ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/IO-AIO/AIO.pm

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.96 by root, Fri Dec 22 04:05:50 2006 UTC vs.
Revision 1.201 by root, Tue Jul 5 09:24:11 2011 UTC

…		…
4		4
5	=head1 SYNOPSIS	5	=head1 SYNOPSIS
6		6
7	use IO::AIO;	7	use IO::AIO;
8		8
9	aio_open "/etc/passwd", O_RDONLY, 0, sub {	9	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
10	my $fh = 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
…		…
62	etc.), but can also be used to easily do operations in parallel that are	42	etc.), but can also be used to easily do operations in parallel that are
63	normally done sequentially, e.g. stat'ing many files, which is much faster	43	normally done sequentially, e.g. stat'ing many files, which is much faster
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 example	47	While most of this works on all types of file descriptors (for
68	sockets), using these functions on file descriptors that support	48	example sockets), using these functions on file descriptors that
69	nonblocking operation (again, sockets, pipes etc.) is very inefficient or	49	support nonblocking operation (again, sockets, pipes etc.) is
70	might not work (aio_read fails on sockets/pipes/fifos). Use an event loop	50	very inefficient. Use an event loop for that (such as the L<EV>
71	for that (such as the L<Event|Event> module): IO::AIO will naturally fit	51	module): IO::AIO will naturally fit into such an event loop itself.
72	into such an event loop itself.
73		52
74	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
75	requests and signal their completion. You don't need thread support	54	requests and signal their completion. You don't need thread support
76	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
77	to perl. In the future, this module might make use of the native aio	56	to perl. In the future, this module might make use of the native aio
…		…
79	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
80	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
81	aio_write, so the remaining functionality would have to be implemented	60	aio_write, so the remaining functionality would have to be implemented
82	using threads anyway.	61	using threads anyway.
83		62
84	Although the module will work with in the presence of other (Perl-)	63	Although the module will work in the presence of other (Perl-) threads,
85	threads, it is currently not reentrant in any way, so use appropriate	64	it is currently not reentrant in any way, so use appropriate locking
86	locking yourself, always call C<poll_cb> from within the same thread, or	65	yourself, always call C<poll_cb> from within the same thread, or never
87	never call C<poll_cb> (or other C<aio_> functions) recursively.	66	call C<poll_cb> (or other C<aio_> functions) recursively.
88		67
89	=head2 EXAMPLE	68	=head2 EXAMPLE
90		69
91	This is a simple example that uses the Event module and loads	70	This is a simple example that uses the EV module and loads
92	F</etc/passwd> asynchronously:	71	F</etc/passwd> asynchronously:
93		72
94	use Fcntl;	73	use Fcntl;
95	use Event;	74	use EV;
96	use IO::AIO;	75	use IO::AIO;
97		76
98	# register the IO::AIO callback with Event	77	# register the IO::AIO callback with EV
99	Event->io (fd => IO::AIO::poll_fileno,	78	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
100	poll => 'r',
101	cb => \&IO::AIO::poll_cb);
102		79
103	# queue the request to open /etc/passwd	80	# queue the request to open /etc/passwd
104	aio_open "/etc/passwd", O_RDONLY, 0, sub {	81	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
105	my $fh = shift	82	my $fh = shift
106	or die "error while opening: $!";	83	or die "error while opening: $!";
107		84
108	# stat'ing filehandles is generally non-blocking	85	# stat'ing filehandles is generally non-blocking
109	my $size = -s $fh;	86	my $size = -s $fh;
…		…
118		95
119	# file contents now in $contents	96	# file contents now in $contents
120	print $contents;	97	print $contents;
121		98
122	# exit event loop and program	99	# exit event loop and program
123	Event::unloop;	100	EV::unloop;
124	};	101	};
125	};	102	};
126		103
127	# possibly queue up other requests, or open GUI windows,	104	# possibly queue up other requests, or open GUI windows,
128	# check for sockets etc. etc.	105	# check for sockets etc. etc.
129		106
130	# process events as long as there are some:	107	# process events as long as there are some:
131	Event::loop;	108	EV::loop;
132		109
133	=head1 REQUEST ANATOMY AND LIFETIME	110	=head1 REQUEST ANATOMY AND LIFETIME
134		111
135	Every C<aio_*> function creates a request. which is a C data structure not	112	Every C<aio_*> function creates a request. which is a C data structure not
136	directly visible to Perl.	113	directly visible to Perl.
…		…
184		161
185	=cut	162	=cut
186		163
187	package IO::AIO;	164	package IO::AIO;
188		165
189	no warnings;	166	use Carp ();
190	use strict 'vars';	167
		168	use common::sense;
191		169
192	use base 'Exporter';	170	use base 'Exporter';
193		171
194	BEGIN {	172	BEGIN {
195	our $VERSION = '2.21';	173	our $VERSION = '3.93';
196		174
197	our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat	175	our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close
198	aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink	176	aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx
199	aio_readlink aio_fsync aio_fdatasync aio_readahead aio_rename aio_link	177	aio_scandir aio_symlink aio_readlink aio_realpath aio_sync aio_fsync
200	aio_move aio_copy aio_group aio_nop aio_mknod);	178	aio_fdatasync aio_sync_file_range aio_pathsync aio_readahead
		179	aio_rename aio_link aio_move aio_copy aio_group
		180	aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown
		181	aio_chmod aio_utime aio_truncate
		182	aio_msync aio_mtouch aio_mlock aio_mlockall
		183	aio_statvfs);
		184
201	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice aio_block));	185	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice));
202	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush	186	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush
203	min_parallel max_parallel max_idle	187	min_parallel max_parallel max_idle idle_timeout
204	nreqs nready npending nthreads	188	nreqs nready npending nthreads
205	max_poll_time max_poll_reqs);	189	max_poll_time max_poll_reqs
		190	sendfile fadvise madvise
		191	mmap munmap munlock munlockall);
		192
		193	push @AIO_REQ, qw(aio_busy); # not exported
206		194
207	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';	195	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';
208		196
209	require XSLoader;	197	require XSLoader;
210	XSLoader::load ("IO::AIO", $VERSION);	198	XSLoader::load ("IO::AIO", $VERSION);
211	}	199	}
212		200
213	=head1 FUNCTIONS	201	=head1 FUNCTIONS
		202
		203	=head2 QUICK OVERVIEW
		204
		205	This section simply lists the prototypes of the most important functions
		206	for quick reference. See the following sections for function-by-function
		207	documentation.
		208
		209	aio_open $pathname, $flags, $mode, $callback->($fh)
		210	aio_close $fh, $callback->($status)
		211	aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
		212	aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
		213	aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
		214	aio_readahead $fh,$offset,$length, $callback->($retval)
		215	aio_stat $fh_or_path, $callback->($status)
		216	aio_lstat $fh, $callback->($status)
		217	aio_statvfs $fh_or_path, $callback->($statvfs)
		218	aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
		219	aio_chown $fh_or_path, $uid, $gid, $callback->($status)
		220	aio_truncate $fh_or_path, $offset, $callback->($status)
		221	aio_chmod $fh_or_path, $mode, $callback->($status)
		222	aio_unlink $pathname, $callback->($status)
		223	aio_mknod $path, $mode, $dev, $callback->($status)
		224	aio_link $srcpath, $dstpath, $callback->($status)
		225	aio_symlink $srcpath, $dstpath, $callback->($status)
		226	aio_readlink $path, $callback->($link)
		227	aio_realpath $path, $callback->($link)
		228	aio_rename $srcpath, $dstpath, $callback->($status)
		229	aio_mkdir $pathname, $mode, $callback->($status)
		230	aio_rmdir $pathname, $callback->($status)
		231	aio_readdir $pathname, $callback->($entries)
		232	aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		233	IO::AIO::READDIR_DENTS IO::AIO::READDIR_DIRS_FIRST
		234	IO::AIO::READDIR_STAT_ORDER IO::AIO::READDIR_FOUND_UNKNOWN
		235	aio_load $path, $data, $callback->($status)
		236	aio_copy $srcpath, $dstpath, $callback->($status)
		237	aio_move $srcpath, $dstpath, $callback->($status)
		238	aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
		239	aio_rmtree $path, $callback->($status)
		240	aio_sync $callback->($status)
		241	aio_fsync $fh, $callback->($status)
		242	aio_fdatasync $fh, $callback->($status)
		243	aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		244	aio_pathsync $path, $callback->($status)
		245	aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		246	aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		247	aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
		248	aio_mlockall $flags, $callback->($status)
		249	aio_group $callback->(...)
		250	aio_nop $callback->()
		251
		252	$prev_pri = aioreq_pri [$pri]
		253	aioreq_nice $pri_adjust
		254
		255	IO::AIO::poll_wait
		256	IO::AIO::poll_cb
		257	IO::AIO::poll
		258	IO::AIO::flush
		259	IO::AIO::max_poll_reqs $nreqs
		260	IO::AIO::max_poll_time $seconds
		261	IO::AIO::min_parallel $nthreads
		262	IO::AIO::max_parallel $nthreads
		263	IO::AIO::max_idle $nthreads
		264	IO::AIO::idle_timeout $seconds
		265	IO::AIO::max_outstanding $maxreqs
		266	IO::AIO::nreqs
		267	IO::AIO::nready
		268	IO::AIO::npending
		269
		270	IO::AIO::sendfile $ofh, $ifh, $offset, $count
		271	IO::AIO::fadvise $fh, $offset, $len, $advice
		272	IO::AIO::madvise $scalar, $offset, $length, $advice
		273	IO::AIO::mprotect $scalar, $offset, $length, $protect
		274	IO::AIO::munlock $scalar, $offset = 0, $length = undef
		275	IO::AIO::munlockall
214		276
215	=head2 AIO REQUEST FUNCTIONS	277	=head2 AIO REQUEST FUNCTIONS
216		278
217	All the C<aio_*> calls are more or less thin wrappers around the syscall	279	All the C<aio_*> calls are more or less thin wrappers around the syscall
218	with the same name (sans C<aio_>). The arguments are similar or identical,	280	with the same name (sans C<aio_>). The arguments are similar or identical,
219	and they all accept an additional (and optional) C<$callback> argument	281	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	282	which must be a code reference. This code reference will get called with
221	the syscall return code (e.g. most syscalls return C<-1> on error, unlike	283	the syscall return code (e.g. most syscalls return C<-1> on error, unlike
222	perl, which usually delivers "false") as it's sole argument when the given	284	perl, which usually delivers "false") as its sole argument after the given
223	syscall has been executed asynchronously.	285	syscall has been executed asynchronously.
