[ViewVC] Diff of: cvs/IO-AIO/AIO.pm

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.33 by root, Wed Aug 17 06:12:10 2005 UTC vs.
Revision 1.100 by root, Sun Jan 7 21:36:58 2007 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
16	aio_read $fh, 30000, 1024, $buffer, 0, sub {	17	aio_read $fh, 30000, 1024, $buffer, 0, sub {
17	$_[0] > 0 or die "read error: $!";	18	$_[0] > 0 or die "read error: $!";
18	};	19	};
19		20
20	# Event	21	# version 2+ has request and group objects
		22	use IO::AIO 2;
		23
		24	aioreq_pri 4; # give next request a very high priority
		25	my $req = aio_unlink "/tmp/file", sub { };
		26	$req->cancel; # cancel request if still in queue
		27
		28	my $grp = aio_group sub { print "all stats done\n" };
		29	add $grp aio_stat "..." for ...;
		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
21	Event->io (fd => IO::AIO::poll_fileno,	36	Event->io (fd => IO::AIO::poll_fileno,
22	poll => 'r',	37	poll => 'r',
23	cb => \&IO::AIO::poll_cb);	38	cb => \&IO::AIO::poll_cb);
24		39
25	# Glib/Gtk2	40	# Glib/Gtk2 integration
26	add_watch Glib::IO IO::AIO::poll_fileno,	41	add_watch Glib::IO IO::AIO::poll_fileno,
27	in => sub { IO::AIO::poll_cb; 1 };	42	in => sub { IO::AIO::poll_cb; 1 };
28		43
29	# Tk	44	# Tk integration
30	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",	45	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
31	readable => \&IO::AIO::poll_cb);	46	readable => \&IO::AIO::poll_cb);
32		47
33	# Danga::Socket	48	# Danga::Socket integration
34	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>	49	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
35	\&IO::AIO::poll_cb);	50	\&IO::AIO::poll_cb);
36		51
37
38	=head1 DESCRIPTION	52	=head1 DESCRIPTION
39		53
40	This module implements asynchronous I/O using whatever means your	54	This module implements asynchronous I/O using whatever means your
41	operating system supports.	55	operating system supports.
42		56
		57	Asynchronous means that operations that can normally block your program
		58	(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
		60	is extremely useful for programs that need to stay interactive even
		61	when doing heavy I/O (GUI programs, high performance network servers
		62	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
		64	on a RAID volume or over NFS when you do a number of stat operations
		65	concurrently.
		66
		67	While most of this works on all types of file descriptors (for example
		68	sockets), using these functions on file descriptors that support
		69	nonblocking operation (again, sockets, pipes etc.) is very inefficient or
		70	might not work (aio_read fails on sockets/pipes/fifos). Use an event loop
		71	for that (such as the L<Event\|Event> module): IO::AIO will naturally fit
		72	into such an event loop itself.
		73
43	Currently, a number of threads are started that execute your read/writes	74	In this version, a number of threads are started that execute your
44	and signal their completion. You don't need thread support in your libc or	75	requests and signal their completion. You don't need thread support
45	perl, and the threads created by this module will not be visible to the	76	in perl, and the threads created by this module will not be visible
46	pthreads library. In the future, this module might make use of the native	77	to perl. In the future, this module might make use of the native aio
47	aio functions available on many operating systems. However, they are often	78	functions available on many operating systems. However, they are often
48	not well-supported (Linux doesn't allow them on normal files currently,	79	not well-supported or restricted (GNU/Linux doesn't allow them on normal
49	for example), and they would only support aio_read and aio_write, so the	80	files currently, for example), and they would only support aio_read and
50	remaining functionality would have to be implemented using threads anyway.	81	aio_write, so the remaining functionality would have to be implemented
		82	using threads anyway.
51		83
52	Although the module will work with in the presence of other threads, it is	84	Although the module will work with in the presence of other (Perl-)
53	currently not reentrant, so use appropriate locking yourself, always call	85	threads, it is currently not reentrant in any way, so use appropriate
54	C<poll_cb> from within the same thread, or never call C<poll_cb> (or other	86	locking yourself, always call C<poll_cb> from within the same thread, or
55	C<aio_> functions) recursively.	87	never call C<poll_cb> (or other C<aio_> functions) recursively.
		88
		89	=head2 EXAMPLE
		90
		91	This is a simple example that uses the Event module and loads
		92	F</etc/passwd> asynchronously:
		93
		94	use Fcntl;
		95	use Event;
		96	use IO::AIO;
		97
		98	# register the IO::AIO callback with Event
		99	Event->io (fd => IO::AIO::poll_fileno,
		100	poll => 'r',
		101	cb => \&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	Event::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	Event::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
56		184
57	=cut	185	=cut
58		186
59	package IO::AIO;	187	package IO::AIO;
60		188
61	no warnings;	189	no warnings;
		190	use strict 'vars';
62		191
63	use base 'Exporter';	192	use base 'Exporter';
64		193
65	use Fcntl ();
66
67	BEGIN {	194	BEGIN {
68	$VERSION = 1.4;	195	our $VERSION = '2.32';
69		196
70	@EXPORT = qw(aio_read aio_write aio_open aio_close aio_stat aio_lstat aio_unlink	197	our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat
		198	aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink
71	aio_rmdir aio_symlink aio_fsync aio_fdatasync aio_readahead);	199	aio_readlink aio_fsync aio_fdatasync aio_readahead aio_rename aio_link
72	@EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs);	200	aio_move aio_copy aio_group aio_nop aio_mknod aio_load aio_rmtree);
		201	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice aio_block));
		202	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush
		203	min_parallel max_parallel max_idle
		204	nreqs nready npending nthreads
		205	max_poll_time max_poll_reqs);
		206
		207	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';
73		208
74	require XSLoader;	209	require XSLoader;
75	XSLoader::load IO::AIO, $VERSION;	210	XSLoader::load ("IO::AIO", $VERSION);
76	}	211	}
77		212
78	=head1 FUNCTIONS	213	=head1 FUNCTIONS
79		214
80	=head2 AIO FUNCTIONS	215	=head2 AIO REQUEST FUNCTIONS
81		216
82	All the C<aio_*> calls are more or less thin wrappers around the syscall	217	All the C<aio_*> calls are more or less thin wrappers around the syscall
83	with the same name (sans C<aio_>). The arguments are similar or identical,	218	with the same name (sans C<aio_>). The arguments are similar or identical,
84	and they all accept an additional (and optional) C<$callback> argument	219	and they all accept an additional (and optional) C<$callback> argument
85	which must be a code reference. This code reference will get called with	220	which must be a code reference. This code reference will get called with
…		…
88	syscall has been executed asynchronously.	223	syscall has been executed asynchronously.
