ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/IO-AIO/AIO.pm

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.116 by root, Wed Oct 3 21:27:51 2007 UTC vs.
Revision 1.294 by root, Sat Aug 25 19:25:32 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 = shift	10	my $fh = shift
11	or die "/etc/passwd: $!";	11	or die "/etc/passwd: $!";
12	...	12	...
13	};	13	};
14		14
…		…
26	$req->cancel; # cancel request if still in queue	26	$req->cancel; # cancel request if still in queue
27		27
28	my $grp = aio_group sub { print "all stats done\n" };	28	my $grp = aio_group sub { print "all stats done\n" };
29	add $grp aio_stat "..." for ...;	29	add $grp aio_stat "..." for ...;
30		30
31	# AnyEvent integration
32	open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!";
33	my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb });
34
35	# Event integration
36	Event->io (fd => IO::AIO::poll_fileno,
37	poll => 'r',
38	cb => \&IO::AIO::poll_cb);
39
40	# Glib/Gtk2 integration
41	add_watch Glib::IO IO::AIO::poll_fileno,
42	in => sub { IO::AIO::poll_cb; 1 };
43
44	# Tk integration
45	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
46	readable => \&IO::AIO::poll_cb);
47
48	# Danga::Socket integration
49	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
50	\&IO::AIO::poll_cb);
51
52	=head1 DESCRIPTION	31	=head1 DESCRIPTION
53		32
54	This module implements asynchronous I/O using whatever means your	33	This module implements asynchronous I/O using whatever means your
55	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>).
56		36
57	Asynchronous means that operations that can normally block your program	37	Asynchronous means that operations that can normally block your program
58	(e.g. reading from disk) will be done asynchronously: the operation	38	(e.g. reading from disk) will be done asynchronously: the operation
59	will still block, but you can do something else in the meantime. This	39	will still block, but you can do something else in the meantime. This
60	is extremely useful for programs that need to stay interactive even	40	is extremely useful for programs that need to stay interactive even
…		…
64	on a RAID volume or over NFS when you do a number of stat operations	44	on a RAID volume or over NFS when you do a number of stat operations
65	concurrently.	45	concurrently.
66		46
67	While most of this works on all types of file descriptors (for	47	While most of this works on all types of file descriptors (for
68	example sockets), using these functions on file descriptors that	48	example sockets), using these functions on file descriptors that
69	support nonblocking operation (again, sockets, pipes etc.) is very	49	support nonblocking operation (again, sockets, pipes etc.) is
70	inefficient. Use an event loop for that (such as the L<Event|Event>	50	very inefficient. Use an event loop for that (such as the L<EV>
71	module): IO::AIO will naturally fit into such an event loop itself.	51	module): IO::AIO will naturally fit into such an event loop itself.
72		52
73	In this version, a number of threads are started that execute your	53	In this version, a number of threads are started that execute your
74	requests and signal their completion. You don't need thread support	54	requests and signal their completion. You don't need thread support
75	in perl, and the threads created by this module will not be visible	55	in perl, and the threads created by this module will not be visible
…		…
78	not well-supported or restricted (GNU/Linux doesn't allow them on normal	58	not well-supported or restricted (GNU/Linux doesn't allow them on normal
79	files currently, for example), and they would only support aio_read and	59	files currently, for example), and they would only support aio_read and
80	aio_write, so the remaining functionality would have to be implemented	60	aio_write, so the remaining functionality would have to be implemented
81	using threads anyway.	61	using threads anyway.
82		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
83	Although the module will work in the presence of other (Perl-) threads,	67	Although the module will work in the presence of other (Perl-) threads,
84	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
85	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
86	call C<poll_cb> (or other C<aio_> functions) recursively.	70	call C<poll_cb> (or other C<aio_> functions) recursively.
87		71
88	=head2 EXAMPLE	72	=head2 EXAMPLE
89		73
90	This is a simple example that uses the Event module and loads	74	This is a simple example that uses the EV module and loads
91	F</etc/passwd> asynchronously:	75	F</etc/passwd> asynchronously:
92		76
93	use Fcntl;
94	use Event;	77	use EV;
95	use IO::AIO;	78	use IO::AIO;
96		79
97	# register the IO::AIO callback with Event	80	# register the IO::AIO callback with EV
98	Event->io (fd => IO::AIO::poll_fileno,	81	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
99	poll => 'r',
100	cb => \&IO::AIO::poll_cb);
101		82
102	# queue the request to open /etc/passwd	83	# queue the request to open /etc/passwd
103	aio_open "/etc/passwd", O_RDONLY, 0, sub {	84	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
104	my $fh = shift	85	my $fh = shift
105	or die "error while opening: $!";	86	or die "error while opening: $!";
106		87
107	# stat'ing filehandles is generally non-blocking	88	# stat'ing filehandles is generally non-blocking
108	my $size = -s $fh;	89	my $size = -s $fh;
…		…
117		98
118	# file contents now in $contents	99	# file contents now in $contents
119	print $contents;	100	print $contents;
120		101
121	# exit event loop and program	102	# exit event loop and program
122	Event::unloop;	103	EV::break;
123	};	104	};
124	};	105	};
125		106
126	# possibly queue up other requests, or open GUI windows,	107	# possibly queue up other requests, or open GUI windows,
127	# check for sockets etc. etc.	108	# check for sockets etc. etc.
128		109
129	# process events as long as there are some:	110	# process events as long as there are some:
130	Event::loop;	111	EV::run;
131		112
132	=head1 REQUEST ANATOMY AND LIFETIME	113	=head1 REQUEST ANATOMY AND LIFETIME
133		114
134	Every C<aio_*> function creates a request. which is a C data structure not	115	Every C<aio_*> function creates a request. which is a C data structure not
135	directly visible to Perl.	116	directly visible to Perl.
