ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/IO-AIO/AIO.pm

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.70 by root, Tue Oct 24 03:40:38 2006 UTC vs.
Revision 1.170 by root, Sat Jan 2 14:11:32 2010 UTC

…		…
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", O_RDONLY, 0, sub {
10	my ($fh) = @_;	10	my $fh = shift
		11	or die "/etc/passwd: $!";
11	...	12	...
12	};	13	};
13		14
14	aio_unlink "/tmp/file", sub { };	15	aio_unlink "/tmp/file", sub { };
15		16
…		…
25	$req->cancel; # cancel request if still in queue	26	$req->cancel; # cancel request if still in queue
26		27
27	my $grp = aio_group sub { print "all stats done\n" };	28	my $grp = aio_group sub { print "all stats done\n" };
28	add $grp aio_stat "..." for ...;	29	add $grp aio_stat "..." for ...;
29		30
		31	# AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...)
		32	use AnyEvent::AIO;
		33
30	# AnyEvent integration	34	# EV integration
31	open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!";	35	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
32	my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb });
33		36
34	# Event integration	37	# Event integration
35	Event->io (fd => IO::AIO::poll_fileno,	38	Event->io (fd => IO::AIO::poll_fileno,
36	poll => 'r',	39	poll => 'r',
37	cb => \&IO::AIO::poll_cb);	40	cb => \&IO::AIO::poll_cb);
…		…
49	\&IO::AIO::poll_cb);	52	\&IO::AIO::poll_cb);
50		53
51	=head1 DESCRIPTION	54	=head1 DESCRIPTION
52		55
53	This module implements asynchronous I/O using whatever means your	56	This module implements asynchronous I/O using whatever means your
54	operating system supports.	57	operating system supports. It is implemented as an interface to C<libeio>
		58	(L<http://software.schmorp.de/pkg/libeio.html>).
55		59
		60	Asynchronous means that operations that can normally block your program
		61	(e.g. reading from disk) will be done asynchronously: the operation
		62	will still block, but you can do something else in the meantime. This
		63	is extremely useful for programs that need to stay interactive even
		64	when doing heavy I/O (GUI programs, high performance network servers
		65	etc.), but can also be used to easily do operations in parallel that are
		66	normally done sequentially, e.g. stat'ing many files, which is much faster
		67	on a RAID volume or over NFS when you do a number of stat operations
		68	concurrently.
		69
		70	While most of this works on all types of file descriptors (for
		71	example sockets), using these functions on file descriptors that
		72	support nonblocking operation (again, sockets, pipes etc.) is
		73	very inefficient. Use an event loop for that (such as the L<EV>
		74	module): IO::AIO will naturally fit into such an event loop itself.
		75
56	Currently, a number of threads are started that execute your read/writes	76	In this version, a number of threads are started that execute your
57	and signal their completion. You don't need thread support in perl, and	77	requests and signal their completion. You don't need thread support
58	the threads created by this module will not be visible to perl. In the	78	in perl, and the threads created by this module will not be visible
59	future, this module might make use of the native aio functions available	79	to perl. In the future, this module might make use of the native aio
60	on many operating systems. However, they are often not well-supported	80	functions available on many operating systems. However, they are often
61	(Linux doesn't allow them on normal files currently, for example),	81	not well-supported or restricted (GNU/Linux doesn't allow them on normal
62	and they would only support aio_read and aio_write, so the remaining	82	files currently, for example), and they would only support aio_read and
63	functionality would have to be implemented using threads anyway.	83	aio_write, so the remaining functionality would have to be implemented
		84	using threads anyway.
64		85
65	Although the module will work with in the presence of other threads,	86	Although the module will work in the presence of other (Perl-) threads,
66	it is currently not reentrant in any way, so use appropriate locking	87	it is currently not reentrant in any way, so use appropriate locking
67	yourself, always call C<poll_cb> from within the same thread, or never	88	yourself, always call C<poll_cb> from within the same thread, or never
68	call C<poll_cb> (or other C<aio_> functions) recursively.	89	call C<poll_cb> (or other C<aio_> functions) recursively.
69		90
		91	=head2 EXAMPLE
		92
		93	This is a simple example that uses the EV module and loads
		94	F</etc/passwd> asynchronously:
		95
		96	use Fcntl;
		97	use EV;
		98	use IO::AIO;
		99
		100	# register the IO::AIO callback with EV
		101	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
		102
		103	# queue the request to open /etc/passwd
		104	aio_open "/etc/passwd", O_RDONLY, 0, sub {
		105	my $fh = shift
		106	or die "error while opening: $!";
		107
		108	# stat'ing filehandles is generally non-blocking
		109	my $size = -s $fh;
		110
		111	# queue a request to read the file
		112	my $contents;
		113	aio_read $fh, 0, $size, $contents, 0, sub {
		114	$_[0] == $size
		115	or die "short read: $!";
		116
		117	close $fh;
		118
		119	# file contents now in $contents
		120	print $contents;
		121
		122	# exit event loop and program
		123	EV::unloop;
		124	};
		125	};
		126
		127	# possibly queue up other requests, or open GUI windows,
		128	# check for sockets etc. etc.
		129
		130	# process events as long as there are some:
		131	EV::loop;
		132
		133	=head1 REQUEST ANATOMY AND LIFETIME
		134
		135	Every C<aio_*> function creates a request. which is a C data structure not
		136	directly visible to Perl.
		137
		138	If called in non-void context, every request function returns a Perl
		139	object representing the request. In void context, nothing is returned,
		140	which saves a bit of memory.
		141
		142	The perl object is a fairly standard ref-to-hash object. The hash contents
		143	are not used by IO::AIO so you are free to store anything you like in it.
		144
		145	During their existance, aio requests travel through the following states,
		146	in order:
		147
		148	=over 4
		149
		150	=item ready
		151
		152	Immediately after a request is created it is put into the ready state,
		153	waiting for a thread to execute it.
		154
		155	=item execute
		156
		157	A thread has accepted the request for processing and is currently
		158	executing it (e.g. blocking in read).
		159
		160	=item pending
		161
		162	The request has been executed and is waiting for result processing.
		163
		164	While request submission and execution is fully asynchronous, result
		165	processing is not and relies on the perl interpreter calling C<poll_cb>
		166	(or another function with the same effect).
		167
		168	=item result
		169
		170	The request results are processed synchronously by C<poll_cb>.
		171
		172	The C<poll_cb> function will process all outstanding aio requests by
		173	calling their callbacks, freeing memory associated with them and managing
		174	any groups they are contained in.
		175
		176	=item done
		177
		178	Request has reached the end of its lifetime and holds no resources anymore
		179	(except possibly for the Perl object, but its connection to the actual
		180	aio request is severed and calling its methods will either do nothing or
		181	result in a runtime error).
		182
		183	=back
		184
70	=cut	185	=cut
71		186
72	package IO::AIO;	187	package IO::AIO;
73		188
74	no warnings;	189	use Carp ();
75	use strict 'vars';	190
		191	use common::sense;
76		192
77	use base 'Exporter';	193	use base 'Exporter';
78		194
79	BEGIN {	195	BEGIN {
80	our $VERSION = '2.0';	196	our $VERSION = '3.31';
81		197
82	our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat	198	our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close
83	aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink	199	aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx
84	aio_fsync aio_fdatasync aio_readahead aio_rename aio_link aio_move	200	aio_scandir aio_symlink aio_readlink aio_sync aio_fsync
		201	aio_fdatasync aio_sync_file_range aio_pathsync aio_readahead
		202	aio_rename aio_link aio_move aio_copy aio_group
		203	aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown
		204	aio_chmod aio_utime aio_truncate
85	aio_group aio_nop);	205	aio_msync aio_mtouch);
		206
86	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice));	207	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice));
87	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush	208	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush
88	min_parallel max_parallel max_outstanding nreqs);	209	min_parallel max_parallel max_idle
		210	nreqs nready npending nthreads
		211	max_poll_time max_poll_reqs
		212	sendfile fadvise);
		213
		214	push @AIO_REQ, qw(aio_busy); # not exported
89		215
90	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';	216	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';
91		217
92	require XSLoader;	218	require XSLoader;
93	XSLoader::load ("IO::AIO", $VERSION);	219	XSLoader::load ("IO::AIO", $VERSION);
94	}	220	}
95		221
96	=head1 FUNCTIONS	222	=head1 FUNCTIONS
97		223
98	=head2 AIO FUNCTIONS	224	=head2 AIO REQUEST FUNCTIONS
99		225
100	All the C<aio_*> calls are more or less thin wrappers around the syscall	226	All the C<aio_*> calls are more or less thin wrappers around the syscall
101	with the same name (sans C<aio_>). The arguments are similar or identical,	227	with the same name (sans C<aio_>). The arguments are similar or identical,
102	and they all accept an additional (and optional) C<$callback> argument	228	and they all accept an additional (and optional) C<$callback> argument
103	which must be a code reference. This code reference will get called with	229	which must be a code reference. This code reference will get called with
104	the syscall return code (e.g. most syscalls return C<-1> on error, unlike	230	the syscall return code (e.g. most syscalls return C<-1> on error, unlike
105	perl, which usually delivers "false") as it's sole argument when the given	231	perl, which usually delivers "false") as its sole argument after the given
106	syscall has been executed asynchronously.	232	syscall has been executed asynchronously.
