_fileno,	1869	Event->io (fd => IO::AIO::poll_fileno,
772	poll => 'r', async => 1,	1870	poll => 'r', async => 1,
773	cb => \&IO::AIO::poll_cb);	1871	cb => \&IO::AIO::poll_cb);
774		1872
775	=item IO::AIO::poll_wait	1873	=item IO::AIO::poll_wait
776		1874
777	Wait till the result filehandle becomes ready for reading (simply does a	1875	Wait until either at least one request is in the result phase or no
778	C<select> on the filehandle. This is useful if you want to synchronously wait	1876	requests are outstanding anymore.
779	for some requests to finish).	1877
		1878	This is useful if you want to synchronously wait for some requests to
		1879	become ready, without actually handling them.
780		1880
781	See C<nreqs> for an example.	1881	See C<nreqs> for an example.
782		1882
		1883	=item IO::AIO::poll
		1884
		1885	Waits until some requests have been handled.
		1886
		1887	Returns the number of requests processed, but is otherwise strictly
		1888	equivalent to:
		1889
		1890	IO::AIO::poll_wait, IO::AIO::poll_cb
		1891
783	=item IO::AIO::nreqs	1892	=item IO::AIO::flush
784		1893
785	Returns the number of requests currently outstanding (i.e. for which their	1894	Wait till all outstanding AIO requests have been handled.
786	callback has not been invoked yet).
787		1895
788	Example: wait till there are no outstanding requests anymore:	1896	Strictly equivalent to:
789		1897
790	IO::AIO::poll_wait, IO::AIO::poll_cb	1898	IO::AIO::poll_wait, IO::AIO::poll_cb
791	while IO::AIO::nreqs;	1899	while IO::AIO::nreqs;
792		1900
793	=item IO::AIO::flush	1901	=item IO::AIO::max_poll_reqs $nreqs
794		1902
795	Wait till all outstanding AIO requests have been handled.	1903	=item IO::AIO::max_poll_time $seconds
796		1904
797	Strictly equivalent to:	1905	These set the maximum number of requests (default C<0>, meaning infinity)
		1906	that are being processed by C<IO::AIO::poll_cb> in one call, respectively
		1907	the maximum amount of time (default C<0>, meaning infinity) spent in
		1908	C<IO::AIO::poll_cb> to process requests (more correctly the mininum amount
		1909	of time C<poll_cb> is allowed to use).
798		1910
799	IO::AIO::poll_wait, IO::AIO::poll_cb	1911	Setting C<max_poll_time> to a non-zero value creates an overhead of one
800	while IO::AIO::nreqs;	1912	syscall per request processed, which is not normally a problem unless your
		1913	callbacks are really really fast or your OS is really really slow (I am
		1914	not mentioning Solaris here). Using C<max_poll_reqs> incurs no overhead.
801		1915
802	=item IO::AIO::poll	1916	Setting these is useful if you want to ensure some level of
		1917	interactiveness when perl is not fast enough to process all requests in
		1918	time.
803		1919
804	Waits until some requests have been handled.	1920	For interactive programs, values such as C<0.01> to C<0.1> should be fine.
805		1921
806	Strictly equivalent to:	1922	Example: Install an Event watcher that automatically calls
		1923	IO::AIO::poll_cb with low priority, to ensure that other parts of the
		1924	program get the CPU sometimes even under high AIO load.
807		1925
808	IO::AIO::poll_wait, IO::AIO::poll_cb	1926	# try not to spend much more than 0.1s in poll_cb
809	if IO::AIO::nreqs;	1927	IO::AIO::max_poll_time 0.1;
		1928
		1929	# use a low priority so other tasks have priority
		1930	Event->io (fd => IO::AIO::poll_fileno,
		1931	poll => 'r', nice => 1,
		1932	cb => &IO::AIO::poll_cb);
		1933
		1934	=back
		1935
		1936	=head3 CONTROLLING THE NUMBER OF THREADS
		1937
		1938	=over
810		1939
811	=item IO::AIO::min_parallel $nthreads	1940	=item IO::AIO::min_parallel $nthreads
812		1941
813	Set the minimum number of AIO threads to C<$nthreads>. The current	1942	Set the minimum number of AIO threads to C<$nthreads>. The current
814	default is C<8>, which means eight asynchronous operations can execute	1943	default is C<8>, which means eight asynchronous operations can execute
815	concurrently at any one time (the number of outstanding requests,	1944	concurrently at any one time (the number of outstanding requests,
816	however, is unlimited).	1945	however, is unlimited).