…		…
183		164
184	=cut	165	=cut
185		166
186	package IO::AIO;	167	package IO::AIO;
187		168
188	no warnings;	169	use Carp ();
189	use strict 'vars';	170
		171	use common::sense;
190		172
191	use base 'Exporter';	173	use base 'Exporter';
192		174
193	BEGIN {	175	BEGIN {
194	our $VERSION = '2.5';	176	our $VERSION = 4.54;
195		177
196	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
197	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
198	aio_readlink aio_fsync aio_fdatasync aio_readahead aio_rename aio_link	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
199	aio_move aio_copy aio_group aio_nop aio_mknod aio_load aio_rmtree aio_mkdir	184	aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown
200	aio_chown aio_chmod aio_utime aio_truncate);	185	aio_chmod aio_utime aio_truncate
		186	aio_msync aio_mtouch aio_mlock aio_mlockall
		187	aio_statvfs
		188	aio_slurp
		189	aio_wd);
		190
201	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice aio_block));	191	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice));
202	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush	192	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush
203	min_parallel max_parallel max_idle	193	min_parallel max_parallel max_idle idle_timeout
204	nreqs nready npending nthreads	194	nreqs nready npending nthreads
205	max_poll_time max_poll_reqs);	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
206		200
207	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';	201	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';
208		202
209	require XSLoader;	203	require XSLoader;
210	XSLoader::load ("IO::AIO", $VERSION);	204	XSLoader::load ("IO::AIO", $VERSION);
211	}	205	}
212		206
213	=head1 FUNCTIONS	207	=head1 FUNCTIONS
214		208
215	=head2 AIO REQUEST 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, $length = undef
		294	IO::AIO::munlockall
		295
		296	=head2 API NOTES
216		297
217	All the C<aio_*> calls are more or less thin wrappers around the syscall	298	All the C<aio_*> calls are more or less thin wrappers around the syscall
218	with the same name (sans C<aio_>). The arguments are similar or identical,	299	with the same name (sans C<aio_>). The arguments are similar or identical,
219	and they all accept an additional (and optional) C<$callback> argument	300	and they all accept an additional (and optional) C<$callback> argument
220	which must be a code reference. This code reference will get called with	301	which must be a code reference. This code reference will be called after
221	the syscall return code (e.g. most syscalls return C<-1> on error, unlike	302	the syscall has been executed in an asynchronous fashion. The results
222	perl, which usually delivers "false") as it's sole argument when the given	303	of the request will be passed as arguments to the callback (and, if an
223	syscall has been executed asynchronously.	304	error occured, in C<$!>) - 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>.
224		310
225	All functions expecting a filehandle keep a copy of the filehandle	311	All functions expecting a filehandle keep a copy of the filehandle
226	internally until the request has finished.	312	internally until the request has finished.
227		313
228	All functions return request objects of type L<IO::AIO::REQ> that allow	314	All functions return request objects of type L<IO::AIO::REQ> that allow
229	further manipulation of those requests while they are in-flight.	315	further manipulation of those requests while they are in-flight.
230		316
231	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
232	encoded as octets. 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
233	request is being executed, the current working directory could have	319	current working directory could have changed. Alternatively, you can
234	changed. Alternatively, you can make sure that you never change the	320	make sure that you never change the current working directory anywhere
235	current working directory anywhere in the program and then use relative	321	in the program and then use relative paths. You can also take advantage
236	paths.	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.
237		325
238	To encode pathnames as octets, either make sure you either: a) always pass	326	To encode pathnames as octets, either make sure you either: a) always pass
239	in filenames you got from outside (command line, readdir etc.) without	327	in filenames you got from outside (command line, readdir etc.) without
240	tinkering, 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
241	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
242	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
243	use something else to ensure your scalar has the correct contents.	331	unicode filenames or e) use something else to ensure your scalar has the
		332	correct contents.
244		333
245	This works, btw. independent of the internal UTF-8 bit, which IO::AIO	334	This works, btw. independent of the internal UTF-8 bit, which IO::AIO
246	handles correctly wether it is set or not.	335	handles correctly whether it is set or not.
		336
		337	=head2 AIO REQUEST FUNCTIONS
247		338
248	=over 4	339	=over 4
249		340
250	=item $prev_pri = aioreq_pri [$pri]	341	=item $prev_pri = aioreq_pri [$pri]
251		342
…		…
281		372
282		373
283	=item aio_open $pathname, $flags, $mode, $callback->($fh)	374	=item aio_open $pathname, $flags, $mode, $callback->($fh)
284		375
285	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
286	created filehandle for the file.	377	created filehandle for the file (or C<undef> in case of an error).
287		378
288	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,
289	for an explanation.	380	for an explanation.
290		381
291	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
…		…
298	by the umask in effect then the request is being executed, so better never	389	by the umask in effect then the request is being executed, so better never
299	change the umask.	390	change the umask.
300		391
301	Example:	392	Example:
302		393
303	aio_open "/etc/passwd", O_RDONLY, 0, sub {	394	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
304	if ($_[0]) {	395	if ($_[0]) {
305	print "open successful, fh is $_[0]\n";	396	print "open successful, fh is $_[0]\n";
306	...	397	...
307	} else {	398	} else {
308	die "open failed: $!\n";	399	die "open failed: $!\n";
309	}	400	}
310	};	401	};
311		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
312		412
313	=item aio_close $fh, $callback->($status)	413	=item aio_close $fh, $callback->($status)
314		414
315	Asynchronously close a file and call the callback with the result	415	Asynchronously close a file and call the callback with the result
316	code.	416	code.
317		417
318	Unlike the other functions operating on files, this function uses the	418	Unfortunately, you can't do this to perl. Perl I<insists> very strongly on
319	PerlIO layer to close the filehandle. The reason is that the PerlIO API	419	closing the file descriptor associated with the filehandle itself.
320	insists on closing the underlying fd itself, no matter what, and doesn't
321	allow modifications to the fd. Unfortunately, it is not clear that you can
322	call PerlIO from different threads (actually, its quite clear that this
323	won't work in some cases), so while it likely works perfectly with simple
324	file handles (such as the ones created by C<aio_open>) it might fail in
325	interesting ways for others.
326		420
327	Having said that, aio_close tries to clean up the filehandle as much as	421	Therefore, C<aio_close> will not close the filehandle - instead it will
328	possible before handing it to an io thread, and generally does work.	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).
329		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".
330		449
331	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	450	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
332		451
333	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	452	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
334		453
335	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<$fh> and
336	into the scalar given by C<$data> and offset C<$dataoffset> and calls the	455	C<$offset> into the scalar given by C<$data> and offset C<$dataoffset> and
337	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
338	like the syscall).	457	error, just like the syscall).
		458
		459	C<aio_read> will, like C<sysread>, shrink or grow the C<$data> scalar to
		460	offset plus the actual number of bytes read.
339		461
340	If C<$offset> is undefined, then the current file descriptor offset will	462	If C<$offset> is undefined, then the current file descriptor offset will
341	be used (and updated), otherwise the file descriptor offset will not be	463	be used (and updated), otherwise the file descriptor offset will not be
342	changed by these calls.	464	changed by these calls.