89		224
90	All functions expecting a filehandle keep a copy of the filehandle	225	All functions expecting a filehandle keep a copy of the filehandle
91	internally until the request has finished.	226	internally until the request has finished.
92		227
		228	All functions return request objects of type L<IO::AIO::REQ> that allow
		229	further manipulation of those requests while they are in-flight.
		230
93	The pathnames you pass to these routines I<must> be absolute and	231	The pathnames you pass to these routines I<must> be absolute and
94	encoded in byte form. The reason for the former is that at the time the	232	encoded as octets. The reason for the former is that at the time the
95	request is being executed, the current working directory could have	233	request is being executed, the current working directory could have
96	changed. Alternatively, you can make sure that you never change the	234	changed. Alternatively, you can make sure that you never change the
97	current working directory.	235	current working directory anywhere in the program and then use relative
		236	paths.
98		237
99	To encode pathnames to byte form, either make sure you either: a)	238	To encode pathnames as octets, either make sure you either: a) always pass
100	always pass in filenames you got from outside (command line, readdir	239	in filenames you got from outside (command line, readdir etc.) without
101	etc.), b) are ASCII or ISO 8859-1, c) use the Encode module and encode	240	tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module and encode
102	your pathnames to the locale (or other) encoding in effect in the user	241	your pathnames to the locale (or other) encoding in effect in the user
103	environment, d) use Glib::filename_from_unicode on unicode filenames or e)	242	environment, d) use Glib::filename_from_unicode on unicode filenames or e)
104	use something else.	243	use something else to ensure your scalar has the correct contents.
		244
		245	This works, btw. independent of the internal UTF-8 bit, which IO::AIO
		246	handles correctly wether it is set or not.
105		247
106	=over 4	248	=over 4
107		249
		250	=item $prev_pri = aioreq_pri [$pri]
		251
		252	Returns the priority value that would be used for the next request and, if
		253	C<$pri> is given, sets the priority for the next aio request.
		254
		255	The default priority is C<0>, the minimum and maximum priorities are C<-4>
		256	and C<4>, respectively. Requests with higher priority will be serviced
		257	first.
		258
		259	The priority will be reset to C<0> after each call to one of the C<aio_*>
		260	functions.
		261
		262	Example: open a file with low priority, then read something from it with
		263	higher priority so the read request is serviced before other low priority
		264	open requests (potentially spamming the cache):
		265
		266	aioreq_pri -3;
		267	aio_open ..., sub {
		268	return unless $_[0];
		269
		270	aioreq_pri -2;
		271	aio_read $_[0], ..., sub {
		272	...
		273	};
		274	};
		275
		276	=item aioreq_nice $pri_adjust
		277
		278	Similar to C<aioreq_pri>, but subtracts the given value from the current
		279	priority, so the effect is cumulative.
		280
108	=item aio_open $pathname, $flags, $mode, $callback	281	=item aio_open $pathname, $flags, $mode, $callback->($fh)
109		282
110	Asynchronously open or create a file and call the callback with a newly	283	Asynchronously open or create a file and call the callback with a newly
111	created filehandle for the file.	284	created filehandle for the file.
112		285
113	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,	286	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,
…		…
130	} else {	303	} else {
131	die "open failed: $!\n";	304	die "open failed: $!\n";
132	}	305	}
133	};	306	};
134		307
135	=item aio_close $fh, $callback	308	=item aio_close $fh, $callback->($status)
136		309
137	Asynchronously close a file and call the callback with the result	310	Asynchronously close a file and call the callback with the result
138	code. I<WARNING:> although accepted, you should not pass in a perl	311	code. I<WARNING:> although accepted, you should not pass in a perl
139	filehandle here, as perl will likely close the file descriptor another	312	filehandle here, as perl will likely close the file descriptor another
140	time when the filehandle is destroyed. Normally, you can safely call perls	313	time when the filehandle is destroyed. Normally, you can safely call perls
141	C<close> or just let filehandles go out of scope.	314	C<close> or just let filehandles go out of scope.
142		315
143	This is supposed to be a bug in the API, so that might change. It's	316	This is supposed to be a bug in the API, so that might change. It's
144	therefore best to avoid this function.	317	therefore best to avoid this function.
145		318
146	=item aio_read $fh,$offset,$length, $data,$dataoffset,$callback	319	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
147		320
148	=item aio_write $fh,$offset,$length, $data,$dataoffset,$callback	321	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
149		322
150	Reads or writes C<length> bytes from the specified C<fh> and C<offset>	323	Reads or writes C<length> bytes from the specified C<fh> and C<offset>
151	into the scalar given by C<data> and offset C<dataoffset> and calls the	324	into the scalar given by C<data> and offset C<dataoffset> and calls the
152	callback without the actual number of bytes read (or -1 on error, just	325	callback without the actual number of bytes read (or -1 on error, just
153	like the syscall).	326	like the syscall).
…		…
162	aio_read $fh, 7, 15, $buffer, 0, sub {	335	aio_read $fh, 7, 15, $buffer, 0, sub {
163	$_[0] > 0 or die "read error: $!";	336	$_[0] > 0 or die "read error: $!";
164	print "read $_[0] bytes: <$buffer>\n";	337	print "read $_[0] bytes: <$buffer>\n";
165	};	338	};
166		339
		340	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
		341
		342	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
		344	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
		346	other.
