ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/IO-AIO/AIO.pm

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.71 by root, Tue Oct 24 11:57:30 2006 UTC vs.
Revision 1.296 by root, Sun Aug 26 03:17:35 2018 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 = 4.6;
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
		188	aio_slurp
85	aio_group aio_nop);	189	aio_wd);
		190
86	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice));	191	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice));
87	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush	192	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush
88	min_parallel max_parallel max_outstanding nreqs);	193	min_parallel max_parallel max_idle idle_timeout
		194	nreqs nready npending nthreads
		195	max_poll_time max_poll_reqs
		196	sendfile fadvise madvise
		197	mmap munmap mremap munlock munlockall);
		198
		199	push @AIO_REQ, qw(aio_busy); # not exported
89		200
90	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';	201	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';
91		202
92	require XSLoader;	203	require XSLoader;
93	XSLoader::load ("IO::AIO", $VERSION);	204	XSLoader::load ("IO::AIO", $VERSION);
94	}	205	}
95		206
96	=head1 FUNCTIONS	207	=head1 FUNCTIONS
97		208
98	=head2 AIO FUNCTIONS	209	=head2 QUICK OVERVIEW
		210
		211	This section simply lists the prototypes most of the functions for
		212	quick reference. See the following sections for function-by-function
		213	documentation.
		214
		215	aio_wd $pathname, $callback->($wd)
		216	aio_open $pathname, $flags, $mode, $callback->($fh)
		217	aio_close $fh, $callback->($status)
		218	aio_seek $fh,$offset,$whence, $callback->($offs)
		219	aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
		220	aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
		221	aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
		222	aio_readahead $fh,$offset,$length, $callback->($retval)
		223	aio_stat $fh_or_path, $callback->($status)
		224	aio_lstat $fh, $callback->($status)
		225	aio_statvfs $fh_or_path, $callback->($statvfs)
		226	aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
		227	aio_chown $fh_or_path, $uid, $gid, $callback->($status)
		228	aio_chmod $fh_or_path, $mode, $callback->($status)
		229	aio_truncate $fh_or_path, $offset, $callback->($status)
		230	aio_allocate $fh, $mode, $offset, $len, $callback->($status)
		231	aio_fiemap $fh, $start, $length, $flags, $count, $cb->(\@extents)
		232	aio_unlink $pathname, $callback->($status)
		233	aio_mknod $pathname, $mode, $dev, $callback->($status)
		234	aio_link $srcpath, $dstpath, $callback->($status)
		235	aio_symlink $srcpath, $dstpath, $callback->($status)
		236	aio_readlink $pathname, $callback->($link)
		237	aio_realpath $pathname, $callback->($path)
		238	aio_rename $srcpath, $dstpath, $callback->($status)
		239	aio_rename2 $srcpath, $dstpath, $flags, $callback->($status)
		240	aio_mkdir $pathname, $mode, $callback->($status)
		241	aio_rmdir $pathname, $callback->($status)
		242	aio_readdir $pathname, $callback->($entries)
		243	aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		244	IO::AIO::READDIR_DENTS IO::AIO::READDIR_DIRS_FIRST
		245	IO::AIO::READDIR_STAT_ORDER IO::AIO::READDIR_FOUND_UNKNOWN
		246	aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs)
		247	aio_load $pathname, $data, $callback->($status)
		248	aio_copy $srcpath, $dstpath, $callback->($status)
		249	aio_move $srcpath, $dstpath, $callback->($status)
		250	aio_rmtree $pathname, $callback->($status)
		251	aio_fcntl $fh, $cmd, $arg, $callback->($status)
		252	aio_ioctl $fh, $request, $buf, $callback->($status)
		253	aio_sync $callback->($status)
		254	aio_syncfs $fh, $callback->($status)
		255	aio_fsync $fh, $callback->($status)
		256	aio_fdatasync $fh, $callback->($status)
		257	aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		258	aio_pathsync $pathname, $callback->($status)
		259	aio_msync $scalar, $offset = 0, $length = undef, flags = MS_SYNC, $callback->($status)
		260	aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		261	aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
		262	aio_mlockall $flags, $callback->($status)
		263	aio_group $callback->(...)
		264	aio_nop $callback->()
		265
		266	$prev_pri = aioreq_pri [$pri]
		267	aioreq_nice $pri_adjust
		268
		269	IO::AIO::poll_wait
		270	IO::AIO::poll_cb
		271	IO::AIO::poll
		272	IO::AIO::flush
		273	IO::AIO::max_poll_reqs $nreqs
		274	IO::AIO::max_poll_time $seconds
		275	IO::AIO::min_parallel $nthreads
		276	IO::AIO::max_parallel $nthreads
		277	IO::AIO::max_idle $nthreads
		278	IO::AIO::idle_timeout $seconds
		279	IO::AIO::max_outstanding $maxreqs
		280	IO::AIO::nreqs
		281	IO::AIO::nready
		282	IO::AIO::npending
		283	$nfd = IO::AIO::get_fdlimit [EXPERIMENTAL]
		284	IO::AIO::min_fdlimit $nfd [EXPERIMENTAL]
		285
		286	IO::AIO::sendfile $ofh, $ifh, $offset, $count
		287	IO::AIO::fadvise $fh, $offset, $len, $advice
		288	IO::AIO::mmap $scalar, $length, $prot, $flags[, $fh[, $offset]]
		289	IO::AIO::munmap $scalar
		290	IO::AIO::mremap $scalar, $new_length, $flags[, $new_address]
		291	IO::AIO::madvise $scalar, $offset, $length, $advice
		292	IO::AIO::mprotect $scalar, $offset, $length, $protect
		293	IO::AIO::munlock $scalar, $offset = 0, $length = undef
		294	IO::AIO::munlockall
		295
		296	=head2 API NOTES
99		297
100	All the C<aio_*> calls are more or less thin wrappers around the syscall	298	All the C<aio_*> calls are more or less thin wrappers around the syscall
101	with the same name (sans C<aio_>). The arguments are similar or identical,	299	with the same name (sans C<aio_>). The arguments are similar or identical,
102	and they all accept an additional (and optional) C<$callback> argument	300	and they all accept an additional (and optional) C<$callback> argument
103	which must be a code reference. This code reference will get called with	301	which must be a code reference. This code reference will be called after
104	the syscall return code (e.g. most syscalls return C<-1> on error, unlike	302	the syscall has been executed in an asynchronous fashion. The results
105	perl, which usually delivers "false") as it's sole argument when the given	303	of the request will be passed as arguments to the callback (and, if an
106	syscall has been executed asynchronously.	304	error occured, in C<$!>) - for most requests the syscall return code (e.g.
		305	most syscalls return C<-1> on error, unlike perl, which usually delivers
		306	"false").
		307
		308	Some requests (such as C<aio_readdir>) pass the actual results and
		309	communicate failures by passing C<undef>.
107		310
108	All functions expecting a filehandle keep a copy of the filehandle	311	All functions expecting a filehandle keep a copy of the filehandle
109	internally until the request has finished.	312	internally until the request has finished.
110		313
111	All requests return objects of type L<IO::AIO::REQ> that allow further	314	All functions return request objects of type L<IO::AIO::REQ> that allow
112	manipulation of those requests while they are in-flight.	315	further manipulation of those requests while they are in-flight.
113		316
114	The pathnames you pass to these routines I<must> be absolute and	317	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	318	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	319	current working directory could have changed. Alternatively, you can
117	changed. Alternatively, you can make sure that you never change the	320	make sure that you never change the current working directory anywhere
118	current working directory.	321	in the program and then use relative paths. You can also take advantage
		322	of IO::AIOs working directory abstraction, that lets you specify paths
		323	relative to some previously-opened "working directory object" - see the
		324	description of the C<IO::AIO::WD> class later in this document.
119		325
120	To encode pathnames to byte form, either make sure you either: a)	326	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	327	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	328	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	329	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)	330	effect in the user environment, d) use Glib::filename_from_unicode on
125	use something else.	331	unicode filenames or e) use something else to ensure your scalar has the
		332	correct contents.
		333
		334	This works, btw. independent of the internal UTF-8 bit, which IO::AIO
		335	handles correctly whether it is set or not.
		336
		337	=head2 AIO REQUEST FUNCTIONS
126		338
127	=over 4	339	=over 4
128		340
129	=item aioreq_pri $pri	341	=item $prev_pri = aioreq_pri [$pri]
130		342
131	Sets the priority for the next aio request. The default priority	343	Returns the priority value that would be used for the next request and, if
		344	C<$pri> is given, sets the priority for the next aio request.
		345
132	is C<0>, the minimum and maximum priorities are C<-4> and C<4>,	346	The default priority is C<0>, the minimum and maximum priorities are C<-4>
133	respectively. Requests with higher priority will be serviced first.	347	and C<4>, respectively. Requests with higher priority will be serviced
		348	first.
134		349
135	The priority will be reset to C<0> after each call to one of the C<aio_>	350	The priority will be reset to C<0> after each call to one of the C<aio_*>
136	functions.	351	functions.
137		352
138	Example: open a file with low priority, then read something from it with	353	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	354	higher priority so the read request is serviced before other low priority
140	open requests (potentially spamming the cache):	355	open requests (potentially spamming the cache):
…		…
147	aio_read $_[0], ..., sub {	362	aio_read $_[0], ..., sub {
148	...	363	...
149	};	364	};
150	};	365	};
151		366
		367
152	=item aioreq_nice $pri_adjust	368	=item aioreq_nice $pri_adjust
153		369
154	Similar to C<aioreq_pri>, but subtracts the given value from the current	370	Similar to C<aioreq_pri>, but subtracts the given value from the current
155	priority, so effects are cumulative.	371	priority, so the effect is cumulative.
		372
156		373
157	=item aio_open $pathname, $flags, $mode, $callback->($fh)	374	=item aio_open $pathname, $flags, $mode, $callback->($fh)
158		375
159	Asynchronously open or create a file and call the callback with a newly	376	Asynchronously open or create a file and call the callback with a newly
160	created filehandle for the file.	377	created filehandle for the file (or C<undef> in case of an error).
161		378
162	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,	379	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,
163	for an explanation.	380	for an explanation.
164		381
165	The C<$flags> argument is a bitmask. See the C<Fcntl> module for a	382	The C<$flags> argument is a bitmask. See the C<Fcntl> module for a
166	list. They are the same as used by C<sysopen>.	383	list. They are the same as used by C<sysopen>.
167		384
168	Likewise, C<$mode> specifies the mode of the newly created file, if it	385	Likewise, C<$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>,	386	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,	387	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).	388	and C<0666> or C<0777> if you do). Note that the C<$mode> will be modified
		389	by the umask in effect then the request is being executed, so better never
		390	change the umask.
172		391
173	Example:	392	Example:
174		393
175	aio_open "/etc/passwd", O_RDONLY, 0, sub {	394	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
176	if ($_[0]) {	395	if ($_[0]) {
177	print "open successful, fh is $_[0]\n";	396	print "open successful, fh is $_[0]\n";
178	...	397	...
179	} else {	398	} else {
180	die "open failed: $!\n";	399	die "open failed: $!\n";
181	}	400	}
182	};	401	};
183		402
		403	In addition to all the common open modes/flags (C<O_RDONLY>, C<O_WRONLY>,
		404	C<O_RDWR>, C<O_CREAT>, C<O_TRUNC>, C<O_EXCL> and C<O_APPEND>), the
		405	following POSIX and non-POSIX constants are available (missing ones on
		406	your system are, as usual, C<0>):
		407
		408	C<O_ASYNC>, C<O_DIRECT>, C<O_NOATIME>, C<O_CLOEXEC>, C<O_NOCTTY>, C<O_NOFOLLOW>,
		409	C<O_NONBLOCK>, C<O_EXEC>, C<O_SEARCH>, C<O_DIRECTORY>, C<O_DSYNC>,
		410	C<O_RSYNC>, C<O_SYNC>, C<O_PATH>, C<O_TMPFILE>, C<O_TTY_INIT> and C<O_ACCMODE>.
		411
		412
184	=item aio_close $fh, $callback->($status)	413	=item aio_close $fh, $callback->($status)
185		414
186	Asynchronously close a file and call the callback with the result	415	Asynchronously close a file and call the callback with the result
187	code. I<WARNING:> although accepted, you should not pass in a perl	416	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		417
192	This is supposed to be a bug in the API, so that might change. It's	418	Unfortunately, you can't do this to perl. Perl I<insists> very strongly on
193	therefore best to avoid this function.	419	closing the file descriptor associated with the filehandle itself.
		420
		421	Therefore, C<aio_close> will not close the filehandle - instead it will
		422	use dup2 to overwrite the file descriptor with the write-end of a pipe
		423	(the pipe fd will be created on demand and will be cached).
		424
		425	Or in other words: the file descriptor will be closed, but it will not be
		426	free for reuse until the perl filehandle is closed.
		427
		428	=cut
		429
		430	=item aio_seek $fh, $offset, $whence, $callback->($offs)
		431
		432	Seeks the filehandle to the new C<$offset>, similarly to perl's
		433	C<sysseek>. The C<$whence> can use the traditional values (C<0> for
		434	C<IO::AIO::SEEK_SET>, C<1> for C<IO::AIO::SEEK_CUR> or C<2> for
		435	C<IO::AIO::SEEK_END>).
		436
		437	The resulting absolute offset will be passed to the callback, or C<-1> in
		438	case of an error.
		439
		440	In theory, the C<$whence> constants could be different than the
		441	corresponding values from L<Fcntl>, but perl guarantees they are the same,
		442	so don't panic.
		443
		444	As a GNU/Linux (and maybe Solaris) extension, also the constants
		445	C<IO::AIO::SEEK_DATA> and C<IO::AIO::SEEK_HOLE> are available, if they
		446	could be found. No guarantees about suitability for use in C<aio_seek> or
		447	Perl's C<sysseek> can be made though, although I would naively assume they
		448	"just work".
194		449
195	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	450	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
196		451
197	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	452	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
198		453
199	Reads or writes C<length> bytes from the specified C<fh> and C<offset>	454	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	455	C<$offset> into the scalar given by C<$data> and offset C<$dataoffset> and
201	callback without the actual number of bytes read (or -1 on error, just	456	calls the callback with the actual number of bytes transferred (or -1 on
202	like the syscall).	457	error, just like the syscall).
		458
		459	C<aio_read> will, like C<sysread>, shrink or grow the C<$data> scalar to
		460	offset plus the actual number of bytes read.
		461
		462	If C<$offset> is undefined, then the current file descriptor offset will
		463	be used (and updated), otherwise the file descriptor offset will not be
		464	changed by these calls.