343		465
344	If C<$length> is undefined in C<aio_write>, use the remaining length of C<$data>.	466	If C<$length> is undefined in C<aio_write>, use the remaining length of
		467	C<$data>.
345		468
346	If C<$dataoffset> is less than zero, it will be counted from the end of	469	If C<$dataoffset> is less than zero, it will be counted from the end of
347	C<$data>.	470	C<$data>.
348		471
349	The C<$data> scalar I<MUST NOT> be modified in any way while the request	472	The C<$data> scalar I<MUST NOT> be modified in any way while the request
…		…
363		486
364	Tries to copy C<$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<$out_fh>. It starts
365	reading at byte offset C<$in_offset>, and starts writing at the current	488	reading at byte offset C<$in_offset>, and starts writing at the current
366	file offset of C<$out_fh>. Because of that, it is not safe to issue more	489	file offset of C<$out_fh>. Because of that, it is not safe to issue more
367	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each	490	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each
368	other.	491	other. The same C<$in_fh> works fine though, as this function does not
		492	move or use the file offset of C<$in_fh>.
369		493
		494	Please note that C<aio_sendfile> can read more bytes from C<$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
370	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
371	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
372	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.
373		513
374	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>,
375	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
376	regardless of the limitations of the operating system.	517	type of filehandle regardless of the limitations of the operating system.
377		518
378	Please note, however, that C<aio_sendfile> can read more bytes from	519	As native sendfile syscalls (as practically any non-POSIX interface hacked
379	C<$in_fh> than are written, and there is no way to find out how many	520	together in a hurry to improve benchmark numbers) tend to be rather buggy
380	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only	521	on many systems, this implementation tries to work around some known bugs
381	provides the number of bytes written to C<$out_fh>. Only if the result	522	in Linux and FreeBSD kernels (probably others, too), but that might fail,
382	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> -
383	read.	524	fewer bytes than expected might have been transferred.
384		525
385		526
386	=item aio_readahead $fh,$offset,$length, $callback->($retval)	527	=item aio_readahead $fh,$offset,$length, $callback->($retval)
387		528
388	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
…		…
392	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
393	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
394	(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
395	file. The current file offset of the file is left unchanged.	536	file. The current file offset of the file is left unchanged.
396		537
397	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
398	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.
399		540
400		541
401	=item aio_stat $fh_or_path, $callback->($status)	542	=item aio_stat $fh_or_path, $callback->($status)
402		543
403	=item aio_lstat $fh, $callback->($status)	544	=item aio_lstat $fh, $callback->($status)
404		545
405	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
406	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
407	or C<-s _> etc...	548	using C<stat _> or C<-s _> and other tests (with the exception of C<-B>
		549	and C<-T>).
408		550
409	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,
410	for an explanation.	552	for an explanation.
411		553
412	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
413	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
414	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>.
415		569
416	Example: Print the length of F</etc/passwd>:	570	Example: Print the length of F</etc/passwd>:
417		571
418	aio_stat "/etc/passwd", sub {	572	aio_stat "/etc/passwd", sub {
419	$_[0] and die "stat failed: $!";	573	$_[0] and die "stat failed: $!";
420	print "size is ", -s _, "\n";	574	print "size is ", -s _, "\n";
421	};	575	};
422		576
423		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
424	=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)	622	=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
425		623
426	Works like perl's C<utime> function (including the special case of $atime	624	Works like perl's C<utime> function (including the special case of $atime
427	and $mtime being undef). Fractional times are supported if the underlying	625	and $mtime being undef). Fractional times are supported if the underlying
428	syscalls support them.	626	syscalls support them.
429		627
430	When called with a pathname, uses utimes(2) if available, otherwise	628	When called with a pathname, uses utimensat(2) or utimes(2) if available,
431	utime(2). If called on a file descriptor, uses futimes(2) if available,	629	otherwise utime(2). If called on a file descriptor, uses futimens(2)
432	otherwise returns ENOSYS, so this is not portable.	630	or futimes(2) if available, otherwise returns ENOSYS, so this is not
		631	portable.
433		632
434	Examples:	633	Examples:
435		634
436	# set atime and mtime to current time (basically touch(1)):	635	# set atime and mtime to current time (basically touch(1)):
437	aio_utime "path", undef, undef;	636	aio_utime "path", undef, undef;
…		…
455	=item aio_truncate $fh_or_path, $offset, $callback->($status)	654	=item aio_truncate $fh_or_path, $offset, $callback->($status)
456		655
457	Works like truncate(2) or ftruncate(2).	656	Works like truncate(2) or ftruncate(2).
458		657
459		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
460	=item aio_chmod $fh_or_path, $mode, $callback->($status)	681	=item aio_chmod $fh_or_path, $mode, $callback->($status)
461		682
462	Works like perl's C<chmod> function.	683	Works like perl's C<chmod> function.
463		684
464		685
…		…
466		687
467	Asynchronously unlink (delete) a file and call the callback with the	688	Asynchronously unlink (delete) a file and call the callback with the
468	result code.	689	result code.
469		690
470		691
471	=item aio_mknod $path, $mode, $dev, $callback->($status)	692	=item aio_mknod $pathname, $mode, $dev, $callback->($status)
472		693
473	[EXPERIMENTAL]	694	[EXPERIMENTAL]
474		695
475	Asynchronously create a device node (or fifo). See mknod(2).	696	Asynchronously create a device node (or fifo). See mknod(2).
476		697
477	The only (POSIX-) portable way of calling this function is:	698	The only (POSIX-) portable way of calling this function is:
478		699
479	aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ...	700	aio_mknod $pathname, IO::AIO::S_IFIFO | $mode, 0, sub { ...
480		701
		702	See C<aio_stat> for info about some potentially helpful extra constants
		703	and functions.
481		704
482	=item aio_link $srcpath, $dstpath, $callback->($status)	705	=item aio_link $srcpath, $dstpath, $callback->($status)
483		706
484	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
485	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.
…		…
489		712
490	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
491	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.
492		715
493		716
494	=item aio_readlink $path, $callback->($link)	717	=item aio_readlink $pathname, $callback->($link)
495		718
496	Asynchronously read the symlink specified by C<$path> and pass it to	719	Asynchronously read the symlink specified by C<$path> and pass it to
497	the callback. If an error occurs, nothing or undef gets passed to the	720	the callback. If an error occurs, nothing or undef gets passed to the
498	callback.	721	callback.