		347
		348	This call tries to make use of a native C<sendfile> syscall to provide
		349	zero-copy operation. For this to work, C<$out_fh> should refer to a
		350	socket, and C<$in_fh> should refer to mmap'able file.
		351
		352	If the native sendfile call fails or is not implemented, it will be
		353	emulated, so you can call C<aio_sendfile> on any type of filehandle
		354	regardless of the limitations of the operating system.
		355
		356	Please note, however, that C<aio_sendfile> can read more bytes from
		357	C<$in_fh> than are written, and there is no way to find out how many
		358	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only
		359	provides the number of bytes written to C<$out_fh>. Only if the result
		360	value equals C<$length> one can assume that C<$length> bytes have been
		361	read.
		362
167	=item aio_readahead $fh,$offset,$length, $callback	363	=item aio_readahead $fh,$offset,$length, $callback->($retval)
168		364
169	C<aio_readahead> populates the page cache with data from a file so that	365	C<aio_readahead> populates the page cache with data from a file so that
170	subsequent reads from that file will not block on disk I/O. The C<$offset>	366	subsequent reads from that file will not block on disk I/O. The C<$offset>
171	argument specifies the starting point from which data is to be read and	367	argument specifies the starting point from which data is to be read and
172	C<$length> specifies the number of bytes to be read. I/O is performed in	368	C<$length> specifies the number of bytes to be read. I/O is performed in
…		…
176	file. The current file offset of the file is left unchanged.	372	file. The current file offset of the file is left unchanged.
177		373
178	If that syscall doesn't exist (likely if your OS isn't Linux) it will be	374	If that syscall doesn't exist (likely if your OS isn't Linux) it will be
179	emulated by simply reading the data, which would have a similar effect.	375	emulated by simply reading the data, which would have a similar effect.
180		376
181	=item aio_stat $fh_or_path, $callback	377	=item aio_stat $fh_or_path, $callback->($status)
182		378
183	=item aio_lstat $fh, $callback	379	=item aio_lstat $fh, $callback->($status)
184		380
185	Works like perl's C<stat> or C<lstat> in void context. The callback will	381	Works like perl's C<stat> or C<lstat> in void context. The callback will
186	be called after the stat and the results will be available using C<stat _>	382	be called after the stat and the results will be available using C<stat _>
187	or C<-s _> etc...	383	or C<-s _> etc...
188		384
…		…
198	aio_stat "/etc/passwd", sub {	394	aio_stat "/etc/passwd", sub {
199	$_[0] and die "stat failed: $!";	395	$_[0] and die "stat failed: $!";
200	print "size is ", -s _, "\n";	396	print "size is ", -s _, "\n";
201	};	397	};
202		398
203	=item aio_unlink $pathname, $callback	399	=item aio_unlink $pathname, $callback->($status)
204		400
205	Asynchronously unlink (delete) a file and call the callback with the	401	Asynchronously unlink (delete) a file and call the callback with the
206	result code.	402	result code.
207		403
		404	=item aio_mknod $path, $mode, $dev, $callback->($status)
		405
		406	[EXPERIMENTAL]
		407
		408	Asynchronously create a device node (or fifo). See mknod(2).
		409
		410	The only (POSIX-) portable way of calling this function is:
		411
		412	aio_mknod $path, IO::AIO::S_IFIFO \| $mode, 0, sub { ...
		413
		414	=item aio_link $srcpath, $dstpath, $callback->($status)
		415
		416	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.
		418
		419	=item aio_symlink $srcpath, $dstpath, $callback->($status)
		420
		421	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.
		423
		424	=item aio_readlink $path, $callback->($link)
		425
		426	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
		428	callback.
		429
		430	=item aio_rename $srcpath, $dstpath, $callback->($status)
		431
		432	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as
		433	rename(2) and call the callback with the result code.
		434
208	=item aio_rmdir $pathname, $callback	435	=item aio_rmdir $pathname, $callback->($status)
209		436
210	Asynchronously rmdir (delete) a directory and call the callback with the	437	Asynchronously rmdir (delete) a directory and call the callback with the
211	result code.	438	result code.
212		439
		440	=item aio_readdir $pathname, $callback->($entries)
		441
		442	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
		444	sorted, and will B<NOT> include the C<.> and C<..> entries.
		445
		446	The callback a single argument which is either C<undef> or an array-ref
		447	with the filenames.
		448
		449	=item aio_load $path, $data, $callback->($status)
		450
		451	This is a composite request that tries to fully load the given file into
		452	memory. Status is the same as with aio_read.
		453
		454	=cut
		455
		456	sub aio_load($$;$) {
		457	aio_block {
		458	my ($path, undef, $cb) = @_;
		459	my $data = \$_[1];
		460
		461	my $pri = aioreq_pri;
		462	my $grp = aio_group $cb;
		463
		464	aioreq_pri $pri;
		465	add $grp aio_open $path, O_RDONLY, 0, sub {
		466	my ($fh) = @_
		467	or return $grp->result (-1);
		468
		469	aioreq_pri $pri;
		470	add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub {
		471	$grp->result ($_[0]);
		472	};
		473	};
		474
		475	$grp
		476	}
		477	}
		478
		479	=item aio_copy $srcpath, $dstpath, $callback->($status)
		480
		481	Try to copy the I<file> (directories not supported as either source or
		482	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		483	the C<0> (error) or C<-1> ok.
		484
		485	This is a composite request that it creates the destination file with
		486	mode 0200 and copies the contents of the source file into it using
		487	C<aio_sendfile>, followed by restoring atime, mtime, access mode and
		488	uid/gid, in that order.
		489
		490	If an error occurs, the partial destination file will be unlinked, if
		491	possible, except when setting atime, mtime, access mode and uid/gid, where
		492	errors are being ignored.