224		286
225	All functions expecting a filehandle keep a copy of the filehandle	287	All functions expecting a filehandle keep a copy of the filehandle
226	internally until the request has finished.	288	internally until the request has finished.
227		289
…		…
241	your pathnames to the locale (or other) encoding in effect in the user	303	your pathnames to the locale (or other) encoding in effect in the user
242	environment, d) use Glib::filename_from_unicode on unicode filenames or e)	304	environment, d) use Glib::filename_from_unicode on unicode filenames or e)
243	use something else to ensure your scalar has the correct contents.	305	use something else to ensure your scalar has the correct contents.
244		306
245	This works, btw. independent of the internal UTF-8 bit, which IO::AIO	307	This works, btw. independent of the internal UTF-8 bit, which IO::AIO
246	handles correctly wether it is set or not.	308	handles correctly whether it is set or not.
247		309
248	=over 4	310	=over 4
249		311
250	=item $prev_pri = aioreq_pri [$pri]	312	=item $prev_pri = aioreq_pri [$pri]
251		313
…		…
271	aio_read $_[0], ..., sub {	333	aio_read $_[0], ..., sub {
272	...	334	...
273	};	335	};
274	};	336	};
275		337
		338
276	=item aioreq_nice $pri_adjust	339	=item aioreq_nice $pri_adjust
277		340
278	Similar to C<aioreq_pri>, but subtracts the given value from the current	341	Similar to C<aioreq_pri>, but subtracts the given value from the current
279	priority, so the effect is cumulative.	342	priority, so the effect is cumulative.
		343
280		344
281	=item aio_open $pathname, $flags, $mode, $callback->($fh)	345	=item aio_open $pathname, $flags, $mode, $callback->($fh)
282		346
283	Asynchronously open or create a file and call the callback with a newly	347	Asynchronously open or create a file and call the callback with a newly
284	created filehandle for the file.	348	created filehandle for the file.
…		…
290	list. They are the same as used by C<sysopen>.	354	list. They are the same as used by C<sysopen>.
291		355
292	Likewise, C<$mode> specifies the mode of the newly created file, if it	356	Likewise, C<$mode> specifies the mode of the newly created file, if it
293	didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,	357	didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,
294	except that it is mandatory (i.e. use C<0> if you don't create new files,	358	except that it is mandatory (i.e. use C<0> if you don't create new files,
295	and C<0666> or C<0777> if you do).	359	and C<0666> or C<0777> if you do). Note that the C<$mode> will be modified
		360	by the umask in effect then the request is being executed, so better never
		361	change the umask.
296		362
297	Example:	363	Example:
298		364
299	aio_open "/etc/passwd", O_RDONLY, 0, sub {	365	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
300	if ($_[0]) {	366	if ($_[0]) {
301	print "open successful, fh is $_[0]\n";	367	print "open successful, fh is $_[0]\n";
302	...	368	...
303	} else {	369	} else {
304	die "open failed: $!\n";	370	die "open failed: $!\n";
305	}	371	}
306	};	372	};
307		373
		374	In addition to all the common open modes/flags (C<O_RDONLY>, C<O_WRONLY>,
		375	C<O_RDWR>, C<O_CREAT>, C<O_TRUNC>, C<O_EXCL> and C<O_APPEND>), the
		376	following POSIX and non-POSIX constants are available (missing ones on
		377	your system are, as usual, C<0>):
		378
		379	C<O_ASYNC>, C<O_DIRECT>, C<O_NOATIME>, C<O_CLOEXEC>, C<O_NOCTTY>, C<O_NOFOLLOW>,
		380	C<O_NONBLOCK>, C<O_EXEC>, C<O_SEARCH>, C<O_DIRECTORY>, C<O_DSYNC>,
		381	C<O_RSYNC>, C<O_SYNC> and C<O_TTY_INIT>.
		382
		383
308	=item aio_close $fh, $callback->($status)	384	=item aio_close $fh, $callback->($status)
309		385
310	Asynchronously close a file and call the callback with the result	386	Asynchronously close a file and call the callback with the result
311	code. I<WARNING:> although accepted, you should not pass in a perl	387	code.
312	filehandle here, as perl will likely close the file descriptor another
313	time when the filehandle is destroyed. Normally, you can safely call perls
314	C<close> or just let filehandles go out of scope.
315		388
316	This is supposed to be a bug in the API, so that might change. It's	389	Unfortunately, you can't do this to perl. Perl I<insists> very strongly on
317	therefore best to avoid this function.	390	closing the file descriptor associated with the filehandle itself.
		391
		392	Therefore, C<aio_close> will not close the filehandle - instead it will
		393	use dup2 to overwrite the file descriptor with the write-end of a pipe
		394	(the pipe fd will be created on demand and will be cached).
		395
		396	Or in other words: the file descriptor will be closed, but it will not be
		397	free for reuse until the perl filehandle is closed.
		398
		399	=cut
318		400
319	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	401	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
320		402
321	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	403	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
322		404
323	Reads or writes C<length> bytes from the specified C<fh> and C<offset>	405	Reads or writes C<$length> bytes from or to the specified C<$fh> and
324	into the scalar given by C<data> and offset C<dataoffset> and calls the	406	C<$offset> into the scalar given by C<$data> and offset C<$dataoffset>
325	callback without the actual number of bytes read (or -1 on error, just	407	and calls the callback without the actual number of bytes read (or -1 on
326	like the syscall).	408	error, just like the syscall).
		409
		410	C<aio_read> will, like C<sysread>, shrink or grow the C<$data> scalar to
		411	offset plus the actual number of bytes read.
		412
		413	If C<$offset> is undefined, then the current file descriptor offset will
		414	be used (and updated), otherwise the file descriptor offset will not be
		415	changed by these calls.
		416
		417	If C<$length> is undefined in C<aio_write>, use the remaining length of
		418	C<$data>.
		419
		420	If C<$dataoffset> is less than zero, it will be counted from the end of
		421	C<$data>.
327		422
328	The C<$data> scalar I<MUST NOT> be modified in any way while the request	423	The C<$data> scalar I<MUST NOT> be modified in any way while the request
329	is outstanding. Modifying it can result in segfaults or WW3 (if the	424	is outstanding. Modifying it can result in segfaults or World War III (if
330	necessary/optional hardware is installed).	425	the necessary/optional hardware is installed).
331		426
332	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at	427	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at
333	offset C<0> within the scalar:	428	offset C<0> within the scalar:
334		429
335	aio_read $fh, 7, 15, $buffer, 0, sub {	430	aio_read $fh, 7, 15, $buffer, 0, sub {
336	$_[0] > 0 or die "read error: $!";	431	$_[0] > 0 or die "read error: $!";
337	print "read $_[0] bytes: <$buffer>\n";	432	print "read $_[0] bytes: <$buffer>\n";
338	};	433	};
339		434
		435
340	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)	436	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
341		437
342	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts	438	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
343	reading at byte offset C<$in_offset>, and starts writing at the current	439	reading at byte offset C<$in_offset>, and starts writing at the current
344	file offset of C<$out_fh>. Because of that, it is not safe to issue more	440	file offset of C<$out_fh>. Because of that, it is not safe to issue more
345	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each	441	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each
346	other.	442	other. The same C<$in_fh> works fine though, as this function does not
		443	move or use the file offset of C<$in_fh>.
347		444
		445	Please note that C<aio_sendfile> can read more bytes from C<$in_fh> than
		446	are written, and there is no way to find out how many more bytes have been
		447	read from C<aio_sendfile> alone, as C<aio_sendfile> only provides the
		448	number of bytes written to C<$out_fh>. Only if the result value equals
		449	C<$length> one can assume that C<$length> bytes have been read.
		450
		451	Unlike with other C<aio_> functions, it makes a lot of sense to use
		452	C<aio_sendfile> on non-blocking sockets, as long as one end (typically
		453	the C<$in_fh>) is a file - the file I/O will then be asynchronous, while
		454	the socket I/O will be non-blocking. Note, however, that you can run
		455	into a trap where C<aio_sendfile> reads some data with readahead, then
		456	fails to write all data, and when the socket is ready the next time, the
		457	data in the cache is already lost, forcing C<aio_sendfile> to again hit
		458	the disk. Explicit C<aio_read> + C<aio_write> let's you better control
		459	resource usage.
		460
348	This call tries to make use of a native C<sendfile> syscall to provide	461	This call tries to make use of a native C<sendfile>-like syscall to
349	zero-copy operation. For this to work, C<$out_fh> should refer to a	462	provide zero-copy operation. For this to work, C<$out_fh> should refer to
350	socket, and C<$in_fh> should refer to mmap'able file.	463	a socket, and C<$in_fh> should refer to an mmap'able file.
351		464
352	If the native sendfile call fails or is not implemented, it will be	465	If a native sendfile cannot be found or it fails with C<ENOSYS>,
353	emulated, so you can call C<aio_sendfile> on any type of filehandle	466	C<EINVAL>, C<ENOTSUP>, C<EOPNOTSUPP>, C<EAFNOSUPPORT>, C<EPROTOTYPE> or
		467	C<ENOTSOCK>, it will be emulated, so you can call C<aio_sendfile> on any
354	regardless of the limitations of the operating system.	468	type of filehandle regardless of the limitations of the operating system.
355		469
356	Please note, however, that C<aio_sendfile> can read more bytes from	470	As native sendfile syscalls (as practically any non-POSIX interface hacked
357	C<$in_fh> than are written, and there is no way to find out how many	471	together in a hurry to improve benchmark numbers) tend to be rather buggy
358	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only	472	on many systems, this implementation tries to work around some known bugs
359	provides the number of bytes written to C<$out_fh>. Only if the result	473	in Linux and FreeBSD kernels (probably others, too), but that might fail,
360	value equals C<$length> one can assume that C<$length> bytes have been	474	so you really really should check the return value of C<aio_sendfile> -
361	read.	475	fewre bytes than expected might have been transferred.