499		722
500		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
501	=item aio_rename $srcpath, $dstpath, $callback->($status)	734	=item aio_rename $srcpath, $dstpath, $callback->($status)
502		735
503	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
504	rename(2) and call the callback with the result code.	737	rename(2) and call the callback with the result code.
		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>.
505		758
506		759
507	=item aio_mkdir $pathname, $mode, $callback->($status)	760	=item aio_mkdir $pathname, $mode, $callback->($status)
508		761
509	Asynchronously mkdir (create) a directory and call the callback with	762	Asynchronously mkdir (create) a directory and call the callback with
…		…
514	=item aio_rmdir $pathname, $callback->($status)	767	=item aio_rmdir $pathname, $callback->($status)
515		768
516	Asynchronously rmdir (delete) a directory and call the callback with the	769	Asynchronously rmdir (delete) a directory and call the callback with the
517	result code.	770	result code.
518		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
519		776
520	=item aio_readdir $pathname, $callback->($entries)	777	=item aio_readdir $pathname, $callback->($entries)
521		778
522	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
523	directory (i.e. opendir + readdir + closedir). The entries will not be	780	directory (i.e. opendir + readdir + closedir). The entries will not be
524	sorted, and will B<NOT> include the C<.> and C<..> entries.	781	sorted, and will B<NOT> include the C<.> and C<..> entries.
525		782
526	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
527	with the filenames.	784	array-ref with the filenames.
528		785
529		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
530	=item aio_load $path, $data, $callback->($status)	884	=item aio_load $pathname, $data, $callback->($status)
531		885
532	This is a composite request that tries to fully load the given file into	886	This is a composite request that tries to fully load the given file into
533	memory. Status is the same as with aio_read.	887	memory. Status is the same as with aio_read.
534		888
		889	Using C<aio_slurp> might be more efficient, as it is a single request.
		890
535	=cut	891	=cut
536		892
537	sub aio_load($$;$) {	893	sub aio_load($$;$) {
538	aio_block {
539	my ($path, undef, $cb) = @_;	894	my ($path, undef, $cb) = @_;
540	my $data = \$_[1];	895	my $data = \$_[1];
541		896
542	my $pri = aioreq_pri;	897	my $pri = aioreq_pri;
543	my $grp = aio_group $cb;	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);
544		904
545	aioreq_pri $pri;	905	aioreq_pri $pri;
546	add $grp aio_open $path, O_RDONLY, 0, sub {
547	my $fh = shift
548	or return $grp->result (-1);
549
550	aioreq_pri $pri;
551	add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub {	906	add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub {
552	$grp->result ($_[0]);	907	$grp->result ($_[0]);
553	};
554	};	908	};
555
556	$grp
557	}	909	};
		910
		911	$grp
558	}	912	}
559		913
560	=item aio_copy $srcpath, $dstpath, $callback->($status)	914	=item aio_copy $srcpath, $dstpath, $callback->($status)
561		915
562	Try to copy the I<file> (directories not supported as either source or	916	Try to copy the I<file> (directories not supported as either source or
563	destination) from C<$srcpath> to C<$dstpath> and call the callback with	917	destination) from C<$srcpath> to C<$dstpath> and call the callback with
564	the C<0> (error) or C<-1> ok.	918	a status of C<0> (ok) or C<-1> (error, see C<$!>).
565		919
		920	Existing destination files will be truncated.
		921
566	This is a composite request that it creates the destination file with	922	This is a composite request that creates the destination file with
567	mode 0200 and copies the contents of the source file into it using	923	mode 0200 and copies the contents of the source file into it using
568	C<aio_sendfile>, followed by restoring atime, mtime, access mode and	924	C<aio_sendfile>, followed by restoring atime, mtime, access mode and
569	uid/gid, in that order.	925	uid/gid, in that order.
570		926
571	If an error occurs, the partial destination file will be unlinked, if	927	If an error occurs, the partial destination file will be unlinked, if
…		…
573	errors are being ignored.	929	errors are being ignored.
574		930
575	=cut	931	=cut
576		932
577	sub aio_copy($$;$) {	933	sub aio_copy($$;$) {
578	aio_block {
579	my ($src, $dst, $cb) = @_;	934	my ($src, $dst, $cb) = @_;
580		935
581	my $pri = aioreq_pri;	936	my $pri = aioreq_pri;
582	my $grp = aio_group $cb;	937	my $grp = aio_group $cb;
583		938
584	aioreq_pri $pri;	939	aioreq_pri $pri;
585	add $grp aio_open $src, O_RDONLY, 0, sub {	940	add $grp aio_open $src, O_RDONLY, 0, sub {
586	if (my $src_fh = $_[0]) {	941	if (my $src_fh = $_[0]) {
587	my @stat = stat $src_fh;	942	my @stat = stat $src_fh; # hmm, might block over nfs?
588		943
589	aioreq_pri $pri;	944	aioreq_pri $pri;
590	add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {	945	add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {
591	if (my $dst_fh = $_[0]) {	946	if (my $dst_fh = $_[0]) {
592	aioreq_pri $pri;	947	aioreq_pri $pri;
593	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {	948	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
594	if ($_[0] == $stat[7]) {	949	if ($_[0] == $stat[7]) {
595	$grp->result (0);	950	$grp->result (0);
596	close $src_fh;	951	close $src_fh;
597		952
598	# those should not normally block. should. should.
599	utime $stat[8], $stat[9], $dst;
600	chmod $stat[2] & 07777, $dst_fh;
601	chown $stat[4], $stat[5], $dst_fh;
602	close $dst_fh;
603	} else {	953	my $ch = sub {
604	$grp->result (-1);
605	close $src_fh;
606	close $dst_fh;
607
608	aioreq $pri;	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;
609	add $grp aio_unlink $dst;	959	add $grp aio_close $dst_fh;
		960	}
		961	};
610	}	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;
611	};	980	}
612	} else {
613	$grp->result (-1);
614	}	981	};
		982	} else {
		983	$grp->result (-1);
615	},	984	}
616
617	} else {
618	$grp->result (-1);
619	}	985	},
		986
		987	} else {
		988	$grp->result (-1);
620	};	989	}
621
622	$grp
623	}	990	};
		991
		992	$grp
624	}	993	}
625		994
626	=item aio_move $srcpath, $dstpath, $callback->($status)	995	=item aio_move $srcpath, $dstpath, $callback->($status)
627		996
628	Try to move the I<file> (directories not supported as either source or	997	Try to move the I<file> (directories not supported as either source or
629	destination) from C<$srcpath> to C<$dstpath> and call the callback with	998	destination) from C<$srcpath> to C<$dstpath> and call the callback with
630	the C<0> (error) or C<-1> ok.	999	a status of C<0> (ok) or C<-1> (error, see C<$!>).