107		233
108	All functions expecting a filehandle keep a copy of the filehandle	234	All functions expecting a filehandle keep a copy of the filehandle
109	internally until the request has finished.	235	internally until the request has finished.
110		236
111	All requests return objects of type L<IO::AIO::REQ> that allow further	237	All functions return request objects of type L<IO::AIO::REQ> that allow
112	manipulation of those requests while they are in-flight.	238	further manipulation of those requests while they are in-flight.
113		239
114	The pathnames you pass to these routines I<must> be absolute and	240	The pathnames you pass to these routines I<must> be absolute and
115	encoded in byte form. The reason for the former is that at the time the	241	encoded as octets. The reason for the former is that at the time the
116	request is being executed, the current working directory could have	242	request is being executed, the current working directory could have
117	changed. Alternatively, you can make sure that you never change the	243	changed. Alternatively, you can make sure that you never change the
118	current working directory.	244	current working directory anywhere in the program and then use relative
		245	paths.
119		246
120	To encode pathnames to byte form, either make sure you either: a)	247	To encode pathnames as octets, either make sure you either: a) always pass
121	always pass in filenames you got from outside (command line, readdir	248	in filenames you got from outside (command line, readdir etc.) without
122	etc.), b) are ASCII or ISO 8859-1, c) use the Encode module and encode	249	tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module and encode
123	your pathnames to the locale (or other) encoding in effect in the user	250	your pathnames to the locale (or other) encoding in effect in the user
124	environment, d) use Glib::filename_from_unicode on unicode filenames or e)	251	environment, d) use Glib::filename_from_unicode on unicode filenames or e)
125	use something else.	252	use something else to ensure your scalar has the correct contents.
		253
		254	This works, btw. independent of the internal UTF-8 bit, which IO::AIO
		255	handles correctly whether it is set or not.
126		256
127	=over 4	257	=over 4
128		258
129	=item aioreq_pri $pri	259	=item $prev_pri = aioreq_pri [$pri]
130		260
131	Sets the priority for the next aio request. The default priority	261	Returns the priority value that would be used for the next request and, if
		262	C<$pri> is given, sets the priority for the next aio request.
		263
132	is C<0>, the minimum and maximum priorities are C<-4> and C<4>,	264	The default priority is C<0>, the minimum and maximum priorities are C<-4>
133	respectively. Requests with higher priority will be serviced first.	265	and C<4>, respectively. Requests with higher priority will be serviced
		266	first.
134		267
135	The priority will be reset to C<0> after each call to one of the C<aio_>	268	The priority will be reset to C<0> after each call to one of the C<aio_*>
136	functions.	269	functions.
137		270
138	Example: open a file with low priority, then read something from it with	271	Example: open a file with low priority, then read something from it with
139	higher priority so the read request is serviced before other low priority	272	higher priority so the read request is serviced before other low priority
140	open requests (potentially spamming the cache):	273	open requests (potentially spamming the cache):
…		…
147	aio_read $_[0], ..., sub {	280	aio_read $_[0], ..., sub {
148	...	281	...
149	};	282	};
150	};	283	};
151		284
		285
152	=item aioreq_nice $pri_adjust	286	=item aioreq_nice $pri_adjust
153		287
154	Similar to C<aioreq_pri>, but subtracts the given value from the current	288	Similar to C<aioreq_pri>, but subtracts the given value from the current
155	priority, so effects are cumulative.	289	priority, so the effect is cumulative.
		290
156		291
157	=item aio_open $pathname, $flags, $mode, $callback->($fh)	292	=item aio_open $pathname, $flags, $mode, $callback->($fh)
158		293
159	Asynchronously open or create a file and call the callback with a newly	294	Asynchronously open or create a file and call the callback with a newly
160	created filehandle for the file.	295	created filehandle for the file.
…		…
166	list. They are the same as used by C<sysopen>.	301	list. They are the same as used by C<sysopen>.
167		302
168	Likewise, C<$mode> specifies the mode of the newly created file, if it	303	Likewise, C<$mode> specifies the mode of the newly created file, if it
169	didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,	304	didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,
170	except that it is mandatory (i.e. use C<0> if you don't create new files,	305	except that it is mandatory (i.e. use C<0> if you don't create new files,
171	and C<0666> or C<0777> if you do).	306	and C<0666> or C<0777> if you do). Note that the C<$mode> will be modified
		307	by the umask in effect then the request is being executed, so better never
		308	change the umask.
172		309
173	Example:	310	Example:
174		311
175	aio_open "/etc/passwd", O_RDONLY, 0, sub {	312	aio_open "/etc/passwd", O_RDONLY, 0, sub {
176	if ($_[0]) {	313	if ($_[0]) {
…		…
179	} else {	316	} else {
180	die "open failed: $!\n";	317	die "open failed: $!\n";
181	}	318	}
182	};	319	};
183		320
		321
184	=item aio_close $fh, $callback->($status)	322	=item aio_close $fh, $callback->($status)
185		323
186	Asynchronously close a file and call the callback with the result	324	Asynchronously close a file and call the callback with the result
187	code. I<WARNING:> although accepted, you should not pass in a perl	325	code.
188	filehandle here, as perl will likely close the file descriptor another
189	time when the filehandle is destroyed. Normally, you can safely call perls
190	C<close> or just let filehandles go out of scope.
191		326
192	This is supposed to be a bug in the API, so that might change. It's	327	Unfortunately, you can't do this to perl. Perl I<insists> very strongly on
193	therefore best to avoid this function.	328	closing the file descriptor associated with the filehandle itself.
		329
		330	Therefore, C<aio_close> will not close the filehandle - instead it will
		331	use dup2 to overwrite the file descriptor with the write-end of a pipe
		332	(the pipe fd will be created on demand and will be cached).
		333
		334	Or in other words: the file descriptor will be closed, but it will not be
		335	free for reuse until the perl filehandle is closed.
		336
		337	=cut
194		338
195	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	339	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
196		340
197	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	341	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
198		342
199	Reads or writes C<length> bytes from the specified C<fh> and C<offset>	343	Reads or writes C<$length> bytes from or to the specified C<$fh> and
200	into the scalar given by C<data> and offset C<dataoffset> and calls the	344	C<$offset> into the scalar given by C<$data> and offset C<$dataoffset>
201	callback without the actual number of bytes read (or -1 on error, just	345	and calls the callback without the actual number of bytes read (or -1 on
202	like the syscall).	346	error, just like the syscall).
		347
		348	C<aio_read> will, like C<sysread>, shrink or grow the C<$data> scalar to
		349	offset plus the actual number of bytes read.
		350
		351	If C<$offset> is undefined, then the current file descriptor offset will
		352	be used (and updated), otherwise the file descriptor offset will not be
		353	changed by these calls.
		354
		355	If C<$length> is undefined in C<aio_write>, use the remaining length of
		356	C<$data>.
		357
		358	If C<$dataoffset> is less than zero, it will be counted from the end of
		359	C<$data>.
203		360
204	The C<$data> scalar I<MUST NOT> be modified in any way while the request	361	The C<$data> scalar I<MUST NOT> be modified in any way while the request
205	is outstanding. Modifying it can result in segfaults or WW3 (if the	362	is outstanding. Modifying it can result in segfaults or World War III (if
206	necessary/optional hardware is installed).	363	the necessary/optional hardware is installed).
207		364
208	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at	365	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at
209	offset C<0> within the scalar:	366	offset C<0> within the scalar:
210		367
211	aio_read $fh, 7, 15, $buffer, 0, sub {	368	aio_read $fh, 7, 15, $buffer, 0, sub {
212	$_[0] > 0 or die "read error: $!";	369	$_[0] > 0 or die "read error: $!";
213	print "read $_[0] bytes: <$buffer>\n";	370	print "read $_[0] bytes: <$buffer>\n";
214	};	371	};
215		372
216	=item aio_move $srcpath, $dstpath, $callback->($status)
217
218	[EXPERIMENTAL due to internal aio_group use]
219
220	Try to move the I<file> (directories not supported as either source or
221	destination) from C<$srcpath> to C<$dstpath> and call the callback with
222	the C<0> (error) or C<-1> ok.
223
224	This is a composite request that tries to rename(2) the file first. If
225	rename files with C<EXDEV>, it creates the destination file with mode 0200
226	and copies the contents of the source file into it using C<aio_sendfile>,
227	followed by restoring atime, mtime, access mode and uid/gid, in that
228	order, and unlinking the C<$srcpath>.
229
230	If an error occurs, the partial destination file will be unlinked, if
231	possible, except when setting atime, mtime, access mode and uid/gid, where
232	errors are being ignored.