		476
362		477
363	=item aio_readahead $fh,$offset,$length, $callback->($retval)	478	=item aio_readahead $fh,$offset,$length, $callback->($retval)
364		479
365	C<aio_readahead> populates the page cache with data from a file so that	480	C<aio_readahead> populates the page cache with data from a file so that
366	subsequent reads from that file will not block on disk I/O. The C<$offset>	481	subsequent reads from that file will not block on disk I/O. The C<$offset>
…		…
372	file. The current file offset of the file is left unchanged.	487	file. The current file offset of the file is left unchanged.
373		488
374	If that syscall doesn't exist (likely if your OS isn't Linux) it will be	489	If that syscall doesn't exist (likely if your OS isn't Linux) it will be
375	emulated by simply reading the data, which would have a similar effect.	490	emulated by simply reading the data, which would have a similar effect.
376		491
		492
377	=item aio_stat $fh_or_path, $callback->($status)	493	=item aio_stat $fh_or_path, $callback->($status)
378		494
379	=item aio_lstat $fh, $callback->($status)	495	=item aio_lstat $fh, $callback->($status)
380		496
381	Works like perl's C<stat> or C<lstat> in void context. The callback will	497	Works like perl's C<stat> or C<lstat> in void context. The callback will
…		…
386	for an explanation.	502	for an explanation.
387		503
388	Currently, the stats are always 64-bit-stats, i.e. instead of returning an	504	Currently, the stats are always 64-bit-stats, i.e. instead of returning an
389	error when stat'ing a large file, the results will be silently truncated	505	error when stat'ing a large file, the results will be silently truncated
390	unless perl itself is compiled with large file support.	506	unless perl itself is compiled with large file support.
		507
		508	To help interpret the mode and dev/rdev stat values, IO::AIO offers the
		509	following constants and functions (if not implemented, the constants will
		510	be C<0> and the functions will either C<croak> or fall back on traditional
		511	behaviour).
		512
		513	C<S_IFMT>, C<S_IFIFO>, C<S_IFCHR>, C<S_IFBLK>, C<S_IFLNK>, C<S_IFREG>,
		514	C<S_IFDIR>, C<S_IFWHT>, C<S_IFSOCK>, C<IO::AIO::major $dev_t>,
		515	C<IO::AIO::minor $dev_t>, C<IO::AIO::makedev $major, $minor>.
391		516
392	Example: Print the length of F</etc/passwd>:	517	Example: Print the length of F</etc/passwd>:
393		518
394	aio_stat "/etc/passwd", sub {	519	aio_stat "/etc/passwd", sub {
395	$_[0] and die "stat failed: $!";	520	$_[0] and die "stat failed: $!";
396	print "size is ", -s _, "\n";	521	print "size is ", -s _, "\n";
397	};	522	};
398		523
		524
		525	=item aio_statvfs $fh_or_path, $callback->($statvfs)
		526
		527	Works like the POSIX C<statvfs> or C<fstatvfs> syscalls, depending on
		528	whether a file handle or path was passed.
		529
		530	On success, the callback is passed a hash reference with the following
		531	members: C<bsize>, C<frsize>, C<blocks>, C<bfree>, C<bavail>, C<files>,
		532	C<ffree>, C<favail>, C<fsid>, C<flag> and C<namemax>. On failure, C<undef>
		533	is passed.
		534
		535	The following POSIX IO::AIO::ST_* constants are defined: C<ST_RDONLY> and
		536	C<ST_NOSUID>.
		537
		538	The following non-POSIX IO::AIO::ST_* flag masks are defined to
		539	their correct value when available, or to C<0> on systems that do
		540	not support them: C<ST_NODEV>, C<ST_NOEXEC>, C<ST_SYNCHRONOUS>,
		541	C<ST_MANDLOCK>, C<ST_WRITE>, C<ST_APPEND>, C<ST_IMMUTABLE>, C<ST_NOATIME>,
		542	C<ST_NODIRATIME> and C<ST_RELATIME>.
		543
		544	Example: stat C</wd> and dump out the data if successful.
		545
		546	aio_statvfs "/wd", sub {
		547	my $f = $_[0]
		548	or die "statvfs: $!";
		549
		550	use Data::Dumper;
		551	say Dumper $f;
		552	};
		553
		554	# result:
		555	{
		556	bsize => 1024,
		557	bfree => 4333064312,
		558	blocks => 10253828096,
		559	files => 2050765568,
		560	flag => 4096,
		561	favail => 2042092649,
		562	bavail => 4333064312,
		563	ffree => 2042092649,
		564	namemax => 255,
		565	frsize => 1024,
		566	fsid => 1810
		567	}
		568
		569
		570	=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
		571
		572	Works like perl's C<utime> function (including the special case of $atime
		573	and $mtime being undef). Fractional times are supported if the underlying
		574	syscalls support them.
		575
		576	When called with a pathname, uses utimes(2) if available, otherwise
		577	utime(2). If called on a file descriptor, uses futimes(2) if available,
		578	otherwise returns ENOSYS, so this is not portable.
		579
		580	Examples:
		581
		582	# set atime and mtime to current time (basically touch(1)):
		583	aio_utime "path", undef, undef;
		584	# set atime to current time and mtime to beginning of the epoch:
		585	aio_utime "path", time, undef; # undef==0
		586
		587
		588	=item aio_chown $fh_or_path, $uid, $gid, $callback->($status)
		589
		590	Works like perl's C<chown> function, except that C<undef> for either $uid
		591	or $gid is being interpreted as "do not change" (but -1 can also be used).
		592
		593	Examples:
		594
		595	# same as "chown root path" in the shell:
		596	aio_chown "path", 0, -1;
		597	# same as above:
		598	aio_chown "path", 0, undef;
		599
		600
		601	=item aio_truncate $fh_or_path, $offset, $callback->($status)
		602
		603	Works like truncate(2) or ftruncate(2).
		604
		605
		606	=item aio_chmod $fh_or_path, $mode, $callback->($status)
		607
		608	Works like perl's C<chmod> function.
		609
		610
399	=item aio_unlink $pathname, $callback->($status)	611	=item aio_unlink $pathname, $callback->($status)
400		612
401	Asynchronously unlink (delete) a file and call the callback with the	613	Asynchronously unlink (delete) a file and call the callback with the
402	result code.	614	result code.
403		615
		616
404	=item aio_mknod $path, $mode, $dev, $callback->($status)	617	=item aio_mknod $path, $mode, $dev, $callback->($status)
405		618
406	[EXPERIMENTAL]	619	[EXPERIMENTAL]
407		620
408	Asynchronously create a device node (or fifo). See mknod(2).	621	Asynchronously create a device node (or fifo). See mknod(2).
409		622
410	The only (POSIX-) portable way of calling this function is:	623	The only (POSIX-) portable way of calling this function is:
411		624
412	aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ...	625	aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ...
		626
		627	See C<aio_stat> for info about some potentially helpful extra constants
		628	and functions.
413		629
414	=item aio_link $srcpath, $dstpath, $callback->($status)	630	=item aio_link $srcpath, $dstpath, $callback->($status)
415		631
416	Asynchronously create a new link to the existing object at C<$srcpath> at	632	Asynchronously create a new link to the existing object at C<$srcpath> at
417	the path C<$dstpath> and call the callback with the result code.	633	the path C<$dstpath> and call the callback with the result code.
418		634
		635
419	=item aio_symlink $srcpath, $dstpath, $callback->($status)	636	=item aio_symlink $srcpath, $dstpath, $callback->($status)
420		637
421	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at	638	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at
422	the path C<$dstpath> and call the callback with the result code.	639	the path C<$dstpath> and call the callback with the result code.
		640
423		641
424	=item aio_readlink $path, $callback->($link)	642	=item aio_readlink $path, $callback->($link)
425		643
426	Asynchronously read the symlink specified by C<$path> and pass it to	644	Asynchronously read the symlink specified by C<$path> and pass it to
427	the callback. If an error occurs, nothing or undef gets passed to the	645	the callback. If an error occurs, nothing or undef gets passed to the
428	callback.	646	callback.
429		647
		648
		649	=item aio_realpath $path, $callback->($path)
		650
		651	Asynchronously make the path absolute and resolve any symlinks in
		652	C<$path>. The resulting path only consists of directories.
		653
		654	This request can be used to get the absolute path of the current working
		655	directory by passing it a path of F<.> (a single dot).
		656
		657
430	=item aio_rename $srcpath, $dstpath, $callback->($status)	658	=item aio_rename $srcpath, $dstpath, $callback->($status)
431		659
432	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as	660	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as
433	rename(2) and call the callback with the result code.	661	rename(2) and call the callback with the result code.
434		662
		663
		664	=item aio_mkdir $pathname, $mode, $callback->($status)
		665
		666	Asynchronously mkdir (create) a directory and call the callback with
		667	the result code. C<$mode> will be modified by the umask at the time the
		668	request is executed, so do not change your umask.
		669
		670
435	=item aio_rmdir $pathname, $callback->($status)	671	=item aio_rmdir $pathname, $callback->($status)
436		672
437	Asynchronously rmdir (delete) a directory and call the callback with the	673	Asynchronously rmdir (delete) a directory and call the callback with the
438	result code.	674	result code.
		675
439		676
440	=item aio_readdir $pathname, $callback->($entries)	677	=item aio_readdir $pathname, $callback->($entries)
441		678
442	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire	679	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
443	directory (i.e. opendir + readdir + closedir). The entries will not be	680	directory (i.e. opendir + readdir + closedir). The entries will not be
444	sorted, and will B<NOT> include the C<.> and C<..> entries.	681	sorted, and will B<NOT> include the C<.> and C<..> entries.
445		682
446	The callback a single argument which is either C<undef> or an array-ref	683	The callback is passed a single argument which is either C<undef> or an
447	with the filenames.	684	array-ref with the filenames.
		685
		686
		687	=item aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		688
		689	Quite similar to C<aio_readdir>, but the C<$flags> argument allows to tune
		690	behaviour and output format. In case of an error, C<$entries> will be
		691	C<undef>.
		692
		693	The flags are a combination of the following constants, ORed together (the
		694	flags will also be passed to the callback, possibly modified):
		695
		696	=over 4
		697
		698	=item IO::AIO::READDIR_DENTS
		699
		700	When this flag is off, then the callback gets an arrayref consisting of
		701	names only (as with C<aio_readdir>), otherwise it gets an arrayref with
		702	C<[$name, $type, $inode]> arrayrefs, each describing a single directory
		703	entry in more detail.