817		1946
818	IO::AIO starts threads only on demand, when an AIO request is queued and	1947	IO::AIO starts threads only on demand, when an AIO request is queued and
819	no free thread exists.	1948	no free thread exists. Please note that queueing up a hundred requests can
		1949	create demand for a hundred threads, even if it turns out that everything
		1950	is in the cache and could have been processed faster by a single thread.
820		1951
821	It is recommended to keep the number of threads relatively low, as some	1952	It is recommended to keep the number of threads relatively low, as some
822	Linux kernel versions will scale negatively with the number of threads	1953	Linux kernel versions will scale negatively with the number of threads
823	(higher parallelity => MUCH higher latency). With current Linux 2.6	1954	(higher parallelity => MUCH higher latency). With current Linux 2.6
824	versions, 4-32 threads should be fine.	1955	versions, 4-32 threads should be fine.
…		…
838	This module automatically runs C<max_parallel 0> at program end, to ensure	1969	This module automatically runs C<max_parallel 0> at program end, to ensure
839	that all threads are killed and that there are no outstanding requests.	1970	that all threads are killed and that there are no outstanding requests.
840		1971
841	Under normal circumstances you don't need to call this function.	1972	Under normal circumstances you don't need to call this function.
842		1973
		1974	=item IO::AIO::max_idle $nthreads
		1975
		1976	Limit the number of threads (default: 4) that are allowed to idle
		1977	(i.e., threads that did not get a request to process within the idle
		1978	timeout (default: 10 seconds). That means if a thread becomes idle while
		1979	C<$nthreads> other threads are also idle, it will free its resources and
		1980	exit.
		1981
		1982	This is useful when you allow a large number of threads (e.g. 100 or 1000)
		1983	to allow for extremely high load situations, but want to free resources
		1984	under normal circumstances (1000 threads can easily consume 30MB of RAM).
		1985
		1986	The default is probably ok in most situations, especially if thread
		1987	creation is fast. If thread creation is very slow on your system you might
		1988	want to use larger values.
		1989
		1990	=item IO::AIO::idle_timeout $seconds
		1991
		1992	Sets the minimum idle timeout (default 10) after which worker threads are
		1993	allowed to exit. SEe C<IO::AIO::max_idle>.
		1994
843	=item $oldnreqs = IO::AIO::max_outstanding $nreqs	1995	=item IO::AIO::max_outstanding $maxreqs
844		1996
845	[DEPRECATED]
846
847	Sets the maximum number of outstanding requests to C<$nreqs>. If you	1997	Sets the maximum number of outstanding requests to C<$nreqs>. If
848	try to queue up more than this number of requests, the caller will block until	1998	you do queue up more than this number of requests, the next call to
849	some requests have been handled.	1999	C<IO::AIO::poll_cb> (and other functions calling C<poll_cb>, such as
		2000	C<IO::AIO::flush> or C<IO::AIO::poll>) will block until the limit is no
		2001	longer exceeded.
850		2002
851	The default is very large, so normally there is no practical limit. If you	2003	In other words, this setting does not enforce a queue limit, but can be
852	queue up many requests in a loop it often improves speed if you set	2004	used to make poll functions block if the limit is exceeded.
853	this to a relatively low number, such as C<100>.
854		2005
855	This function does not work well together with C<aio_group>'s, and their	2006	This is a very bad function to use in interactive programs because it
856	feeder interface is better suited to limiting concurrency, so do not use	2007	blocks, and a bad way to reduce concurrency because it is inexact: Better
857	this function.	2008	use an C<aio_group> together with a feed callback.