		465
		466	If C<$length> is undefined in C<aio_write>, use the remaining length of
		467	C<$data>.
		468
		469	If C<$dataoffset> is less than zero, it will be counted from the end of
		470	C<$data>.
203		471
204	The C<$data> scalar I<MUST NOT> be modified in any way while the request	472	The C<$data> scalar I<MUST NOT> be modified in any way while the request
205	is outstanding. Modifying it can result in segfaults or WW3 (if the	473	is outstanding. Modifying it can result in segfaults or World War III (if
206	necessary/optional hardware is installed).	474	the necessary/optional hardware is installed).
207		475
208	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at	476	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at
209	offset C<0> within the scalar:	477	offset C<0> within the scalar:
210		478
211	aio_read $fh, 7, 15, $buffer, 0, sub {	479	aio_read $fh, 7, 15, $buffer, 0, sub {
212	$_[0] > 0 or die "read error: $!";	480	$_[0] > 0 or die "read error: $!";
213	print "read $_[0] bytes: <$buffer>\n";	481	print "read $_[0] bytes: <$buffer>\n";
214	};	482	};
215		483
216	=item aio_move $srcpath, $dstpath, $callback->($status)
217
218	Try to move the I<file> (directories not supported as either source or
219	destination) from C<$srcpath> to C<$dstpath> and call the callback with
220	the C<0> (error) or C<-1> ok.
221
222	This is a composite request that tries to rename(2) the file first. If
223	rename files with C<EXDEV>, it creates the destination file with mode 0200
224	and copies the contents of the source file into it using C<aio_sendfile>,
225	followed by restoring atime, mtime, access mode and uid/gid, in that
226	order, and unlinking the C<$srcpath>.
227
228	If an error occurs, the partial destination file will be unlinked, if
229	possible, except when setting atime, mtime, access mode and uid/gid, where
230	errors are being ignored.
231
232	=cut
233
234	sub aio_move($$$) {
235	my ($src, $dst, $cb) = @_;
236
237	my $grp = aio_group $cb;
238
239	add $grp aio_rename $src, $dst, sub {
240	if ($_[0] && $! == EXDEV) {
241	add $grp aio_open $src, O_RDONLY, 0, sub {
242	if (my $src_fh = $_[0]) {
243	my @stat = stat $src_fh;
244
245	add $grp aio_open $dst, O_WRONLY, 0200, sub {
246	if (my $dst_fh = $_[0]) {
247	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
248	close $src_fh;
249
250	if ($_[0] == $stat[7]) {
251	utime $stat[8], $stat[9], $dst;
252	chmod $stat[2] & 07777, $dst_fh;
253	chown $stat[4], $stat[5], $dst_fh;
254	close $dst_fh;
255
256	add $grp aio_unlink $src, sub {
257	$grp->result ($_[0]);
258	};
259	} else {
260	my $errno = $!;
261	add $grp aio_unlink $dst, sub {
262	$! = $errno;
263	$grp->result (-1);
264	};
265	}
266	};
267	} else {
268	$grp->result (-1);
269	}
270	},
271
272	} else {
273	$grp->result (-1);
274	}
275	};
276	} else {
277	$grp->result ($_[0]);
278	}
279	};
280
281	$grp
282	}
283		484
284	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)	485	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
285		486
286	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts	487	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
287	reading at byte offset C<$in_offset>, and starts writing at the current	488	reading at byte offset C<$in_offset>, and starts writing at the current
288	file offset of C<$out_fh>. Because of that, it is not safe to issue more	489	file offset of C<$out_fh>. Because of that, it is not safe to issue more
289	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each	490	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each
290	other.	491	other. The same C<$in_fh> works fine though, as this function does not
		492	move or use the file offset of C<$in_fh>.
291		493
		494	Please note that C<aio_sendfile> can read more bytes from C<$in_fh> than
		495	are written, and there is no way to find out how many more bytes have been
		496	read from C<aio_sendfile> alone, as C<aio_sendfile> only provides the
		497	number of bytes written to C<$out_fh>. Only if the result value equals
		498	C<$length> one can assume that C<$length> bytes have been read.
		499
		500	Unlike with other C<aio_> functions, it makes a lot of sense to use
		501	C<aio_sendfile> on non-blocking sockets, as long as one end (typically
		502	the C<$in_fh>) is a file - the file I/O will then be asynchronous, while
		503	the socket I/O will be non-blocking. Note, however, that you can run
		504	into a trap where C<aio_sendfile> reads some data with readahead, then
		505	fails to write all data, and when the socket is ready the next time, the
		506	data in the cache is already lost, forcing C<aio_sendfile> to again hit
		507	the disk. Explicit C<aio_read> + C<aio_write> let's you better control
		508	resource usage.
		509
292	This call tries to make use of a native C<sendfile> syscall to provide	510	This call tries to make use of a native C<sendfile>-like syscall to
293	zero-copy operation. For this to work, C<$out_fh> should refer to a	511	provide zero-copy operation. For this to work, C<$out_fh> should refer to
294	socket, and C<$in_fh> should refer to mmap'able file.	512	a socket, and C<$in_fh> should refer to an mmap'able file.
295		513
296	If the native sendfile call fails or is not implemented, it will be	514	If a native sendfile cannot be found or it fails with C<ENOSYS>,
297	emulated, so you can call C<aio_sendfile> on any type of filehandle	515	C<EINVAL>, C<ENOTSUP>, C<EOPNOTSUPP>, C<EAFNOSUPPORT>, C<EPROTOTYPE> or
		516	C<ENOTSOCK>, it will be emulated, so you can call C<aio_sendfile> on any
298	regardless of the limitations of the operating system.	517	type of filehandle regardless of the limitations of the operating system.
299		518
300	Please note, however, that C<aio_sendfile> can read more bytes from	519	As native sendfile syscalls (as practically any non-POSIX interface hacked
301	C<$in_fh> than are written, and there is no way to find out how many	520	together in a hurry to improve benchmark numbers) tend to be rather buggy
302	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only	521	on many systems, this implementation tries to work around some known bugs
303	provides the number of bytes written to C<$out_fh>. Only if the result	522	in Linux and FreeBSD kernels (probably others, too), but that might fail,
304	value equals C<$length> one can assume that C<$length> bytes have been	523	so you really really should check the return value of C<aio_sendfile> -
305	read.	524	fewer bytes than expected might have been transferred.
		525
306		526
307	=item aio_readahead $fh,$offset,$length, $callback->($retval)	527	=item aio_readahead $fh,$offset,$length, $callback->($retval)
308		528
309	C<aio_readahead> populates the page cache with data from a file so that	529	C<aio_readahead> populates the page cache with data from a file so that
310	subsequent reads from that file will not block on disk I/O. The C<$offset>	530	subsequent reads from that file will not block on disk I/O. The C<$offset>
…		…
313	whole pages, so that offset is effectively rounded down to a page boundary	533	whole pages, so that offset is effectively rounded down to a page boundary
314	and bytes are read up to the next page boundary greater than or equal to	534	and bytes are read up to the next page boundary greater than or equal to
315	(off-set+length). C<aio_readahead> does not read beyond the end of the	535	(off-set+length). C<aio_readahead> does not read beyond the end of the
316	file. The current file offset of the file is left unchanged.	536	file. The current file offset of the file is left unchanged.
317		537
318	If that syscall doesn't exist (likely if your OS isn't Linux) it will be	538	If that syscall doesn't exist (likely if your kernel isn't Linux) it will
319	emulated by simply reading the data, which would have a similar effect.	539	be emulated by simply reading the data, which would have a similar effect.
		540
320		541
321	=item aio_stat $fh_or_path, $callback->($status)	542	=item aio_stat $fh_or_path, $callback->($status)
322		543
323	=item aio_lstat $fh, $callback->($status)	544	=item aio_lstat $fh, $callback->($status)
324		545
325	Works like perl's C<stat> or C<lstat> in void context. The callback will	546	Works almost exactly like perl's C<stat> or C<lstat> in void context. The
326	be called after the stat and the results will be available using C<stat _>	547	callback will be called after the stat and the results will be available
327	or C<-s _> etc...	548	using C<stat _> or C<-s _> and other tests (with the exception of C<-B>
		549	and C<-T>).
328		550
329	The pathname passed to C<aio_stat> must be absolute. See API NOTES, above,	551	The pathname passed to C<aio_stat> must be absolute. See API NOTES, above,
330	for an explanation.	552	for an explanation.
331		553
332	Currently, the stats are always 64-bit-stats, i.e. instead of returning an	554	Currently, the stats are always 64-bit-stats, i.e. instead of returning an
333	error when stat'ing a large file, the results will be silently truncated	555	error when stat'ing a large file, the results will be silently truncated
334	unless perl itself is compiled with large file support.	556	unless perl itself is compiled with large file support.
		557
		558	To help interpret the mode and dev/rdev stat values, IO::AIO offers the
		559	following constants and functions (if not implemented, the constants will
		560	be C<0> and the functions will either C<croak> or fall back on traditional
		561	behaviour).
		562
		563	C<S_IFMT>, C<S_IFIFO>, C<S_IFCHR>, C<S_IFBLK>, C<S_IFLNK>, C<S_IFREG>,
		564	C<S_IFDIR>, C<S_IFWHT>, C<S_IFSOCK>, C<IO::AIO::major $dev_t>,
		565	C<IO::AIO::minor $dev_t>, C<IO::AIO::makedev $major, $minor>.
		566
		567	To access higher resolution stat timestamps, see L<SUBSECOND STAT TIME
		568	ACCESS>.
335		569
336	Example: Print the length of F</etc/passwd>:	570	Example: Print the length of F</etc/passwd>:
337		571
338	aio_stat "/etc/passwd", sub {	572	aio_stat "/etc/passwd", sub {
339	$_[0] and die "stat failed: $!";	573	$_[0] and die "stat failed: $!";
340	print "size is ", -s _, "\n";	574	print "size is ", -s _, "\n";
341	};	575	};
342		576
		577
		578	=item aio_statvfs $fh_or_path, $callback->($statvfs)
		579
		580	Works like the POSIX C<statvfs> or C<fstatvfs> syscalls, depending on
		581	whether a file handle or path was passed.
		582
		583	On success, the callback is passed a hash reference with the following
		584	members: C<bsize>, C<frsize>, C<blocks>, C<bfree>, C<bavail>, C<files>,
		585	C<ffree>, C<favail>, C<fsid>, C<flag> and C<namemax>. On failure, C<undef>
		586	is passed.
		587
		588	The following POSIX IO::AIO::ST_* constants are defined: C<ST_RDONLY> and
		589	C<ST_NOSUID>.
		590
		591	The following non-POSIX IO::AIO::ST_* flag masks are defined to
		592	their correct value when available, or to C<0> on systems that do
		593	not support them: C<ST_NODEV>, C<ST_NOEXEC>, C<ST_SYNCHRONOUS>,
		594	C<ST_MANDLOCK>, C<ST_WRITE>, C<ST_APPEND>, C<ST_IMMUTABLE>, C<ST_NOATIME>,
		595	C<ST_NODIRATIME> and C<ST_RELATIME>.
		596
		597	Example: stat C</wd> and dump out the data if successful.
		598
		599	aio_statvfs "/wd", sub {
		600	my $f = $_[0]
		601	or die "statvfs: $!";
		602
		603	use Data::Dumper;
		604	say Dumper $f;
		605	};
		606
		607	# result:
		608	{
		609	bsize => 1024,
		610	bfree => 4333064312,
		611	blocks => 10253828096,
		612	files => 2050765568,
		613	flag => 4096,
		614	favail => 2042092649,
		615	bavail => 4333064312,
		616	ffree => 2042092649,
		617	namemax => 255,
		618	frsize => 1024,
		619	fsid => 1810
		620	}
		621
		622	=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
		623
		624	Works like perl's C<utime> function (including the special case of $atime
		625	and $mtime being undef). Fractional times are supported if the underlying
		626	syscalls support them.
		627
		628	When called with a pathname, uses utimensat(2) or utimes(2) if available,
		629	otherwise utime(2). If called on a file descriptor, uses futimens(2)
		630	or futimes(2) if available, otherwise returns ENOSYS, so this is not
		631	portable.
		632
		633	Examples:
		634
		635	# set atime and mtime to current time (basically touch(1)):
		636	aio_utime "path", undef, undef;
		637	# set atime to current time and mtime to beginning of the epoch:
		638	aio_utime "path", time, undef; # undef==0
		639
		640
		641	=item aio_chown $fh_or_path, $uid, $gid, $callback->($status)
		642
		643	Works like perl's C<chown> function, except that C<undef> for either $uid
		644	or $gid is being interpreted as "do not change" (but -1 can also be used).
		645
		646	Examples:
		647
		648	# same as "chown root path" in the shell:
		649	aio_chown "path", 0, -1;
		650	# same as above:
		651	aio_chown "path", 0, undef;
		652
		653
		654	=item aio_truncate $fh_or_path, $offset, $callback->($status)
		655
		656	Works like truncate(2) or ftruncate(2).
		657
		658
		659	=item aio_allocate $fh, $mode, $offset, $len, $callback->($status)
		660
		661	Allocates or frees disk space according to the C<$mode> argument. See the
		662	linux C<fallocate> documentation for details.
		663
		664	C<$mode> is usually C<0> or C<IO::AIO::FALLOC_FL_KEEP_SIZE> to allocate
		665	space, or C<IO::AIO::FALLOC_FL_PUNCH_HOLE | IO::AIO::FALLOC_FL_KEEP_SIZE>,
		666	to deallocate a file range.
		667
		668	IO::AIO also supports C<FALLOC_FL_COLLAPSE_RANGE>, to remove a range
		669	(without leaving a hole), C<FALLOC_FL_ZERO_RANGE>, to zero a range,
		670	C<FALLOC_FL_INSERT_RANGE> to insert a range and C<FALLOC_FL_UNSHARE_RANGE>
		671	to unshare shared blocks (see your L<fallocate(2)> manpage).
		672
		673	The file system block size used by C<fallocate> is presumably the
		674	C<f_bsize> returned by C<statvfs>, but different filesystems and filetypes
		675	can dictate other limitations.
		676
		677	If C<fallocate> isn't available or cannot be emulated (currently no
		678	emulation will be attempted), passes C<-1> and sets C<$!> to C<ENOSYS>.
		679
		680
		681	=item aio_chmod $fh_or_path, $mode, $callback->($status)
		682
		683	Works like perl's C<chmod> function.
		684
		685
343	=item aio_unlink $pathname, $callback->($status)	686	=item aio_unlink $pathname, $callback->($status)
344		687
345	Asynchronously unlink (delete) a file and call the callback with the	688	Asynchronously unlink (delete) a file and call the callback with the
346	result code.	689	result code.
347		690
		691
		692	=item aio_mknod $pathname, $mode, $dev, $callback->($status)
		693
		694	[EXPERIMENTAL]
		695
		696	Asynchronously create a device node (or fifo). See mknod(2).
		697
		698	The only (POSIX-) portable way of calling this function is:
		699
		700	aio_mknod $pathname, IO::AIO::S_IFIFO | $mode, 0, sub { ...