		704
		705	C<$name> is the name of the entry.
		706
		707	C<$type> is one of the C<IO::AIO::DT_xxx> constants:
		708
		709	C<IO::AIO::DT_UNKNOWN>, C<IO::AIO::DT_FIFO>, C<IO::AIO::DT_CHR>, C<IO::AIO::DT_DIR>,
		710	C<IO::AIO::DT_BLK>, C<IO::AIO::DT_REG>, C<IO::AIO::DT_LNK>, C<IO::AIO::DT_SOCK>,
		711	C<IO::AIO::DT_WHT>.
		712
		713	C<IO::AIO::DT_UNKNOWN> means just that: readdir does not know. If you need to
		714	know, you have to run stat yourself. Also, for speed reasons, the C<$type>
		715	scalars are read-only: you can not modify them.
		716
		717	C<$inode> is the inode number (which might not be exact on systems with 64
		718	bit inode numbers and 32 bit perls). This field has unspecified content on
		719	systems that do not deliver the inode information.
		720
		721	=item IO::AIO::READDIR_DIRS_FIRST
		722
		723	When this flag is set, then the names will be returned in an order where
		724	likely directories come first, in optimal stat order. This is useful when
		725	you need to quickly find directories, or you want to find all directories
		726	while avoiding to stat() each entry.
		727
		728	If the system returns type information in readdir, then this is used
		729	to find directories directly. Otherwise, likely directories are names
		730	beginning with ".", or otherwise names with no dots, of which names with
		731	short names are tried first.
		732
		733	=item IO::AIO::READDIR_STAT_ORDER
		734
		735	When this flag is set, then the names will be returned in an order
		736	suitable for stat()'ing each one. That is, when you plan to stat()
		737	all files in the given directory, then the returned order will likely
		738	be fastest.
		739
		740	If both this flag and C<IO::AIO::READDIR_DIRS_FIRST> are specified, then
		741	the likely dirs come first, resulting in a less optimal stat order.
		742
		743	=item IO::AIO::READDIR_FOUND_UNKNOWN
		744
		745	This flag should not be set when calling C<aio_readdirx>. Instead, it
		746	is being set by C<aio_readdirx>, when any of the C<$type>'s found were
		747	C<IO::AIO::DT_UNKNOWN>. The absense of this flag therefore indicates that all
		748	C<$type>'s are known, which can be used to speed up some algorithms.
		749
		750	=back
		751
		752
		753	=item aio_load $path, $data, $callback->($status)
		754
		755	This is a composite request that tries to fully load the given file into
		756	memory. Status is the same as with aio_read.
		757
		758	=cut
		759
		760	sub aio_load($$;$) {
		761	my ($path, undef, $cb) = @_;
		762	my $data = \$_[1];
		763
		764	my $pri = aioreq_pri;
		765	my $grp = aio_group $cb;
		766
		767	aioreq_pri $pri;
		768	add $grp aio_open $path, O_RDONLY, 0, sub {
		769	my $fh = shift
		770	or return $grp->result (-1);
		771
		772	aioreq_pri $pri;
		773	add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub {
		774	$grp->result ($_[0]);
		775	};
		776	};
		777
		778	$grp
		779	}
448		780
449	=item aio_copy $srcpath, $dstpath, $callback->($status)	781	=item aio_copy $srcpath, $dstpath, $callback->($status)
450		782
451	Try to copy the I<file> (directories not supported as either source or	783	Try to copy the I<file> (directories not supported as either source or
452	destination) from C<$srcpath> to C<$dstpath> and call the callback with	784	destination) from C<$srcpath> to C<$dstpath> and call the callback with
453	the C<0> (error) or C<-1> ok.	785	a status of C<0> (ok) or C<-1> (error, see C<$!>).
454		786
455	This is a composite request that it creates the destination file with	787	This is a composite request that creates the destination file with
456	mode 0200 and copies the contents of the source file into it using	788	mode 0200 and copies the contents of the source file into it using
457	C<aio_sendfile>, followed by restoring atime, mtime, access mode and	789	C<aio_sendfile>, followed by restoring atime, mtime, access mode and
458	uid/gid, in that order.	790	uid/gid, in that order.
459		791
460	If an error occurs, the partial destination file will be unlinked, if	792	If an error occurs, the partial destination file will be unlinked, if
…		…
462	errors are being ignored.	794	errors are being ignored.
463		795
464	=cut	796	=cut
465		797
466	sub aio_copy($$;$) {	798	sub aio_copy($$;$) {
467	aio_block {
468	my ($src, $dst, $cb) = @_;	799	my ($src, $dst, $cb) = @_;
469		800
470	my $pri = aioreq_pri;	801	my $pri = aioreq_pri;
471	my $grp = aio_group $cb;	802	my $grp = aio_group $cb;
472		803
473	aioreq_pri $pri;	804	aioreq_pri $pri;
474	add $grp aio_open $src, O_RDONLY, 0, sub {	805	add $grp aio_open $src, O_RDONLY, 0, sub {
475	if (my $src_fh = $_[0]) {	806	if (my $src_fh = $_[0]) {
476	my @stat = stat $src_fh;	807	my @stat = stat $src_fh; # hmm, might block over nfs?
477		808
478	aioreq_pri $pri;	809	aioreq_pri $pri;
479	add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {	810	add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {
480	if (my $dst_fh = $_[0]) {	811	if (my $dst_fh = $_[0]) {
481	aioreq_pri $pri;	812	aioreq_pri $pri;
482	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {	813	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
483	if ($_[0] == $stat[7]) {	814	if ($_[0] == $stat[7]) {
484	$grp->result (0);	815	$grp->result (0);
485	close $src_fh;	816	close $src_fh;
486		817
487	# those should not normally block. should. should.
488	utime $stat[8], $stat[9], $dst;
489	chmod $stat[2] & 07777, $dst_fh;
490	chown $stat[4], $stat[5], $dst_fh;
491	close $dst_fh;
492	} else {	818	my $ch = sub {
493	$grp->result (-1);
494	close $src_fh;
495	close $dst_fh;
496
497	aioreq $pri;	819	aioreq_pri $pri;
		820	add $grp aio_chmod $dst_fh, $stat[2] & 07777, sub {
		821	aioreq_pri $pri;
		822	add $grp aio_chown $dst_fh, $stat[4], $stat[5], sub {
		823	aioreq_pri $pri;
498	add $grp aio_unlink $dst;	824	add $grp aio_close $dst_fh;
		825	}
		826	};
499	}	827	};
		828
		829	aioreq_pri $pri;
		830	add $grp aio_utime $dst_fh, $stat[8], $stat[9], sub {
		831	if ($_[0] < 0 && $! == ENOSYS) {
		832	aioreq_pri $pri;
		833	add $grp aio_utime $dst, $stat[8], $stat[9], $ch;
		834	} else {
		835	$ch->();
		836	}
		837	};
		838	} else {
		839	$grp->result (-1);
		840	close $src_fh;
		841	close $dst_fh;
		842
		843	aioreq $pri;
		844	add $grp aio_unlink $dst;
500	};	845	}
501	} else {
502	$grp->result (-1);
503	}	846	};
		847	} else {
		848	$grp->result (-1);
504	},	849	}
505
506	} else {
507	$grp->result (-1);
508	}	850	},
		851
		852	} else {
		853	$grp->result (-1);
509	};	854	}
510
511	$grp
512	}	855	};
		856
		857	$grp
513	}	858	}
514		859
515	=item aio_move $srcpath, $dstpath, $callback->($status)	860	=item aio_move $srcpath, $dstpath, $callback->($status)
516		861
517	Try to move the I<file> (directories not supported as either source or	862	Try to move the I<file> (directories not supported as either source or
518	destination) from C<$srcpath> to C<$dstpath> and call the callback with	863	destination) from C<$srcpath> to C<$dstpath> and call the callback with
519	the C<0> (error) or C<-1> ok.	864	a status of C<0> (ok) or C<-1> (error, see C<$!>).
520		865
521	This is a composite request that tries to rename(2) the file first. If	866	This is a composite request that tries to rename(2) the file first; if
522	rename files with C<EXDEV>, it copies the file with C<aio_copy> and, if	867	rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if
523	that is successful, unlinking the C<$srcpath>.	868	that is successful, unlinks the C<$srcpath>.
524		869
525	=cut	870	=cut
526		871
527	sub aio_move($$;$) {	872	sub aio_move($$;$) {
528	aio_block {
529	my ($src, $dst, $cb) = @_;	873	my ($src, $dst, $cb) = @_;
530		874
531	my $pri = aioreq_pri;	875	my $pri = aioreq_pri;
532	my $grp = aio_group $cb;	876	my $grp = aio_group $cb;
533		877
534	aioreq_pri $pri;	878	aioreq_pri $pri;
535	add $grp aio_rename $src, $dst, sub {	879	add $grp aio_rename $src, $dst, sub {
536	if ($_[0] && $! == EXDEV) {	880	if ($_[0] && $! == EXDEV) {
537	aioreq_pri $pri;	881	aioreq_pri $pri;
538	add $grp aio_copy $src, $dst, sub {	882	add $grp aio_copy $src, $dst, sub {
539	$grp->result ($_[0]);
540
541	if (!$_[0]) {
542	aioreq_pri $pri;
543	add $grp aio_unlink $src;
544	}
545	};
546	} else {
547	$grp->result ($_[0]);	883	$grp->result ($_[0]);
		884
		885	unless ($_[0]) {
		886	aioreq_pri $pri;
		887	add $grp aio_unlink $src;
		888	}
548	}	889	};
		890	} else {
		891	$grp->result ($_[0]);
549	};	892	}
550
551	$grp
552	}	893	};
		894
		895	$grp
553	}	896	}
554		897
555	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)	898	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
556		899
557	Scans a directory (similar to C<aio_readdir>) but additionally tries to	900	Scans a directory (similar to C<aio_readdir>) but additionally tries to
…		…
577		920
578	Implementation notes.	921	Implementation notes.
579		922
580	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.	923	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.