858		2009
859	Under normal circumstances you don't need to call this function.	2010	Its main use is in scripts without an event loop - when you want to stat
		2011	a lot of files, you can write somehting like this:
		2012
		2013	IO::AIO::max_outstanding 32;
		2014
		2015	for my $path (...) {
		2016	aio_stat $path , ...;
		2017	IO::AIO::poll_cb;
		2018	}
		2019
		2020	IO::AIO::flush;
		2021
		2022	The call to C<poll_cb> inside the loop will normally return instantly, but
		2023	as soon as more thna C<32> reqeusts are in-flight, it will block until
		2024	some requests have been handled. This keeps the loop from pushing a large
		2025	number of C<aio_stat> requests onto the queue.
		2026
		2027	The default value for C<max_outstanding> is very large, so there is no
		2028	practical limit on the number of outstanding requests.
860		2029
861	=back	2030	=back
862		2031
		2032	=head3 STATISTICAL INFORMATION
		2033
		2034	=over
		2035
		2036	=item IO::AIO::nreqs
		2037
		2038	Returns the number of requests currently in the ready, execute or pending
		2039	states (i.e. for which their callback has not been invoked yet).
		2040
		2041	Example: wait till there are no outstanding requests anymore:
		2042
		2043	IO::AIO::poll_wait, IO::AIO::poll_cb
		2044	while IO::AIO::nreqs;
		2045
		2046	=item IO::AIO::nready
		2047
		2048	Returns the number of requests currently in the ready state (not yet
		2049	executed).
		2050
		2051	=item IO::AIO::npending
		2052
		2053	Returns the number of requests currently in the pending state (executed,
		2054	but not yet processed by poll_cb).
		2055
		2056	=back
		2057
		2058	=head3 MISCELLANEOUS FUNCTIONS
		2059
		2060	IO::AIO implements some functions that are useful when you want to use
		2061	some "Advanced I/O" function not available to in Perl, without going the
		2062	"Asynchronous I/O" route. Many of these have an asynchronous C<aio_*>
		2063	counterpart.
		2064
		2065	=over 4
		2066
		2067	=item IO::AIO::sendfile $ofh, $ifh, $offset, $count
		2068
		2069	Calls the C<eio_sendfile_sync> function, which is like C<aio_sendfile>,
		2070	but is blocking (this makes most sense if you know the input data is
		2071	likely cached already and the output filehandle is set to non-blocking
		2072	operations).
		2073
		2074	Returns the number of bytes copied, or C<-1> on error.
		2075
		2076	=item IO::AIO::fadvise $fh, $offset, $len, $advice
		2077
		2078	Simply calls the C<posix_fadvise> function (see its
		2079	manpage for details). The following advice constants are
		2080	available: C<IO::AIO::FADV_NORMAL>, C<IO::AIO::FADV_SEQUENTIAL>,
		2081	C<IO::AIO::FADV_RANDOM>, C<IO::AIO::FADV_NOREUSE>,
		2082	C<IO::AIO::FADV_WILLNEED>, C<IO::AIO::FADV_DONTNEED>.
		2083
		2084	On systems that do not implement C<posix_fadvise>, this function returns
		2085	ENOSYS, otherwise the return value of C<posix_fadvise>.
		2086
		2087	=item IO::AIO::madvise $scalar, $offset, $len, $advice
		2088
		2089	Simply calls the C<posix_madvise> function (see its
		2090	manpage for details). The following advice constants are
		2091	available: C<IO::AIO::MADV_NORMAL>, C<IO::AIO::MADV_SEQUENTIAL>,
		2092	C<IO::AIO::MADV_RANDOM>, C<IO::AIO::MADV_WILLNEED>,
		2093	C<IO::AIO::MADV_DONTNEED>.
		2094
		2095	If C<$offset> is negative, counts from the end. If C<$length> is negative,
		2096	the remaining length of the C<$scalar> is used. If possible, C<$length>
		2097	will be reduced to fit into the C<$scalar>.
		2098
		2099	On systems that do not implement C<posix_madvise>, this function returns
		2100	ENOSYS, otherwise the return value of C<posix_madvise>.
		2101
		2102	=item IO::AIO::mprotect $scalar, $offset, $len, $protect
		2103
		2104	Simply calls the C<mprotect> function on the preferably AIO::mmap'ed
		2105	$scalar (see its manpage for details). The following protect
		2106	constants are available: C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_READ>,
		2107	C<IO::AIO::PROT_WRITE>, C<IO::AIO::PROT_EXEC>.
		2108
		2109	If C<$offset> is negative, counts from the end. If C<$length> is negative,
		2110	the remaining length of the C<$scalar> is used. If possible, C<$length>
		2111	will be reduced to fit into the C<$scalar>.