233
234	=cut
235
236	sub aio_move($$$) {
237	my ($src, $dst, $cb) = @_;
238
239	my $grp = aio_group $cb;
240
241	add $grp aio_rename $src, $dst, sub {
242	if ($_[0] && $! == EXDEV) {
243	add $grp aio_open $src, O_RDONLY, 0, sub {
244	if (my $src_fh = $_[0]) {
245	my @stat = stat $src_fh;
246
247	add $grp aio_open $dst, O_WRONLY, 0200, sub {
248	if (my $dst_fh = $_[0]) {
249	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
250	close $src_fh;
251
252	if ($_[0] == $stat[7]) {
253	utime $stat[8], $stat[9], $dst;
254	chmod $stat[2] & 07777, $dst_fh;
255	chown $stat[4], $stat[5], $dst_fh;
256	close $dst_fh;
257
258	add $grp aio_unlink $src, sub {
259	$grp->result ($_[0]);
260	};
261	} else {
262	my $errno = $!;
263	add $grp aio_unlink $dst, sub {
264	$! = $errno;
265	$grp->result (-1);
266	};
267	}
268	};
269	} else {
270	$grp->result (-1);
271	}
272	},
273
274	} else {
275	$grp->result (-1);
276	}
277	};
278	} else {
279	$grp->result ($_[0]);
280	}
281	};
282
283	$grp
284	}
285		373
286	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)	374	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
287		375
288	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts	376	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
289	reading at byte offset C<$in_offset>, and starts writing at the current	377	reading at byte offset C<$in_offset>, and starts writing at the current
…		…
293		381
294	This call tries to make use of a native C<sendfile> syscall to provide	382	This call tries to make use of a native C<sendfile> syscall to provide
295	zero-copy operation. For this to work, C<$out_fh> should refer to a	383	zero-copy operation. For this to work, C<$out_fh> should refer to a
296	socket, and C<$in_fh> should refer to mmap'able file.	384	socket, and C<$in_fh> should refer to mmap'able file.
297		385
298	If the native sendfile call fails or is not implemented, it will be	386	If a native sendfile cannot be found or it fails with C<ENOSYS>,
		387	C<ENOTSUP>, C<EOPNOTSUPP>, C<EAFNOSUPPORT>, C<EPROTOTYPE> or C<ENOTSOCK>,
299	emulated, so you can call C<aio_sendfile> on any type of filehandle	388	it will be emulated, so you can call C<aio_sendfile> on any type of
300	regardless of the limitations of the operating system.	389	filehandle regardless of the limitations of the operating system.
301		390
302	Please note, however, that C<aio_sendfile> can read more bytes from	391	Please note, however, that C<aio_sendfile> can read more bytes from
303	C<$in_fh> than are written, and there is no way to find out how many	392	C<$in_fh> than are written, and there is no way to find out how many
304	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only	393	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only
305	provides the number of bytes written to C<$out_fh>. Only if the result	394	provides the number of bytes written to C<$out_fh>. Only if the result
306	value equals C<$length> one can assume that C<$length> bytes have been	395	value equals C<$length> one can assume that C<$length> bytes have been
307	read.	396	read.
		397
308		398
309	=item aio_readahead $fh,$offset,$length, $callback->($retval)	399	=item aio_readahead $fh,$offset,$length, $callback->($retval)
310		400
311	C<aio_readahead> populates the page cache with data from a file so that	401	C<aio_readahead> populates the page cache with data from a file so that
312	subsequent reads from that file will not block on disk I/O. The C<$offset>	402	subsequent reads from that file will not block on disk I/O. The C<$offset>
…		…
318	file. The current file offset of the file is left unchanged.	408	file. The current file offset of the file is left unchanged.
319		409
320	If that syscall doesn't exist (likely if your OS isn't Linux) it will be	410	If that syscall doesn't exist (likely if your OS isn't Linux) it will be
321	emulated by simply reading the data, which would have a similar effect.	411	emulated by simply reading the data, which would have a similar effect.
322		412
		413
323	=item aio_stat $fh_or_path, $callback->($status)	414	=item aio_stat $fh_or_path, $callback->($status)
324		415
325	=item aio_lstat $fh, $callback->($status)	416	=item aio_lstat $fh, $callback->($status)
326		417
327	Works like perl's C<stat> or C<lstat> in void context. The callback will	418	Works like perl's C<stat> or C<lstat> in void context. The callback will
…		…
340	aio_stat "/etc/passwd", sub {	431	aio_stat "/etc/passwd", sub {
341	$_[0] and die "stat failed: $!";	432	$_[0] and die "stat failed: $!";
342	print "size is ", -s _, "\n";	433	print "size is ", -s _, "\n";
343	};	434	};
344		435
		436
		437	=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
		438
		439	Works like perl's C<utime> function (including the special case of $atime
		440	and $mtime being undef). Fractional times are supported if the underlying
		441	syscalls support them.
		442
		443	When called with a pathname, uses utimes(2) if available, otherwise
		444	utime(2). If called on a file descriptor, uses futimes(2) if available,
		445	otherwise returns ENOSYS, so this is not portable.
		446
		447	Examples:
		448
		449	# set atime and mtime to current time (basically touch(1)):
		450	aio_utime "path", undef, undef;
		451	# set atime to current time and mtime to beginning of the epoch:
		452	aio_utime "path", time, undef; # undef==0
		453
		454
		455	=item aio_chown $fh_or_path, $uid, $gid, $callback->($status)
		456
		457	Works like perl's C<chown> function, except that C<undef> for either $uid
		458	or $gid is being interpreted as "do not change" (but -1 can also be used).
		459
		460	Examples:
		461
		462	# same as "chown root path" in the shell:
		463	aio_chown "path", 0, -1;
		464	# same as above:
		465	aio_chown "path", 0, undef;
		466
		467
		468	=item aio_truncate $fh_or_path, $offset, $callback->($status)
		469
		470	Works like truncate(2) or ftruncate(2).
		471
		472
		473	=item aio_chmod $fh_or_path, $mode, $callback->($status)
		474
		475	Works like perl's C<chmod> function.
		476
		477
345	=item aio_unlink $pathname, $callback->($status)	478	=item aio_unlink $pathname, $callback->($status)
346		479
347	Asynchronously unlink (delete) a file and call the callback with the	480	Asynchronously unlink (delete) a file and call the callback with the
348	result code.	481	result code.
349		482
		483
		484	=item aio_mknod $path, $mode, $dev, $callback->($status)
		485
		486	[EXPERIMENTAL]
		487
		488	Asynchronously create a device node (or fifo). See mknod(2).
		489
		490	The only (POSIX-) portable way of calling this function is:
		491
		492	aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ...
		493
		494
350	=item aio_link $srcpath, $dstpath, $callback->($status)	495	=item aio_link $srcpath, $dstpath, $callback->($status)
351		496
352	Asynchronously create a new link to the existing object at C<$srcpath> at	497	Asynchronously create a new link to the existing object at C<$srcpath> at
353	the path C<$dstpath> and call the callback with the result code.	498	the path C<$dstpath> and call the callback with the result code.
354		499
		500
355	=item aio_symlink $srcpath, $dstpath, $callback->($status)	501	=item aio_symlink $srcpath, $dstpath, $callback->($status)
356		502
357	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at	503	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at
358	the path C<$dstpath> and call the callback with the result code.	504	the path C<$dstpath> and call the callback with the result code.
359		505
		506
		507	=item aio_readlink $path, $callback->($link)
		508
		509	Asynchronously read the symlink specified by C<$path> and pass it to
		510	the callback. If an error occurs, nothing or undef gets passed to the
		511	callback.
		512
		513
360	=item aio_rename $srcpath, $dstpath, $callback->($status)	514	=item aio_rename $srcpath, $dstpath, $callback->($status)
361		515
362	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as	516	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as
363	rename(2) and call the callback with the result code.	517	rename(2) and call the callback with the result code.
364		518
		519
		520	=item aio_mkdir $pathname, $mode, $callback->($status)
		521
		522	Asynchronously mkdir (create) a directory and call the callback with
		523	the result code. C<$mode> will be modified by the umask at the time the
		524	request is executed, so do not change your umask.
		525
		526
365	=item aio_rmdir $pathname, $callback->($status)	527	=item aio_rmdir $pathname, $callback->($status)
366		528
367	Asynchronously rmdir (delete) a directory and call the callback with the	529	Asynchronously rmdir (delete) a directory and call the callback with the
368	result code.	530	result code.
		531
369		532
370	=item aio_readdir $pathname, $callback->($entries)	533	=item aio_readdir $pathname, $callback->($entries)
371		534
372	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire	535	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
373	directory (i.e. opendir + readdir + closedir). The entries will not be	536	directory (i.e. opendir + readdir + closedir). The entries will not be
374	sorted, and will B<NOT> include the C<.> and C<..> entries.	537	sorted, and will B<NOT> include the C<.> and C<..> entries.
375		538
376	The callback a single argument which is either C<undef> or an array-ref	539	The callback is passed a single argument which is either C<undef> or an
377	with the filenames.	540	array-ref with the filenames.
		541
		542
		543	=item aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		544
		545	Quite similar to C<aio_readdir>, but the C<$flags> argument allows to tune
		546	behaviour and output format. In case of an error, C<$entries> will be
		547	C<undef>.
		548
		549	The flags are a combination of the following constants, ORed together (the
		550	flags will also be passed to the callback, possibly modified):
		551
		552	=over 4
		553
		554	=item IO::AIO::READDIR_DENTS
		555
		556	When this flag is off, then the callback gets an arrayref with of names
		557	only (as with C<aio_readdir>), otherwise it gets an arrayref with
		558	C<[$name, $type, $inode]> arrayrefs, each describing a single directory
		559	entry in more detail.