631		1000
632	This is a composite request that tries to rename(2) the file first. If	1001	This is a composite request that tries to rename(2) the file first; if
633	rename files with C<EXDEV>, it copies the file with C<aio_copy> and, if	1002	rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if
634	that is successful, unlinking the C<$srcpath>.	1003	that is successful, unlinks the C<$srcpath>.
635		1004
636	=cut	1005	=cut
637		1006
638	sub aio_move($$;$) {	1007	sub aio_move($$;$) {
639	aio_block {
640	my ($src, $dst, $cb) = @_;	1008	my ($src, $dst, $cb) = @_;
641		1009
642	my $pri = aioreq_pri;	1010	my $pri = aioreq_pri;
643	my $grp = aio_group $cb;	1011	my $grp = aio_group $cb;
644		1012
645	aioreq_pri $pri;	1013	aioreq_pri $pri;
646	add $grp aio_rename $src, $dst, sub {	1014	add $grp aio_rename $src, $dst, sub {
647	if ($_[0] && $! == EXDEV) {	1015	if ($_[0] && $! == EXDEV) {
648	aioreq_pri $pri;	1016	aioreq_pri $pri;
649	add $grp aio_copy $src, $dst, sub {	1017	add $grp aio_copy $src, $dst, sub {
650	$grp->result ($_[0]);
651
652	if (!$_[0]) {
653	aioreq_pri $pri;
654	add $grp aio_unlink $src;
655	}
656	};
657	} else {
658	$grp->result ($_[0]);	1018	$grp->result ($_[0]);
		1019
		1020	unless ($_[0]) {
		1021	aioreq_pri $pri;
		1022	add $grp aio_unlink $src;
		1023	}
659	}	1024	};
		1025	} else {
		1026	$grp->result ($_[0]);
660	};	1027	}
661
662	$grp
663	}	1028	};
		1029
		1030	$grp
664	}	1031	}
665		1032
666	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)	1033	=item aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs)
667		1034
668	Scans a directory (similar to C<aio_readdir>) but additionally tries to	1035	Scans a directory (similar to C<aio_readdir>) but additionally tries to
669	efficiently separate the entries of directory C<$path> into two sets of	1036	efficiently separate the entries of directory C<$path> into two sets of
670	names, directories you can recurse into (directories), and ones you cannot	1037	names, directories you can recurse into (directories), and ones you cannot
671	recurse into (everything else, including symlinks to directories).	1038	recurse into (everything else, including symlinks to directories).
672		1039
673	C<aio_scandir> is a composite request that creates of many sub requests_	1040	C<aio_scandir> is a composite request that generates many sub requests.
674	C<$maxreq> specifies the maximum number of outstanding aio requests that	1041	C<$maxreq> specifies the maximum number of outstanding aio requests that
675	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
676	will be chosen (currently 4).	1043	will be chosen (currently 4).
677		1044
678	On error, the callback is called without arguments, otherwise it receives	1045	On error, the callback is called without arguments, otherwise it receives
…		…
688		1055
689	Implementation notes.	1056	Implementation notes.
690		1057
691	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.
692		1059
		1060	If readdir returns file type information, then this is used directly to
		1061	find directories.
		1062
693	After reading the directory, the modification time, size etc. of the	1063	Otherwise, after reading the directory, the modification time, size etc.
694	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
695	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
696	entries are directories (if >= 2). Otherwise, no knowledge of the number	1066	how many entries are directories (if >= 2). Otherwise, no knowledge of the
697	of subdirectories will be assumed.	1067	number of subdirectories will be assumed.
698		1068
699	Then entries will be sorted into likely directories (everything without	1069	Then entries will be sorted into likely directories a non-initial dot
700	a non-initial dot currently) and likely non-directories (everything	1070	currently) and likely non-directories (see C<aio_readdirx>). Then every
701	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,
702	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
703	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
704	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
705	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
706	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.
707		1078
708	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
709	rest of the entries is assumed to be non-directories.	1080	rest of the entries is assumed to be non-directories.
710		1081
711	This only works with certainty on POSIX (= UNIX) filesystems, which	1082	This only works with certainty on POSIX (= UNIX) filesystems, which
…		…
716	directory counting heuristic.	1087	directory counting heuristic.
717		1088
718	=cut	1089	=cut
719		1090
720	sub aio_scandir($$;$) {	1091	sub aio_scandir($$;$) {
721	aio_block {
722	my ($path, $maxreq, $cb) = @_;	1092	my ($path, $maxreq, $cb) = @_;
723		1093
724	my $pri = aioreq_pri;	1094	my $pri = aioreq_pri;
725		1095
726	my $grp = aio_group $cb;	1096	my $grp = aio_group $cb;
727		1097
728	$maxreq = 4 if $maxreq <= 0;	1098	$maxreq = 4 if $maxreq <= 0;
		1099
		1100	# get a wd object
		1101	aioreq_pri $pri;
		1102	add $grp aio_wd $path, sub {
		1103	$_[0]
		1104	or return $grp->result ();
		1105
		1106	my $wd = [shift, "."];
729		1107
730	# stat once	1108	# stat once
731	aioreq_pri $pri;	1109	aioreq_pri $pri;
732	add $grp aio_stat $path, sub {	1110	add $grp aio_stat $wd, sub {
733	return $grp->result () if $_[0];	1111	return $grp->result () if $_[0];
734	my $now = time;	1112	my $now = time;
735	my $hash1 = join ":", (stat _)[0,1,3,7,9];	1113	my $hash1 = join ":", (stat _)[0,1,3,7,9];
736		1114
737	# read the directory entries	1115	# read the directory entries
738	aioreq_pri $pri;	1116	aioreq_pri $pri;
739	add $grp aio_readdir $path, sub {	1117	add $grp aio_readdirx $wd, READDIR_DIRS_FIRST, sub {
740	my $entries = shift	1118	my $entries = shift
741	or return $grp->result ();	1119	or return $grp->result ();
742		1120
743	# stat the dir another time	1121	# stat the dir another time
744	aioreq_pri $pri;	1122	aioreq_pri $pri;
745	add $grp aio_stat $path, sub {	1123	add $grp aio_stat $wd, sub {