		2112
		2113	On systems that do not implement C<mprotect>, this function returns
		2114	ENOSYS, otherwise the return value of C<mprotect>.
		2115
		2116	=item IO::AIO::mmap $scalar, $length, $prot, $flags, $fh[, $offset]
		2117
		2118	Memory-maps a file (or anonymous memory range) and attaches it to the
		2119	given C<$scalar>, which will act like a string scalar. Returns true on
		2120	success, and false otherwise.
		2121
		2122	The scalar must exist, but its contents do not matter - this means you
		2123	cannot use a nonexistant array or hash element. When in doubt, C<undef>
		2124	the scalar first.
		2125
		2126	The only operations allowed on the mmapped scalar are C<substr>/C<vec>,
		2127	which don't change the string length, and most read-only operations such
		2128	as copying it or searching it with regexes and so on.
		2129
		2130	Anything else is unsafe and will, at best, result in memory leaks.
		2131
		2132	The memory map associated with the C<$scalar> is automatically removed
		2133	when the C<$scalar> is undef'd or destroyed, or when the C<IO::AIO::mmap>
		2134	or C<IO::AIO::munmap> functions are called on it.
		2135
		2136	This calls the C<mmap>(2) function internally. See your system's manual
		2137	page for details on the C<$length>, C<$prot> and C<$flags> parameters.
		2138
		2139	The C<$length> must be larger than zero and smaller than the actual
		2140	filesize.
		2141
		2142	C<$prot> is a combination of C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_EXEC>,
		2143	C<IO::AIO::PROT_READ> and/or C<IO::AIO::PROT_WRITE>,
		2144
		2145	C<$flags> can be a combination of
		2146	C<IO::AIO::MAP_SHARED> or
		2147	C<IO::AIO::MAP_PRIVATE>,
		2148	or a number of system-specific flags (when not available, the are C<0>):
		2149	C<IO::AIO::MAP_ANONYMOUS> (which is set to C<MAP_ANON> if your system only provides this constant),
		2150	C<IO::AIO::MAP_LOCKED>,
		2151	C<IO::AIO::MAP_NORESERVE>,
		2152	C<IO::AIO::MAP_POPULATE>,
		2153	C<IO::AIO::MAP_NONBLOCK>,
		2154	C<IO::AIO::MAP_FIXED>,
		2155	C<IO::AIO::MAP_GROWSDOWN>,
		2156	C<IO::AIO::MAP_32BIT>,
		2157	C<IO::AIO::MAP_HUGETLB> or
		2158	C<IO::AIO::MAP_STACK>.
		2159
		2160	If C<$fh> is C<undef>, then a file descriptor of C<-1> is passed.
		2161
		2162	C<$offset> is the offset from the start of the file - it generally must be
		2163	a multiple of C<IO::AIO::PAGESIZE> and defaults to C<0>.
		2164
		2165	Example:
		2166
		2167	use Digest::MD5;
		2168	use IO::AIO;
		2169
		2170	open my $fh, "<verybigfile"
		2171	or die "$!";
		2172
		2173	IO::AIO::mmap my $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh
		2174	or die "verybigfile: $!";
		2175
		2176	my $fast_md5 = md5 $data;
		2177
		2178	=item IO::AIO::munmap $scalar
		2179
		2180	Removes a previous mmap and undefines the C<$scalar>.
		2181
		2182	=item IO::AIO::munlock $scalar, $offset = 0, $length = undef
		2183
		2184	Calls the C<munlock> function, undoing the effects of a previous
		2185	C<aio_mlock> call (see its description for details).
		2186
		2187	=item IO::AIO::munlockall
		2188
		2189	Calls the C<munlockall> function.
		2190
		2191	On systems that do not implement C<munlockall>, this function returns
		2192	ENOSYS, otherwise the return value of C<munlockall>.
		2193
		2194	=item IO::AIO::splice $r_fh, $r_off, $w_fh, $w_off, $length, $flags
		2195
		2196	Calls the GNU/Linux C<splice(2)> syscall, if available. If C<$r_off> or
		2197	C<$w_off> are C<undef>, then C<NULL> is passed for these, otherwise they
		2198	should be the file offset.