		560
		561	C<$name> is the name of the entry.
		562
		563	C<$type> is one of the C<IO::AIO::DT_xxx> constants:
		564
		565	C<IO::AIO::DT_UNKNOWN>, C<IO::AIO::DT_FIFO>, C<IO::AIO::DT_CHR>, C<IO::AIO::DT_DIR>,
		566	C<IO::AIO::DT_BLK>, C<IO::AIO::DT_REG>, C<IO::AIO::DT_LNK>, C<IO::AIO::DT_SOCK>,
		567	C<IO::AIO::DT_WHT>.
		568
		569	C<IO::AIO::DT_UNKNOWN> means just that: readdir does not know. If you need to
		570	know, you have to run stat yourself. Also, for speed reasons, the C<$type>
		571	scalars are read-only: you can not modify them.
		572
		573	C<$inode> is the inode number (which might not be exact on systems with 64
		574	bit inode numbers and 32 bit perls). This field has unspecified content on
		575	systems that do not deliver the inode information.
		576
		577	=item IO::AIO::READDIR_DIRS_FIRST
		578
		579	When this flag is set, then the names will be returned in an order where
		580	likely directories come first. This is useful when you need to quickly
		581	find directories, or you want to find all directories while avoiding to
		582	stat() each entry.
		583
		584	If the system returns type information in readdir, then this is used
		585	to find directories directly. Otherwise, likely directories are files
		586	beginning with ".", or otherwise files with no dots, of which files with
		587	short names are tried first.
		588
		589	=item IO::AIO::READDIR_STAT_ORDER
		590
		591	When this flag is set, then the names will be returned in an order
		592	suitable for stat()'ing each one. That is, when you plan to stat()
		593	all files in the given directory, then the returned order will likely
		594	be fastest.
		595
		596	If both this flag and C<IO::AIO::READDIR_DIRS_FIRST> are specified, then
		597	the likely dirs come first, resulting in a less optimal stat order.
		598
		599	=item IO::AIO::READDIR_FOUND_UNKNOWN
		600
		601	This flag should not be set when calling C<aio_readdirx>. Instead, it
		602	is being set by C<aio_readdirx>, when any of the C<$type>'s found were
		603	C<IO::AIO::DT_UNKNOWN>. The absense of this flag therefore indicates that all
		604	C<$type>'s are known, which can be used to speed up some algorithms.
		605
		606	=back
		607
		608
		609	=item aio_load $path, $data, $callback->($status)
		610
		611	This is a composite request that tries to fully load the given file into
		612	memory. Status is the same as with aio_read.
		613
		614	=cut
		615
		616	sub aio_load($$;$) {
		617	my ($path, undef, $cb) = @_;
		618	my $data = \$_[1];
		619
		620	my $pri = aioreq_pri;
		621	my $grp = aio_group $cb;
		622
		623	aioreq_pri $pri;
		624	add $grp aio_open $path, O_RDONLY, 0, sub {
		625	my $fh = shift
		626	or return $grp->result (-1);
		627
		628	aioreq_pri $pri;
		629	add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub {
		630	$grp->result ($_[0]);
		631	};
		632	};
		633
		634	$grp
		635	}
		636
		637	=item aio_copy $srcpath, $dstpath, $callback->($status)
		638
		639	Try to copy the I<file> (directories not supported as either source or
		640	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		641	a status of C<0> (ok) or C<-1> (error, see C<$!>).
		642
		643	This is a composite request that creates the destination file with
		644	mode 0200 and copies the contents of the source file into it using
		645	C<aio_sendfile>, followed by restoring atime, mtime, access mode and
		646	uid/gid, in that order.
		647
		648	If an error occurs, the partial destination file will be unlinked, if
		649	possible, except when setting atime, mtime, access mode and uid/gid, where
		650	errors are being ignored.
		651
		652	=cut
		653
		654	sub aio_copy($$;$) {
		655	my ($src, $dst, $cb) = @_;
		656
		657	my $pri = aioreq_pri;
		658	my $grp = aio_group $cb;
		659
		660	aioreq_pri $pri;
		661	add $grp aio_open $src, O_RDONLY, 0, sub {
		662	if (my $src_fh = $_[0]) {
		663	my @stat = stat $src_fh; # hmm, might block over nfs?
		664
		665	aioreq_pri $pri;
		666	add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {
		667	if (my $dst_fh = $_[0]) {
		668	aioreq_pri $pri;
		669	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
		670	if ($_[0] == $stat[7]) {
		671	$grp->result (0);
		672	close $src_fh;
		673
		674	my $ch = sub {
		675	aioreq_pri $pri;
		676	add $grp aio_chmod $dst_fh, $stat[2] & 07777, sub {
		677	aioreq_pri $pri;
		678	add $grp aio_chown $dst_fh, $stat[4], $stat[5], sub {
		679	aioreq_pri $pri;
		680	add $grp aio_close $dst_fh;
		681	}
		682	};
		683	};
		684
		685	aioreq_pri $pri;
		686	add $grp aio_utime $dst_fh, $stat[8], $stat[9], sub {
		687	if ($_[0] < 0 && $! == ENOSYS) {
		688	aioreq_pri $pri;
		689	add $grp aio_utime $dst, $stat[8], $stat[9], $ch;
		690	} else {
		691	$ch->();
		692	}
		693	};
		694	} else {
		695	$grp->result (-1);
		696	close $src_fh;
		697	close $dst_fh;
		698
		699	aioreq $pri;
		700	add $grp aio_unlink $dst;
		701	}
		702	};
		703	} else {
		704	$grp->result (-1);
		705	}
		706	},
		707
		708	} else {
		709	$grp->result (-1);
		710	}
		711	};
		712
		713	$grp
		714	}
		715
		716	=item aio_move $srcpath, $dstpath, $callback->($status)
		717
		718	Try to move the I<file> (directories not supported as either source or
		719	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		720	a status of C<0> (ok) or C<-1> (error, see C<$!>).
		721
		722	This is a composite request that tries to rename(2) the file first; if
		723	rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if
		724	that is successful, unlinks the C<$srcpath>.
		725
		726	=cut
		727
		728	sub aio_move($$;$) {
		729	my ($src, $dst, $cb) = @_;
		730
		731	my $pri = aioreq_pri;
		732	my $grp = aio_group $cb;
		733
		734	aioreq_pri $pri;
		735	add $grp aio_rename $src, $dst, sub {
		736	if ($_[0] && $! == EXDEV) {
		737	aioreq_pri $pri;
		738	add $grp aio_copy $src, $dst, sub {
		739	$grp->result ($_[0]);
		740
		741	if (!$_[0]) {
		742	aioreq_pri $pri;
		743	add $grp aio_unlink $src;
		744	}
		745	};
		746	} else {
		747	$grp->result ($_[0]);
		748	}
		749	};
		750
		751	$grp
		752	}
378		753
379	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)	754	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
380		755
381	[EXPERIMENTAL due to internal aio_group use]
382
383	Scans a directory (similar to C<aio_readdir>) but additionally tries to	756	Scans a directory (similar to C<aio_readdir>) but additionally tries to
384	separate the entries of directory C<$path> into two sets of names, ones	757	efficiently separate the entries of directory C<$path> into two sets of
385	you can recurse into (directories or links to them), and ones you cannot	758	names, directories you can recurse into (directories), and ones you cannot
386	recurse into (everything else).	759	recurse into (everything else, including symlinks to directories).
387		760
388	C<aio_scandir> is a composite request that creates of many sub requests_	761	C<aio_scandir> is a composite request that creates of many sub requests_
389	C<$maxreq> specifies the maximum number of outstanding aio requests that	762	C<$maxreq> specifies the maximum number of outstanding aio requests that
390	this function generates. If it is C<< <= 0 >>, then a suitable default	763	this function generates. If it is C<< <= 0 >>, then a suitable default
391	will be chosen (currently 6).	764	will be chosen (currently 4).
392		765
393	On error, the callback is called without arguments, otherwise it receives	766	On error, the callback is called without arguments, otherwise it receives
394	two array-refs with path-relative entry names.	767	two array-refs with path-relative entry names.
395		768
396	Example:	769	Example:
…		…
403		776
404	Implementation notes.	777	Implementation notes.
405		778
406	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.	779	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.
407		780
		781	If readdir returns file type information, then this is used directly to
		782	find directories.
		783
408	After reading the directory, the modification time, size etc. of the	784	Otherwise, after reading the directory, the modification time, size etc.
409	directory before and after the readdir is checked, and if they match (and	785	of the directory before and after the readdir is checked, and if they
410	isn't the current time), the link count will be used to decide how many	786	match (and isn't the current time), the link count will be used to decide
411	entries are directories (if >= 2). Otherwise, no knowledge of the number	787	how many entries are directories (if >= 2). Otherwise, no knowledge of the
412	of subdirectories will be assumed.	788	number of subdirectories will be assumed.