		493
		494	=cut
		495
		496	sub aio_copy($$;$) {
		497	aio_block {
		498	my ($src, $dst, $cb) = @_;
		499
		500	my $pri = aioreq_pri;
		501	my $grp = aio_group $cb;
		502
		503	aioreq_pri $pri;
		504	add $grp aio_open $src, O_RDONLY, 0, sub {
		505	if (my $src_fh = $_[0]) {
		506	my @stat = stat $src_fh;
		507
		508	aioreq_pri $pri;
		509	add $grp aio_open $dst, O_CREAT \| O_WRONLY \| O_TRUNC, 0200, sub {
		510	if (my $dst_fh = $_[0]) {
		511	aioreq_pri $pri;
		512	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
		513	if ($_[0] == $stat[7]) {
		514	$grp->result (0);
		515	close $src_fh;
		516
		517	# those should not normally block. should. should.
		518	utime $stat[8], $stat[9], $dst;
		519	chmod $stat[2] & 07777, $dst_fh;
		520	chown $stat[4], $stat[5], $dst_fh;
		521	close $dst_fh;
		522	} else {
		523	$grp->result (-1);
		524	close $src_fh;
		525	close $dst_fh;
		526
		527	aioreq $pri;
		528	add $grp aio_unlink $dst;
		529	}
		530	};
		531	} else {
		532	$grp->result (-1);
		533	}
		534	},
		535
		536	} else {
		537	$grp->result (-1);
		538	}
		539	};
		540
		541	$grp
		542	}
		543	}
		544
		545	=item aio_move $srcpath, $dstpath, $callback->($status)
		546
		547	Try to move the I<file> (directories not supported as either source or
		548	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		549	the C<0> (error) or C<-1> ok.
		550
		551	This is a composite request that tries to rename(2) the file first. If
		552	rename files with C<EXDEV>, it copies the file with C<aio_copy> and, if
		553	that is successful, unlinking the C<$srcpath>.
		554
		555	=cut
		556
		557	sub aio_move($$;$) {
		558	aio_block {
		559	my ($src, $dst, $cb) = @_;
		560
		561	my $pri = aioreq_pri;
		562	my $grp = aio_group $cb;
		563
		564	aioreq_pri $pri;
		565	add $grp aio_rename $src, $dst, sub {
		566	if ($_[0] && $! == EXDEV) {
		567	aioreq_pri $pri;
		568	add $grp aio_copy $src, $dst, sub {
		569	$grp->result ($_[0]);
		570
		571	if (!$_[0]) {
		572	aioreq_pri $pri;
		573	add $grp aio_unlink $src;
		574	}
		575	};
		576	} else {
		577	$grp->result ($_[0]);
		578	}
		579	};
		580
		581	$grp
		582	}
		583	}
		584
		585	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
		586
		587	Scans a directory (similar to C<aio_readdir>) but additionally tries to
		588	efficiently separate the entries of directory C<$path> into two sets of
		589	names, directories you can recurse into (directories), and ones you cannot
		590	recurse into (everything else, including symlinks to directories).
		591
		592	C<aio_scandir> is a composite request that creates of many sub requests_
		593	C<$maxreq> specifies the maximum number of outstanding aio requests that
		594	this function generates. If it is C<< <= 0 >>, then a suitable default
		595	will be chosen (currently 4).
		596
		597	On error, the callback is called without arguments, otherwise it receives
		598	two array-refs with path-relative entry names.
		599
		600	Example:
		601
		602	aio_scandir $dir, 0, sub {
		603	my ($dirs, $nondirs) = @_;
		604	print "real directories: @$dirs\n";
		605	print "everything else: @$nondirs\n";
		606	};
		607
		608	Implementation notes.
		609
		610	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.
		611
		612	After reading the directory, the modification time, size etc. of the
		613	directory before and after the readdir is checked, and if they match (and
		614	isn't the current time), the link count will be used to decide how many
		615	entries are directories (if >= 2). Otherwise, no knowledge of the number
		616	of subdirectories will be assumed.
		617
		618	Then entries will be sorted into likely directories (everything without
		619	a non-initial dot currently) and likely non-directories (everything
		620	else). Then every entry plus an appended C</.> will be C<stat>'ed,
		621	likely directories first. If that succeeds, it assumes that the entry
		622	is a directory or a symlink to directory (which will be checked
		623	seperately). This is often faster than stat'ing the entry itself because
		624	filesystems might detect the type of the entry without reading the inode
		625	data (e.g. ext2fs filetype feature).
		626
		627	If the known number of directories (link count - 2) has been reached, the
		628	rest of the entries is assumed to be non-directories.
		629
		630	This only works with certainty on POSIX (= UNIX) filesystems, which
		631	fortunately are the vast majority of filesystems around.
		632
		633	It will also likely work on non-POSIX filesystems with reduced efficiency
		634	as those tend to return 0 or 1 as link counts, which disables the
		635	directory counting heuristic.