		2199
		2200	C<$r_fh> and C<$w_fh> should not refer to the same file, as splice might
		2201	silently corrupt the data in this case.
		2202
		2203	The following symbol flag values are available: C<IO::AIO::SPLICE_F_MOVE>,
		2204	C<IO::AIO::SPLICE_F_NONBLOCK>, C<IO::AIO::SPLICE_F_MORE> and
		2205	C<IO::AIO::SPLICE_F_GIFT>.
		2206
		2207	See the C<splice(2)> manpage for details.
		2208
		2209	=item IO::AIO::tee $r_fh, $w_fh, $length, $flags
		2210
		2211	Calls the GNU/Linux C<tee(2)> syscall, see its manpage and the
		2212	description for C<IO::AIO::splice> above for details.
		2213
		2214	=item $actual_size = IO::AIO::pipesize $r_fh[, $new_size]
		2215
		2216	Attempts to query or change the pipe buffer size. Obviously works only
		2217	on pipes, and currently works only on GNU/Linux systems, and fails with
		2218	C<-1>/C<ENOSYS> everywhere else. If anybody knows how to influence pipe buffer
		2219	size on other systems, drop me a note.
		2220
		2221	=item ($rfh, $wfh) = IO::AIO::pipe2 [$flags]
		2222
		2223	This is a direct interface to the Linux L<pipe2(2)> system call. If
		2224	C<$flags> is missing or C<0>, then this should be the same as a call to
		2225	perl's built-in C<pipe> function and create a new pipe, and works on
		2226	systems that lack the pipe2 syscall. On win32, this case invokes C<_pipe
		2227	(..., 4096, O_BINARY)>.
		2228
		2229	If C<$flags> is non-zero, it tries to invoke the pipe2 system call with
		2230	the given flags (Linux 2.6.27, glibc 2.9).
		2231
		2232	On success, the read and write file handles are returned.
		2233
		2234	On error, nothing will be returned. If the pipe2 syscall is missing and
		2235	C<$flags> is non-zero, fails with C<ENOSYS>.
		2236
		2237	Please refer to L<pipe2(2)> for more info on the C<$flags>, but at the
		2238	time of this writing, C<IO::AIO::O_CLOEXEC>, C<IO::AIO::O_NONBLOCK> and
		2239	C<IO::AIO::O_DIRECT> (Linux 3.4, for packet-based pipes) were supported.
		2240
		2241	=back
		2242
863	=cut	2243	=cut
864		2244
865	# support function to convert a fd into a perl filehandle
866	sub _fd2fh {
867	return undef if $_[0] < 0;
868
869	# try to generate nice filehandles
870	my $sym = "IO::AIO::fd#$_[0]";
871	local *$sym;
872
873	open *$sym, "+<&=$_[0]" # usually works under any unix
874	or open *$sym, "<&=$_[0]" # cygwin needs this
875	or open *$sym, ">&=$_[0]" # or this
876	or return undef;
877
878	*$sym
879	}
880
881	min_parallel 8;	2245	min_parallel 8;
882		2246
883	END {	2247	END { flush }
884	max_parallel 0;
885	}
886		2248
887	1;	2249	1;
888		2250
		2251	=head1 EVENT LOOP INTEGRATION
		2252
		2253	It is recommended to use L<AnyEvent::AIO> to integrate IO::AIO
		2254	automatically into many event loops:
		2255
		2256	# AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...)