581		924
		925	If readdir returns file type information, then this is used directly to
		926	find directories.
		927
582	After reading the directory, the modification time, size etc. of the	928	Otherwise, after reading the directory, the modification time, size etc.
583	directory before and after the readdir is checked, and if they match (and	929	of the directory before and after the readdir is checked, and if they
584	isn't the current time), the link count will be used to decide how many	930	match (and isn't the current time), the link count will be used to decide
585	entries are directories (if >= 2). Otherwise, no knowledge of the number	931	how many entries are directories (if >= 2). Otherwise, no knowledge of the
586	of subdirectories will be assumed.	932	number of subdirectories will be assumed.
587		933
588	Then entries will be sorted into likely directories (everything without	934	Then entries will be sorted into likely directories a non-initial dot
589	a non-initial dot currently) and likely non-directories (everything	935	currently) and likely non-directories (see C<aio_readdirx>). Then every
590	else). Then every entry plus an appended C</.> will be C<stat>'ed,	936	entry plus an appended C</.> will be C<stat>'ed, likely directories first,
591	likely directories first. If that succeeds, it assumes that the entry	937	in order of their inode numbers. If that succeeds, it assumes that the
592	is a directory or a symlink to directory (which will be checked	938	entry is a directory or a symlink to directory (which will be checked
593	seperately). This is often faster than stat'ing the entry itself because	939	seperately). This is often faster than stat'ing the entry itself because
594	filesystems might detect the type of the entry without reading the inode	940	filesystems might detect the type of the entry without reading the inode
595	data (e.g. ext2fs filetype feature).	941	data (e.g. ext2fs filetype feature), even on systems that cannot return
		942	the filetype information on readdir.
596		943
597	If the known number of directories (link count - 2) has been reached, the	944	If the known number of directories (link count - 2) has been reached, the
598	rest of the entries is assumed to be non-directories.	945	rest of the entries is assumed to be non-directories.
599		946
600	This only works with certainty on POSIX (= UNIX) filesystems, which	947	This only works with certainty on POSIX (= UNIX) filesystems, which
…		…
604	as those tend to return 0 or 1 as link counts, which disables the	951	as those tend to return 0 or 1 as link counts, which disables the
605	directory counting heuristic.	952	directory counting heuristic.
606		953
607	=cut	954	=cut
608		955
609	sub aio_scandir($$$) {	956	sub aio_scandir($$;$) {
610	aio_block {
611	my ($path, $maxreq, $cb) = @_;	957	my ($path, $maxreq, $cb) = @_;
612		958
613	my $pri = aioreq_pri;	959	my $pri = aioreq_pri;
614		960
615	my $grp = aio_group $cb;	961	my $grp = aio_group $cb;
616		962
617	$maxreq = 4 if $maxreq <= 0;	963	$maxreq = 4 if $maxreq <= 0;
618		964
619	# stat once	965	# stat once
		966	aioreq_pri $pri;
		967	add $grp aio_stat $path, sub {
		968	return $grp->result () if $_[0];
		969	my $now = time;
		970	my $hash1 = join ":", (stat _)[0,1,3,7,9];
		971
		972	# read the directory entries
620	aioreq_pri $pri;	973	aioreq_pri $pri;
621	add $grp aio_stat $path, sub {	974	add $grp aio_readdirx $path, READDIR_DIRS_FIRST, sub {
		975	my $entries = shift
622	return $grp->result () if $_[0];	976	or return $grp->result ();
623	my $now = time;
624	my $hash1 = join ":", (stat _)[0,1,3,7,9];
625		977
626	# read the directory entries	978	# stat the dir another time
627	aioreq_pri $pri;	979	aioreq_pri $pri;
628	add $grp aio_readdir $path, sub {
629	my $entries = shift
630	or return $grp->result ();
631
632	# stat the dir another time
633	aioreq_pri $pri;
634	add $grp aio_stat $path, sub {	980	add $grp aio_stat $path, sub {
635	my $hash2 = join ":", (stat _)[0,1,3,7,9];	981	my $hash2 = join ":", (stat _)[0,1,3,7,9];
636		982
637	my $ndirs;	983	my $ndirs;
638		984
639	# take the slow route if anything looks fishy	985	# take the slow route if anything looks fishy
640	if ($hash1 ne $hash2 or (stat _)[9] == $now) {	986	if ($hash1 ne $hash2 or (stat _)[9] == $now) {
641	$ndirs = -1;	987	$ndirs = -1;
642	} else {	988	} else {
643	# if nlink == 2, we are finished	989	# if nlink == 2, we are finished
644	# on non-posix-fs's, we rely on nlink < 2	990	# for non-posix-fs's, we rely on nlink < 2
645	$ndirs = (stat _)[3] - 2	991	$ndirs = (stat _)[3] - 2
646	or return $grp->result ([], $entries);	992	or return $grp->result ([], $entries);
647	}	993	}
648		994
649	# sort into likely dirs and likely nondirs
650	# dirs == files without ".", short entries first
651	$entries = [map $_->[0],
652	sort { $b->[1] cmp $a->[1] }
653	map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],
654	@$entries];
655
656	my (@dirs, @nondirs);	995	my (@dirs, @nondirs);
657		996
658	my $statgrp = add $grp aio_group sub {	997	my $statgrp = add $grp aio_group sub {
659	$grp->result (\@dirs, \@nondirs);	998	$grp->result (\@dirs, \@nondirs);
660	};	999	};
661		1000
662	limit $statgrp $maxreq;	1001	limit $statgrp $maxreq;
663	feed $statgrp sub {	1002	feed $statgrp sub {
664	return unless @$entries;	1003	return unless @$entries;
665	my $entry = pop @$entries;	1004	my $entry = shift @$entries;
666		1005
667	aioreq_pri $pri;	1006	aioreq_pri $pri;
668	add $statgrp aio_stat "$path/$entry/.", sub {	1007	add $statgrp aio_stat "$path/$entry/.", sub {
669	if ($_[0] < 0) {	1008	if ($_[0] < 0) {
670	push @nondirs, $entry;	1009	push @nondirs, $entry;
671	} else {	1010	} else {
672	# need to check for real directory	1011	# need to check for real directory
673	aioreq_pri $pri;	1012	aioreq_pri $pri;
674	add $statgrp aio_lstat "$path/$entry", sub {	1013	add $statgrp aio_lstat "$path/$entry", sub {
675	if (-d _) {	1014	if (-d _) {
676	push @dirs, $entry;	1015	push @dirs, $entry;
677		1016
678	unless (--$ndirs) {	1017	unless (--$ndirs) {
679	push @nondirs, @$entries;	1018	push @nondirs, @$entries;
680	feed $statgrp;	1019	feed $statgrp;
681	}
682	} else {
683	push @nondirs, $entry;
684	}	1020	}
		1021	} else {
		1022	push @nondirs, $entry;
685	}	1023	}
686	}	1024	}
687	};	1025	}
688	};	1026	};
689	};	1027	};
690	};	1028	};
691	};	1029	};
692
693	$grp
694	}	1030	};
		1031
		1032	$grp
695	}	1033	}
		1034
		1035	=item aio_rmtree $path, $callback->($status)
		1036
		1037	Delete a directory tree starting (and including) C<$path>, return the
		1038	status of the final C<rmdir> only. This is a composite request that
		1039	uses C<aio_scandir> to recurse into and rmdir directories, and unlink
		1040	everything else.
		1041
		1042	=cut
		1043
		1044	sub aio_rmtree;
		1045	sub aio_rmtree($;$) {
		1046	my ($path, $cb) = @_;
		1047
		1048	my $pri = aioreq_pri;
		1049	my $grp = aio_group $cb;
		1050
		1051	aioreq_pri $pri;
		1052	add $grp aio_scandir $path, 0, sub {
		1053	my ($dirs, $nondirs) = @_;
		1054
		1055	my $dirgrp = aio_group sub {
		1056	add $grp aio_rmdir $path, sub {
		1057	$grp->result ($_[0]);
		1058	};
		1059	};
		1060
		1061	(aioreq_pri $pri), add $dirgrp aio_rmtree "$path/$_" for @$dirs;
		1062	(aioreq_pri $pri), add $dirgrp aio_unlink "$path/$_" for @$nondirs;
		1063
		1064	add $grp $dirgrp;
		1065	};
		1066
		1067	$grp
		1068	}
		1069
		1070	=item aio_sync $callback->($status)
		1071
		1072	Asynchronously call sync and call the callback when finished.
696		1073
697	=item aio_fsync $fh, $callback->($status)	1074	=item aio_fsync $fh, $callback->($status)
698		1075
699	Asynchronously call fsync on the given filehandle and call the callback	1076	Asynchronously call fsync on the given filehandle and call the callback
700	with the fsync result code.	1077	with the fsync result code.
…		…
704	Asynchronously call fdatasync on the given filehandle and call the	1081	Asynchronously call fdatasync on the given filehandle and call the
705	callback with the fdatasync result code.	1082	callback with the fdatasync result code.
706		1083
707	If this call isn't available because your OS lacks it or it couldn't be	1084	If this call isn't available because your OS lacks it or it couldn't be
708	detected, it will be emulated by calling C<fsync> instead.	1085	detected, it will be emulated by calling C<fsync> instead.
		1086
		1087	=item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		1088
		1089	Sync the data portion of the file specified by C<$offset> and C<$length>
		1090	to disk (but NOT the metadata), by calling the Linux-specific
		1091	sync_file_range call. If sync_file_range is not available or it returns
		1092	ENOSYS, then fdatasync or fsync is being substituted.
		1093
		1094	C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>,
		1095	C<IO::AIO::SYNC_FILE_RANGE_WRITE> and
		1096	C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range
		1097	manpage for details.
		1098
		1099	=item aio_pathsync $path, $callback->($status)
		1100
		1101	This request tries to open, fsync and close the given path. This is a
		1102	composite request intended to sync directories after directory operations
		1103	(E.g. rename). This might not work on all operating systems or have any
		1104	specific effect, but usually it makes sure that directory changes get
		1105	written to disc. It works for anything that can be opened for read-only,
		1106	not just directories.