746	my $hash2 = join ":", (stat _)[0,1,3,7,9];	1124	my $hash2 = join ":", (stat _)[0,1,3,7,9];
747		1125
748	my $ndirs;	1126	my $ndirs;
749		1127
750	# take the slow route if anything looks fishy	1128	# take the slow route if anything looks fishy
751	if ($hash1 ne $hash2 or (stat _)[9] == $now) {	1129	if ($hash1 ne $hash2 or (stat _)[9] == $now) {
752	$ndirs = -1;	1130	$ndirs = -1;
753	} else {	1131	} else {
754	# if nlink == 2, we are finished	1132	# if nlink == 2, we are finished
755	# on non-posix-fs's, we rely on nlink < 2	1133	# for non-posix-fs's, we rely on nlink < 2
756	$ndirs = (stat _)[3] - 2	1134	$ndirs = (stat _)[3] - 2
757	or return $grp->result ([], $entries);	1135	or return $grp->result ([], $entries);
758	}	1136	}
759		1137
760	# sort into likely dirs and likely nondirs
761	# dirs == files without ".", short entries first
762	$entries = [map $_->[0],
763	sort { $b->[1] cmp $a->[1] }
764	map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],
765	@$entries];
766
767	my (@dirs, @nondirs);	1138	my (@dirs, @nondirs);
768		1139
769	my $statgrp = add $grp aio_group sub {	1140	my $statgrp = add $grp aio_group sub {
770	$grp->result (\@dirs, \@nondirs);	1141	$grp->result (\@dirs, \@nondirs);
771	};	1142	};
772		1143
773	limit $statgrp $maxreq;	1144	limit $statgrp $maxreq;
774	feed $statgrp sub {	1145	feed $statgrp sub {
775	return unless @$entries;	1146	return unless @$entries;
776	my $entry = pop @$entries;	1147	my $entry = shift @$entries;
777		1148
778	aioreq_pri $pri;	1149	aioreq_pri $pri;
		1150	$wd->[1] = "$entry/.";
779	add $statgrp aio_stat "$path/$entry/.", sub {	1151	add $statgrp aio_stat $wd, sub {
780	if ($_[0] < 0) {	1152	if ($_[0] < 0) {
781	push @nondirs, $entry;	1153	push @nondirs, $entry;
782	} else {	1154	} else {
783	# need to check for real directory	1155	# need to check for real directory
784	aioreq_pri $pri;	1156	aioreq_pri $pri;
		1157	$wd->[1] = $entry;
785	add $statgrp aio_lstat "$path/$entry", sub {	1158	add $statgrp aio_lstat $wd, sub {
786	if (-d _) {	1159	if (-d _) {
787	push @dirs, $entry;	1160	push @dirs, $entry;
788		1161
789	unless (--$ndirs) {	1162	unless (--$ndirs) {
790	push @nondirs, @$entries;	1163	push @nondirs, @$entries;
…		…
798	};	1171	};
799	};	1172	};
800	};	1173	};
801	};	1174	};
802	};	1175	};
803
804	$grp
805	}	1176	};
		1177
		1178	$grp
806	}	1179	}
807		1180
808	=item aio_rmtree $path, $callback->($status)	1181	=item aio_rmtree $pathname, $callback->($status)
809		1182
810	Delete a directory tree starting (and including) C<$path>, return the	1183	Delete a directory tree starting (and including) C<$path>, return the
811	status of the final C<rmdir> only. This is a composite request that	1184	status of the final C<rmdir> only. This is a composite request that
812	uses C<aio_scandir> to recurse into and rmdir directories, and unlink	1185	uses C<aio_scandir> to recurse into and rmdir directories, and unlink
813	everything else.	1186	everything else.
814		1187
815	=cut	1188	=cut
816		1189
817	sub aio_rmtree;	1190	sub aio_rmtree;
818	sub aio_rmtree($;$) {	1191	sub aio_rmtree($;$) {
819	aio_block {
820	my ($path, $cb) = @_;	1192	my ($path, $cb) = @_;
821		1193
822	my $pri = aioreq_pri;	1194	my $pri = aioreq_pri;
823	my $grp = aio_group $cb;	1195	my $grp = aio_group $cb;
824		1196
825	aioreq_pri $pri;	1197	aioreq_pri $pri;
826	add $grp aio_scandir $path, 0, sub {	1198	add $grp aio_scandir $path, 0, sub {
827	my ($dirs, $nondirs) = @_;	1199	my ($dirs, $nondirs) = @_;
828		1200
829	my $dirgrp = aio_group sub {	1201	my $dirgrp = aio_group sub {
830	add $grp aio_rmdir $path, sub {	1202	add $grp aio_rmdir $path, sub {
831	$grp->result ($_[0]);	1203	$grp->result ($_[0]);
832	};
833	};	1204	};
834
835	(aioreq_pri $pri), add $dirgrp aio_rmtree "$path/$_" for @$dirs;
836	(aioreq_pri $pri), add $dirgrp aio_unlink "$path/$_" for @$nondirs;
837
838	add $grp $dirgrp;
839	};	1205	};
840		1206
841	$grp	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;
842	}	1211	};
		1212
		1213	$grp
843	}	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.
844		1263
845	=item aio_fsync $fh, $callback->($status)	1264	=item aio_fsync $fh, $callback->($status)
846		1265
847	Asynchronously call fsync on the given filehandle and call the callback	1266	Asynchronously call fsync on the given filehandle and call the callback
848	with the fsync result code.	1267	with the fsync result code.
…		…
852	Asynchronously call fdatasync on the given filehandle and call the	1271	Asynchronously call fdatasync on the given filehandle and call the
853	callback with the fdatasync result code.	1272	callback with the fdatasync result code.
854		1273
855	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
856	detected, it will be emulated by calling C<fsync> instead.	1275	detected, it will be emulated by calling C<fsync> instead.
		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>.
857		1448
858	=item aio_group $callback->(...)	1449	=item aio_group $callback->(...)
859		1450
860	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
861	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
…		…
899	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
900	except to put your application under artificial I/O pressure.	1491	except to put your application under artificial I/O pressure.
901		1492
902	=back	1493	=back
903		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
904	=head2 IO::AIO::REQ CLASS	1620	=head2 IO::AIO::REQ CLASS
905		1621
906	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
907	called in non-void context.	1623	called in non-void context.
908		1624
…		…
911	=item cancel $req	1627	=item cancel $req
912		1628
913	Cancels the request, if possible. Has the effect of skipping execution	1629	Cancels the request, if possible. Has the effect of skipping execution
914	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
915	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
916	untouched. That means that requests that currently execute will not be	1632	untouched (with the exception of readdir). That means that requests that
917	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.