		2257	use AnyEvent::AIO;
		2258
		2259	You can also integrate IO::AIO manually into many event loops, here are
		2260	some examples of how to do this:
		2261
		2262	# EV integration
		2263	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
		2264
		2265	# Event integration
		2266	Event->io (fd => IO::AIO::poll_fileno,
		2267	poll => 'r',
		2268	cb => \&IO::AIO::poll_cb);
		2269
		2270	# Glib/Gtk2 integration
		2271	add_watch Glib::IO IO::AIO::poll_fileno,
		2272	in => sub { IO::AIO::poll_cb; 1 };
		2273
		2274	# Tk integration
		2275	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
		2276	readable => \&IO::AIO::poll_cb);
		2277
		2278	# Danga::Socket integration
		2279	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
		2280	\&IO::AIO::poll_cb);
		2281
889	=head2 FORK BEHAVIOUR	2282	=head2 FORK BEHAVIOUR
890		2283
891	This module should do "the right thing" when the process using it forks:	2284	Usage of pthreads in a program changes the semantics of fork
		2285	considerably. Specifically, only async-safe functions can be called after
		2286	fork. Perl doesn't know about this, so in general, you cannot call fork
		2287	with defined behaviour in perl if pthreads are involved. IO::AIO uses
		2288	pthreads, so this applies, but many other extensions and (for inexplicable
		2289	reasons) perl itself often is linked against pthreads, so this limitation
		2290	applies to quite a lot of perls.
892		2291
893	Before the fork, IO::AIO enters a quiescent state where no requests	2292	This module no longer tries to fight your OS, or POSIX. That means IO::AIO
894	can be added in other threads and no results will be processed. After	2293	only works in the process that loaded it. Forking is fully supported, but
895	the fork the parent simply leaves the quiescent state and continues	2294	using IO::AIO in the child is not.
896	request/result processing, while the child clears the request/result
897	queue (so the requests started before the fork will only be handled in
898	the parent). Threads will be started on demand until the limit ste in the
899	parent process has been reached again.
900		2295
901	In short: the parent will, after a short pause, continue as if fork had	2296	You might get around by not I<using> IO::AIO before (or after)
902	not been called, while the child will act as if IO::AIO has not been used	2297	forking. You could also try to call the L<IO::AIO::reinit> function in the
903	yet.	2298	child:
		2299
		2300	=over 4
		2301
		2302	=item IO::AIO::reinit
		2303
		2304	Abandons all current requests and I/O threads and simply reinitialises all
		2305	data structures. This is not an operation supported by any standards, but
		2306	happens to work on GNU/Linux and some newer BSD systems.
		2307
		2308	The only reasonable use for this function is to call it after forking, if
		2309	C<IO::AIO> was used in the parent. Calling it while IO::AIO is active in
		2310	the process will result in undefined behaviour. Calling it at any time
		2311	will also result in any undefined (by POSIX) behaviour.
		2312
		2313	=back
904		2314
905	=head2 MEMORY USAGE	2315	=head2 MEMORY USAGE
906		2316
		2317	Per-request usage:
		2318
907	Each aio request uses - depending on your architecture - around 128 bytes	2319	Each aio request uses - depending on your architecture - around 100-200
908	of memory. In addition, stat requests need a stat buffer (possibly a few	2320	bytes of memory. In addition, stat requests need a stat buffer (possibly
909	hundred bytes). Perl scalars and other data passed into aio requests will	2321	a few hundred bytes), readdir requires a result buffer and so on. Perl
910	also be locked.	2322	scalars and other data passed into aio requests will also be locked and
		2323	will consume memory till the request has entered the done state.
911		2324
912	This is now awfully much, so queuing lots of requests is not usually a	2325	This is not awfully much, so queuing lots of requests is not usually a
913	problem.	2326	problem.
914		2327
915	Each thread needs a stack area which is usually around 16k, sometimes much	2328	Per-thread usage:
916	larger, depending on the OS.	2329
		2330	In the execution phase, some aio requests require more memory for
		2331	temporary buffers, and each thread requires a stack and other data
		2332	structures (usually around 16k-128k, depending on the OS).
		2333
		2334	=head1 KNOWN BUGS
		2335
		2336	Known bugs will be fixed in the next release.
917		2337
918	=head1 SEE ALSO	2338	=head1 SEE ALSO
919		2339
920	L<Coro::AIO>.	2340	L<AnyEvent::AIO> for easy integration into event loops, L<Coro::AIO> for a
		2341	more natural syntax.
921		2342
922	=head1 AUTHOR	2343	=head1 AUTHOR
923		2344
924	Marc Lehmann <schmorp@schmorp.de>	2345	Marc Lehmann <schmorp@schmorp.de>
925	http://home.schmorp.de/	2346	http://home.schmorp.de/

Diff Legend

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