		1107
		1108	Future versions of this function might fall back to other methods when
		1109	C<fsync> on the directory fails (such as calling C<sync>).
		1110
		1111	Passes C<0> when everything went ok, and C<-1> on error.
		1112
		1113	=cut
		1114
		1115	sub aio_pathsync($;$) {
		1116	my ($path, $cb) = @_;
		1117
		1118	my $pri = aioreq_pri;
		1119	my $grp = aio_group $cb;
		1120
		1121	aioreq_pri $pri;
		1122	add $grp aio_open $path, O_RDONLY, 0, sub {
		1123	my ($fh) = @_;
		1124	if ($fh) {
		1125	aioreq_pri $pri;
		1126	add $grp aio_fsync $fh, sub {
		1127	$grp->result ($_[0]);
		1128
		1129	aioreq_pri $pri;
		1130	add $grp aio_close $fh;
		1131	};
		1132	} else {
		1133	$grp->result (-1);
		1134	}
		1135	};
		1136
		1137	$grp
		1138	}
		1139
		1140	=item aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		1141
		1142	This is a rather advanced IO::AIO call, which only works on mmap(2)ed
		1143	scalars (see the C<IO::AIO::mmap> function, although it also works on data
		1144	scalars managed by the L<Sys::Mmap> or L<Mmap> modules, note that the
		1145	scalar must only be modified in-place while an aio operation is pending on
		1146	it).
		1147
		1148	It calls the C<msync> function of your OS, if available, with the memory
		1149	area starting at C<$offset> in the string and ending C<$length> bytes
		1150	later. If C<$length> is negative, counts from the end, and if C<$length>
		1151	is C<undef>, then it goes till the end of the string. The flags can be
		1152	a combination of C<IO::AIO::MS_ASYNC>, C<IO::AIO::MS_INVALIDATE> and
		1153	C<IO::AIO::MS_SYNC>.
		1154
		1155	=item aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		1156
		1157	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1158	scalars.
		1159
		1160	It touches (reads or writes) all memory pages in the specified
		1161	range inside the scalar. All caveats and parameters are the same
		1162	as for C<aio_msync>, above, except for flags, which must be either
		1163	C<0> (which reads all pages and ensures they are instantiated) or
		1164	C<IO::AIO::MT_MODIFY>, which modifies the memory page s(by reading and
		1165	writing an octet from it, which dirties the page).
		1166
		1167	=item aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
		1168
		1169	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1170	scalars.
		1171
		1172	It reads in all the pages of the underlying storage into memory (if any)
		1173	and locks them, so they are not getting swapped/paged out or removed.
		1174
		1175	If C<$length> is undefined, then the scalar will be locked till the end.
		1176
		1177	On systems that do not implement C<mlock>, this function returns C<-1>
		1178	and sets errno to C<ENOSYS>.
		1179
		1180	Note that the corresponding C<munlock> is synchronous and is
		1181	documented under L<MISCELLANEOUS FUNCTIONS>.
		1182
		1183	Example: open a file, mmap and mlock it - both will be undone when
		1184	C<$data> gets destroyed.
		1185
		1186	open my $fh, "<", $path or die "$path: $!";
		1187	my $data;
		1188	IO::AIO::mmap $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh;
		1189	aio_mlock $data; # mlock in background
		1190
		1191	=item aio_mlockall $flags, $callback->($status)
		1192
		1193	Calls the C<mlockall> function with the given C<$flags> (a combination of
		1194	C<IO::AIO::MCL_CURRENT> and C<IO::AIO::MCL_FUTURE>).
		1195
		1196	On systems that do not implement C<mlockall>, this function returns C<-1>
		1197	and sets errno to C<ENOSYS>.
		1198
		1199	Note that the corresponding C<munlockall> is synchronous and is
		1200	documented under L<MISCELLANEOUS FUNCTIONS>.
		1201
		1202	Example: asynchronously lock all current and future pages into memory.
		1203
		1204	aio_mlockall IO::AIO::MCL_FUTURE;
709		1205
710	=item aio_group $callback->(...)	1206	=item aio_group $callback->(...)
711		1207
712	This is a very special aio request: Instead of doing something, it is a	1208	This is a very special aio request: Instead of doing something, it is a
713	container for other aio requests, which is useful if you want to bundle	1209	container for other aio requests, which is useful if you want to bundle
…		…
763	=item cancel $req	1259	=item cancel $req
764		1260
765	Cancels the request, if possible. Has the effect of skipping execution	1261	Cancels the request, if possible. Has the effect of skipping execution
766	when entering the B<execute> state and skipping calling the callback when	1262	when entering the B<execute> state and skipping calling the callback when
767	entering the the B<result> state, but will leave the request otherwise	1263	entering the the B<result> state, but will leave the request otherwise
768	untouched. That means that requests that currently execute will not be	1264	untouched (with the exception of readdir). That means that requests that
769	stopped and resources held by the request will not be freed prematurely.	1265	currently execute will not be stopped and resources held by the request
		1266	will not be freed prematurely.
770		1267
771	=item cb $req $callback->(...)	1268	=item cb $req $callback->(...)
772		1269
773	Replace (or simply set) the callback registered to the request.	1270	Replace (or simply set) the callback registered to the request.
774		1271
…		…
825	Their lifetime, simplified, looks like this: when they are empty, they	1322	Their lifetime, simplified, looks like this: when they are empty, they
826	will finish very quickly. If they contain only requests that are in the	1323	will finish very quickly. If they contain only requests that are in the
827	C<done> state, they will also finish. Otherwise they will continue to	1324	C<done> state, they will also finish. Otherwise they will continue to
828	exist.	1325	exist.
829		1326
830	That means after creating a group you have some time to add requests. And	1327	That means after creating a group you have some time to add requests
831	in the callbacks of those requests, you can add further requests to the	1328	(precisely before the callback has been invoked, which is only done within
832	group. And only when all those requests have finished will the the group	1329	the C<poll_cb>). And in the callbacks of those requests, you can add
833	itself finish.	1330	further requests to the group. And only when all those requests have
		1331	finished will the the group itself finish.
834		1332
835	=over 4	1333	=over 4
836		1334
837	=item add $grp ...	1335	=item add $grp ...
838		1336
…		…
847	=item $grp->cancel_subs	1345	=item $grp->cancel_subs
848		1346
849	Cancel all subrequests and clears any feeder, but not the group request	1347	Cancel all subrequests and clears any feeder, but not the group request
850	itself. Useful when you queued a lot of events but got a result early.	1348	itself. Useful when you queued a lot of events but got a result early.
851		1349
		1350	The group request will finish normally (you cannot add requests to the
		1351	group).
		1352
852	=item $grp->result (...)	1353	=item $grp->result (...)
853		1354
854	Set the result value(s) that will be passed to the group callback when all	1355	Set the result value(s) that will be passed to the group callback when all
855	subrequests have finished and set thre groups errno to the current value	1356	subrequests have finished and set the groups errno to the current value
856	of errno (just like calling C<errno> without an error number). By default,	1357	of errno (just like calling C<errno> without an error number). By default,
857	no argument will be passed and errno is zero.	1358	no argument will be passed and errno is zero.
858		1359
859	=item $grp->errno ([$errno])	1360	=item $grp->errno ([$errno])
860		1361
…		…
871	=item feed $grp $callback->($grp)	1372	=item feed $grp $callback->($grp)
872		1373
873	Sets a feeder/generator on this group: every group can have an attached	1374	Sets a feeder/generator on this group: every group can have an attached
874	generator that generates requests if idle. The idea behind this is that,	1375	generator that generates requests if idle. The idea behind this is that,
875	although you could just queue as many requests as you want in a group,	1376	although you could just queue as many requests as you want in a group,
876	this might starve other requests for a potentially long time. For	1377	this might starve other requests for a potentially long time. For example,
877	example, C<aio_scandir> might generate hundreds of thousands C<aio_stat>	1378	C<aio_scandir> might generate hundreds of thousands C<aio_stat> requests,
878	requests, delaying any later requests for a long time.	1379	delaying any later requests for a long time.
879		1380
880	To avoid this, and allow incremental generation of requests, you can	1381	To avoid this, and allow incremental generation of requests, you can
881	instead a group and set a feeder on it that generates those requests. The	1382	instead a group and set a feeder on it that generates those requests. The
882	feed callback will be called whenever there are few enough (see C<limit>,	1383	feed callback will be called whenever there are few enough (see C<limit>,
883	below) requests active in the group itself and is expected to queue more	1384	below) requests active in the group itself and is expected to queue more
…		…
887	not impose any limits).	1388	not impose any limits).
888		1389
889	If the feed does not queue more requests when called, it will be	1390	If the feed does not queue more requests when called, it will be
890	automatically removed from the group.	1391	automatically removed from the group.
891		1392
892	If the feed limit is C<0>, it will be set to C<2> automatically.	1393	If the feed limit is C<0> when this method is called, it will be set to
		1394	C<2> automatically.
893		1395
894	Example:	1396	Example:
895		1397
896	# stat all files in @files, but only ever use four aio requests concurrently:	1398	# stat all files in @files, but only ever use four aio requests concurrently:
897		1399
…		…
909	Sets the feeder limit for the group: The feeder will be called whenever	1411	Sets the feeder limit for the group: The feeder will be called whenever
910	the group contains less than this many requests.	1412	the group contains less than this many requests.
911		1413
912	Setting the limit to C<0> will pause the feeding process.	1414	Setting the limit to C<0> will pause the feeding process.
913		1415
		1416	The default value for the limit is C<0>, but note that setting a feeder
		1417	automatically bumps it up to C<2>.
		1418
914	=back	1419	=back
915		1420
916	=head2 SUPPORT FUNCTIONS	1421	=head2 SUPPORT FUNCTIONS
917		1422
918	=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION	1423	=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION
…		…
920	=over 4	1425	=over 4
921		1426
922	=item $fileno = IO::AIO::poll_fileno	1427	=item $fileno = IO::AIO::poll_fileno
923		1428
924	Return the I<request result pipe file descriptor>. This filehandle must be	1429	Return the I<request result pipe file descriptor>. This filehandle must be
925	polled for reading by some mechanism outside this module (e.g. Event or	1430	polled for reading by some mechanism outside this module (e.g. EV, Glib,
926	select, see below or the SYNOPSIS). If the pipe becomes readable you have	1431	select and so on, see below or the SYNOPSIS). If the pipe becomes readable
927	to call C<poll_cb> to check the results.	1432	you have to call C<poll_cb> to check the results.