413		789
414	Then entries will be sorted into likely directories (everything without	790	Then entries will be sorted into likely directories a non-initial dot
415	a non-initial dot currently) and likely non-directories (everything	791	currently) and likely non-directories (see C<aio_readdirx>). Then every
416	else). Then every entry plus an appended C</.> will be C<stat>'ed,	792	entry plus an appended C</.> will be C<stat>'ed, likely directories first,
417	likely directories first. If that succeeds, it assumes that the entry	793	in order of their inode numbers. If that succeeds, it assumes that the
418	is a directory or a symlink to directory (which will be checked	794	entry is a directory or a symlink to directory (which will be checked
419	seperately). This is often faster than stat'ing the entry itself because	795	seperately). This is often faster than stat'ing the entry itself because
420	filesystems might detect the type of the entry without reading the inode	796	filesystems might detect the type of the entry without reading the inode
421	data (e.g. ext2fs filetype feature).	797	data (e.g. ext2fs filetype feature), even on systems that cannot return
		798	the filetype information on readdir.
422		799
423	If the known number of directories (link count - 2) has been reached, the	800	If the known number of directories (link count - 2) has been reached, the
424	rest of the entries is assumed to be non-directories.	801	rest of the entries is assumed to be non-directories.
425		802
426	This only works with certainty on POSIX (= UNIX) filesystems, which	803	This only works with certainty on POSIX (= UNIX) filesystems, which
…		…
430	as those tend to return 0 or 1 as link counts, which disables the	807	as those tend to return 0 or 1 as link counts, which disables the
431	directory counting heuristic.	808	directory counting heuristic.
432		809
433	=cut	810	=cut
434		811
435	sub aio_scandir($$$) {	812	sub aio_scandir($$;$) {
436	my ($path, $maxreq, $cb) = @_;	813	my ($path, $maxreq, $cb) = @_;
437		814
		815	my $pri = aioreq_pri;
		816
438	my $grp = aio_group $cb;	817	my $grp = aio_group $cb;
439		818
440	$maxreq = 6 if $maxreq <= 0;	819	$maxreq = 4 if $maxreq <= 0;
441		820
442	# stat once	821	# stat once
		822	aioreq_pri $pri;
443	add $grp aio_stat $path, sub {	823	add $grp aio_stat $path, sub {
444	return $grp->result () if $_[0];	824	return $grp->result () if $_[0];
445	my $now = time;	825	my $now = time;
446	my $hash1 = join ":", (stat _)[0,1,3,7,9];	826	my $hash1 = join ":", (stat _)[0,1,3,7,9];
447		827
448	# read the directory entries	828	# read the directory entries
		829	aioreq_pri $pri;
449	add $grp aio_readdir $path, sub {	830	add $grp aio_readdirx $path, READDIR_DIRS_FIRST, sub {
450	my $entries = shift	831	my $entries = shift
451	or return $grp->result ();	832	or return $grp->result ();
452		833
453	# stat the dir another time	834	# stat the dir another time
		835	aioreq_pri $pri;
454	add $grp aio_stat $path, sub {	836	add $grp aio_stat $path, sub {
455	my $hash2 = join ":", (stat _)[0,1,3,7,9];	837	my $hash2 = join ":", (stat _)[0,1,3,7,9];
456		838
457	my $ndirs;	839	my $ndirs;
458		840
459	# take the slow route if anything looks fishy	841	# take the slow route if anything looks fishy
460	if ($hash1 ne $hash2 or (stat _)[9] == $now) {	842	if ($hash1 ne $hash2 or (stat _)[9] == $now) {
461	$ndirs = -1;	843	$ndirs = -1;
462	} else {	844	} else {
463	# if nlink == 2, we are finished	845	# if nlink == 2, we are finished
464	# on non-posix-fs's, we rely on nlink < 2	846	# for non-posix-fs's, we rely on nlink < 2
465	$ndirs = (stat _)[3] - 2	847	$ndirs = (stat _)[3] - 2
466	or return $grp->result ([], $entries);	848	or return $grp->result ([], $entries);
467	}	849	}
468		850
469	# sort into likely dirs and likely nondirs
470	# dirs == files without ".", short entries first
471	$entries = [map $_->[0],
472	sort { $b->[1] cmp $a->[1] }
473	map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],
474	@$entries];
475
476	my (@dirs, @nondirs);	851	my (@dirs, @nondirs);
477		852
478	my ($statcb, $schedcb);
479	my $nreq = 0;
480
481	my $statgrp = add $grp aio_group;	853	my $statgrp = add $grp aio_group sub {
		854	$grp->result (\@dirs, \@nondirs);
		855	};
482		856
483	$schedcb = sub {	857	limit $statgrp $maxreq;
484	if (@$entries) {	858	feed $statgrp sub {
485	if ($nreq < $maxreq) {	859	return unless @$entries;
486	my $ent = pop @$entries;	860	my $entry = shift @$entries;
		861
		862	aioreq_pri $pri;
		863	add $statgrp aio_stat "$path/$entry/.", sub {
		864	if ($_[0] < 0) {
		865	push @nondirs, $entry;
		866	} else {
		867	# need to check for real directory
		868	aioreq_pri $pri;
		869	add $statgrp aio_lstat "$path/$entry", sub {
		870	if (-d _) {
		871	push @dirs, $entry;
		872
		873	unless (--$ndirs) {
		874	push @nondirs, @$entries;
		875	feed $statgrp;
		876	}
		877	} else {
		878	push @nondirs, $entry;
		879	}
487	$nreq++;	880	}
488	add $statgrp aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) };
489	}	881	}
490	} elsif (!$nreq) {
491	# finished
492	$statgrp->cancel;
493	undef $statcb;
494	undef $schedcb;
495	$grp->result (\@dirs, \@nondirs);
496	}	882	};
497	};	883	};
498	$statcb = sub {
499	my ($status, $entry) = @_;
500
501	if ($status < 0) {
502	$nreq--;
503	push @nondirs, $entry;
504	&$schedcb;
505	} else {
506	# need to check for real directory
507	add $grp aio_lstat "$path/$entry", sub {
508	$nreq--;
509
510	if (-d _) {
511	push @dirs, $entry;
512
513	if (!--$ndirs) {
514	push @nondirs, @$entries;
515	$entries = [];
516	}
517	} else {
518	push @nondirs, $entry;
519	}
520
521	&$schedcb;
522	}
523	}
524	};
525
526	&$schedcb while @$entries && $nreq < $maxreq;
527	};	884	};
528	};	885	};
529	};	886	};
530		887
531	$grp	888	$grp
532	}	889	}
533		890
		891	=item aio_rmtree $path, $callback->($status)
		892
		893	Delete a directory tree starting (and including) C<$path>, return the
		894	status of the final C<rmdir> only. This is a composite request that
		895	uses C<aio_scandir> to recurse into and rmdir directories, and unlink
		896	everything else.
		897
		898	=cut
		899
		900	sub aio_rmtree;
		901	sub aio_rmtree($;$) {
		902	my ($path, $cb) = @_;
		903
		904	my $pri = aioreq_pri;
		905	my $grp = aio_group $cb;
		906
		907	aioreq_pri $pri;
		908	add $grp aio_scandir $path, 0, sub {
		909	my ($dirs, $nondirs) = @_;
		910
		911	my $dirgrp = aio_group sub {
		912	add $grp aio_rmdir $path, sub {
		913	$grp->result ($_[0]);
		914	};
		915	};
		916
		917	(aioreq_pri $pri), add $dirgrp aio_rmtree "$path/$_" for @$dirs;
		918	(aioreq_pri $pri), add $dirgrp aio_unlink "$path/$_" for @$nondirs;
		919
		920	add $grp $dirgrp;
		921	};
		922
		923	$grp
		924	}
		925
		926	=item aio_sync $callback->($status)
		927
		928	Asynchronously call sync and call the callback when finished.
		929
534	=item aio_fsync $fh, $callback->($status)	930	=item aio_fsync $fh, $callback->($status)
535		931
536	Asynchronously call fsync on the given filehandle and call the callback	932	Asynchronously call fsync on the given filehandle and call the callback
537	with the fsync result code.	933	with the fsync result code.
538		934
…		…
542	callback with the fdatasync result code.	938	callback with the fdatasync result code.
543		939
544	If this call isn't available because your OS lacks it or it couldn't be	940	If this call isn't available because your OS lacks it or it couldn't be
545	detected, it will be emulated by calling C<fsync> instead.	941	detected, it will be emulated by calling C<fsync> instead.
546		942
		943	=item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		944
		945	Sync the data portion of the file specified by C<$offset> and C<$length>
		946	to disk (but NOT the metadata), by calling the Linux-specific
		947	sync_file_range call. If sync_file_range is not available or it returns
		948	ENOSYS, then fdatasync or fsync is being substituted.
		949
		950	C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>,
		951	C<IO::AIO::SYNC_FILE_RANGE_WRITE> and
		952	C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range
		953	manpage for details.