		701
		702	See C<aio_stat> for info about some potentially helpful extra constants
		703	and functions.
		704
348	=item aio_link $srcpath, $dstpath, $callback->($status)	705	=item aio_link $srcpath, $dstpath, $callback->($status)
349		706
350	Asynchronously create a new link to the existing object at C<$srcpath> at	707	Asynchronously create a new link to the existing object at C<$srcpath> at
351	the path C<$dstpath> and call the callback with the result code.	708	the path C<$dstpath> and call the callback with the result code.
352		709
		710
353	=item aio_symlink $srcpath, $dstpath, $callback->($status)	711	=item aio_symlink $srcpath, $dstpath, $callback->($status)
354		712
355	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at	713	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at
356	the path C<$dstpath> and call the callback with the result code.	714	the path C<$dstpath> and call the callback with the result code.
357		715
		716
		717	=item aio_readlink $pathname, $callback->($link)
		718
		719	Asynchronously read the symlink specified by C<$path> and pass it to
		720	the callback. If an error occurs, nothing or undef gets passed to the
		721	callback.
		722
		723
		724	=item aio_realpath $pathname, $callback->($path)
		725
		726	Asynchronously make the path absolute and resolve any symlinks in
		727	C<$path>. The resulting path only consists of directories (same as
		728	L<Cwd::realpath>).
		729
		730	This request can be used to get the absolute path of the current working
		731	directory by passing it a path of F<.> (a single dot).
		732
		733
358	=item aio_rename $srcpath, $dstpath, $callback->($status)	734	=item aio_rename $srcpath, $dstpath, $callback->($status)
359		735
360	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as	736	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as
361	rename(2) and call the callback with the result code.	737	rename(2) and call the callback with the result code.
362		738
		739	On systems that support the AIO::WD working directory abstraction
		740	natively, the case C<[$wd, "."]> as C<$srcpath> is specialcased - instead
		741	of failing, C<rename> is called on the absolute path of C<$wd>.
		742
		743
		744	=item aio_rename2 $srcpath, $dstpath, $flags, $callback->($status)
		745
		746	Basically a version of C<aio_rename> with an additional C<$flags>
		747	argument. Calling this with C<$flags=0> is the same as calling
		748	C<aio_rename>.
		749
		750	Non-zero flags are currently only supported on GNU/Linux systems that
		751	support renameat2. Other systems fail with C<ENOSYS> in this case.
		752
		753	The following constants are available (missing ones are, as usual C<0>),
		754	see renameat2(2) for details:
		755
		756	C<IO::AIO::RENAME_NOREPLACE>, C<IO::AIO::RENAME_EXCHANGE>
		757	and C<IO::AIO::RENAME_WHITEOUT>.
		758
		759
		760	=item aio_mkdir $pathname, $mode, $callback->($status)
		761
		762	Asynchronously mkdir (create) a directory and call the callback with
		763	the result code. C<$mode> will be modified by the umask at the time the
		764	request is executed, so do not change your umask.
		765
		766
363	=item aio_rmdir $pathname, $callback->($status)	767	=item aio_rmdir $pathname, $callback->($status)
364		768
365	Asynchronously rmdir (delete) a directory and call the callback with the	769	Asynchronously rmdir (delete) a directory and call the callback with the
366	result code.	770	result code.
		771
		772	On systems that support the AIO::WD working directory abstraction
		773	natively, the case C<[$wd, "."]> is specialcased - instead of failing,
		774	C<rmdir> is called on the absolute path of C<$wd>.
		775
367		776
368	=item aio_readdir $pathname, $callback->($entries)	777	=item aio_readdir $pathname, $callback->($entries)
369		778
370	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire	779	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
371	directory (i.e. opendir + readdir + closedir). The entries will not be	780	directory (i.e. opendir + readdir + closedir). The entries will not be
372	sorted, and will B<NOT> include the C<.> and C<..> entries.	781	sorted, and will B<NOT> include the C<.> and C<..> entries.
373		782
374	The callback a single argument which is either C<undef> or an array-ref	783	The callback is passed a single argument which is either C<undef> or an
375	with the filenames.	784	array-ref with the filenames.
376		785
		786
		787	=item aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		788
		789	Quite similar to C<aio_readdir>, but the C<$flags> argument allows one to
		790	tune behaviour and output format. In case of an error, C<$entries> will be
		791	C<undef>.
		792
		793	The flags are a combination of the following constants, ORed together (the
		794	flags will also be passed to the callback, possibly modified):
		795
		796	=over 4
		797
		798	=item IO::AIO::READDIR_DENTS
		799
		800	Normally the callback gets an arrayref consisting of names only (as
		801	with C<aio_readdir>). If this flag is set, then the callback gets an
		802	arrayref with C<[$name, $type, $inode]> arrayrefs, each describing a
		803	single directory entry in more detail:
		804
		805	C<$name> is the name of the entry.
		806
		807	C<$type> is one of the C<IO::AIO::DT_xxx> constants:
		808
		809	C<IO::AIO::DT_UNKNOWN>, C<IO::AIO::DT_FIFO>, C<IO::AIO::DT_CHR>, C<IO::AIO::DT_DIR>,
		810	C<IO::AIO::DT_BLK>, C<IO::AIO::DT_REG>, C<IO::AIO::DT_LNK>, C<IO::AIO::DT_SOCK>,
		811	C<IO::AIO::DT_WHT>.
		812
		813	C<IO::AIO::DT_UNKNOWN> means just that: readdir does not know. If you need
		814	to know, you have to run stat yourself. Also, for speed/memory reasons,
		815	the C<$type> scalars are read-only: you must not modify them.
		816
		817	C<$inode> is the inode number (which might not be exact on systems with 64
		818	bit inode numbers and 32 bit perls). This field has unspecified content on
		819	systems that do not deliver the inode information.
		820
		821	=item IO::AIO::READDIR_DIRS_FIRST
		822
		823	When this flag is set, then the names will be returned in an order where
		824	likely directories come first, in optimal stat order. This is useful when
		825	you need to quickly find directories, or you want to find all directories
		826	while avoiding to stat() each entry.
		827
		828	If the system returns type information in readdir, then this is used
		829	to find directories directly. Otherwise, likely directories are names
		830	beginning with ".", or otherwise names with no dots, of which names with
		831	short names are tried first.
		832
		833	=item IO::AIO::READDIR_STAT_ORDER
		834
		835	When this flag is set, then the names will be returned in an order
		836	suitable for stat()'ing each one. That is, when you plan to stat() most or
		837	all files in the given directory, then the returned order will likely be
		838	faster.
		839
		840	If both this flag and C<IO::AIO::READDIR_DIRS_FIRST> are specified,
		841	then the likely dirs come first, resulting in a less optimal stat order
		842	for stat'ing all entries, but likely a more optimal order for finding
		843	subdirectories.
		844
		845	=item IO::AIO::READDIR_FOUND_UNKNOWN
		846
		847	This flag should not be set when calling C<aio_readdirx>. Instead, it
		848	is being set by C<aio_readdirx>, when any of the C<$type>'s found were
		849	C<IO::AIO::DT_UNKNOWN>. The absence of this flag therefore indicates that all
		850	C<$type>'s are known, which can be used to speed up some algorithms.
		851
		852	=back
		853
		854
		855	=item aio_slurp $pathname, $offset, $length, $data, $callback->($status)
		856
		857	Opens, reads and closes the given file. The data is put into C<$data>,
		858	which is resized as required.
		859
		860	If C<$offset> is negative, then it is counted from the end of the file.
		861
		862	If C<$length> is zero, then the remaining length of the file is
		863	used. Also, in this case, the same limitations to modifying C<$data> apply
		864	as when IO::AIO::mmap is used, i.e. it must only be modified in-place
		865	with C<substr>. If the size of the file is known, specifying a non-zero
		866	C<$length> results in a performance advantage.
		867
		868	This request is similar to the older C<aio_load> request, but since it is
		869	a single request, it might be more efficient to use.
		870
		871	Example: load F</etc/passwd> into C<$passwd>.
		872
		873	my $passwd;
		874	aio_slurp "/etc/passwd", 0, 0, $passwd, sub {
		875	$_[0] >= 0
		876	or die "/etc/passwd: $!\n";
		877
		878	printf "/etc/passwd is %d bytes long, and contains:\n", length $passwd;
		879	print $passwd;
		880	};
		881	IO::AIO::flush;
		882
		883
		884	=item aio_load $pathname, $data, $callback->($status)
		885
		886	This is a composite request that tries to fully load the given file into
		887	memory. Status is the same as with aio_read.
		888
		889	Using C<aio_slurp> might be more efficient, as it is a single request.
		890
		891	=cut
		892
		893	sub aio_load($$;$) {
		894	my ($path, undef, $cb) = @_;
		895	my $data = \$_[1];
		896
		897	my $pri = aioreq_pri;
		898	my $grp = aio_group $cb;
		899
		900	aioreq_pri $pri;
		901	add $grp aio_open $path, O_RDONLY, 0, sub {
		902	my $fh = shift
		903	or return $grp->result (-1);
		904
		905	aioreq_pri $pri;
		906	add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub {
		907	$grp->result ($_[0]);
		908	};
		909	};
		910
		911	$grp
		912	}
		913
		914	=item aio_copy $srcpath, $dstpath, $callback->($status)
		915
		916	Try to copy the I<file> (directories not supported as either source or
		917	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		918	a status of C<0> (ok) or C<-1> (error, see C<$!>).
		919
		920	Existing destination files will be truncated.
		921
		922	This is a composite request that creates the destination file with
		923	mode 0200 and copies the contents of the source file into it using
		924	C<aio_sendfile>, followed by restoring atime, mtime, access mode and
		925	uid/gid, in that order.
		926
		927	If an error occurs, the partial destination file will be unlinked, if
		928	possible, except when setting atime, mtime, access mode and uid/gid, where
		929	errors are being ignored.
		930
		931	=cut
		932
		933	sub aio_copy($$;$) {
		934	my ($src, $dst, $cb) = @_;
		935
		936	my $pri = aioreq_pri;
		937	my $grp = aio_group $cb;
		938
		939	aioreq_pri $pri;
		940	add $grp aio_open $src, O_RDONLY, 0, sub {
		941	if (my $src_fh = $_[0]) {
		942	my @stat = stat $src_fh; # hmm, might block over nfs?
		943
		944	aioreq_pri $pri;
		945	add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {
		946	if (my $dst_fh = $_[0]) {
		947	aioreq_pri $pri;
		948	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
		949	if ($_[0] == $stat[7]) {
		950	$grp->result (0);
		951	close $src_fh;
		952
		953	my $ch = sub {
		954	aioreq_pri $pri;
		955	add $grp aio_chmod $dst_fh, $stat[2] & 07777, sub {
		956	aioreq_pri $pri;
		957	add $grp aio_chown $dst_fh, $stat[4], $stat[5], sub {
		958	aioreq_pri $pri;
		959	add $grp aio_close $dst_fh;
		960	}
		961	};
		962	};
		963
		964	aioreq_pri $pri;
		965	add $grp aio_utime $dst_fh, $stat[8], $stat[9], sub {
		966	if ($_[0] < 0 && $! == ENOSYS) {
		967	aioreq_pri $pri;
		968	add $grp aio_utime $dst, $stat[8], $stat[9], $ch;
		969	} else {
		970	$ch->();
		971	}
		972	};
		973	} else {
		974	$grp->result (-1);
		975	close $src_fh;
		976	close $dst_fh;
		977
		978	aioreq $pri;
		979	add $grp aio_unlink $dst;
		980	}
		981	};
		982	} else {
		983	$grp->result (-1);
		984	}
		985	},
		986
		987	} else {
		988	$grp->result (-1);
		989	}
		990	};
		991
		992	$grp
		993	}
		994
		995	=item aio_move $srcpath, $dstpath, $callback->($status)
		996
		997	Try to move the I<file> (directories not supported as either source or
		998	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		999	a status of C<0> (ok) or C<-1> (error, see C<$!>).
		1000
		1001	This is a composite request that tries to rename(2) the file first; if
		1002	rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if
		1003	that is successful, unlinks the C<$srcpath>.
		1004
		1005	=cut
		1006
		1007	sub aio_move($$;$) {
		1008	my ($src, $dst, $cb) = @_;
		1009
		1010	my $pri = aioreq_pri;
		1011	my $grp = aio_group $cb;
		1012
		1013	aioreq_pri $pri;
		1014	add $grp aio_rename $src, $dst, sub {
		1015	if ($_[0] && $! == EXDEV) {
		1016	aioreq_pri $pri;
		1017	add $grp aio_copy $src, $dst, sub {
		1018	$grp->result ($_[0]);
		1019
		1020	unless ($_[0]) {
		1021	aioreq_pri $pri;
		1022	add $grp aio_unlink $src;
		1023	}
		1024	};
		1025	} else {
		1026	$grp->result ($_[0]);
		1027	}
		1028	};
		1029
		1030	$grp
		1031	}
		1032
377	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)	1033	=item aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs)
378		1034
379	Scans a directory (similar to C<aio_readdir>) but additionally tries to	1035	Scans a directory (similar to C<aio_readdir>) but additionally tries to
380	separate the entries of directory C<$path> into two sets of names, ones	1036	efficiently separate the entries of directory C<$path> into two sets of
381	you can recurse into (directories or links to them), and ones you cannot	1037	names, directories you can recurse into (directories), and ones you cannot
382	recurse into (everything else).	1038	recurse into (everything else, including symlinks to directories).
383		1039
384	C<aio_scandir> is a composite request that creates of many sub requests_	1040	C<aio_scandir> is a composite request that generates many sub requests.
385	C<$maxreq> specifies the maximum number of outstanding aio requests that	1041	C<$maxreq> specifies the maximum number of outstanding aio requests that
386	this function generates. If it is C<< <= 0 >>, then a suitable default	1042	this function generates. If it is C<< <= 0 >>, then a suitable default
387	will be chosen (currently 6).	1043	will be chosen (currently 4).
388		1044
389	On error, the callback is called without arguments, otherwise it receives	1045	On error, the callback is called without arguments, otherwise it receives
390	two array-refs with path-relative entry names.	1046	two array-refs with path-relative entry names.
391		1047
392	Example:	1048	Example:
…		…
399		1055
400	Implementation notes.	1056	Implementation notes.
401		1057
402	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.	1058	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.
403		1059
		1060	If readdir returns file type information, then this is used directly to
		1061	find directories.
		1062
404	After reading the directory, the modification time, size etc. of the	1063	Otherwise, after reading the directory, the modification time, size etc.