928		1433
929	See C<poll_cb> for an example.	1434	See C<poll_cb> for an example.
930		1435
931	=item IO::AIO::poll_cb	1436	=item IO::AIO::poll_cb
932		1437
933	Process some outstanding events on the result pipe. You have to call this	1438	Process some outstanding events on the result pipe. You have to call
934	regularly. Returns the number of events processed. Returns immediately	1439	this regularly. Returns C<0> if all events could be processed (or there
935	when no events are outstanding. The amount of events processed depends on	1440	were no events to process), or C<-1> if it returned earlier for whatever
936	the settings of C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>.	1441	reason. Returns immediately when no events are outstanding. The amount of
		1442	events processed depends on the settings of C<IO::AIO::max_poll_req> and
		1443	C<IO::AIO::max_poll_time>.
937		1444
938	If not all requests were processed for whatever reason, the filehandle	1445	If not all requests were processed for whatever reason, the filehandle
939	will still be ready when C<poll_cb> returns.	1446	will still be ready when C<poll_cb> returns, so normally you don't have to
		1447	do anything special to have it called later.
		1448
		1449	Apart from calling C<IO::AIO::poll_cb> when the event filehandle becomes
		1450	ready, it can be beneficial to call this function from loops which submit
		1451	a lot of requests, to make sure the results get processed when they become
		1452	available and not just when the loop is finished and the event loop takes
		1453	over again. This function returns very fast when there are no outstanding
		1454	requests.
940		1455
941	Example: Install an Event watcher that automatically calls	1456	Example: Install an Event watcher that automatically calls
942	IO::AIO::poll_cb with high priority:	1457	IO::AIO::poll_cb with high priority (more examples can be found in the
		1458	SYNOPSIS section, at the top of this document):
943		1459
944	Event->io (fd => IO::AIO::poll_fileno,	1460	Event->io (fd => IO::AIO::poll_fileno,
945	poll => 'r', async => 1,	1461	poll => 'r', async => 1,
946	cb => \&IO::AIO::poll_cb);	1462	cb => \&IO::AIO::poll_cb);
		1463
		1464	=item IO::AIO::poll_wait
		1465
		1466	If there are any outstanding requests and none of them in the result
		1467	phase, wait till the result filehandle becomes ready for reading (simply
		1468	does a C<select> on the filehandle. This is useful if you want to
		1469	synchronously wait for some requests to finish).
		1470
		1471	See C<nreqs> for an example.
		1472
		1473	=item IO::AIO::poll
		1474
		1475	Waits until some requests have been handled.
		1476
		1477	Returns the number of requests processed, but is otherwise strictly
		1478	equivalent to:
		1479
		1480	IO::AIO::poll_wait, IO::AIO::poll_cb
		1481
		1482	=item IO::AIO::flush
		1483
		1484	Wait till all outstanding AIO requests have been handled.
		1485
		1486	Strictly equivalent to:
		1487
		1488	IO::AIO::poll_wait, IO::AIO::poll_cb
		1489	while IO::AIO::nreqs;
947		1490
948	=item IO::AIO::max_poll_reqs $nreqs	1491	=item IO::AIO::max_poll_reqs $nreqs
949		1492
950	=item IO::AIO::max_poll_time $seconds	1493	=item IO::AIO::max_poll_time $seconds
951		1494
…		…
976	# use a low priority so other tasks have priority	1519	# use a low priority so other tasks have priority
977	Event->io (fd => IO::AIO::poll_fileno,	1520	Event->io (fd => IO::AIO::poll_fileno,
978	poll => 'r', nice => 1,	1521	poll => 'r', nice => 1,
979	cb => &IO::AIO::poll_cb);	1522	cb => &IO::AIO::poll_cb);
980		1523
981	=item IO::AIO::poll_wait	1524	=back
982
983	If there are any outstanding requests and none of them in the result
984	phase, wait till the result filehandle becomes ready for reading (simply
985	does a C<select> on the filehandle. This is useful if you want to
986	synchronously wait for some requests to finish).
987
988	See C<nreqs> for an example.
989
990	=item IO::AIO::poll
991
992	Waits until some requests have been handled.
993
994	Returns the number of requests processed, but is otherwise strictly
995	equivalent to:
996
997	IO::AIO::poll_wait, IO::AIO::poll_cb
998
999	=item IO::AIO::flush
1000
1001	Wait till all outstanding AIO requests have been handled.
1002
1003	Strictly equivalent to:
1004
1005	IO::AIO::poll_wait, IO::AIO::poll_cb
1006	while IO::AIO::nreqs;
1007		1525
1008	=head3 CONTROLLING THE NUMBER OF THREADS	1526	=head3 CONTROLLING THE NUMBER OF THREADS
		1527
		1528	=over
1009		1529
1010	=item IO::AIO::min_parallel $nthreads	1530	=item IO::AIO::min_parallel $nthreads
1011		1531
1012	Set the minimum number of AIO threads to C<$nthreads>. The current	1532	Set the minimum number of AIO threads to C<$nthreads>. The current
1013	default is C<8>, which means eight asynchronous operations can execute	1533	default is C<8>, which means eight asynchronous operations can execute
…		…
1041		1561
1042	Under normal circumstances you don't need to call this function.	1562	Under normal circumstances you don't need to call this function.
1043		1563
1044	=item IO::AIO::max_idle $nthreads	1564	=item IO::AIO::max_idle $nthreads
1045		1565
1046	Limit the number of threads (default: 4) that are allowed to idle (i.e.,	1566	Limit the number of threads (default: 4) that are allowed to idle
1047	threads that did not get a request to process within 10 seconds). That	1567	(i.e., threads that did not get a request to process within the idle
1048	means if a thread becomes idle while C<$nthreads> other threads are also	1568	timeout (default: 10 seconds). That means if a thread becomes idle while
1049	idle, it will free its resources and exit.	1569	C<$nthreads> other threads are also idle, it will free its resources and
		1570	exit.
1050		1571
1051	This is useful when you allow a large number of threads (e.g. 100 or 1000)	1572	This is useful when you allow a large number of threads (e.g. 100 or 1000)
1052	to allow for extremely high load situations, but want to free resources	1573	to allow for extremely high load situations, but want to free resources
1053	under normal circumstances (1000 threads can easily consume 30MB of RAM).	1574	under normal circumstances (1000 threads can easily consume 30MB of RAM).
1054		1575
1055	The default is probably ok in most situations, especially if thread	1576	The default is probably ok in most situations, especially if thread
1056	creation is fast. If thread creation is very slow on your system you might	1577	creation is fast. If thread creation is very slow on your system you might
1057	want to use larger values.	1578	want to use larger values.
1058		1579
		1580	=item IO::AIO::idle_timeout $seconds
		1581
		1582	Sets the minimum idle timeout (default 10) after which worker threads are
		1583	allowed to exit. SEe C<IO::AIO::max_idle>.
		1584
1059	=item $oldmaxreqs = IO::AIO::max_outstanding $maxreqs	1585	=item IO::AIO::max_outstanding $maxreqs
		1586
		1587	Sets the maximum number of outstanding requests to C<$nreqs>. If
		1588	you do queue up more than this number of requests, the next call to
		1589	C<IO::AIO::poll_cb> (and other functions calling C<poll_cb>, such as
		1590	C<IO::AIO::flush> or C<IO::AIO::poll>) will block until the limit is no
		1591	longer exceeded.
		1592
		1593	In other words, this setting does not enforce a queue limit, but can be
		1594	used to make poll functions block if the limit is exceeded.
1060		1595
1061	This is a very bad function to use in interactive programs because it	1596	This is a very bad function to use in interactive programs because it
1062	blocks, and a bad way to reduce concurrency because it is inexact: Better	1597	blocks, and a bad way to reduce concurrency because it is inexact: Better
1063	use an C<aio_group> together with a feed callback.	1598	use an C<aio_group> together with a feed callback.
1064		1599
1065	Sets the maximum number of outstanding requests to C<$nreqs>. If you	1600	It's main use is in scripts without an event loop - when you want to stat
1066	to queue up more than this number of requests, the next call to the	1601	a lot of files, you can write somehting like this:
1067	C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>)
1068	function will block until the limit is no longer exceeded.
1069		1602
1070	The default value is very large, so there is no practical limit on the	1603	IO::AIO::max_outstanding 32;
1071	number of outstanding requests.
1072		1604
1073	You can still queue as many requests as you want. Therefore,	1605	for my $path (...) {
1074	C<max_oustsanding> is mainly useful in simple scripts (with low values) or	1606	aio_stat $path , ...;
1075	as a stop gap to shield against fatal memory overflow (with large values).	1607	IO::AIO::poll_cb;
		1608	}
		1609
		1610	IO::AIO::flush;
		1611
		1612	The call to C<poll_cb> inside the loop will normally return instantly, but
		1613	as soon as more thna C<32> reqeusts are in-flight, it will block until
		1614	some requests have been handled. This keeps the loop from pushing a large
		1615	number of C<aio_stat> requests onto the queue.
		1616
		1617	The default value for C<max_outstanding> is very large, so there is no
		1618	practical limit on the number of outstanding requests.
		1619
		1620	=back
1076		1621
1077	=head3 STATISTICAL INFORMATION	1622	=head3 STATISTICAL INFORMATION
		1623
		1624	=over
1078		1625
1079	=item IO::AIO::nreqs	1626	=item IO::AIO::nreqs
1080		1627
1081	Returns the number of requests currently in the ready, execute or pending	1628	Returns the number of requests currently in the ready, execute or pending
1082	states (i.e. for which their callback has not been invoked yet).	1629	states (i.e. for which their callback has not been invoked yet).
…		…
1096	Returns the number of requests currently in the pending state (executed,	1643	Returns the number of requests currently in the pending state (executed,
1097	but not yet processed by poll_cb).	1644	but not yet processed by poll_cb).
1098		1645
1099	=back	1646	=back
1100		1647
		1648	=head3 MISCELLANEOUS FUNCTIONS
		1649
		1650	IO::AIO implements some functions that might be useful, but are not
		1651	asynchronous.