918		1635
919	=item cb $req $callback->(...)	1636	=item cb $req $callback->(...)
920		1637
921	Replace (or simply set) the callback registered to the request.	1638	Replace (or simply set) the callback registered to the request.
922		1639
…		…
973	Their lifetime, simplified, looks like this: when they are empty, they	1690	Their lifetime, simplified, looks like this: when they are empty, they
974	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
975	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
976	exist.	1693	exist.
977		1694
978	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
979	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
980	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
981	itself finish.	1698	further requests to the group. And only when all those requests have
		1699	finished will the the group itself finish.
982		1700
983	=over 4	1701	=over 4
984		1702
985	=item add $grp ...	1703	=item add $grp ...
986		1704
…		…
995	=item $grp->cancel_subs	1713	=item $grp->cancel_subs
996		1714
997	Cancel all subrequests and clears any feeder, but not the group request	1715	Cancel all subrequests and clears any feeder, but not the group request
998	itself. Useful when you queued a lot of events but got a result early.	1716	itself. Useful when you queued a lot of events but got a result early.
999		1717
		1718	The group request will finish normally (you cannot add requests to the
		1719	group).
		1720
1000	=item $grp->result (...)	1721	=item $grp->result (...)
1001		1722
1002	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
1003	subrequests have finished and set thre groups errno to the current value	1724	subrequests have finished and set the groups errno to the current value
1004	of errno (just like calling C<errno> without an error number). By default,	1725	of errno (just like calling C<errno> without an error number). By default,
1005	no argument will be passed and errno is zero.	1726	no argument will be passed and errno is zero.
1006		1727
1007	=item $grp->errno ([$errno])	1728	=item $grp->errno ([$errno])
1008		1729
…		…
1019	=item feed $grp $callback->($grp)	1740	=item feed $grp $callback->($grp)
1020		1741
1021	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
1022	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,
1023	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,
1024	this might starve other requests for a potentially long time. For	1745	this might starve other requests for a potentially long time. For example,
1025	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>
1026	requests, delaying any later requests for a long time.	1747	requests, delaying any later requests for a long time.
1027		1748
1028	To avoid this, and allow incremental generation of requests, you can	1749	To avoid this, and allow incremental generation of requests, you can
1029	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
1030	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>,
…		…
1035	not impose any limits).	1756	not impose any limits).
1036		1757
1037	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
1038	automatically removed from the group.	1759	automatically removed from the group.
1039		1760
1040	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.
1041		1763
1042	Example:	1764	Example:
1043		1765
1044	# 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:
1045		1767
…		…
1057	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
1058	the group contains less than this many requests.	1780	the group contains less than this many requests.
1059		1781
1060	Setting the limit to C<0> will pause the feeding process.	1782	Setting the limit to C<0> will pause the feeding process.
1061		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
1062	=back	1787	=back
1063		1788
		1789
1064	=head2 SUPPORT FUNCTIONS	1790	=head2 SUPPORT FUNCTIONS
1065		1791
1066	=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION	1792	=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION
1067		1793
1068	=over 4	1794	=over 4
1069		1795
1070	=item $fileno = IO::AIO::poll_fileno	1796	=item $fileno = IO::AIO::poll_fileno
1071		1797
1072	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
1073	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,
1074	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
1075	to call C<poll_cb> to check the results.	1801	you have to call C<poll_cb> to check the results.
1076		1802
1077	See C<poll_cb> for an example.	1803	See C<poll_cb> for an example.
1078		1804
1079	=item IO::AIO::poll_cb	1805	=item IO::AIO::poll_cb
1080		1806
1081	Process some 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
1082	regularly. Returns the number of events processed. Returns immediately	1808	been executed but the results are not yet reported). You have to call
1083	when no events are outstanding. The amount of events processed depends on	1809	this "regularly" to finish outstanding requests.
1084	the settings of C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>.
1085		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
1086	If not all requests were processed for whatever reason, the filehandle	1817	If not all requests were processed for whatever reason, the poll file
1087	will still be ready when C<poll_cb> returns.	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.
1088		1827
1089	Example: Install an Event watcher that automatically calls	1828	Example: Install an Event watcher that automatically calls
1090	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):
1091		1831
1092	Event->io (fd => IO::AIO::poll_fileno,	1832	Event->io (fd => IO::AIO::poll_fileno,
1093	poll => 'r', async => 1,	1833	poll => 'r', async => 1,
1094	cb => \&IO::AIO::poll_cb);	1834	cb => \&IO::AIO::poll_cb);
		1835
		1836	=item IO::AIO::poll_wait
		1837
		1838	Wait until either at least one request is in the result phase or no
		1839	requests are outstanding anymore.
		1840
		1841	This is useful if you want to synchronously wait for some requests to
		1842	become ready, without actually handling them.
		1843
		1844	See C<nreqs> for an example.
		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
		1855	=item IO::AIO::flush
		1856
		1857	Wait till all outstanding AIO requests have been handled.
		1858
		1859	Strictly equivalent to:
		1860
		1861	IO::AIO::poll_wait, IO::AIO::poll_cb
		1862	while IO::AIO::nreqs;
		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) = @_ };
		1871	IO::AIO::flush;
		1872	# $dirs, $nondirs are now set
1095		1873
1096	=item IO::AIO::max_poll_reqs $nreqs	1874	=item IO::AIO::max_poll_reqs $nreqs
1097		1875
1098	=item IO::AIO::max_poll_time $seconds	1876	=item IO::AIO::max_poll_time $seconds
1099		1877
…		…
1124	# use a low priority so other tasks have priority	1902	# use a low priority so other tasks have priority
1125	Event->io (fd => IO::AIO::poll_fileno,	1903	Event->io (fd => IO::AIO::poll_fileno,
1126	poll => 'r', nice => 1,	1904	poll => 'r', nice => 1,
1127	cb => &IO::AIO::poll_cb);	1905	cb => &IO::AIO::poll_cb);
1128		1906
1129	=item IO::AIO::poll_wait
1130
1131	If there are any outstanding requests and none of them in the result
1132	phase, wait till the result filehandle becomes ready for reading (simply
1133	does a C<select> on the filehandle. This is useful if you want to
1134	synchronously wait for some requests to finish).