		954
		955	=item aio_pathsync $path, $callback->($status)
		956
		957	This request tries to open, fsync and close the given path. This is a
		958	composite request intended to sync directories after directory operations
		959	(E.g. rename). This might not work on all operating systems or have any
		960	specific effect, but usually it makes sure that directory changes get
		961	written to disc. It works for anything that can be opened for read-only,
		962	not just directories.
		963
		964	Future versions of this function might fall back to other methods when
		965	C<fsync> on the directory fails (such as calling C<sync>).
		966
		967	Passes C<0> when everything went ok, and C<-1> on error.
		968
		969	=cut
		970
		971	sub aio_pathsync($;$) {
		972	my ($path, $cb) = @_;
		973
		974	my $pri = aioreq_pri;
		975	my $grp = aio_group $cb;
		976
		977	aioreq_pri $pri;
		978	add $grp aio_open $path, O_RDONLY, 0, sub {
		979	my ($fh) = @_;
		980	if ($fh) {
		981	aioreq_pri $pri;
		982	add $grp aio_fsync $fh, sub {
		983	$grp->result ($_[0]);
		984
		985	aioreq_pri $pri;
		986	add $grp aio_close $fh;
		987	};
		988	} else {
		989	$grp->result (-1);
		990	}
		991	};
		992
		993	$grp
		994	}
		995
		996	=item aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		997
		998	This is a rather advanced IO::AIO call, which only works on mmap(2)ed
		999	scalars (see the L<Sys::Mmap> or L<Mmap> modules for details on this, note
		1000	that the scalar must only be modified in-place while an aio operation is
		1001	pending on it).
		1002
		1003	It calls the C<msync> function of your OS, if available, with the memory
		1004	area starting at C<$offset> in the string and ending C<$length> bytes
		1005	later. If C<$length> is negative, counts from the end, and if C<$length>
		1006	is C<undef>, then it goes till the end of the string. The flags can be
		1007	a combination of C<IO::AIO::MS_ASYNC>, C<IO::AIO::MS_INVALIDATE> and
		1008	C<IO::AIO::MS_SYNC>.
		1009
		1010	=item aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		1011
		1012	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1013	scalars.
		1014
		1015	It touches (reads or writes) all memory pages in the specified
		1016	range inside the scalar. All caveats and parameters are the same
		1017	as for C<aio_msync>, above, except for flags, which must be either
		1018	C<0> (which reads all pages and ensures they are instantiated) or
		1019	C<IO::AIO::MT_MODIFY>, which modifies the memory page s(by reading and
		1020	writing an octet from it, which dirties the page).
		1021
547	=item aio_group $callback->(...)	1022	=item aio_group $callback->(...)
548
549	[EXPERIMENTAL]
550		1023
551	This is a very special aio request: Instead of doing something, it is a	1024	This is a very special aio request: Instead of doing something, it is a
552	container for other aio requests, which is useful if you want to bundle	1025	container for other aio requests, which is useful if you want to bundle
553	many requests into a single, composite, request.	1026	many requests into a single, composite, request with a definite callback
		1027	and the ability to cancel the whole request with its subrequests.
554		1028
555	Returns an object of class L<IO::AIO::GRP>. See its documentation below	1029	Returns an object of class L<IO::AIO::GRP>. See its documentation below
556	for more info.	1030	for more info.
557		1031
558	Example:	1032	Example:
…		…
577	phase and still requires a worker thread. Thus, the callback will not	1051	phase and still requires a worker thread. Thus, the callback will not
578	be executed immediately but only after other requests in the queue have	1052	be executed immediately but only after other requests in the queue have
579	entered their execution phase. This can be used to measure request	1053	entered their execution phase. This can be used to measure request
580	latency.	1054	latency.
581		1055
582	=item IO::AIO::aio_sleep $fractional_seconds, $callback->() *NOT EXPORTED*	1056	=item IO::AIO::aio_busy $fractional_seconds, $callback->() *NOT EXPORTED*
583		1057
584	Mainly used for debugging and benchmarking, this aio request puts one of	1058	Mainly used for debugging and benchmarking, this aio request puts one of
585	the request workers to sleep for the given time.	1059	the request workers to sleep for the given time.
586		1060
587	While it is theoretically handy to have simple I/O scheduling requests	1061	While it is theoretically handy to have simple I/O scheduling requests
588	like sleep and file handle readable/writable, the overhead this creates	1062	like sleep and file handle readable/writable, the overhead this creates is
589	is immense, so do not use this function except to put your application	1063	immense (it blocks a thread for a long time) so do not use this function
590	under artificial I/O pressure.	1064	except to put your application under artificial I/O pressure.
591		1065
592	=back	1066	=back
593		1067
594	=head2 IO::AIO::REQ CLASS	1068	=head2 IO::AIO::REQ CLASS
595		1069
596	All non-aggregate C<aio_*> functions return an object of this class when	1070	All non-aggregate C<aio_*> functions return an object of this class when
597	called in non-void context.	1071	called in non-void context.
598
599	A request always moves through the following five states in its lifetime,
600	in order: B<ready> (request has been created, but has not been executed
601	yet), B<execute> (request is currently being executed), B<pending>
602	(request has been executed but callback has not been called yet),
603	B<result> (results are being processed synchronously, includes calling the
604	callback) and B<done> (request has reached the end of its lifetime and
605	holds no resources anymore).
606		1072
607	=over 4	1073	=over 4
608		1074
609	=item cancel $req	1075	=item cancel $req
610		1076
611	Cancels the request, if possible. Has the effect of skipping execution	1077	Cancels the request, if possible. Has the effect of skipping execution
612	when entering the B<execute> state and skipping calling the callback when	1078	when entering the B<execute> state and skipping calling the callback when
613	entering the the B<result> state, but will leave the request otherwise	1079	entering the the B<result> state, but will leave the request otherwise
614	untouched. That means that requests that currently execute will not be	1080	untouched (with the exception of readdir). That means that requests that
615	stopped and resources held by the request will not be freed prematurely.	1081	currently execute will not be stopped and resources held by the request
		1082	will not be freed prematurely.
616		1083
617	=item cb $req $callback->(...)	1084	=item cb $req $callback->(...)
618		1085
619	Replace (or simply set) the callback registered to the request.	1086	Replace (or simply set) the callback registered to the request.
620		1087
…		…
664	=item * They can also can also be added to other IO::AIO::GRP objects.	1131	=item * They can also can also be added to other IO::AIO::GRP objects.
665		1132
666	=item * You must not add requests to a group from within the group callback (or	1133	=item * You must not add requests to a group from within the group callback (or
667	any later time).	1134	any later time).
668		1135
669	=item * This does not harmonise well with C<max_outstanding>, so best do
670	not combine C<aio_group> with it. Groups and feeders are recommended for
671	this kind of concurrency-limiting.
672
673	=back	1136	=back
674		1137
675	Their lifetime, simplified, looks like this: when they are empty, they	1138	Their lifetime, simplified, looks like this: when they are empty, they
676	will finish very quickly. If they contain only requests that are in the	1139	will finish very quickly. If they contain only requests that are in the
677	C<done> state, they will also finish. Otherwise they will continue to	1140	C<done> state, they will also finish. Otherwise they will continue to
678	exist.	1141	exist.
679		1142
680	That means after creating a group you have some time to add requests. And	1143	That means after creating a group you have some time to add requests
681	in the callbacks of those requests, you can add further requests to the	1144	(precisely before the callback has been invoked, which is only done within
682	group. And only when all those requests have finished will the the group	1145	the C<poll_cb>). And in the callbacks of those requests, you can add
683	itself finish.	1146	further requests to the group. And only when all those requests have
		1147	finished will the the group itself finish.
684		1148
685	=over 4	1149	=over 4
686		1150
687	=item add $grp ...	1151	=item add $grp ...
688		1152
…		…
692	be added, including other groups, as long as you do not create circular	1156	be added, including other groups, as long as you do not create circular
693	dependencies.	1157	dependencies.
694		1158
695	Returns all its arguments.	1159	Returns all its arguments.
696		1160
		1161	=item $grp->cancel_subs
		1162
		1163	Cancel all subrequests and clears any feeder, but not the group request
		1164	itself. Useful when you queued a lot of events but got a result early.
		1165
		1166	The group request will finish normally (you cannot add requests to the
		1167	group).
		1168
697	=item $grp->result (...)	1169	=item $grp->result (...)
698		1170
699	Set the result value(s) that will be passed to the group callback when all	1171	Set the result value(s) that will be passed to the group callback when all
700	subrequests have finished. By default, no argument will be passed.	1172	subrequests have finished and set the groups errno to the current value
		1173	of errno (just like calling C<errno> without an error number). By default,
		1174	no argument will be passed and errno is zero.
		1175
		1176	=item $grp->errno ([$errno])
		1177
		1178	Sets the group errno value to C<$errno>, or the current value of errno
		1179	when the argument is missing.
		1180
		1181	Every aio request has an associated errno value that is restored when
		1182	the callback is invoked. This method lets you change this value from its
		1183	default (0).
		1184
		1185	Calling C<result> will also set errno, so make sure you either set C<$!>
		1186	before the call to C<result>, or call c<errno> after it.