405	directory before and after the readdir is checked, and if they match (and	1064	of the directory before and after the readdir is checked, and if they
406	isn't the current time), the link count will be used to decide how many	1065	match (and isn't the current time), the link count will be used to decide
407	entries are directories (if >= 2). Otherwise, no knowledge of the number	1066	how many entries are directories (if >= 2). Otherwise, no knowledge of the
408	of subdirectories will be assumed.	1067	number of subdirectories will be assumed.
409		1068
410	Then entries will be sorted into likely directories (everything without	1069	Then entries will be sorted into likely directories a non-initial dot
411	a non-initial dot currently) and likely non-directories (everything	1070	currently) and likely non-directories (see C<aio_readdirx>). Then every
412	else). Then every entry plus an appended C</.> will be C<stat>'ed,	1071	entry plus an appended C</.> will be C<stat>'ed, likely directories first,
413	likely directories first. If that succeeds, it assumes that the entry	1072	in order of their inode numbers. If that succeeds, it assumes that the
414	is a directory or a symlink to directory (which will be checked	1073	entry is a directory or a symlink to directory (which will be checked
415	seperately). This is often faster than stat'ing the entry itself because	1074	separately). This is often faster than stat'ing the entry itself because
416	filesystems might detect the type of the entry without reading the inode	1075	filesystems might detect the type of the entry without reading the inode
417	data (e.g. ext2fs filetype feature).	1076	data (e.g. ext2fs filetype feature), even on systems that cannot return
		1077	the filetype information on readdir.
418		1078
419	If the known number of directories (link count - 2) has been reached, the	1079	If the known number of directories (link count - 2) has been reached, the
420	rest of the entries is assumed to be non-directories.	1080	rest of the entries is assumed to be non-directories.
421		1081
422	This only works with certainty on POSIX (= UNIX) filesystems, which	1082	This only works with certainty on POSIX (= UNIX) filesystems, which
…		…
426	as those tend to return 0 or 1 as link counts, which disables the	1086	as those tend to return 0 or 1 as link counts, which disables the
427	directory counting heuristic.	1087	directory counting heuristic.
428		1088
429	=cut	1089	=cut
430		1090
431	sub aio_scandir($$$) {	1091	sub aio_scandir($$;$) {
432	my ($path, $maxreq, $cb) = @_;	1092	my ($path, $maxreq, $cb) = @_;
433		1093
		1094	my $pri = aioreq_pri;
		1095
434	my $grp = aio_group $cb;	1096	my $grp = aio_group $cb;
435		1097
436	$maxreq = 6 if $maxreq <= 0;	1098	$maxreq = 4 if $maxreq <= 0;
437		1099
438	# stat once	1100	# get a wd object
		1101	aioreq_pri $pri;
439	add $grp aio_stat $path, sub {	1102	add $grp aio_wd $path, sub {
		1103	$_[0]
		1104	or return $grp->result ();
		1105
		1106	my $wd = [shift, "."];
		1107
		1108	# stat once
		1109	aioreq_pri $pri;
		1110	add $grp aio_stat $wd, sub {
440	return $grp->result () if $_[0];	1111	return $grp->result () if $_[0];
441	my $now = time;	1112	my $now = time;
442	my $hash1 = join ":", (stat _)[0,1,3,7,9];	1113	my $hash1 = join ":", (stat _)[0,1,3,7,9];
443		1114
444	# read the directory entries	1115	# read the directory entries
445	add $grp aio_readdir $path, sub {	1116	aioreq_pri $pri;
		1117	add $grp aio_readdirx $wd, READDIR_DIRS_FIRST, sub {
446	my $entries = shift	1118	my $entries = shift
447	or return $grp->result ();	1119	or return $grp->result ();
448		1120
449	# stat the dir another time	1121	# stat the dir another time
		1122	aioreq_pri $pri;
450	add $grp aio_stat $path, sub {	1123	add $grp aio_stat $wd, sub {
451	my $hash2 = join ":", (stat _)[0,1,3,7,9];	1124	my $hash2 = join ":", (stat _)[0,1,3,7,9];
452		1125
453	my $ndirs;	1126	my $ndirs;
454		1127
455	# take the slow route if anything looks fishy	1128	# take the slow route if anything looks fishy
456	if ($hash1 ne $hash2 or (stat _)[9] == $now) {	1129	if ($hash1 ne $hash2 or (stat _)[9] == $now) {
457	$ndirs = -1;	1130	$ndirs = -1;
458	} else {	1131	} else {
459	# if nlink == 2, we are finished	1132	# if nlink == 2, we are finished
460	# on non-posix-fs's, we rely on nlink < 2	1133	# for non-posix-fs's, we rely on nlink < 2
461	$ndirs = (stat _)[3] - 2	1134	$ndirs = (stat _)[3] - 2
462	or return $grp->result ([], $entries);	1135	or return $grp->result ([], $entries);
463	}	1136	}
464		1137
465	# sort into likely dirs and likely nondirs
466	# dirs == files without ".", short entries first
467	$entries = [map $_->[0],
468	sort { $b->[1] cmp $a->[1] }
469	map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],
470	@$entries];
471
472	my (@dirs, @nondirs);	1138	my (@dirs, @nondirs);
473		1139
474	my ($statcb, $schedcb);
475	my $nreq = 0;
476
477	my $statgrp = add $grp aio_group;	1140	my $statgrp = add $grp aio_group sub {
478
479	$schedcb = sub {
480	if (@$entries) {
481	if ($nreq < $maxreq) {
482	my $ent = pop @$entries;
483	$nreq++;
484	add $statgrp aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) };
485	}
486	} elsif (!$nreq) {
487	# finished
488	$statgrp->cancel;
489	undef $statcb;
490	undef $schedcb;
491	$grp->result (\@dirs, \@nondirs);	1141	$grp->result (\@dirs, \@nondirs);
492	}	1142	};
		1143
		1144	limit $statgrp $maxreq;
		1145	feed $statgrp sub {
		1146	return unless @$entries;
		1147	my $entry = shift @$entries;
		1148
		1149	aioreq_pri $pri;
		1150	$wd->[1] = "$entry/.";
		1151	add $statgrp aio_stat $wd, sub {
		1152	if ($_[0] < 0) {
		1153	push @nondirs, $entry;
		1154	} else {
		1155	# need to check for real directory
		1156	aioreq_pri $pri;
		1157	$wd->[1] = $entry;
		1158	add $statgrp aio_lstat $wd, sub {
		1159	if (-d _) {
		1160	push @dirs, $entry;
		1161
		1162	unless (--$ndirs) {
		1163	push @nondirs, @$entries;
		1164	feed $statgrp;
		1165	}
		1166	} else {
		1167	push @nondirs, $entry;
		1168	}
		1169	}
		1170	}
		1171	};
		1172	};
493	};	1173	};
494	$statcb = sub {
495	my ($status, $entry) = @_;
496
497	if ($status < 0) {
498	$nreq--;
499	push @nondirs, $entry;
500	&$schedcb;
501	} else {
502	# need to check for real directory
503	add $grp aio_lstat "$path/$entry", sub {
504	$nreq--;
505
506	if (-d _) {
507	push @dirs, $entry;
508
509	if (!--$ndirs) {
510	push @nondirs, @$entries;
511	$entries = [];
512	}
513	} else {
514	push @nondirs, $entry;
515	}
516
517	&$schedcb;
518	}
519	}
520	};
521
522	&$schedcb while @$entries && $nreq < $maxreq;
523	};	1174	};
524	};	1175	};
525	};	1176	};
526		1177
527	$grp	1178	$grp
528	}	1179	}
529		1180
		1181	=item aio_rmtree $pathname, $callback->($status)
		1182
		1183	Delete a directory tree starting (and including) C<$path>, return the
		1184	status of the final C<rmdir> only. This is a composite request that
		1185	uses C<aio_scandir> to recurse into and rmdir directories, and unlink
		1186	everything else.
		1187
		1188	=cut
		1189
		1190	sub aio_rmtree;
		1191	sub aio_rmtree($;$) {
		1192	my ($path, $cb) = @_;
		1193
		1194	my $pri = aioreq_pri;
		1195	my $grp = aio_group $cb;
		1196
		1197	aioreq_pri $pri;
		1198	add $grp aio_scandir $path, 0, sub {
		1199	my ($dirs, $nondirs) = @_;
		1200
		1201	my $dirgrp = aio_group sub {
		1202	add $grp aio_rmdir $path, sub {
		1203	$grp->result ($_[0]);
		1204	};
		1205	};
		1206
		1207	(aioreq_pri $pri), add $dirgrp aio_rmtree "$path/$_" for @$dirs;
		1208	(aioreq_pri $pri), add $dirgrp aio_unlink "$path/$_" for @$nondirs;
		1209
		1210	add $grp $dirgrp;
		1211	};
		1212
		1213	$grp
		1214	}
		1215
		1216	=item aio_fcntl $fh, $cmd, $arg, $callback->($status)
		1217
		1218	=item aio_ioctl $fh, $request, $buf, $callback->($status)
		1219
		1220	These work just like the C<fcntl> and C<ioctl> built-in functions, except
		1221	they execute asynchronously and pass the return value to the callback.
		1222
		1223	Both calls can be used for a lot of things, some of which make more sense
		1224	to run asynchronously in their own thread, while some others make less
		1225	sense. For example, calls that block waiting for external events, such
		1226	as locking, will also lock down an I/O thread while it is waiting, which
		1227	can deadlock the whole I/O system. At the same time, there might be no
		1228	alternative to using a thread to wait.
		1229
		1230	So in general, you should only use these calls for things that do
		1231	(filesystem) I/O, not for things that wait for other events (network,
		1232	other processes), although if you are careful and know what you are doing,
		1233	you still can.
		1234
		1235	The following constants are available (missing ones are, as usual C<0>):
		1236
		1237	C<F_DUPFD_CLOEXEC>,
		1238
		1239	C<F_OFD_GETLK>, C<F_OFD_SETLK>, C<F_OFD_GETLKW>,
		1240
		1241	C<FIFREEZE>, C<FITHAW>, C<FITRIM>, C<FICLONE>, C<FICLONERANGE>, C<FIDEDUPERANGE>.
		1242
		1243	C<FS_IOC_GETFLAGS>, C<FS_IOC_SETFLAGS>, C<FS_IOC_GETVERSION>, C<FS_IOC_SETVERSION>,
		1244	C<FS_IOC_FIEMAP>.
		1245
		1246	C<FS_IOC_FSGETXATTR>, C<FS_IOC_FSSETXATTR>, C<FS_IOC_SET_ENCRYPTION_POLICY>,
		1247	C<FS_IOC_GET_ENCRYPTION_PWSALT>, C<FS_IOC_GET_ENCRYPTION_POLICY>, C<FS_KEY_DESCRIPTOR_SIZE>.
		1248
		1249	C<FS_SECRM_FL>, C<FS_UNRM_FL>, C<FS_COMPR_FL>, C<FS_SYNC_FL>, C<FS_IMMUTABLE_FL>,
		1250	C<FS_APPEND_FL>, C<FS_NODUMP_FL>, C<FS_NOATIME_FL>, C<FS_DIRTY_FL>,
		1251	C<FS_COMPRBLK_FL>, C<FS_NOCOMP_FL>, C<FS_ENCRYPT_FL>, C<FS_BTREE_FL>,
		1252	C<FS_INDEX_FL>, C<FS_JOURNAL_DATA_FL>, C<FS_NOTAIL_FL>, C<FS_DIRSYNC_FL>, C<FS_TOPDIR_FL>,
		1253	C<FS_FL_USER_MODIFIABLE>.
		1254
		1255	C<FS_XFLAG_REALTIME>, C<FS_XFLAG_PREALLOC>, C<FS_XFLAG_IMMUTABLE>, C<FS_XFLAG_APPEND>,
		1256	C<FS_XFLAG_SYNC>, C<FS_XFLAG_NOATIME>, C<FS_XFLAG_NODUMP>, C<FS_XFLAG_RTINHERIT>,
		1257	C<FS_XFLAG_PROJINHERIT>, C<FS_XFLAG_NOSYMLINKS>, C<FS_XFLAG_EXTSIZE>, C<FS_XFLAG_EXTSZINHERIT>,
		1258	C<FS_XFLAG_NODEFRAG>, C<FS_XFLAG_FILESTREAM>, C<FS_XFLAG_DAX>, C<FS_XFLAG_HASATTR>,
		1259
		1260	=item aio_sync $callback->($status)
		1261
		1262	Asynchronously call sync and call the callback when finished.
		1263
530	=item aio_fsync $fh, $callback->($status)	1264	=item aio_fsync $fh, $callback->($status)
531		1265
532	Asynchronously call fsync on the given filehandle and call the callback	1266	Asynchronously call fsync on the given filehandle and call the callback
533	with the fsync result code.	1267	with the fsync result code.
534		1268
…		…
538	callback with the fdatasync result code.	1272	callback with the fdatasync result code.
539		1273
540	If this call isn't available because your OS lacks it or it couldn't be	1274	If this call isn't available because your OS lacks it or it couldn't be
541	detected, it will be emulated by calling C<fsync> instead.	1275	detected, it will be emulated by calling C<fsync> instead.
542		1276
		1277	=item aio_syncfs $fh, $callback->($status)
		1278
		1279	Asynchronously call the syncfs syscall to sync the filesystem associated
		1280	to the given filehandle and call the callback with the syncfs result
		1281	code. If syncfs is not available, calls sync(), but returns C<-1> and sets
		1282	errno to C<ENOSYS> nevertheless.
		1283
		1284	=item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		1285
		1286	Sync the data portion of the file specified by C<$offset> and C<$length>
		1287	to disk (but NOT the metadata), by calling the Linux-specific
		1288	sync_file_range call. If sync_file_range is not available or it returns
		1289	ENOSYS, then fdatasync or fsync is being substituted.
		1290
		1291	C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>,
		1292	C<IO::AIO::SYNC_FILE_RANGE_WRITE> and
		1293	C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range
		1294	manpage for details.
		1295
		1296	=item aio_pathsync $pathname, $callback->($status)
		1297
		1298	This request tries to open, fsync and close the given path. This is a
		1299	composite request intended to sync directories after directory operations
		1300	(E.g. rename). This might not work on all operating systems or have any
		1301	specific effect, but usually it makes sure that directory changes get
		1302	written to disc. It works for anything that can be opened for read-only,
		1303	not just directories.