		636
		637	=cut
		638
		639	sub aio_scandir($$;$) {
		640	aio_block {
		641	my ($path, $maxreq, $cb) = @_;
		642
		643	my $pri = aioreq_pri;
		644
		645	my $grp = aio_group $cb;
		646
		647	$maxreq = 4 if $maxreq <= 0;
		648
		649	# stat once
		650	aioreq_pri $pri;
		651	add $grp aio_stat $path, sub {
		652	return $grp->result () if $_[0];
		653	my $now = time;
		654	my $hash1 = join ":", (stat _)[0,1,3,7,9];
		655
		656	# read the directory entries
		657	aioreq_pri $pri;
		658	add $grp aio_readdir $path, sub {
		659	my $entries = shift
		660	or return $grp->result ();
		661
		662	# stat the dir another time
		663	aioreq_pri $pri;
		664	add $grp aio_stat $path, sub {
		665	my $hash2 = join ":", (stat _)[0,1,3,7,9];
		666
		667	my $ndirs;
		668
		669	# take the slow route if anything looks fishy
		670	if ($hash1 ne $hash2 or (stat _)[9] == $now) {
		671	$ndirs = -1;
		672	} else {
		673	# if nlink == 2, we are finished
		674	# on non-posix-fs's, we rely on nlink < 2
		675	$ndirs = (stat _)[3] - 2
		676	or return $grp->result ([], $entries);
		677	}
		678
		679	# sort into likely dirs and likely nondirs
		680	# dirs == files without ".", short entries first
		681	$entries = [map $_->[0],
		682	sort { $b->[1] cmp $a->[1] }
		683	map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],
		684	@$entries];
		685
		686	my (@dirs, @nondirs);
		687
		688	my $statgrp = add $grp aio_group sub {
		689	$grp->result (\@dirs, \@nondirs);
		690	};
		691
		692	limit $statgrp $maxreq;
		693	feed $statgrp sub {
		694	return unless @$entries;
		695	my $entry = pop @$entries;
		696
		697	aioreq_pri $pri;
		698	add $statgrp aio_stat "$path/$entry/.", sub {
		699	if ($_[0] < 0) {
		700	push @nondirs, $entry;
		701	} else {
		702	# need to check for real directory
		703	aioreq_pri $pri;
		704	add $statgrp aio_lstat "$path/$entry", sub {
		705	if (-d _) {
		706	push @dirs, $entry;
		707
		708	unless (--$ndirs) {
		709	push @nondirs, @$entries;
		710	feed $statgrp;
		711	}
		712	} else {
		713	push @nondirs, $entry;
		714	}
		715	}
		716	}
		717	};
		718	};
		719	};
		720	};
		721	};
		722
		723	$grp
		724	}
		725	}
		726
		727	=item aio_rmtree $path, $callback->($status)
		728
		729	Delete a directory tree starting (and including) C<$path>, return the
		730	status of the final C<rmdir> only. This is a composite request that
		731	uses C<aio_scandir> to recurse into and rmdir directories, and unlink
		732	everything else.
		733
		734	=cut
		735
		736	sub aio_rmtree;
		737	sub aio_rmtree($;$) {
		738	aio_block {
		739	my ($path, $cb) = @_;
		740
		741	my $pri = aioreq_pri;
		742	my $grp = aio_group $cb;
		743
		744	aioreq_pri $pri;
		745	add $grp aio_scandir $path, 0, sub {
		746	my ($dirs, $nondirs) = @_;
		747
		748	my $dirgrp = aio_group sub {
		749	add $grp aio_rmdir $path, sub {
		750	$grp->result ($_[0]);
		751	};
		752	};
		753
		754	(aioreq_pri $pri), add $dirgrp aio_rmtree "$path/$_" for @$dirs;
		755	(aioreq_pri $pri), add $dirgrp aio_unlink "$path/$_" for @$nondirs;
		756
		757	add $grp $dirgrp;
		758	};
		759
		760	$grp
		761	}
		762	}
		763
213	=item aio_fsync $fh, $callback	764	=item aio_fsync $fh, $callback->($status)
214		765
215	Asynchronously call fsync on the given filehandle and call the callback	766	Asynchronously call fsync on the given filehandle and call the callback
216	with the fsync result code.	767	with the fsync result code.
217		768
218	=item aio_fdatasync $fh, $callback	769	=item aio_fdatasync $fh, $callback->($status)
219		770
220	Asynchronously call fdatasync on the given filehandle and call the	771	Asynchronously call fdatasync on the given filehandle and call the
221	callback with the fdatasync result code.	772	callback with the fdatasync result code.
222		773
223	If this call isn't available because your OS lacks it or it couldn't be	774	If this call isn't available because your OS lacks it or it couldn't be
224	detected, it will be emulated by calling C<fsync> instead.	775	detected, it will be emulated by calling C<fsync> instead.
225		776
		777	=item aio_group $callback->(...)
		778
		779	This is a very special aio request: Instead of doing something, it is a
		780	container for other aio requests, which is useful if you want to bundle
		781	many requests into a single, composite, request with a definite callback
		782	and the ability to cancel the whole request with its subrequests.
		783
		784	Returns an object of class L<IO::AIO::GRP>. See its documentation below
		785	for more info.
		786
		787	Example:
		788
		789	my $grp = aio_group sub {
		790	print "all stats done\n";
		791	};
		792
		793	add $grp
		794	(aio_stat ...),
		795	(aio_stat ...),
		796	...;
		797
		798	=item aio_nop $callback->()
		799
		800	This is a special request - it does nothing in itself and is only used for
		801	side effects, such as when you want to add a dummy request to a group so
		802	that finishing the requests in the group depends on executing the given
		803	code.
		804
		805	While this request does nothing, it still goes through the execution
		806	phase and still requires a worker thread. Thus, the callback will not
		807	be executed immediately but only after other requests in the queue have
		808	entered their execution phase. This can be used to measure request
		809	latency.
		810
		811	=item IO::AIO::aio_busy $fractional_seconds, $callback->() NOT EXPORTED
		812
		813	Mainly used for debugging and benchmarking, this aio request puts one of
		814	the request workers to sleep for the given time.
		815
		816	While it is theoretically handy to have simple I/O scheduling requests
		817	like sleep and file handle readable/writable, the overhead this creates is
		818	immense (it blocks a thread for a long time) so do not use this function
		819	except to put your application under artificial I/O pressure.
		820
226	=back	821	=back
227		822
		823	=head2 IO::AIO::REQ CLASS
		824
		825	All non-aggregate C<aio_*> functions return an object of this class when
		826	called in non-void context.
		827
		828	=over 4
		829
		830	=item cancel $req
		831
		832	Cancels the request, if possible. Has the effect of skipping execution
		833	when entering the B<execute> state and skipping calling the callback when
		834	entering the the B<result> state, but will leave the request otherwise
		835	untouched. That means that requests that currently execute will not be
		836	stopped and resources held by the request will not be freed prematurely.
		837
		838	=item cb $req $callback->(...)
		839
		840	Replace (or simply set) the callback registered to the request.
		841
		842	=back
		843
		844	=head2 IO::AIO::GRP CLASS
		845
		846	This class is a subclass of L<IO::AIO::REQ>, so all its methods apply to
		847	objects of this class, too.
		848
		849	A IO::AIO::GRP object is a special request that can contain multiple other
		850	aio requests.