701		1187
702	=item feed $grp $callback->($grp)	1188	=item feed $grp $callback->($grp)
703
704	[VERY EXPERIMENTAL]
705		1189
706	Sets a feeder/generator on this group: every group can have an attached	1190	Sets a feeder/generator on this group: every group can have an attached
707	generator that generates requests if idle. The idea behind this is that,	1191	generator that generates requests if idle. The idea behind this is that,
708	although you could just queue as many requests as you want in a group,	1192	although you could just queue as many requests as you want in a group,
709	this might starve other requests for a potentially long time. For	1193	this might starve other requests for a potentially long time. For example,
710	example, C<aio_scandir> might generate hundreds of thousands C<aio_stat>	1194	C<aio_scandir> might generate hundreds of thousands C<aio_stat> requests,
711	requests, delaying any later requests for a long time.	1195	delaying any later requests for a long time.
712		1196
713	To avoid this, and allow incremental generation of requests, you can	1197	To avoid this, and allow incremental generation of requests, you can
714	instead a group and set a feeder on it that generates those requests. The	1198	instead a group and set a feeder on it that generates those requests. The
715	feed callback will be called whenever there are few enough (see C<limit>,	1199	feed callback will be called whenever there are few enough (see C<limit>,
716	below) requests active in the group itself and is expected to queue more	1200	below) requests active in the group itself and is expected to queue more
…		…
720	not impose any limits).	1204	not impose any limits).
721		1205
722	If the feed does not queue more requests when called, it will be	1206	If the feed does not queue more requests when called, it will be
723	automatically removed from the group.	1207	automatically removed from the group.
724		1208
725	If the feed limit is C<0>, it will be set to C<2> automatically.	1209	If the feed limit is C<0> when this method is called, it will be set to
		1210	C<2> automatically.
726		1211
727	Example:	1212	Example:
728		1213
729	# stat all files in @files, but only ever use four aio requests concurrently:	1214	# stat all files in @files, but only ever use four aio requests concurrently:
730		1215
…		…
742	Sets the feeder limit for the group: The feeder will be called whenever	1227	Sets the feeder limit for the group: The feeder will be called whenever
743	the group contains less than this many requests.	1228	the group contains less than this many requests.
744		1229
745	Setting the limit to C<0> will pause the feeding process.	1230	Setting the limit to C<0> will pause the feeding process.
746		1231
		1232	The default value for the limit is C<0>, but note that setting a feeder
		1233	automatically bumps it up to C<2>.
		1234
747	=back	1235	=back
748		1236
749	=head2 SUPPORT FUNCTIONS	1237	=head2 SUPPORT FUNCTIONS
750		1238
		1239	=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION
		1240
751	=over 4	1241	=over 4
752		1242
753	=item $fileno = IO::AIO::poll_fileno	1243	=item $fileno = IO::AIO::poll_fileno
754		1244
755	Return the I<request result pipe file descriptor>. This filehandle must be	1245	Return the I<request result pipe file descriptor>. This filehandle must be
756	polled for reading by some mechanism outside this module (e.g. Event or	1246	polled for reading by some mechanism outside this module (e.g. EV, Glib,
757	select, see below or the SYNOPSIS). If the pipe becomes readable you have	1247	select and so on, see below or the SYNOPSIS). If the pipe becomes readable
758	to call C<poll_cb> to check the results.	1248	you have to call C<poll_cb> to check the results.
759		1249
760	See C<poll_cb> for an example.	1250	See C<poll_cb> for an example.
761		1251
762	=item IO::AIO::poll_cb	1252	=item IO::AIO::poll_cb
763		1253
764	Process all outstanding events on the result pipe. You have to call this	1254	Process some outstanding events on the result pipe. You have to call this
765	regularly. Returns the number of events processed. Returns immediately	1255	regularly. Returns C<0> if all events could be processed, or C<-1> if it
766	when no events are outstanding.	1256	returned earlier for whatever reason. Returns immediately when no events
		1257	are outstanding. The amount of events processed depends on the settings of
		1258	C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>.
		1259
		1260	If not all requests were processed for whatever reason, the filehandle
		1261	will still be ready when C<poll_cb> returns, so normally you don't have to
		1262	do anything special to have it called later.
767		1263
768	Example: Install an Event watcher that automatically calls	1264	Example: Install an Event watcher that automatically calls
769	IO::AIO::poll_cb with high priority:	1265	IO::AIO::poll_cb with high priority (more examples can be found in the
		1266	SYNOPSIS section, at the top of this document):
770		1267
771	Event->io (fd => IO::AIO::poll_fileno,	1268	Event->io (fd => IO::AIO::poll_fileno,
772	poll => 'r', async => 1,	1269	poll => 'r', async => 1,
773	cb => \&IO::AIO::poll_cb);	1270	cb => \&IO::AIO::poll_cb);
774		1271
		1272	=item IO::AIO::max_poll_reqs $nreqs
		1273
		1274	=item IO::AIO::max_poll_time $seconds
		1275
		1276	These set the maximum number of requests (default C<0>, meaning infinity)
		1277	that are being processed by C<IO::AIO::poll_cb> in one call, respectively
		1278	the maximum amount of time (default C<0>, meaning infinity) spent in
		1279	C<IO::AIO::poll_cb> to process requests (more correctly the mininum amount
		1280	of time C<poll_cb> is allowed to use).
		1281
		1282	Setting C<max_poll_time> to a non-zero value creates an overhead of one
		1283	syscall per request processed, which is not normally a problem unless your
		1284	callbacks are really really fast or your OS is really really slow (I am
		1285	not mentioning Solaris here). Using C<max_poll_reqs> incurs no overhead.
		1286
		1287	Setting these is useful if you want to ensure some level of
		1288	interactiveness when perl is not fast enough to process all requests in
		1289	time.
		1290
		1291	For interactive programs, values such as C<0.01> to C<0.1> should be fine.
		1292
		1293	Example: Install an Event watcher that automatically calls
		1294	IO::AIO::poll_cb with low priority, to ensure that other parts of the
		1295	program get the CPU sometimes even under high AIO load.
		1296
		1297	# try not to spend much more than 0.1s in poll_cb
		1298	IO::AIO::max_poll_time 0.1;
		1299
		1300	# use a low priority so other tasks have priority
		1301	Event->io (fd => IO::AIO::poll_fileno,
		1302	poll => 'r', nice => 1,
		1303	cb => &IO::AIO::poll_cb);
		1304
775	=item IO::AIO::poll_wait	1305	=item IO::AIO::poll_wait
776		1306
		1307	If there are any outstanding requests and none of them in the result
777	Wait till the result filehandle becomes ready for reading (simply does a	1308	phase, wait till the result filehandle becomes ready for reading (simply
778	C<select> on the filehandle. This is useful if you want to synchronously wait	1309	does a C<select> on the filehandle. This is useful if you want to
779	for some requests to finish).	1310	synchronously wait for some requests to finish).
780		1311
781	See C<nreqs> for an example.	1312	See C<nreqs> for an example.
782		1313
		1314	=item IO::AIO::poll
		1315
		1316	Waits until some requests have been handled.
		1317
		1318	Returns the number of requests processed, but is otherwise strictly
		1319	equivalent to:
		1320
		1321	IO::AIO::poll_wait, IO::AIO::poll_cb
		1322
783	=item IO::AIO::nreqs	1323	=item IO::AIO::flush
784		1324
785	Returns the number of requests currently outstanding (i.e. for which their	1325	Wait till all outstanding AIO requests have been handled.
786	callback has not been invoked yet).
787		1326
788	Example: wait till there are no outstanding requests anymore:	1327	Strictly equivalent to:
789		1328
790	IO::AIO::poll_wait, IO::AIO::poll_cb	1329	IO::AIO::poll_wait, IO::AIO::poll_cb
791	while IO::AIO::nreqs;	1330	while IO::AIO::nreqs;
792		1331
793	=item IO::AIO::flush	1332	=back
794		1333
795	Wait till all outstanding AIO requests have been handled.	1334	=head3 CONTROLLING THE NUMBER OF THREADS
796		1335
797	Strictly equivalent to:	1336	=over
798
799	IO::AIO::poll_wait, IO::AIO::poll_cb
800	while IO::AIO::nreqs;
801
802	=item IO::AIO::poll
803
804	Waits until some requests have been handled.
805
806	Strictly equivalent to:
807
808	IO::AIO::poll_wait, IO::AIO::poll_cb
809	if IO::AIO::nreqs;
810		1337
811	=item IO::AIO::min_parallel $nthreads	1338	=item IO::AIO::min_parallel $nthreads
812		1339
813	Set the minimum number of AIO threads to C<$nthreads>. The current	1340	Set the minimum number of AIO threads to C<$nthreads>. The current
814	default is C<8>, which means eight asynchronous operations can execute	1341	default is C<8>, which means eight asynchronous operations can execute
815	concurrently at any one time (the number of outstanding requests,	1342	concurrently at any one time (the number of outstanding requests,
816	however, is unlimited).	1343	however, is unlimited).
817		1344
818	IO::AIO starts threads only on demand, when an AIO request is queued and	1345	IO::AIO starts threads only on demand, when an AIO request is queued and
819	no free thread exists.	1346	no free thread exists. Please note that queueing up a hundred requests can
		1347	create demand for a hundred threads, even if it turns out that everything
		1348	is in the cache and could have been processed faster by a single thread.