		1304
		1305	Future versions of this function might fall back to other methods when
		1306	C<fsync> on the directory fails (such as calling C<sync>).
		1307
		1308	Passes C<0> when everything went ok, and C<-1> on error.
		1309
		1310	=cut
		1311
		1312	sub aio_pathsync($;$) {
		1313	my ($path, $cb) = @_;
		1314
		1315	my $pri = aioreq_pri;
		1316	my $grp = aio_group $cb;
		1317
		1318	aioreq_pri $pri;
		1319	add $grp aio_open $path, O_RDONLY, 0, sub {
		1320	my ($fh) = @_;
		1321	if ($fh) {
		1322	aioreq_pri $pri;
		1323	add $grp aio_fsync $fh, sub {
		1324	$grp->result ($_[0]);
		1325
		1326	aioreq_pri $pri;
		1327	add $grp aio_close $fh;
		1328	};
		1329	} else {
		1330	$grp->result (-1);
		1331	}
		1332	};
		1333
		1334	$grp
		1335	}
		1336
		1337	=item aio_msync $scalar, $offset = 0, $length = undef, flags = MS_SYNC, $callback->($status)
		1338
		1339	This is a rather advanced IO::AIO call, which only works on mmap(2)ed
		1340	scalars (see the C<IO::AIO::mmap> function, although it also works on data
		1341	scalars managed by the L<Sys::Mmap> or L<Mmap> modules, note that the
		1342	scalar must only be modified in-place while an aio operation is pending on
		1343	it).
		1344
		1345	It calls the C<msync> function of your OS, if available, with the memory
		1346	area starting at C<$offset> in the string and ending C<$length> bytes
		1347	later. If C<$length> is negative, counts from the end, and if C<$length>
		1348	is C<undef>, then it goes till the end of the string. The flags can be
		1349	either C<IO::AIO::MS_ASYNC> or C<IO::AIO::MS_SYNC>, plus an optional
		1350	C<IO::AIO::MS_INVALIDATE>.
		1351
		1352	=item aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		1353
		1354	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1355	scalars.
		1356
		1357	It touches (reads or writes) all memory pages in the specified
		1358	range inside the scalar. All caveats and parameters are the same
		1359	as for C<aio_msync>, above, except for flags, which must be either
		1360	C<0> (which reads all pages and ensures they are instantiated) or
		1361	C<IO::AIO::MT_MODIFY>, which modifies the memory pages (by reading and
		1362	writing an octet from it, which dirties the page).
		1363
		1364	=item aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
		1365
		1366	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1367	scalars.
		1368
		1369	It reads in all the pages of the underlying storage into memory (if any)
		1370	and locks them, so they are not getting swapped/paged out or removed.
		1371
		1372	If C<$length> is undefined, then the scalar will be locked till the end.
		1373
		1374	On systems that do not implement C<mlock>, this function returns C<-1>
		1375	and sets errno to C<ENOSYS>.
		1376
		1377	Note that the corresponding C<munlock> is synchronous and is
		1378	documented under L<MISCELLANEOUS FUNCTIONS>.
		1379
		1380	Example: open a file, mmap and mlock it - both will be undone when
		1381	C<$data> gets destroyed.
		1382
		1383	open my $fh, "<", $path or die "$path: $!";
		1384	my $data;
		1385	IO::AIO::mmap $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh;
		1386	aio_mlock $data; # mlock in background
		1387
		1388	=item aio_mlockall $flags, $callback->($status)
		1389
		1390	Calls the C<mlockall> function with the given C<$flags> (a combination of
		1391	C<IO::AIO::MCL_CURRENT> and C<IO::AIO::MCL_FUTURE>).
		1392
		1393	On systems that do not implement C<mlockall>, this function returns C<-1>
		1394	and sets errno to C<ENOSYS>.
		1395
		1396	Note that the corresponding C<munlockall> is synchronous and is
		1397	documented under L<MISCELLANEOUS FUNCTIONS>.
		1398
		1399	Example: asynchronously lock all current and future pages into memory.
		1400
		1401	aio_mlockall IO::AIO::MCL_FUTURE;
		1402
		1403	=item aio_fiemap $fh, $start, $length, $flags, $count, $cb->(\@extents)
		1404
		1405	Queries the extents of the given file (by calling the Linux C<FIEMAP>
		1406	ioctl, see L<http://cvs.schmorp.de/IO-AIO/doc/fiemap.txt> for details). If
		1407	the ioctl is not available on your OS, then this request will fail with
		1408	C<ENOSYS>.
		1409
		1410	C<$start> is the starting offset to query extents for, C<$length> is the
		1411	size of the range to query - if it is C<undef>, then the whole file will
		1412	be queried.
		1413
		1414	C<$flags> is a combination of flags (C<IO::AIO::FIEMAP_FLAG_SYNC> or
		1415	C<IO::AIO::FIEMAP_FLAG_XATTR> - C<IO::AIO::FIEMAP_FLAGS_COMPAT> is also
		1416	exported), and is normally C<0> or C<IO::AIO::FIEMAP_FLAG_SYNC> to query
		1417	the data portion.
		1418
		1419	C<$count> is the maximum number of extent records to return. If it is
		1420	C<undef>, then IO::AIO queries all extents of the range. As a very special
		1421	case, if it is C<0>, then the callback receives the number of extents
		1422	instead of the extents themselves (which is unreliable, see below).
		1423
		1424	If an error occurs, the callback receives no arguments. The special
		1425	C<errno> value C<IO::AIO::EBADR> is available to test for flag errors.
		1426
		1427	Otherwise, the callback receives an array reference with extent
		1428	structures. Each extent structure is an array reference itself, with the
		1429	following members:
		1430
		1431	[$logical, $physical, $length, $flags]
		1432
		1433	Flags is any combination of the following flag values (typically either C<0>
		1434	or C<IO::AIO::FIEMAP_EXTENT_LAST> (1)):
		1435
		1436	C<IO::AIO::FIEMAP_EXTENT_LAST>, C<IO::AIO::FIEMAP_EXTENT_UNKNOWN>,
		1437	C<IO::AIO::FIEMAP_EXTENT_DELALLOC>, C<IO::AIO::FIEMAP_EXTENT_ENCODED>,
		1438	C<IO::AIO::FIEMAP_EXTENT_DATA_ENCRYPTED>, C<IO::AIO::FIEMAP_EXTENT_NOT_ALIGNED>,
		1439	C<IO::AIO::FIEMAP_EXTENT_DATA_INLINE>, C<IO::AIO::FIEMAP_EXTENT_DATA_TAIL>,
		1440	C<IO::AIO::FIEMAP_EXTENT_UNWRITTEN>, C<IO::AIO::FIEMAP_EXTENT_MERGED> or
		1441	C<IO::AIO::FIEMAP_EXTENT_SHARED>.
		1442
		1443	At the time of this writing (Linux 3.2), this request is unreliable unless
		1444	C<$count> is C<undef>, as the kernel has all sorts of bugs preventing
		1445	it to return all extents of a range for files with a large number of
		1446	extents. The code (only) works around all these issues if C<$count> is
		1447	C<undef>.
		1448
543	=item aio_group $callback->(...)	1449	=item aio_group $callback->(...)
544
545	[EXPERIMENTAL]
546		1450
547	This is a very special aio request: Instead of doing something, it is a	1451	This is a very special aio request: Instead of doing something, it is a
548	container for other aio requests, which is useful if you want to bundle	1452	container for other aio requests, which is useful if you want to bundle
549	many requests into a single, composite, request with a definite callback	1453	many requests into a single, composite, request with a definite callback
550	and the ability to cancel the whole request with its subrequests.	1454	and the ability to cancel the whole request with its subrequests.
…		…
586	immense (it blocks a thread for a long time) so do not use this function	1490	immense (it blocks a thread for a long time) so do not use this function
587	except to put your application under artificial I/O pressure.	1491	except to put your application under artificial I/O pressure.
588		1492
589	=back	1493	=back
590		1494
		1495
		1496	=head2 IO::AIO::WD - multiple working directories
		1497
		1498	Your process only has one current working directory, which is used by all
		1499	threads. This makes it hard to use relative paths (some other component
		1500	could call C<chdir> at any time, and it is hard to control when the path
		1501	will be used by IO::AIO).
		1502
		1503	One solution for this is to always use absolute paths. This usually works,
		1504	but can be quite slow (the kernel has to walk the whole path on every
		1505	access), and can also be a hassle to implement.
		1506
		1507	Newer POSIX systems have a number of functions (openat, fdopendir,
		1508	futimensat and so on) that make it possible to specify working directories
		1509	per operation.
		1510
		1511	For portability, and because the clowns who "designed", or shall I write,
		1512	perpetrated this new interface were obviously half-drunk, this abstraction
		1513	cannot be perfect, though.
		1514
		1515	IO::AIO allows you to convert directory paths into a so-called IO::AIO::WD
		1516	object. This object stores the canonicalised, absolute version of the
		1517	path, and on systems that allow it, also a directory file descriptor.
		1518
		1519	Everywhere where a pathname is accepted by IO::AIO (e.g. in C<aio_stat>
		1520	or C<aio_unlink>), one can specify an array reference with an IO::AIO::WD
		1521	object and a pathname instead (or the IO::AIO::WD object alone, which
		1522	gets interpreted as C<[$wd, "."]>). If the pathname is absolute, the
		1523	IO::AIO::WD object is ignored, otherwise the pathname is resolved relative
		1524	to that IO::AIO::WD object.
		1525
		1526	For example, to get a wd object for F</etc> and then stat F<passwd>
		1527	inside, you would write:
		1528
		1529	aio_wd "/etc", sub {
		1530	my $etcdir = shift;
		1531
		1532	# although $etcdir can be undef on error, there is generally no reason
		1533	# to check for errors here, as aio_stat will fail with ENOENT
		1534	# when $etcdir is undef.
		1535
		1536	aio_stat [$etcdir, "passwd"], sub {
		1537	# yay
		1538	};
		1539	};
		1540
		1541	The fact that C<aio_wd> is a request and not a normal function shows that
		1542	creating an IO::AIO::WD object is itself a potentially blocking operation,
		1543	which is why it is done asynchronously.
		1544
		1545	To stat the directory obtained with C<aio_wd> above, one could write
		1546	either of the following three request calls:
		1547
		1548	aio_lstat "/etc" , sub { ... # pathname as normal string
		1549	aio_lstat [$wd, "."], sub { ... # "." relative to $wd (i.e. $wd itself)
		1550	aio_lstat $wd , sub { ... # shorthand for the previous
		1551
		1552	As with normal pathnames, IO::AIO keeps a copy of the working directory
		1553	object and the pathname string, so you could write the following without
		1554	causing any issues due to C<$path> getting reused:
		1555
		1556	my $path = [$wd, undef];
		1557
		1558	for my $name (qw(abc def ghi)) {
		1559	$path->[1] = $name;
		1560	aio_stat $path, sub {
		1561	# ...
		1562	};
		1563	}
		1564
		1565	There are some caveats: when directories get renamed (or deleted), the
		1566	pathname string doesn't change, so will point to the new directory (or
		1567	nowhere at all), while the directory fd, if available on the system,
		1568	will still point to the original directory. Most functions accepting a
		1569	pathname will use the directory fd on newer systems, and the string on
		1570	older systems. Some functions (such as C<aio_realpath>) will always rely on
		1571	the string form of the pathname.
		1572
		1573	So this functionality is mainly useful to get some protection against
		1574	C<chdir>, to easily get an absolute path out of a relative path for future
		1575	reference, and to speed up doing many operations in the same directory
		1576	(e.g. when stat'ing all files in a directory).
		1577
		1578	The following functions implement this working directory abstraction:
		1579
		1580	=over 4
		1581
		1582	=item aio_wd $pathname, $callback->($wd)
		1583
		1584	Asynchonously canonicalise the given pathname and convert it to an
		1585	IO::AIO::WD object representing it. If possible and supported on the
		1586	system, also open a directory fd to speed up pathname resolution relative
		1587	to this working directory.
		1588
		1589	If something goes wrong, then C<undef> is passwd to the callback instead
		1590	of a working directory object and C<$!> is set appropriately. Since
		1591	passing C<undef> as working directory component of a pathname fails the
		1592	request with C<ENOENT>, there is often no need for error checking in the
		1593	C<aio_wd> callback, as future requests using the value will fail in the
		1594	expected way.
		1595
		1596	=item IO::AIO::CWD
		1597
		1598	This is a compiletime constant (object) that represents the process
		1599	current working directory.
		1600
		1601	Specifying this object as working directory object for a pathname is as if
		1602	the pathname would be specified directly, without a directory object. For
		1603	example, these calls are functionally identical:
		1604
		1605	aio_stat "somefile", sub { ... };
		1606	aio_stat [IO::AIO::CWD, "somefile"], sub { ... };
		1607
		1608	=back
		1609
		1610	To recover the path associated with an IO::AIO::WD object, you can use
		1611	C<aio_realpath>:
		1612
		1613	aio_realpath $wd, sub {
		1614	warn "path is $_[0]\n";
		1615	};
		1616
		1617	Currently, C<aio_statvfs> always, and C<aio_rename> and C<aio_rmdir>
		1618	sometimes, fall back to using an absolue path.
		1619
591	=head2 IO::AIO::REQ CLASS	1620	=head2 IO::AIO::REQ CLASS
592		1621
593	All non-aggregate C<aio_*> functions return an object of this class when	1622	All non-aggregate C<aio_*> functions return an object of this class when
594	called in non-void context.	1623	called in non-void context.
595
596	A request always moves through the following five states in its lifetime,
597	in order: B<ready> (request has been created, but has not been executed
598	yet), B<execute> (request is currently being executed), B<pending>
599	(request has been executed but callback has not been called yet),
600	B<result> (results are being processed synchronously, includes calling the
601	callback) and B<done> (request has reached the end of its lifetime and
602	holds no resources anymore).
603		1624
604	=over 4	1625	=over 4
605		1626
606	=item cancel $req	1627	=item cancel $req
607		1628
608	Cancels the request, if possible. Has the effect of skipping execution	1629	Cancels the request, if possible. Has the effect of skipping execution
609	when entering the B<execute> state and skipping calling the callback when	1630	when entering the B<execute> state and skipping calling the callback when
610	entering the the B<result> state, but will leave the request otherwise	1631	entering the the B<result> state, but will leave the request otherwise
611	untouched. That means that requests that currently execute will not be	1632	untouched (with the exception of readdir). That means that requests that
612	stopped and resources held by the request will not be freed prematurely.	1633	currently execute will not be stopped and resources held by the request
		1634	will not be freed prematurely.
613		1635
614	=item cb $req $callback->(...)	1636	=item cb $req $callback->(...)
615		1637
616	Replace (or simply set) the callback registered to the request.	1638	Replace (or simply set) the callback registered to the request.
617		1639
…		…
661	=item * They can also can also be added to other IO::AIO::GRP objects.	1683	=item * They can also can also be added to other IO::AIO::GRP objects.
662		1684
663	=item * You must not add requests to a group from within the group callback (or	1685	=item * You must not add requests to a group from within the group callback (or
664	any later time).	1686	any later time).
665		1687
666	=item * This does not harmonise well with C<max_outstanding>, so best do
667	not combine C<aio_group> with it. Groups and feeders are recommended for
668	this kind of concurrency-limiting.