1135
1136	See C<nreqs> for an example.
1137
1138	=item IO::AIO::poll
1139
1140	Waits until some requests have been handled.
1141
1142	Returns the number of requests processed, but is otherwise strictly
1143	equivalent to:
1144
1145	IO::AIO::poll_wait, IO::AIO::poll_cb
1146
1147	=item IO::AIO::flush
1148
1149	Wait till all outstanding AIO requests have been handled.
1150
1151	Strictly equivalent to:
1152
1153	IO::AIO::poll_wait, IO::AIO::poll_cb
1154	while IO::AIO::nreqs;
1155
1156	=back	1907	=back
		1908
1157		1909
1158	=head3 CONTROLLING THE NUMBER OF THREADS	1910	=head3 CONTROLLING THE NUMBER OF THREADS
1159		1911
1160	=over	1912	=over
1161		1913
…		…
1193		1945
1194	Under normal circumstances you don't need to call this function.	1946	Under normal circumstances you don't need to call this function.
1195		1947
1196	=item IO::AIO::max_idle $nthreads	1948	=item IO::AIO::max_idle $nthreads
1197		1949
1198	Limit the number of threads (default: 4) that are allowed to idle (i.e.,	1950	Limit the number of threads (default: 4) that are allowed to idle
1199	threads that did not get a request to process within 10 seconds). That	1951	(i.e., threads that did not get a request to process within the idle
1200	means if a thread becomes idle while C<$nthreads> other threads are also	1952	timeout (default: 10 seconds). That means if a thread becomes idle while
1201	idle, it will free its resources and exit.	1953	C<$nthreads> other threads are also idle, it will free its resources and
		1954	exit.
1202		1955
1203	This is useful when you allow a large number of threads (e.g. 100 or 1000)	1956	This is useful when you allow a large number of threads (e.g. 100 or 1000)
1204	to allow for extremely high load situations, but want to free resources	1957	to allow for extremely high load situations, but want to free resources
1205	under normal circumstances (1000 threads can easily consume 30MB of RAM).	1958	under normal circumstances (1000 threads can easily consume 30MB of RAM).
1206		1959
1207	The default is probably ok in most situations, especially if thread	1960	The default is probably ok in most situations, especially if thread
1208	creation is fast. If thread creation is very slow on your system you might	1961	creation is fast. If thread creation is very slow on your system you might
1209	want to use larger values.	1962	want to use larger values.
1210		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
1211	=item $oldmaxreqs = IO::AIO::max_outstanding $maxreqs	1969	=item IO::AIO::max_outstanding $maxreqs
		1970
		1971	Sets the maximum number of outstanding requests to C<$nreqs>. If
		1972	you do queue up more than this number of requests, the next call to
		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.
		1976
		1977	In other words, this setting does not enforce a queue limit, but can be
		1978	used to make poll functions block if the limit is exceeded.
1212		1979
1213	This is a very bad function to use in interactive programs because it	1980	This is a very bad function to use in interactive programs because it
1214	blocks, and a bad way to reduce concurrency because it is inexact: Better	1981	blocks, and a bad way to reduce concurrency because it is inexact: Better
1215	use an C<aio_group> together with a feed callback.	1982	use an C<aio_group> together with a feed callback.
1216		1983
1217	Sets the maximum number of outstanding requests to C<$nreqs>. If you	1984	Its main use is in scripts without an event loop - when you want to stat
1218	do queue up more than this number of requests, the next call to the	1985	a lot of files, you can write something like this:
1219	C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>)
1220	function will block until the limit is no longer exceeded.
1221		1986
1222	The default value is very large, so there is no practical limit on the	1987	IO::AIO::max_outstanding 32;
1223	number of outstanding requests.
1224		1988
1225	You can still queue as many requests as you want. Therefore,	1989	for my $path (...) {
1226	C<max_oustsanding> is mainly useful in simple scripts (with low values) or	1990	aio_stat $path , ...;
1227	as a stop gap to shield against fatal memory overflow (with large values).	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.
1228		2003
1229	=back	2004	=back
		2005
1230		2006
1231	=head3 STATISTICAL INFORMATION	2007	=head3 STATISTICAL INFORMATION
1232		2008
1233	=over	2009	=over
1234		2010
…		…
1252	Returns the number of requests currently in the pending state (executed,	2028	Returns the number of requests currently in the pending state (executed,
1253	but not yet processed by poll_cb).	2029	but not yet processed by poll_cb).
1254		2030
1255	=back	2031	=back
1256		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 of the file. This is only available on
		2099	platforms which have this member in their C<struct stat> (most BSDs
		2100	at the time of this writing) and generally only to the root usert. If
		2101	unsupported, C<0> is returned, but this might change to C<undef> in a
		2102	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
1257	=cut	2446	=cut
1258		2447
1259	min_parallel 8;	2448	min_parallel 8;
1260		2449
1261	END { flush }	2450	END { flush }
1262		2451
1263	1;	2452	1;
1264		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
1265	=head2 FORK BEHAVIOUR	2485	=head2 FORK BEHAVIOUR
1266		2486
1267	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.
1268		2494
1269	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
1270	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
1271	the fork the parent simply leaves the quiescent state and continues	2497	using IO::AIO in the child is not.
1272	request/result processing, while the child frees the request/result queue
1273	(so that the requests started before the fork will only be handled in the
1274	parent). Threads will be started on demand until the limit set in the
1275	parent process has been reached again.
1276		2498
1277	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)
1278	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
1279	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>.
1280		2526
1281	=head2 MEMORY USAGE	2527	=head2 MEMORY USAGE
1282		2528
1283	Per-request usage:	2529	Per-request usage:
1284		2530
…		…
1297	temporary buffers, and each thread requires a stack and other data	2543	temporary buffers, and each thread requires a stack and other data
1298	structures (usually around 16k-128k, depending on the OS).	2544	structures (usually around 16k-128k, depending on the OS).
1299		2545
1300	=head1 KNOWN BUGS	2546	=head1 KNOWN BUGS
1301		2547
1302	Known bugs will be fixed in the next release.	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.
1303		2560
1304	=head1 SEE ALSO	2561	=head1 SEE ALSO
1305		2562
1306	L<Coro::AIO>.	2563	L<AnyEvent::AIO> for easy integration into event loops, L<Coro::AIO> for a
		2564	more natural syntax.
1307		2565
1308	=head1 AUTHOR	2566	=head1 AUTHOR
1309		2567
1310	Marc Lehmann <schmorp@schmorp.de>	2568	Marc Lehmann <schmorp@schmorp.de>
1311	http://home.schmorp.de/	2569	http://home.schmorp.de/

Diff Legend

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