		851
		852	You create one by calling the C<aio_group> constructing function with a
		853	callback that will be called when all contained requests have entered the
		854	C<done> state:
		855
		856	my $grp = aio_group sub {
		857	print "all requests are done\n";
		858	};
		859
		860	You add requests by calling the C<add> method with one or more
		861	C<IO::AIO::REQ> objects:
		862
		863	$grp->add (aio_unlink "...");
		864
		865	add $grp aio_stat "...", sub {
		866	$_[0] or return $grp->result ("error");
		867
		868	# add another request dynamically, if first succeeded
		869	add $grp aio_open "...", sub {
		870	$grp->result ("ok");
		871	};
		872	};
		873
		874	This makes it very easy to create composite requests (see the source of
		875	C<aio_move> for an application) that work and feel like simple requests.
		876
		877	=over 4
		878
		879	=item * The IO::AIO::GRP objects will be cleaned up during calls to
		880	C<IO::AIO::poll_cb>, just like any other request.
		881
		882	=item * They can be canceled like any other request. Canceling will cancel not
		883	only the request itself, but also all requests it contains.
		884
		885	=item * They can also can also be added to other IO::AIO::GRP objects.
		886
		887	=item * You must not add requests to a group from within the group callback (or
		888	any later time).
		889
		890	=back
		891
		892	Their lifetime, simplified, looks like this: when they are empty, they
		893	will finish very quickly. If they contain only requests that are in the
		894	C<done> state, they will also finish. Otherwise they will continue to
		895	exist.
		896
		897	That means after creating a group you have some time to add requests. And
		898	in the callbacks of those requests, you can add further requests to the
		899	group. And only when all those requests have finished will the the group
		900	itself finish.
		901
		902	=over 4
		903
		904	=item add $grp ...
		905
		906	=item $grp->add (...)
		907
		908	Add one or more requests to the group. Any type of L<IO::AIO::REQ> can
		909	be added, including other groups, as long as you do not create circular
		910	dependencies.
		911
		912	Returns all its arguments.
		913
		914	=item $grp->cancel_subs
		915
		916	Cancel all subrequests and clears any feeder, but not the group request
		917	itself. Useful when you queued a lot of events but got a result early.
		918
		919	=item $grp->result (...)
		920
		921	Set the result value(s) that will be passed to the group callback when all
		922	subrequests have finished and set thre groups errno to the current value
		923	of errno (just like calling C<errno> without an error number). By default,
		924	no argument will be passed and errno is zero.
		925
		926	=item $grp->errno ([$errno])
		927
		928	Sets the group errno value to C<$errno>, or the current value of errno
		929	when the argument is missing.
		930
		931	Every aio request has an associated errno value that is restored when
		932	the callback is invoked. This method lets you change this value from its
		933	default (0).
		934
		935	Calling C<result> will also set errno, so make sure you either set C<$!>
		936	before the call to C<result>, or call c<errno> after it.
		937
		938	=item feed $grp $callback->($grp)
		939
		940	Sets a feeder/generator on this group: every group can have an attached
		941	generator that generates requests if idle. The idea behind this is that,
		942	although you could just queue as many requests as you want in a group,
		943	this might starve other requests for a potentially long time. For
		944	example, C<aio_scandir> might generate hundreds of thousands C<aio_stat>
		945	requests, delaying any later requests for a long time.
		946
		947	To avoid this, and allow incremental generation of requests, you can
		948	instead a group and set a feeder on it that generates those requests. The
		949	feed callback will be called whenever there are few enough (see C<limit>,
		950	below) requests active in the group itself and is expected to queue more
		951	requests.
		952
		953	The feed callback can queue as many requests as it likes (i.e. C<add> does
		954	not impose any limits).
		955
		956	If the feed does not queue more requests when called, it will be
		957	automatically removed from the group.
		958
		959	If the feed limit is C<0>, it will be set to C<2> automatically.
		960
		961	Example:
		962
		963	# stat all files in @files, but only ever use four aio requests concurrently:
		964
		965	my $grp = aio_group sub { print "finished\n" };
		966	limit $grp 4;
		967	feed $grp sub {
		968	my $file = pop @files
		969	or return;
		970
		971	add $grp aio_stat $file, sub { ... };
		972	};
		973
		974	=item limit $grp $num
		975
		976	Sets the feeder limit for the group: The feeder will be called whenever
		977	the group contains less than this many requests.
		978
		979	Setting the limit to C<0> will pause the feeding process.
		980
		981	=back
		982
228	=head2 SUPPORT FUNCTIONS	983	=head2 SUPPORT FUNCTIONS
		984
		985	=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION
229		986
230	=over 4	987	=over 4
231		988
232	=item $fileno = IO::AIO::poll_fileno	989	=item $fileno = IO::AIO::poll_fileno
233		990
…		…
238		995
239	See C<poll_cb> for an example.	996	See C<poll_cb> for an example.
240		997
241	=item IO::AIO::poll_cb	998	=item IO::AIO::poll_cb
242		999
243	Process all outstanding events on the result pipe. You have to call this	1000	Process some outstanding events on the result pipe. You have to call this
244	regularly. Returns the number of events processed. Returns immediately	1001	regularly. Returns the number of events processed. Returns immediately
245	when no events are outstanding.	1002	when no events are outstanding. The amount of events processed depends on
		1003	the settings of C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>.
		1004
		1005	If not all requests were processed for whatever reason, the filehandle
		1006	will still be ready when C<poll_cb> returns.
246		1007
247	Example: Install an Event watcher that automatically calls	1008	Example: Install an Event watcher that automatically calls
248	IO::AIO::poll_cb with high priority:	1009	IO::AIO::poll_cb with high priority:
249		1010
250	Event->io (fd => IO::AIO::poll_fileno,	1011	Event->io (fd => IO::AIO::poll_fileno,
251	poll => 'r', async => 1,	1012	poll => 'r', async => 1,
252	cb => \&IO::AIO::poll_cb);	1013	cb => \&IO::AIO::poll_cb);
253		1014
		1015	=item IO::AIO::max_poll_reqs $nreqs
		1016
		1017	=item IO::AIO::max_poll_time $seconds
		1018
		1019	These set the maximum number of requests (default C<0>, meaning infinity)
		1020	that are being processed by C<IO::AIO::poll_cb> in one call, respectively
		1021	the maximum amount of time (default C<0>, meaning infinity) spent in
		1022	C<IO::AIO::poll_cb> to process requests (more correctly the mininum amount
		1023	of time C<poll_cb> is allowed to use).