		1652
		1653	=over 4
		1654
		1655	=item IO::AIO::sendfile $ofh, $ifh, $offset, $count
		1656
		1657	Calls the C<eio_sendfile_sync> function, which is like C<aio_sendfile>,
		1658	but is blocking (this makes most sense if you know the input data is
		1659	likely cached already and the output filehandle is set to non-blocking
		1660	operations).
		1661
		1662	Returns the number of bytes copied, or C<-1> on error.
		1663
		1664	=item IO::AIO::fadvise $fh, $offset, $len, $advice
		1665
		1666	Simply calls the C<posix_fadvise> function (see its
		1667	manpage for details). The following advice constants are
		1668	avaiable: C<IO::AIO::FADV_NORMAL>, C<IO::AIO::FADV_SEQUENTIAL>,
		1669	C<IO::AIO::FADV_RANDOM>, C<IO::AIO::FADV_NOREUSE>,
		1670	C<IO::AIO::FADV_WILLNEED>, C<IO::AIO::FADV_DONTNEED>.
		1671
		1672	On systems that do not implement C<posix_fadvise>, this function returns
		1673	ENOSYS, otherwise the return value of C<posix_fadvise>.
		1674
		1675	=item IO::AIO::madvise $scalar, $offset, $len, $advice
		1676
		1677	Simply calls the C<posix_madvise> function (see its
		1678	manpage for details). The following advice constants are
		1679	avaiable: C<IO::AIO::MADV_NORMAL>, C<IO::AIO::MADV_SEQUENTIAL>,
		1680	C<IO::AIO::MADV_RANDOM>, C<IO::AIO::MADV_WILLNEED>, C<IO::AIO::MADV_DONTNEED>.
		1681
		1682	On systems that do not implement C<posix_madvise>, this function returns
		1683	ENOSYS, otherwise the return value of C<posix_madvise>.
		1684
		1685	=item IO::AIO::mprotect $scalar, $offset, $len, $protect
		1686
		1687	Simply calls the C<mprotect> function on the preferably AIO::mmap'ed
		1688	$scalar (see its manpage for details). The following protect
		1689	constants are avaiable: C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_READ>,
		1690	C<IO::AIO::PROT_WRITE>, C<IO::AIO::PROT_EXEC>.
		1691
		1692	On systems that do not implement C<mprotect>, this function returns
		1693	ENOSYS, otherwise the return value of C<mprotect>.
		1694
		1695	=item IO::AIO::mmap $scalar, $length, $prot, $flags, $fh[, $offset]
		1696
		1697	Memory-maps a file (or anonymous memory range) and attaches it to the
		1698	given C<$scalar>, which will act like a string scalar.
		1699
		1700	The only operations allowed on the scalar are C<substr>/C<vec> that don't
		1701	change the string length, and most read-only operations such as copying it
		1702	or searching it with regexes and so on.
		1703
		1704	Anything else is unsafe and will, at best, result in memory leaks.
		1705
		1706	The memory map associated with the C<$scalar> is automatically removed
		1707	when the C<$scalar> is destroyed, or when the C<IO::AIO::mmap> or
		1708	C<IO::AIO::munmap> functions are called.
		1709
		1710	This calls the C<mmap>(2) function internally. See your system's manual
		1711	page for details on the C<$length>, C<$prot> and C<$flags> parameters.
		1712
		1713	The C<$length> must be larger than zero and smaller than the actual
		1714	filesize.
		1715
		1716	C<$prot> is a combination of C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_EXEC>,
		1717	C<IO::AIO::PROT_READ> and/or C<IO::AIO::PROT_WRITE>,
		1718
		1719	C<$flags> can be a combination of C<IO::AIO::MAP_SHARED> or
		1720	C<IO::AIO::MAP_PRIVATE>, or a number of system-specific flags (when
		1721	not available, the are defined as 0): C<IO::AIO::MAP_ANONYMOUS>
		1722	(which is set to C<MAP_ANON> if your system only provides this
		1723	constant), C<IO::AIO::MAP_HUGETLB>, C<IO::AIO::MAP_LOCKED>,
		1724	C<IO::AIO::MAP_NORESERVE>, C<IO::AIO::MAP_POPULATE> or
		1725	C<IO::AIO::MAP_NONBLOCK>
		1726
		1727	If C<$fh> is C<undef>, then a file descriptor of C<-1> is passed.
		1728
		1729	C<$offset> is the offset from the start of the file - it generally must be
		1730	a multiple of C<IO::AIO::PAGESIZE> and defaults to C<0>.
		1731
		1732	Example:
		1733
		1734	use Digest::MD5;
		1735	use IO::AIO;
		1736
		1737	open my $fh, "<verybigfile"
		1738	or die "$!";
		1739
		1740	IO::AIO::mmap my $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh
		1741	or die "verybigfile: $!";
		1742
		1743	my $fast_md5 = md5 $data;
		1744
		1745	=item IO::AIO::munmap $scalar
		1746
		1747	Removes a previous mmap and undefines the C<$scalar>.
		1748
		1749	=item IO::AIO::munlock $scalar, $offset = 0, $length = undef
		1750
		1751	Calls the C<munlock> function, undoing the effects of a previous
		1752	C<aio_mlock> call (see its description for details).
		1753
		1754	=item IO::AIO::munlockall
		1755
		1756	Calls the C<munlockall> function.
		1757
		1758	On systems that do not implement C<munlockall>, this function returns
		1759	ENOSYS, otherwise the return value of C<munlockall>.
		1760
		1761	=back
		1762
1101	=cut	1763	=cut
1102		1764
1103	# support function to convert a fd into a perl filehandle
1104	sub _fd2fh {
1105	return undef if $_[0] < 0;
1106
1107	# try to generate nice filehandles
1108	my $sym = "IO::AIO::fd#$_[0]";
1109	local *$sym;
1110
1111	open *$sym, "+<&=$_[0]" # usually works under any unix
1112	or open *$sym, "<&=$_[0]" # cygwin needs this
1113	or open *$sym, ">&=$_[0]" # or this
1114	or return undef;
1115
1116	*$sym
1117	}
1118
1119	min_parallel 8;	1765	min_parallel 8;
1120		1766
1121	END { flush }	1767	END { flush }
1122		1768
1123	1;	1769	1;
1124		1770
		1771	=head1 EVENT LOOP INTEGRATION
		1772
		1773	It is recommended to use L<AnyEvent::AIO> to integrate IO::AIO
		1774	automatically into many event loops:
		1775
		1776	# AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...)
		1777	use AnyEvent::AIO;
		1778
		1779	You can also integrate IO::AIO manually into many event loops, here are
		1780	some examples of how to do this:
		1781
		1782	# EV integration
		1783	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
		1784
		1785	# Event integration
		1786	Event->io (fd => IO::AIO::poll_fileno,
		1787	poll => 'r',
		1788	cb => \&IO::AIO::poll_cb);
		1789
		1790	# Glib/Gtk2 integration
		1791	add_watch Glib::IO IO::AIO::poll_fileno,
		1792	in => sub { IO::AIO::poll_cb; 1 };
		1793
		1794	# Tk integration
		1795	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
		1796	readable => \&IO::AIO::poll_cb);
		1797
		1798	# Danga::Socket integration
		1799	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
		1800	\&IO::AIO::poll_cb);
		1801
1125	=head2 FORK BEHAVIOUR	1802	=head2 FORK BEHAVIOUR
1126		1803
1127	This module should do "the right thing" when the process using it forks:	1804	Usage of pthreads in a program changes the semantics of fork
		1805	considerably. Specifically, only async-safe functions can be called after
		1806	fork. Perl doesn't know about this, so in general, you cannot call fork
		1807	with defined behaviour in perl. IO::AIO uses pthreads, so this applies,
		1808	but many other extensions and (for inexplicable reasons) perl itself often
		1809	is linked against pthreads, so this limitation applies.
1128		1810
1129	Before the fork, IO::AIO enters a quiescent state where no requests	1811	Some operating systems have extensions that allow safe use of fork, and
1130	can be added in other threads and no results will be processed. After	1812	this module should do "the right thing" on those, and tries on others. At
1131	the fork the parent simply leaves the quiescent state and continues	1813	the time of this writing (2011) only GNU/Linux supports these extensions
1132	request/result processing, while the child frees the request/result queue	1814	to POSIX.
1133	(so that the requests started before the fork will only be handled in the
1134	parent). Threads will be started on demand until the limit set in the
1135	parent process has been reached again.
1136
1137	In short: the parent will, after a short pause, continue as if fork had
1138	not been called, while the child will act as if IO::AIO has not been used
1139	yet.
1140		1815
1141	=head2 MEMORY USAGE	1816	=head2 MEMORY USAGE
1142		1817
1143	Per-request usage:	1818	Per-request usage:
1144		1819
…		…
1146	bytes of memory. In addition, stat requests need a stat buffer (possibly	1821	bytes of memory. In addition, stat requests need a stat buffer (possibly
1147	a few hundred bytes), readdir requires a result buffer and so on. Perl	1822	a few hundred bytes), readdir requires a result buffer and so on. Perl
1148	scalars and other data passed into aio requests will also be locked and	1823	scalars and other data passed into aio requests will also be locked and
1149	will consume memory till the request has entered the done state.	1824	will consume memory till the request has entered the done state.
1150		1825
1151	This is now awfully much, so queuing lots of requests is not usually a	1826	This is not awfully much, so queuing lots of requests is not usually a
1152	problem.	1827	problem.
1153		1828
1154	Per-thread usage:	1829	Per-thread usage:
1155		1830
1156	In the execution phase, some aio requests require more memory for	1831	In the execution phase, some aio requests require more memory for
…		…
1161		1836
1162	Known bugs will be fixed in the next release.	1837	Known bugs will be fixed in the next release.
1163		1838
1164	=head1 SEE ALSO	1839	=head1 SEE ALSO
1165		1840
1166	L<Coro::AIO>.	1841	L<AnyEvent::AIO> for easy integration into event loops, L<Coro::AIO> for a
		1842	more natural syntax.
1167		1843
1168	=head1 AUTHOR	1844	=head1 AUTHOR
1169		1845
1170	Marc Lehmann <schmorp@schmorp.de>	1846	Marc Lehmann <schmorp@schmorp.de>
1171	http://home.schmorp.de/	1847	http://home.schmorp.de/

Diff Legend

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