820		1349
821	It is recommended to keep the number of threads relatively low, as some	1350	It is recommended to keep the number of threads relatively low, as some
822	Linux kernel versions will scale negatively with the number of threads	1351	Linux kernel versions will scale negatively with the number of threads
823	(higher parallelity => MUCH higher latency). With current Linux 2.6	1352	(higher parallelity => MUCH higher latency). With current Linux 2.6
824	versions, 4-32 threads should be fine.	1353	versions, 4-32 threads should be fine.
…		…
838	This module automatically runs C<max_parallel 0> at program end, to ensure	1367	This module automatically runs C<max_parallel 0> at program end, to ensure
839	that all threads are killed and that there are no outstanding requests.	1368	that all threads are killed and that there are no outstanding requests.
840		1369
841	Under normal circumstances you don't need to call this function.	1370	Under normal circumstances you don't need to call this function.
842		1371
		1372	=item IO::AIO::max_idle $nthreads
		1373
		1374	Limit the number of threads (default: 4) that are allowed to idle (i.e.,
		1375	threads that did not get a request to process within 10 seconds). That
		1376	means if a thread becomes idle while C<$nthreads> other threads are also
		1377	idle, it will free its resources and exit.
		1378
		1379	This is useful when you allow a large number of threads (e.g. 100 or 1000)
		1380	to allow for extremely high load situations, but want to free resources
		1381	under normal circumstances (1000 threads can easily consume 30MB of RAM).
		1382
		1383	The default is probably ok in most situations, especially if thread
		1384	creation is fast. If thread creation is very slow on your system you might
		1385	want to use larger values.
		1386
843	=item $oldnreqs = IO::AIO::max_outstanding $nreqs	1387	=item IO::AIO::max_outstanding $maxreqs
844		1388
845	[DEPRECATED]	1389	This is a very bad function to use in interactive programs because it
		1390	blocks, and a bad way to reduce concurrency because it is inexact: Better
		1391	use an C<aio_group> together with a feed callback.
846		1392
847	Sets the maximum number of outstanding requests to C<$nreqs>. If you	1393	Sets the maximum number of outstanding requests to C<$nreqs>. If you
848	try to queue up more than this number of requests, the caller will block until	1394	do queue up more than this number of requests, the next call to the
849	some requests have been handled.	1395	C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>)
		1396	function will block until the limit is no longer exceeded.
850		1397
851	The default is very large, so normally there is no practical limit. If you	1398	The default value is very large, so there is no practical limit on the
852	queue up many requests in a loop it often improves speed if you set	1399	number of outstanding requests.
853	this to a relatively low number, such as C<100>.
854		1400
855	This function does not work well together with C<aio_group>'s, and their	1401	You can still queue as many requests as you want. Therefore,
856	feeder interface is better suited to limiting concurrency, so do not use	1402	C<max_outstanding> is mainly useful in simple scripts (with low values) or
857	this function.	1403	as a stop gap to shield against fatal memory overflow (with large values).
858
859	Under normal circumstances you don't need to call this function.
860		1404
861	=back	1405	=back
862		1406
		1407	=head3 STATISTICAL INFORMATION
		1408
		1409	=over
		1410
		1411	=item IO::AIO::nreqs
		1412
		1413	Returns the number of requests currently in the ready, execute or pending
		1414	states (i.e. for which their callback has not been invoked yet).
		1415
		1416	Example: wait till there are no outstanding requests anymore:
		1417
		1418	IO::AIO::poll_wait, IO::AIO::poll_cb
		1419	while IO::AIO::nreqs;
		1420
		1421	=item IO::AIO::nready
		1422
		1423	Returns the number of requests currently in the ready state (not yet
		1424	executed).
		1425
		1426	=item IO::AIO::npending
		1427
		1428	Returns the number of requests currently in the pending state (executed,
		1429	but not yet processed by poll_cb).
		1430
		1431	=back
		1432
		1433	=head3 MISCELLANEOUS FUNCTIONS
		1434
		1435	IO::AIO implements some functions that might be useful, but are not
		1436	asynchronous.
		1437
		1438	=over 4
		1439
		1440	=item IO::AIO::sendfile $ofh, $ifh, $offset, $count
		1441
		1442	Calls the C<eio_sendfile_sync> function, which is like C<aio_sendfile>,
		1443	but is blocking (this makes most sense if you know the input data is
		1444	likely cached already and the output filehandle is set to non-blocking
		1445	operations).
		1446
		1447	Returns the number of bytes copied, or C<-1> on error.
		1448
		1449	=item IO::AIO::fadvise $fh, $offset, $len, $advice
		1450
		1451	Simply calls the C<posix_fadvise> function (see it's
		1452	manpage for details). The following advice constants are
		1453	avaiable: C<IO::AIO::FADV_NORMAL>, C<IO::AIO::FADV_SEQUENTIAL>,
		1454	C<IO::AIO::FADV_RANDOM>, C<IO::AIO::FADV_NOREUSE>,
		1455	C<IO::AIO::FADV_WILLNEED>, C<IO::AIO::FADV_DONTNEED>.
		1456
		1457	On systems that do not implement C<posix_fadvise>, this function returns
		1458	ENOSYS, otherwise the return value of C<posix_fadvise>.
		1459
		1460	=back
		1461
863	=cut	1462	=cut
864		1463
865	# support function to convert a fd into a perl filehandle
866	sub _fd2fh {
867	return undef if $_[0] < 0;
868
869	# try to generate nice filehandles
870	my $sym = "IO::AIO::fd#$_[0]";
871	local *$sym;
872
873	open *$sym, "+<&=$_[0]" # usually works under any unix
874	or open *$sym, "<&=$_[0]" # cygwin needs this
875	or open *$sym, ">&=$_[0]" # or this
876	or return undef;
877
878	*$sym
879	}
880
881	min_parallel 8;	1464	min_parallel 8;
882		1465
883	END {	1466	END { flush }
884	max_parallel 0;
885	}
886		1467
887	1;	1468	1;
888		1469
889	=head2 FORK BEHAVIOUR	1470	=head2 FORK BEHAVIOUR
890		1471
891	This module should do "the right thing" when the process using it forks:	1472	This module should do "the right thing" when the process using it forks:
892		1473
893	Before the fork, IO::AIO enters a quiescent state where no requests	1474	Before the fork, IO::AIO enters a quiescent state where no requests
894	can be added in other threads and no results will be processed. After	1475	can be added in other threads and no results will be processed. After
895	the fork the parent simply leaves the quiescent state and continues	1476	the fork the parent simply leaves the quiescent state and continues
896	request/result processing, while the child clears the request/result	1477	request/result processing, while the child frees the request/result queue
897	queue (so the requests started before the fork will only be handled in	1478	(so that the requests started before the fork will only be handled in the
898	the parent). Threads will be started on demand until the limit ste in the	1479	parent). Threads will be started on demand until the limit set in the
899	parent process has been reached again.	1480	parent process has been reached again.
900		1481
901	In short: the parent will, after a short pause, continue as if fork had	1482	In short: the parent will, after a short pause, continue as if fork had
902	not been called, while the child will act as if IO::AIO has not been used	1483	not been called, while the child will act as if IO::AIO has not been used
903	yet.	1484	yet.
904		1485
905	=head2 MEMORY USAGE	1486	=head2 MEMORY USAGE
906		1487
		1488	Per-request usage:
		1489
907	Each aio request uses - depending on your architecture - around 128 bytes	1490	Each aio request uses - depending on your architecture - around 100-200
908	of memory. In addition, stat requests need a stat buffer (possibly a few	1491	bytes of memory. In addition, stat requests need a stat buffer (possibly
909	hundred bytes). Perl scalars and other data passed into aio requests will	1492	a few hundred bytes), readdir requires a result buffer and so on. Perl
910	also be locked.	1493	scalars and other data passed into aio requests will also be locked and
		1494	will consume memory till the request has entered the done state.
911		1495
912	This is now awfully much, so queuing lots of requests is not usually a	1496	This is not awfully much, so queuing lots of requests is not usually a
913	problem.	1497	problem.
914		1498
915	Each thread needs a stack area which is usually around 16k, sometimes much	1499	Per-thread usage:
916	larger, depending on the OS.	1500
		1501	In the execution phase, some aio requests require more memory for
		1502	temporary buffers, and each thread requires a stack and other data
		1503	structures (usually around 16k-128k, depending on the OS).
		1504
		1505	=head1 KNOWN BUGS
		1506
		1507	Known bugs will be fixed in the next release.
917		1508
918	=head1 SEE ALSO	1509	=head1 SEE ALSO
919		1510
920	L<Coro::AIO>.	1511	L<AnyEvent::AIO> for easy integration into event loops, L<Coro::AIO> for a
		1512	more natural syntax.
921		1513
922	=head1 AUTHOR	1514	=head1 AUTHOR
923		1515
924	Marc Lehmann <schmorp@schmorp.de>	1516	Marc Lehmann <schmorp@schmorp.de>
925	http://home.schmorp.de/	1517	http://home.schmorp.de/

Diff Legend

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