		1024
		1025	Setting C<max_poll_time> to a non-zero value creates an overhead of one
		1026	syscall per request processed, which is not normally a problem unless your
		1027	callbacks are really really fast or your OS is really really slow (I am
		1028	not mentioning Solaris here). Using C<max_poll_reqs> incurs no overhead.
		1029
		1030	Setting these is useful if you want to ensure some level of
		1031	interactiveness when perl is not fast enough to process all requests in
		1032	time.
		1033
		1034	For interactive programs, values such as C<0.01> to C<0.1> should be fine.
		1035
		1036	Example: Install an Event watcher that automatically calls
		1037	IO::AIO::poll_cb with low priority, to ensure that other parts of the
		1038	program get the CPU sometimes even under high AIO load.
		1039
		1040	# try not to spend much more than 0.1s in poll_cb
		1041	IO::AIO::max_poll_time 0.1;
		1042
		1043	# use a low priority so other tasks have priority
		1044	Event->io (fd => IO::AIO::poll_fileno,
		1045	poll => 'r', nice => 1,
		1046	cb => &IO::AIO::poll_cb);
		1047
254	=item IO::AIO::poll_wait	1048	=item IO::AIO::poll_wait
255		1049
		1050	If there are any outstanding requests and none of them in the result
256	Wait till the result filehandle becomes ready for reading (simply does a	1051	phase, wait till the result filehandle becomes ready for reading (simply
257	C<select> on the filehandle. This is useful if you want to synchronously wait	1052	does a C<select> on the filehandle. This is useful if you want to
258	for some requests to finish).	1053	synchronously wait for some requests to finish).
259		1054
260	See C<nreqs> for an example.	1055	See C<nreqs> for an example.
261		1056
		1057	=item IO::AIO::poll
		1058
		1059	Waits until some requests have been handled.
		1060
		1061	Returns the number of requests processed, but is otherwise strictly
		1062	equivalent to:
		1063
		1064	IO::AIO::poll_wait, IO::AIO::poll_cb
		1065
262	=item IO::AIO::nreqs	1066	=item IO::AIO::flush
263		1067
264	Returns the number of requests currently outstanding (i.e. for which their	1068	Wait till all outstanding AIO requests have been handled.
265	callback has not been invoked yet).
266		1069
267	Example: wait till there are no outstanding requests anymore:	1070	Strictly equivalent to:
268		1071
269	IO::AIO::poll_wait, IO::AIO::poll_cb	1072	IO::AIO::poll_wait, IO::AIO::poll_cb
270	while IO::AIO::nreqs;	1073	while IO::AIO::nreqs;
271		1074
		1075	=head3 CONTROLLING THE NUMBER OF THREADS
		1076
		1077	=item IO::AIO::min_parallel $nthreads
		1078
		1079	Set the minimum number of AIO threads to C<$nthreads>. The current
		1080	default is C<8>, which means eight asynchronous operations can execute
		1081	concurrently at any one time (the number of outstanding requests,
		1082	however, is unlimited).
		1083
		1084	IO::AIO starts threads only on demand, when an AIO request is queued and
		1085	no free thread exists. Please note that queueing up a hundred requests can
		1086	create demand for a hundred threads, even if it turns out that everything
		1087	is in the cache and could have been processed faster by a single thread.
		1088
		1089	It is recommended to keep the number of threads relatively low, as some
		1090	Linux kernel versions will scale negatively with the number of threads
		1091	(higher parallelity => MUCH higher latency). With current Linux 2.6
		1092	versions, 4-32 threads should be fine.
		1093
		1094	Under most circumstances you don't need to call this function, as the
		1095	module selects a default that is suitable for low to moderate load.
		1096
		1097	=item IO::AIO::max_parallel $nthreads
		1098
		1099	Sets the maximum number of AIO threads to C<$nthreads>. If more than the
		1100	specified number of threads are currently running, this function kills
		1101	them. This function blocks until the limit is reached.
		1102
		1103	While C<$nthreads> are zero, aio requests get queued but not executed
		1104	until the number of threads has been increased again.
		1105
		1106	This module automatically runs C<max_parallel 0> at program end, to ensure
		1107	that all threads are killed and that there are no outstanding requests.
		1108
		1109	Under normal circumstances you don't need to call this function.
		1110
		1111	=item IO::AIO::max_idle $nthreads
		1112
		1113	Limit the number of threads (default: 4) that are allowed to idle (i.e.,
		1114	threads that did not get a request to process within 10 seconds). That
		1115	means if a thread becomes idle while C<$nthreads> other threads are also
		1116	idle, it will free its resources and exit.
		1117
		1118	This is useful when you allow a large number of threads (e.g. 100 or 1000)
		1119	to allow for extremely high load situations, but want to free resources
		1120	under normal circumstances (1000 threads can easily consume 30MB of RAM).
		1121
		1122	The default is probably ok in most situations, especially if thread
		1123	creation is fast. If thread creation is very slow on your system you might
		1124	want to use larger values.
		1125
		1126	=item $oldmaxreqs = IO::AIO::max_outstanding $maxreqs
		1127
		1128	This is a very bad function to use in interactive programs because it
		1129	blocks, and a bad way to reduce concurrency because it is inexact: Better
		1130	use an C<aio_group> together with a feed callback.
		1131
		1132	Sets the maximum number of outstanding requests to C<$nreqs>. If you
		1133	to queue up more than this number of requests, the next call to the
		1134	C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>)
		1135	function will block until the limit is no longer exceeded.
		1136
		1137	The default value is very large, so there is no practical limit on the
		1138	number of outstanding requests.