669
670	=back	1688	=back
671		1689
672	Their lifetime, simplified, looks like this: when they are empty, they	1690	Their lifetime, simplified, looks like this: when they are empty, they
673	will finish very quickly. If they contain only requests that are in the	1691	will finish very quickly. If they contain only requests that are in the
674	C<done> state, they will also finish. Otherwise they will continue to	1692	C<done> state, they will also finish. Otherwise they will continue to
675	exist.	1693	exist.
676		1694
677	That means after creating a group you have some time to add requests. And	1695	That means after creating a group you have some time to add requests
678	in the callbacks of those requests, you can add further requests to the	1696	(precisely before the callback has been invoked, which is only done within
679	group. And only when all those requests have finished will the the group	1697	the C<poll_cb>). And in the callbacks of those requests, you can add
680	itself finish.	1698	further requests to the group. And only when all those requests have
		1699	finished will the the group itself finish.
681		1700
682	=over 4	1701	=over 4
683		1702
684	=item add $grp ...	1703	=item add $grp ...
685		1704
…		…
689	be added, including other groups, as long as you do not create circular	1708	be added, including other groups, as long as you do not create circular
690	dependencies.	1709	dependencies.
691		1710
692	Returns all its arguments.	1711	Returns all its arguments.
693		1712
		1713	=item $grp->cancel_subs
		1714
		1715	Cancel all subrequests and clears any feeder, but not the group request
		1716	itself. Useful when you queued a lot of events but got a result early.
		1717
		1718	The group request will finish normally (you cannot add requests to the
		1719	group).
		1720
694	=item $grp->result (...)	1721	=item $grp->result (...)
695		1722
696	Set the result value(s) that will be passed to the group callback when all	1723	Set the result value(s) that will be passed to the group callback when all
697	subrequests have finished. By default, no argument will be passed.	1724	subrequests have finished and set the groups errno to the current value
		1725	of errno (just like calling C<errno> without an error number). By default,
		1726	no argument will be passed and errno is zero.
		1727
		1728	=item $grp->errno ([$errno])
		1729
		1730	Sets the group errno value to C<$errno>, or the current value of errno
		1731	when the argument is missing.
		1732
		1733	Every aio request has an associated errno value that is restored when
		1734	the callback is invoked. This method lets you change this value from its
		1735	default (0).
		1736
		1737	Calling C<result> will also set errno, so make sure you either set C<$!>
		1738	before the call to C<result>, or call c<errno> after it.
698		1739
699	=item feed $grp $callback->($grp)	1740	=item feed $grp $callback->($grp)
700
701	[VERY EXPERIMENTAL]
702		1741
703	Sets a feeder/generator on this group: every group can have an attached	1742	Sets a feeder/generator on this group: every group can have an attached
704	generator that generates requests if idle. The idea behind this is that,	1743	generator that generates requests if idle. The idea behind this is that,
705	although you could just queue as many requests as you want in a group,	1744	although you could just queue as many requests as you want in a group,
706	this might starve other requests for a potentially long time. For	1745	this might starve other requests for a potentially long time. For example,
707	example, C<aio_scandir> might generate hundreds of thousands C<aio_stat>	1746	C<aio_scandir> might generate hundreds of thousands of C<aio_stat>
708	requests, delaying any later requests for a long time.	1747	requests, delaying any later requests for a long time.
709		1748
710	To avoid this, and allow incremental generation of requests, you can	1749	To avoid this, and allow incremental generation of requests, you can
711	instead a group and set a feeder on it that generates those requests. The	1750	instead a group and set a feeder on it that generates those requests. The
712	feed callback will be called whenever there are few enough (see C<limit>,	1751	feed callback will be called whenever there are few enough (see C<limit>,
…		…
717	not impose any limits).	1756	not impose any limits).
718		1757
719	If the feed does not queue more requests when called, it will be	1758	If the feed does not queue more requests when called, it will be
720	automatically removed from the group.	1759	automatically removed from the group.
721		1760
722	If the feed limit is C<0>, it will be set to C<2> automatically.	1761	If the feed limit is C<0> when this method is called, it will be set to
		1762	C<2> automatically.
723		1763
724	Example:	1764	Example:
725		1765
726	# stat all files in @files, but only ever use four aio requests concurrently:	1766	# stat all files in @files, but only ever use four aio requests concurrently:
727		1767
…		…
739	Sets the feeder limit for the group: The feeder will be called whenever	1779	Sets the feeder limit for the group: The feeder will be called whenever
740	the group contains less than this many requests.	1780	the group contains less than this many requests.
741		1781
742	Setting the limit to C<0> will pause the feeding process.	1782	Setting the limit to C<0> will pause the feeding process.
743		1783
		1784	The default value for the limit is C<0>, but note that setting a feeder
		1785	automatically bumps it up to C<2>.
		1786
744	=back	1787	=back
745		1788
		1789
746	=head2 SUPPORT FUNCTIONS	1790	=head2 SUPPORT FUNCTIONS
747		1791
		1792	=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION
		1793
748	=over 4	1794	=over 4
749		1795
750	=item $fileno = IO::AIO::poll_fileno	1796	=item $fileno = IO::AIO::poll_fileno
751		1797
752	Return the I<request result pipe file descriptor>. This filehandle must be	1798	Return the I<request result pipe file descriptor>. This filehandle must be
753	polled for reading by some mechanism outside this module (e.g. Event or	1799	polled for reading by some mechanism outside this module (e.g. EV, Glib,
754	select, see below or the SYNOPSIS). If the pipe becomes readable you have	1800	select and so on, see below or the SYNOPSIS). If the pipe becomes readable
755	to call C<poll_cb> to check the results.	1801	you have to call C<poll_cb> to check the results.
756		1802
757	See C<poll_cb> for an example.	1803	See C<poll_cb> for an example.
758		1804
759	=item IO::AIO::poll_cb	1805	=item IO::AIO::poll_cb
760		1806
761	Process all outstanding events on the result pipe. You have to call this	1807	Process some requests that have reached the result phase (i.e. they have
762	regularly. Returns the number of events processed. Returns immediately	1808	been executed but the results are not yet reported). You have to call
763	when no events are outstanding.	1809	this "regularly" to finish outstanding requests.
		1810
		1811	Returns C<0> if all events could be processed (or there were no
		1812	events to process), or C<-1> if it returned earlier for whatever
		1813	reason. Returns immediately when no events are outstanding. The amount
		1814	of events processed depends on the settings of C<IO::AIO::max_poll_req>,
		1815	C<IO::AIO::max_poll_time> and C<IO::AIO::max_outstanding>.
		1816
		1817	If not all requests were processed for whatever reason, the poll file
		1818	descriptor will still be ready when C<poll_cb> returns, so normally you
		1819	don't have to do anything special to have it called later.
		1820
		1821	Apart from calling C<IO::AIO::poll_cb> when the event filehandle becomes
		1822	ready, it can be beneficial to call this function from loops which submit
		1823	a lot of requests, to make sure the results get processed when they become
		1824	available and not just when the loop is finished and the event loop takes
		1825	over again. This function returns very fast when there are no outstanding
		1826	requests.
764		1827
765	Example: Install an Event watcher that automatically calls	1828	Example: Install an Event watcher that automatically calls
766	IO::AIO::poll_cb with high priority:	1829	IO::AIO::poll_cb with high priority (more examples can be found in the
		1830	SYNOPSIS section, at the top of this document):
767		1831
768	Event->io (fd => IO::AIO::poll_fileno,	1832	Event->io (fd => IO::AIO::poll_fileno,
769	poll => 'r', async => 1,	1833	poll => 'r', async => 1,
770	cb => \&IO::AIO::poll_cb);	1834	cb => \&IO::AIO::poll_cb);
771		1835
772	=item IO::AIO::poll_wait	1836	=item IO::AIO::poll_wait
773		1837
774	Wait till the result filehandle becomes ready for reading (simply does a	1838	Wait until either at least one request is in the result phase or no
775	C<select> on the filehandle. This is useful if you want to synchronously wait	1839	requests are outstanding anymore.
776	for some requests to finish).	1840
		1841	This is useful if you want to synchronously wait for some requests to
		1842	become ready, without actually handling them.
777		1843
778	See C<nreqs> for an example.	1844	See C<nreqs> for an example.
779		1845
		1846	=item IO::AIO::poll
		1847
		1848	Waits until some requests have been handled.
		1849
		1850	Returns the number of requests processed, but is otherwise strictly
		1851	equivalent to:
		1852
		1853	IO::AIO::poll_wait, IO::AIO::poll_cb
		1854
780	=item IO::AIO::nreqs	1855	=item IO::AIO::flush
781		1856
782	Returns the number of requests currently outstanding (i.e. for which their	1857	Wait till all outstanding AIO requests have been handled.
783	callback has not been invoked yet).
784		1858
785	Example: wait till there are no outstanding requests anymore:	1859	Strictly equivalent to:
786		1860
787	IO::AIO::poll_wait, IO::AIO::poll_cb	1861	IO::AIO::poll_wait, IO::AIO::poll_cb
788	while IO::AIO::nreqs;	1862	while IO::AIO::nreqs;
789		1863
		1864	This function can be useful at program aborts, to make sure outstanding
		1865	I/O has been done (C<IO::AIO> uses an C<END> block which already calls
		1866	this function on normal exits), or when you are merely using C<IO::AIO>
		1867	for its more advanced functions, rather than for async I/O, e.g.:
		1868
		1869	my ($dirs, $nondirs);
		1870	IO::AIO::aio_scandir "/tmp", 0, sub { ($dirs, $nondirs) = @_ };
790	=item IO::AIO::flush	1871	IO::AIO::flush;
		1872	# $dirs, $nondirs are now set
791		1873
792	Wait till all outstanding AIO requests have been handled.	1874	=item IO::AIO::max_poll_reqs $nreqs
793		1875
794	Strictly equivalent to:	1876	=item IO::AIO::max_poll_time $seconds
795		1877
796	IO::AIO::poll_wait, IO::AIO::poll_cb	1878	These set the maximum number of requests (default C<0>, meaning infinity)
797	while IO::AIO::nreqs;	1879	that are being processed by C<IO::AIO::poll_cb> in one call, respectively
		1880	the maximum amount of time (default C<0>, meaning infinity) spent in
		1881	C<IO::AIO::poll_cb> to process requests (more correctly the mininum amount
		1882	of time C<poll_cb> is allowed to use).
798		1883
799	=item IO::AIO::poll	1884	Setting C<max_poll_time> to a non-zero value creates an overhead of one
		1885	syscall per request processed, which is not normally a problem unless your
		1886	callbacks are really really fast or your OS is really really slow (I am
		1887	not mentioning Solaris here). Using C<max_poll_reqs> incurs no overhead.
800		1888
801	Waits until some requests have been handled.	1889	Setting these is useful if you want to ensure some level of
		1890	interactiveness when perl is not fast enough to process all requests in
		1891	time.
802		1892
803	Strictly equivalent to:	1893	For interactive programs, values such as C<0.01> to C<0.1> should be fine.
804		1894
805	IO::AIO::poll_wait, IO::AIO::poll_cb	1895	Example: Install an Event watcher that automatically calls
806	if IO::AIO::nreqs;	1896	IO::AIO::poll_cb with low priority, to ensure that other parts of the
		1897	program get the CPU sometimes even under high AIO load.
		1898
		1899	# try not to spend much more than 0.1s in poll_cb
		1900	IO::AIO::max_poll_time 0.1;
		1901
		1902	# use a low priority so other tasks have priority
		1903	Event->io (fd => IO::AIO::poll_fileno,
		1904	poll => 'r', nice => 1,
		1905	cb => &IO::AIO::poll_cb);
		1906
		1907	=back
		1908
		1909
		1910	=head3 CONTROLLING THE NUMBER OF THREADS
		1911
		1912	=over
807		1913
808	=item IO::AIO::min_parallel $nthreads	1914	=item IO::AIO::min_parallel $nthreads
809		1915
810	Set the minimum number of AIO threads to C<$nthreads>. The current	1916	Set the minimum number of AIO threads to C<$nthreads>. The current
811	default is C<8>, which means eight asynchronous operations can execute	1917	default is C<8>, which means eight asynchronous operations can execute
812	concurrently at any one time (the number of outstanding requests,	1918	concurrently at any one time (the number of outstanding requests,
813	however, is unlimited).	1919	however, is unlimited).
814		1920
815	IO::AIO starts threads only on demand, when an AIO request is queued and	1921	IO::AIO starts threads only on demand, when an AIO request is queued and
816	no free thread exists.	1922	no free thread exists. Please note that queueing up a hundred requests can
		1923	create demand for a hundred threads, even if it turns out that everything
		1924	is in the cache and could have been processed faster by a single thread.
817		1925
818	It is recommended to keep the number of threads relatively low, as some	1926	It is recommended to keep the number of threads relatively low, as some
819	Linux kernel versions will scale negatively with the number of threads	1927	Linux kernel versions will scale negatively with the number of threads
820	(higher parallelity => MUCH higher latency). With current Linux 2.6	1928	(higher parallelity => MUCH higher latency). With current Linux 2.6
821	versions, 4-32 threads should be fine.	1929	versions, 4-32 threads should be fine.
…		…
835	This module automatically runs C<max_parallel 0> at program end, to ensure	1943	This module automatically runs C<max_parallel 0> at program end, to ensure
836	that all threads are killed and that there are no outstanding requests.	1944	that all threads are killed and that there are no outstanding requests.
837		1945
838	Under normal circumstances you don't need to call this function.	1946	Under normal circumstances you don't need to call this function.
839		1947
		1948	=item IO::AIO::max_idle $nthreads
		1949
		1950	Limit the number of threads (default: 4) that are allowed to idle
		1951	(i.e., threads that did not get a request to process within the idle
		1952	timeout (default: 10 seconds). That means if a thread becomes idle while
		1953	C<$nthreads> other threads are also idle, it will free its resources and
		1954	exit.
		1955
		1956	This is useful when you allow a large number of threads (e.g. 100 or 1000)
		1957	to allow for extremely high load situations, but want to free resources
		1958	under normal circumstances (1000 threads can easily consume 30MB of RAM).
		1959
		1960	The default is probably ok in most situations, especially if thread
		1961	creation is fast. If thread creation is very slow on your system you might
		1962	want to use larger values.
		1963
		1964	=item IO::AIO::idle_timeout $seconds
		1965
		1966	Sets the minimum idle timeout (default 10) after which worker threads are
		1967	allowed to exit. SEe C<IO::AIO::max_idle>.
		1968
840	=item $oldnreqs = IO::AIO::max_outstanding $nreqs	1969	=item IO::AIO::max_outstanding $maxreqs
841		1970
842	[DEPRECATED]
843
844	Sets the maximum number of outstanding requests to C<$nreqs>. If you	1971	Sets the maximum number of outstanding requests to C<$nreqs>. If
845	try to queue up more than this number of requests, the caller will block until	1972	you do queue up more than this number of requests, the next call to
846	some requests have been handled.	1973	C<IO::AIO::poll_cb> (and other functions calling C<poll_cb>, such as
		1974	C<IO::AIO::flush> or C<IO::AIO::poll>) will block until the limit is no
		1975	longer exceeded.