		1139
		1140	You can still queue as many requests as you want. Therefore,
		1141	C<max_oustsanding> is mainly useful in simple scripts (with low values) or
		1142	as a stop gap to shield against fatal memory overflow (with large values).
		1143
		1144	=head3 STATISTICAL INFORMATION
		1145
272	=item IO::AIO::flush	1146	=item IO::AIO::nreqs
273		1147
274	Wait till all outstanding AIO requests have been handled.	1148	Returns the number of requests currently in the ready, execute or pending
		1149	states (i.e. for which their callback has not been invoked yet).
275		1150
276	Strictly equivalent to:	1151	Example: wait till there are no outstanding requests anymore:
277		1152
278	IO::AIO::poll_wait, IO::AIO::poll_cb	1153	IO::AIO::poll_wait, IO::AIO::poll_cb
279	while IO::AIO::nreqs;	1154	while IO::AIO::nreqs;
280		1155
		1156	=item IO::AIO::nready
		1157
		1158	Returns the number of requests currently in the ready state (not yet
		1159	executed).
		1160
281	=item IO::AIO::poll	1161	=item IO::AIO::npending
282		1162
283	Waits until some requests have been handled.	1163	Returns the number of requests currently in the pending state (executed,
284		1164	but not yet processed by poll_cb).
285	Strictly equivalent to:
286
287	IO::AIO::poll_wait, IO::AIO::poll_cb
288	if IO::AIO::nreqs;
289
290	=item IO::AIO::min_parallel $nthreads
291
292	Set the minimum number of AIO threads to C<$nthreads>. The default is
293	C<1>, which means a single asynchronous operation can be done at one time
294	(the number of outstanding operations, however, is unlimited).
295
296	It is recommended to keep the number of threads low, as some Linux
297	kernel versions will scale negatively with the number of threads (higher
298	parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32
299	threads should be fine.
300
301	Under normal circumstances you don't need to call this function, as this
302	module automatically starts some threads (the exact number might change,
303	and is currently 4).
304
305	=item IO::AIO::max_parallel $nthreads
306
307	Sets the maximum number of AIO threads to C<$nthreads>. If more than
308	the specified number of threads are currently running, kill them. This
309	function blocks until the limit is reached.
310
311	This module automatically runs C<max_parallel 0> at program end, to ensure
312	that all threads are killed and that there are no outstanding requests.
313
314	Under normal circumstances you don't need to call this function.
315
316	=item $oldnreqs = IO::AIO::max_outstanding $nreqs
317
318	Sets the maximum number of outstanding requests to C<$nreqs>. If you
319	try to queue up more than this number of requests, the caller will block until
320	some requests have been handled.
321
322	The default is very large, so normally there is no practical limit. If you
323	queue up many requests in a loop it it often improves speed if you set
324	this to a relatively low number, such as C<100>.
325
326	Under normal circumstances you don't need to call this function.
327		1165
328	=back	1166	=back
329		1167
330	=cut	1168	=cut
331		1169
…		…
343	or return undef;	1181	or return undef;
344		1182
345	*$sym	1183	*$sym
346	}	1184	}
347		1185
348	min_parallel 4;	1186	min_parallel 8;
349		1187
350	END {	1188	END { flush }
351	max_parallel 0;
352	}
353		1189
354	1;	1190	1;
355		1191
356	=head2 FORK BEHAVIOUR	1192	=head2 FORK BEHAVIOUR
357		1193
		1194	This module should do "the right thing" when the process using it forks:
		1195
358	Before the fork IO::AIO enters a quiescent state where no requests can be	1196	Before the fork, IO::AIO enters a quiescent state where no requests
359	added in other threads and no results will be processed. After the fork	1197	can be added in other threads and no results will be processed. After
360	the parent simply leaves the quiescent state and continues request/result	1198	the fork the parent simply leaves the quiescent state and continues
361	processing, while the child clears the request/result queue and starts the	1199	request/result processing, while the child frees the request/result queue
362	same number of threads as were in use by the parent.	1200	(so that the requests started before the fork will only be handled in the
		1201	parent). Threads will be started on demand until the limit set in the
		1202	parent process has been reached again.
		1203
		1204	In short: the parent will, after a short pause, continue as if fork had
		1205	not been called, while the child will act as if IO::AIO has not been used
		1206	yet.
		1207
		1208	=head2 MEMORY USAGE
		1209
		1210	Per-request usage:
		1211
		1212	Each aio request uses - depending on your architecture - around 100-200
		1213	bytes of memory. In addition, stat requests need a stat buffer (possibly
		1214	a few hundred bytes), readdir requires a result buffer and so on. Perl
		1215	scalars and other data passed into aio requests will also be locked and
		1216	will consume memory till the request has entered the done state.
		1217
		1218	This is now awfully much, so queuing lots of requests is not usually a
		1219	problem.
		1220
		1221	Per-thread usage:
		1222
		1223	In the execution phase, some aio requests require more memory for
		1224	temporary buffers, and each thread requires a stack and other data
		1225	structures (usually around 16k-128k, depending on the OS).
		1226
		1227	=head1 KNOWN BUGS
		1228
		1229	Known bugs will be fixed in the next release.
363		1230
364	=head1 SEE ALSO	1231	=head1 SEE ALSO
365		1232
366	L<Coro>, L<Linux::AIO>.	1233	L<Coro::AIO>.
367		1234
368	=head1 AUTHOR	1235	=head1 AUTHOR
369		1236
370	Marc Lehmann <schmorp@schmorp.de>	1237	Marc Lehmann <schmorp@schmorp.de>
371	http://home.schmorp.de/	1238	http://home.schmorp.de/

Diff Legend

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

Comparing IO-AIO/AIO.pm (file contents): Revision 1.33 by root, Wed Aug 17 06:12:10 2005 UTC vs. Revision 1.100 by root, Sun Jan 7 21:36:58 2007 UTC

Diff Legend

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.33 by root, Wed Aug 17 06:12:10 2005 UTC vs.
Revision 1.100 by root, Sun Jan 7 21:36:58 2007 UTC