847		1976
848	The default is very large, so normally there is no practical limit. If you	1977	In other words, this setting does not enforce a queue limit, but can be
849	queue up many requests in a loop it often improves speed if you set	1978	used to make poll functions block if the limit is exceeded.
850	this to a relatively low number, such as C<100>.
851		1979
852	This function does not work well together with C<aio_group>'s, and their	1980	This is a very bad function to use in interactive programs because it
853	feeder interface is better suited to limiting concurrency, so do not use	1981	blocks, and a bad way to reduce concurrency because it is inexact: Better
854	this function.	1982	use an C<aio_group> together with a feed callback.
855		1983
856	Under normal circumstances you don't need to call this function.	1984	Its main use is in scripts without an event loop - when you want to stat
		1985	a lot of files, you can write something like this:
		1986
		1987	IO::AIO::max_outstanding 32;
		1988
		1989	for my $path (...) {
		1990	aio_stat $path , ...;
		1991	IO::AIO::poll_cb;
		1992	}
		1993
		1994	IO::AIO::flush;
		1995
		1996	The call to C<poll_cb> inside the loop will normally return instantly, but
		1997	as soon as more thna C<32> reqeusts are in-flight, it will block until
		1998	some requests have been handled. This keeps the loop from pushing a large
		1999	number of C<aio_stat> requests onto the queue.
		2000
		2001	The default value for C<max_outstanding> is very large, so there is no
		2002	practical limit on the number of outstanding requests.
857		2003
858	=back	2004	=back
859		2005
		2006
		2007	=head3 STATISTICAL INFORMATION
		2008
		2009	=over
		2010
		2011	=item IO::AIO::nreqs
		2012
		2013	Returns the number of requests currently in the ready, execute or pending
		2014	states (i.e. for which their callback has not been invoked yet).
		2015
		2016	Example: wait till there are no outstanding requests anymore:
		2017
		2018	IO::AIO::poll_wait, IO::AIO::poll_cb
		2019	while IO::AIO::nreqs;
		2020
		2021	=item IO::AIO::nready
		2022
		2023	Returns the number of requests currently in the ready state (not yet
		2024	executed).
		2025
		2026	=item IO::AIO::npending
		2027
		2028	Returns the number of requests currently in the pending state (executed,
		2029	but not yet processed by poll_cb).
		2030
		2031	=back
		2032
		2033
		2034	=head3 SUBSECOND STAT TIME ACCESS
		2035
		2036	Both C<aio_stat>/C<aio_lstat> and perl's C<stat>/C<lstat> functions can
		2037	generally find access/modification and change times with subsecond time
		2038	accuracy of the system supports it, but perl's built-in functions only
		2039	return the integer part.
		2040
		2041	The following functions return the timestamps of the most recent
		2042	stat with subsecond precision on most systems and work both after
		2043	C<aio_stat>/C<aio_lstat> and perl's C<stat>/C<lstat> calls. Their return
		2044	value is only meaningful after a successful C<stat>/C<lstat> call, or
		2045	during/after a successful C<aio_stat>/C<aio_lstat> callback.
		2046
		2047	This is similar to the L<Time::HiRes> C<stat> functions, but can return
		2048	full resolution without rounding and work with standard perl C<stat>,
		2049	alleviating the need to call the special C<Time::HiRes> functions, which
		2050	do not act like their perl counterparts.
		2051
		2052	On operating systems or file systems where subsecond time resolution is
		2053	not supported or could not be detected, a fractional part of C<0> is
		2054	returned, so it is always safe to call these functions.
		2055
		2056	=over 4
		2057
		2058	=item $seconds = IO::AIO::st_atime, IO::AIO::st_mtime, IO::AIO::st_ctime, IO::AIO::st_btime
		2059
		2060	Return the access, modication, change or birth time, respectively,
		2061	including fractional part. Due to the limited precision of floating point,
		2062	the accuracy on most platforms is only a bit better than milliseconds
		2063	for times around now - see the I<nsec> function family, below, for full
		2064	accuracy.
		2065
		2066	File birth time is only available when the OS and perl support it (on
		2067	FreeBSD and NetBSD at the time of this writing, although support is
		2068	adaptive, so if your OS/perl gains support, IO::AIO can take avdantage of
		2069	it). On systems where it isn't available, C<0> is currently returned, but
		2070	this might change to C<undef> in a future version.
		2071
		2072	=item ($atime, $mtime, $ctime, $btime, ...) = IO::AIO::st_xtime
		2073
		2074	Returns access, modification, change and birth time all in one go, and
		2075	maybe more times in the future version.
		2076
		2077	=item $nanoseconds = IO::AIO::st_atimensec, IO::AIO::st_mtimensec, IO::AIO::st_ctimensec, IO::AIO::st_btimensec
		2078
		2079	Return the fractional access, modifcation, change or birth time, in nanoseconds,
		2080	as an integer in the range C<0> to C<999999999>.
		2081
		2082	Note that no accessors are provided for access, modification and
		2083	change times - you need to get those from C<stat _> if required (C<int
		2084	IO::AIO::st_atime> and so on will I<not> generally give you the correct
		2085	value).
		2086
		2087	=item $seconds = IO::AIO::st_btimesec
		2088
		2089	The (integral) seconds part of the file birth time, if available.
		2090
		2091	=item ($atime, $mtime, $ctime, $btime, ...) = IO::AIO::st_xtimensec
		2092
		2093	Like the functions above, but returns all four times in one go (and maybe
		2094	more in future versions).
		2095
		2096	=item $counter = IO::AIO::st_gen
		2097
		2098	Returns the generation counter (in practice this is just a random number)
		2099	of the file. This is only available on platforms which have this member in
		2100	their C<struct stat> (most BSDs at the time of this writing) and generally
		2101	only to the root usert. If unsupported, C<0> is returned, but this might
		2102	change to C<undef> in a future version.
		2103
		2104	=back
		2105
		2106	Example: print the high resolution modification time of F</etc>, using
		2107	C<stat>, and C<IO::AIO::aio_stat>.
		2108
		2109	if (stat "/etc") {
		2110	printf "stat(/etc) mtime: %f\n", IO::AIO::st_mtime;
		2111	}
		2112
		2113	IO::AIO::aio_stat "/etc", sub {
		2114	$_[0]
		2115	and return;
		2116
		2117	printf "aio_stat(/etc) mtime: %d.%09d\n", (stat _)[9], IO::AIO::st_mtimensec;
		2118	};
		2119
		2120	IO::AIO::flush;
		2121
		2122	Output of the awbove on my system, showing reduced and full accuracy:
		2123
		2124	stat(/etc) mtime: 1534043702.020808
		2125	aio_stat(/etc) mtime: 1534043702.020807792
		2126
		2127
		2128	=head3 MISCELLANEOUS FUNCTIONS
		2129
		2130	IO::AIO implements some functions that are useful when you want to use
		2131	some "Advanced I/O" function not available to in Perl, without going the
		2132	"Asynchronous I/O" route. Many of these have an asynchronous C<aio_*>
		2133	counterpart.
		2134
		2135	=over 4
		2136
		2137	=item $numfd = IO::AIO::get_fdlimit
		2138
		2139	This function is I<EXPERIMENTAL> and subject to change.
		2140
		2141	Tries to find the current file descriptor limit and returns it, or
		2142	C<undef> and sets C<$!> in case of an error. The limit is one larger than
		2143	the highest valid file descriptor number.
		2144
		2145	=item IO::AIO::min_fdlimit [$numfd]
		2146
		2147	This function is I<EXPERIMENTAL> and subject to change.
		2148
		2149	Try to increase the current file descriptor limit(s) to at least C<$numfd>
		2150	by changing the soft or hard file descriptor resource limit. If C<$numfd>
		2151	is missing, it will try to set a very high limit, although this is not
		2152	recommended when you know the actual minimum that you require.
		2153
		2154	If the limit cannot be raised enough, the function makes a best-effort
		2155	attempt to increase the limit as much as possible, using various
		2156	tricks, while still failing. You can query the resulting limit using
		2157	C<IO::AIO::get_fdlimit>.
		2158
		2159	If an error occurs, returns C<undef> and sets C<$!>, otherwise returns
		2160	true.
		2161
		2162	=item IO::AIO::sendfile $ofh, $ifh, $offset, $count
		2163
		2164	Calls the C<eio_sendfile_sync> function, which is like C<aio_sendfile>,
		2165	but is blocking (this makes most sense if you know the input data is
		2166	likely cached already and the output filehandle is set to non-blocking
		2167	operations).
		2168
		2169	Returns the number of bytes copied, or C<-1> on error.
		2170
		2171	=item IO::AIO::fadvise $fh, $offset, $len, $advice
		2172
		2173	Simply calls the C<posix_fadvise> function (see its
		2174	manpage for details). The following advice constants are
		2175	available: C<IO::AIO::FADV_NORMAL>, C<IO::AIO::FADV_SEQUENTIAL>,
		2176	C<IO::AIO::FADV_RANDOM>, C<IO::AIO::FADV_NOREUSE>,
		2177	C<IO::AIO::FADV_WILLNEED>, C<IO::AIO::FADV_DONTNEED>.
		2178
		2179	On systems that do not implement C<posix_fadvise>, this function returns
		2180	ENOSYS, otherwise the return value of C<posix_fadvise>.
		2181
		2182	=item IO::AIO::madvise $scalar, $offset, $len, $advice
		2183
		2184	Simply calls the C<posix_madvise> function (see its
		2185	manpage for details). The following advice constants are
		2186	available: C<IO::AIO::MADV_NORMAL>, C<IO::AIO::MADV_SEQUENTIAL>,
		2187	C<IO::AIO::MADV_RANDOM>, C<IO::AIO::MADV_WILLNEED>,
		2188	C<IO::AIO::MADV_DONTNEED>.
		2189
		2190	If C<$offset> is negative, counts from the end. If C<$length> is negative,
		2191	the remaining length of the C<$scalar> is used. If possible, C<$length>
		2192	will be reduced to fit into the C<$scalar>.
		2193
		2194	On systems that do not implement C<posix_madvise>, this function returns
		2195	ENOSYS, otherwise the return value of C<posix_madvise>.
		2196
		2197	=item IO::AIO::mprotect $scalar, $offset, $len, $protect
		2198
		2199	Simply calls the C<mprotect> function on the preferably AIO::mmap'ed
		2200	$scalar (see its manpage for details). The following protect
		2201	constants are available: C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_READ>,
		2202	C<IO::AIO::PROT_WRITE>, C<IO::AIO::PROT_EXEC>.
		2203
		2204	If C<$offset> is negative, counts from the end. If C<$length> is negative,
		2205	the remaining length of the C<$scalar> is used. If possible, C<$length>
		2206	will be reduced to fit into the C<$scalar>.
		2207
		2208	On systems that do not implement C<mprotect>, this function returns
		2209	ENOSYS, otherwise the return value of C<mprotect>.
		2210
		2211	=item IO::AIO::mmap $scalar, $length, $prot, $flags, $fh[, $offset]
		2212
		2213	Memory-maps a file (or anonymous memory range) and attaches it to the
		2214	given C<$scalar>, which will act like a string scalar. Returns true on
		2215	success, and false otherwise.
		2216
		2217	The scalar must exist, but its contents do not matter - this means you
		2218	cannot use a nonexistant array or hash element. When in doubt, C<undef>
		2219	the scalar first.
		2220
		2221	The only operations allowed on the mmapped scalar are C<substr>/C<vec>,
		2222	which don't change the string length, and most read-only operations such
		2223	as copying it or searching it with regexes and so on.
		2224
		2225	Anything else is unsafe and will, at best, result in memory leaks.
		2226
		2227	The memory map associated with the C<$scalar> is automatically removed
		2228	when the C<$scalar> is undef'd or destroyed, or when the C<IO::AIO::mmap>
		2229	or C<IO::AIO::munmap> functions are called on it.
		2230
		2231	This calls the C<mmap>(2) function internally. See your system's manual
		2232	page for details on the C<$length>, C<$prot> and C<$flags> parameters.
		2233
		2234	The C<$length> must be larger than zero and smaller than the actual
		2235	filesize.
		2236
		2237	C<$prot> is a combination of C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_EXEC>,
		2238	C<IO::AIO::PROT_READ> and/or C<IO::AIO::PROT_WRITE>,
		2239
		2240	C<$flags> can be a combination of
		2241	C<IO::AIO::MAP_SHARED> or
		2242	C<IO::AIO::MAP_PRIVATE>,
		2243	or a number of system-specific flags (when not available, the are C<0>):
		2244	C<IO::AIO::MAP_ANONYMOUS> (which is set to C<MAP_ANON> if your system only provides this constant),
		2245	C<IO::AIO::MAP_LOCKED>,
		2246	C<IO::AIO::MAP_NORESERVE>,
		2247	C<IO::AIO::MAP_POPULATE>,
		2248	C<IO::AIO::MAP_NONBLOCK>,
		2249	C<IO::AIO::MAP_FIXED>,
		2250	C<IO::AIO::MAP_GROWSDOWN>,
		2251	C<IO::AIO::MAP_32BIT>,
		2252	C<IO::AIO::MAP_HUGETLB> or
		2253	C<IO::AIO::MAP_STACK>.
		2254
		2255	If C<$fh> is C<undef>, then a file descriptor of C<-1> is passed.
		2256
		2257	C<$offset> is the offset from the start of the file - it generally must be
		2258	a multiple of C<IO::AIO::PAGESIZE> and defaults to C<0>.
		2259
		2260	Example:
		2261
		2262	use Digest::MD5;
		2263	use IO::AIO;
		2264
		2265	open my $fh, "<verybigfile"
		2266	or die "$!";
		2267
		2268	IO::AIO::mmap my $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh
		2269	or die "verybigfile: $!";
		2270
		2271	my $fast_md5 = md5 $data;
		2272
		2273	=item IO::AIO::munmap $scalar
		2274
		2275	Removes a previous mmap and undefines the C<$scalar>.
		2276
		2277	=item IO::AIO::mremap $scalar, $new_length, $flags = MREMAP_MAYMOVE[, $new_address = 0]
		2278
		2279	Calls the Linux-specific mremap(2) system call. The C<$scalar> must have
		2280	been mapped by C<IO::AIO::mmap>, and C<$flags> must currently either be
		2281	C<0> or C<IO::AIO::MREMAP_MAYMOVE>.
		2282
		2283	Returns true if successful, and false otherwise. If the underlying mmapped
		2284	region has changed address, then the true value has the numerical value
		2285	C<1>, otherwise it has the numerical value C<0>:
		2286
		2287	my $success = IO::AIO::mremap $mmapped, 8192, IO::AIO::MREMAP_MAYMOVE
		2288	or die "mremap: $!";
		2289
		2290	if ($success*1) {
		2291	warn "scalar has chanegd address in memory\n";
		2292	}
		2293
		2294	C<IO::AIO::MREMAP_FIXED> and the C<$new_address> argument are currently
		2295	implemented, but not supported and might go away in a future version.
		2296
		2297	On systems where this call is not supported or is not emulated, this call
		2298	returns falls and sets C<$!> to C<ENOSYS>.
		2299
		2300	=item IO::AIO::munlock $scalar, $offset = 0, $length = undef
		2301
		2302	Calls the C<munlock> function, undoing the effects of a previous
		2303	C<aio_mlock> call (see its description for details).
		2304
		2305	=item IO::AIO::munlockall
		2306
		2307	Calls the C<munlockall> function.
		2308
		2309	On systems that do not implement C<munlockall>, this function returns
		2310	ENOSYS, otherwise the return value of C<munlockall>.
		2311
		2312	=item IO::AIO::splice $r_fh, $r_off, $w_fh, $w_off, $length, $flags
		2313
		2314	Calls the GNU/Linux C<splice(2)> syscall, if available. If C<$r_off> or
		2315	C<$w_off> are C<undef>, then C<NULL> is passed for these, otherwise they
		2316	should be the file offset.
		2317
		2318	C<$r_fh> and C<$w_fh> should not refer to the same file, as splice might
		2319	silently corrupt the data in this case.
		2320
		2321	The following symbol flag values are available: C<IO::AIO::SPLICE_F_MOVE>,
		2322	C<IO::AIO::SPLICE_F_NONBLOCK>, C<IO::AIO::SPLICE_F_MORE> and
		2323	C<IO::AIO::SPLICE_F_GIFT>.
		2324
		2325	See the C<splice(2)> manpage for details.
		2326
		2327	=item IO::AIO::tee $r_fh, $w_fh, $length, $flags
		2328
		2329	Calls the GNU/Linux C<tee(2)> syscall, see its manpage and the
		2330	description for C<IO::AIO::splice> above for details.
		2331
		2332	=item $actual_size = IO::AIO::pipesize $r_fh[, $new_size]
		2333
		2334	Attempts to query or change the pipe buffer size. Obviously works only
		2335	on pipes, and currently works only on GNU/Linux systems, and fails with
		2336	C<-1>/C<ENOSYS> everywhere else. If anybody knows how to influence pipe buffer
		2337	size on other systems, drop me a note.
		2338
		2339	=item ($rfh, $wfh) = IO::AIO::pipe2 [$flags]
		2340
		2341	This is a direct interface to the Linux L<pipe2(2)> system call. If
		2342	C<$flags> is missing or C<0>, then this should be the same as a call to
		2343	perl's built-in C<pipe> function and create a new pipe, and works on
		2344	systems that lack the pipe2 syscall. On win32, this case invokes C<_pipe
		2345	(..., 4096, O_BINARY)>.
		2346
		2347	If C<$flags> is non-zero, it tries to invoke the pipe2 system call with
		2348	the given flags (Linux 2.6.27, glibc 2.9).
		2349
		2350	On success, the read and write file handles are returned.
		2351
		2352	On error, nothing will be returned. If the pipe2 syscall is missing and
		2353	C<$flags> is non-zero, fails with C<ENOSYS>.
		2354
		2355	Please refer to L<pipe2(2)> for more info on the C<$flags>, but at the
		2356	time of this writing, C<IO::AIO::O_CLOEXEC>, C<IO::AIO::O_NONBLOCK> and
		2357	C<IO::AIO::O_DIRECT> (Linux 3.4, for packet-based pipes) were supported.
		2358
		2359	Example: create a pipe race-free w.r.t. threads and fork:
		2360
		2361	my ($rfh, $wfh) = IO::AIO::pipe2 IO::AIO::O_CLOEXEC
		2362	or die "pipe2: $!\n";
		2363
		2364	=item $fh = IO::AIO::eventfd [$initval, [$flags]]
		2365
		2366	This is a direct interface to the Linux L<eventfd(2)> system call. The
		2367	(unhelpful) defaults for C<$initval> and C<$flags> are C<0> for both.
		2368
		2369	On success, the new eventfd filehandle is returned, otherwise returns
		2370	C<undef>. If the eventfd syscall is missing, fails with C<ENOSYS>.
		2371
		2372	Please refer to L<eventfd(2)> for more info on this call.
		2373
		2374	The following symbol flag values are available: C<IO::AIO::EFD_CLOEXEC>,
		2375	C<IO::AIO::EFD_NONBLOCK> and C<IO::AIO::EFD_SEMAPHORE> (Linux 2.6.30).
		2376
		2377	Example: create a new eventfd filehandle:
		2378
		2379	$fh = IO::AIO::eventfd 0, IO::AIO::O_CLOEXEC
		2380	or die "eventfd: $!\n";
		2381
		2382	=item $fh = IO::AIO::timerfd_create $clockid[, $flags]
		2383
		2384	This is a direct interface to the Linux L<timerfd_create(2)> system call. The
		2385	(unhelpful) default for C<$flags> is C<0>.
		2386
		2387	On success, the new timerfd filehandle is returned, otherwise returns
		2388	C<undef>. If the eventfd syscall is missing, fails with C<ENOSYS>.
		2389
		2390	Please refer to L<timerfd_create(2)> for more info on this call.
		2391
		2392	The following C<$clockid> values are
		2393	available: C<IO::AIO::CLOCK_REALTIME>, C<IO::AIO::CLOCK_MONOTONIC>
		2394	C<IO::AIO::CLOCK_CLOCK_BOOTTIME> (Linux 3.15)
		2395	C<IO::AIO::CLOCK_CLOCK_REALTIME_ALARM> (Linux 3.11) and
		2396	C<IO::AIO::CLOCK_CLOCK_BOOTTIME_ALARM> (Linux 3.11).
		2397
		2398	The following C<$flags> values are available (Linux
		2399	2.6.27): C<IO::AIO::TFD_NONBLOCK> and C<IO::AIO::TFD_CLOEXEC>.
		2400
		2401	Example: create a new timerfd and set it to one-second repeated alarms,
		2402	then wait for two alarms:
		2403
		2404	my $fh = IO::AIO::timerfd_create IO::AIO::CLOCK_BOOTTIME, IO::AIO::TFD_CLOEXEC
		2405	or die "timerfd_create: $!\n";
		2406
		2407	defined IO::AIO::timerfd_settime $fh, 0, 1, 1
		2408	or die "timerfd_settime: $!\n";
		2409
		2410	for (1..2) {
		2411	8 == sysread $fh, my $buf, 8
		2412	or die "timerfd read failure\n";
		2413
		2414	printf "number of expirations (likely 1): %d\n",
		2415	unpack "Q", $buf;
		2416	}
		2417
		2418	=item ($cur_interval, $cur_value) = IO::AIO::timerfd_settime $fh, $flags, $new_interval, $nbw_value
		2419
		2420	This is a direct interface to the Linux L<timerfd_settime(2)> system
		2421	call. Please refer to its manpage for more info on this call.
		2422
		2423	The new itimerspec is specified using two (possibly fractional) second
		2424	values, C<$new_interval> and C<$new_value>).
		2425
		2426	On success, the current interval and value are returned (as per
		2427	C<timerfd_gettime>). On failure, the empty list is returned.
		2428
		2429	The following C<$flags> values are
		2430	available: C<IO::AIO::TFD_TIMER_ABSTIME> and
		2431	C<IO::AIO::TFD_TIMER_CANCEL_ON_SET>.
		2432
		2433	See C<IO::AIO::timerfd_create> for a full example.
		2434
		2435	=item ($cur_interval, $cur_value) = IO::AIO::timerfd_gettime $fh
		2436
		2437	This is a direct interface to the Linux L<timerfd_gettime(2)> system
		2438	call. Please refer to its manpage for more info on this call.
		2439
		2440	On success, returns the current values of interval and value for the given
		2441	timerfd (as potentially fractional second values). On failure, the empty
		2442	list is returned.
		2443
		2444	=back
		2445
860	=cut	2446	=cut
861		2447
862	# support function to convert a fd into a perl filehandle
863	sub _fd2fh {
864	return undef if $_[0] < 0;
865
866	# try to generate nice filehandles
867	my $sym = "IO::AIO::fd#$_[0]";
868	local *$sym;
869
870	open *$sym, "+<&=$_[0]" # usually works under any unix
871	or open *$sym, "<&=$_[0]" # cygwin needs this
872	or open *$sym, ">&=$_[0]" # or this
873	or return undef;
874
875	*$sym
876	}
877
878	min_parallel 8;	2448	min_parallel 8;
879		2449
880	END {	2450	END { flush }
881	max_parallel 0;
882	}
883		2451
884	1;	2452	1;
885		2453
		2454	=head1 EVENT LOOP INTEGRATION
		2455
		2456	It is recommended to use L<AnyEvent::AIO> to integrate IO::AIO
		2457	automatically into many event loops:
		2458
		2459	# AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...)
		2460	use AnyEvent::AIO;
		2461
		2462	You can also integrate IO::AIO manually into many event loops, here are
		2463	some examples of how to do this:
		2464
		2465	# EV integration
		2466	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
		2467
		2468	# Event integration
		2469	Event->io (fd => IO::AIO::poll_fileno,
		2470	poll => 'r',
		2471	cb => \&IO::AIO::poll_cb);
		2472
		2473	# Glib/Gtk2 integration
		2474	add_watch Glib::IO IO::AIO::poll_fileno,
		2475	in => sub { IO::AIO::poll_cb; 1 };
		2476
		2477	# Tk integration
		2478	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
		2479	readable => \&IO::AIO::poll_cb);
		2480
		2481	# Danga::Socket integration
		2482	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
		2483	\&IO::AIO::poll_cb);
		2484
886	=head2 FORK BEHAVIOUR	2485	=head2 FORK BEHAVIOUR
887		2486
888	This module should do "the right thing" when the process using it forks:	2487	Usage of pthreads in a program changes the semantics of fork
		2488	considerably. Specifically, only async-safe functions can be called after
		2489	fork. Perl doesn't know about this, so in general, you cannot call fork
		2490	with defined behaviour in perl if pthreads are involved. IO::AIO uses
		2491	pthreads, so this applies, but many other extensions and (for inexplicable
		2492	reasons) perl itself often is linked against pthreads, so this limitation
		2493	applies to quite a lot of perls.
889		2494
890	Before the fork, IO::AIO enters a quiescent state where no requests	2495	This module no longer tries to fight your OS, or POSIX. That means IO::AIO
891	can be added in other threads and no results will be processed. After	2496	only works in the process that loaded it. Forking is fully supported, but
892	the fork the parent simply leaves the quiescent state and continues	2497	using IO::AIO in the child is not.
893	request/result processing, while the child clears the request/result
894	queue (so the requests started before the fork will only be handled in
895	the parent). Threads will be started on demand until the limit ste in the
896	parent process has been reached again.
897		2498
898	In short: the parent will, after a short pause, continue as if fork had	2499	You might get around by not I<using> IO::AIO before (or after)
899	not been called, while the child will act as if IO::AIO has not been used	2500	forking. You could also try to call the L<IO::AIO::reinit> function in the
900	yet.	2501	child:
		2502
		2503	=over 4
		2504
		2505	=item IO::AIO::reinit
		2506
		2507	Abandons all current requests and I/O threads and simply reinitialises all
		2508	data structures. This is not an operation supported by any standards, but
		2509	happens to work on GNU/Linux and some newer BSD systems.
		2510
		2511	The only reasonable use for this function is to call it after forking, if
		2512	C<IO::AIO> was used in the parent. Calling it while IO::AIO is active in
		2513	the process will result in undefined behaviour. Calling it at any time
		2514	will also result in any undefined (by POSIX) behaviour.
		2515
		2516	=back
		2517
		2518	=head2 LINUX-SPECIFIC CALLS
		2519
		2520	When a call is documented as "linux-specific" then this means it
		2521	originated on GNU/Linux. C<IO::AIO> will usually try to autodetect the
		2522	availability and compatibility of such calls regardless of the platform
		2523	it is compiled on, so platforms such as FreeBSD which often implement
		2524	these calls will work. When in doubt, call them and see if they fail wth
		2525	C<ENOSYS>.
901		2526
902	=head2 MEMORY USAGE	2527	=head2 MEMORY USAGE
903		2528
		2529	Per-request usage:
		2530
904	Each aio request uses - depending on your architecture - around 128 bytes	2531	Each aio request uses - depending on your architecture - around 100-200
905	of memory. In addition, stat requests need a stat buffer (possibly a few	2532	bytes of memory. In addition, stat requests need a stat buffer (possibly
906	hundred bytes). Perl scalars and other data passed into aio requests will	2533	a few hundred bytes), readdir requires a result buffer and so on. Perl
907	also be locked.	2534	scalars and other data passed into aio requests will also be locked and
		2535	will consume memory till the request has entered the done state.
908		2536
909	This is now awfully much, so queuing lots of requests is not usually a	2537	This is not awfully much, so queuing lots of requests is not usually a
910	problem.	2538	problem.
911		2539
912	Each thread needs a stack area which is usually around 16k, sometimes much	2540	Per-thread usage:
913	larger, depending on the OS.	2541
		2542	In the execution phase, some aio requests require more memory for
		2543	temporary buffers, and each thread requires a stack and other data
		2544	structures (usually around 16k-128k, depending on the OS).
		2545
		2546	=head1 KNOWN BUGS
		2547
		2548	Known bugs will be fixed in the next release :)
		2549
		2550	=head1 KNOWN ISSUES
		2551
		2552	Calls that try to "import" foreign memory areas (such as C<IO::AIO::mmap>
		2553	or C<IO::AIO::aio_slurp>) do not work with generic lvalues, such as
		2554	non-created hash slots or other scalars I didn't think of. It's best to
		2555	avoid such and either use scalar variables or making sure that the scalar
		2556	exists (e.g. by storing C<undef>) and isn't "funny" (e.g. tied).
		2557
		2558	I am not sure anything can be done about this, so this is considered a
		2559	known issue, rather than a bug.
914		2560
915	=head1 SEE ALSO	2561	=head1 SEE ALSO
916		2562
917	L<Coro::AIO>.	2563	L<AnyEvent::AIO> for easy integration into event loops, L<Coro::AIO> for a
		2564	more natural syntax.
918		2565
919	=head1 AUTHOR	2566	=head1 AUTHOR
920		2567
921	Marc Lehmann <schmorp@schmorp.de>	2568	Marc Lehmann <schmorp@schmorp.de>
922	http://home.schmorp.de/	2569	http://home.schmorp.de/

Diff Legend

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