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

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.6 by root, Sun Jul 10 22:19:48 2005 UTC vs.
Revision 1.87 by root, Sun Oct 29 00:52:02 2006 UTC

…		…
12	};	12	};
13		13
14	aio_unlink "/tmp/file", sub { };	14	aio_unlink "/tmp/file", sub { };
15		15
16	aio_read $fh, 30000, 1024, $buffer, 0, sub {	16	aio_read $fh, 30000, 1024, $buffer, 0, sub {
17	$_[0] >= 0 or die "read error: $!";	17	$_[0] > 0 or die "read error: $!";
18	};	18	};
19		19
20	# Event	20	# version 2+ has request and group objects
		21	use IO::AIO 2;
		22
		23	aioreq_pri 4; # give next request a very high priority
		24	my $req = aio_unlink "/tmp/file", sub { };
		25	$req->cancel; # cancel request if still in queue
		26
		27	my $grp = aio_group sub { print "all stats done\n" };
		28	add $grp aio_stat "..." for ...;
		29
		30	# AnyEvent integration
		31	open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!";
		32	my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb });
		33
		34	# Event integration
21	Event->io (fd => IO::AIO::poll_fileno,	35	Event->io (fd => IO::AIO::poll_fileno,
22	poll => 'r', async => 1,	36	poll => 'r',
23	cb => \&IO::AIO::poll_cb);	37	cb => \&IO::AIO::poll_cb);
24		38
25	# Glib/Gtk2	39	# Glib/Gtk2 integration
26	add_watch Glib::IO IO::AIO::poll_fileno,	40	add_watch Glib::IO IO::AIO::poll_fileno,
27	\&IO::AIO::poll_cb;	41	in => sub { IO::AIO::poll_cb; 1 };
28		42
29	# Tk	43	# Tk integration
30	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",	44	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
31	readable => \&IO::AIO::poll_cb);	45	readable => \&IO::AIO::poll_cb);
32		46
		47	# Danga::Socket integration
		48	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
		49	\&IO::AIO::poll_cb);
		50
33	=head1 DESCRIPTION	51	=head1 DESCRIPTION
34		52
35	This module implements asynchronous I/O using whatever means your	53	This module implements asynchronous I/O using whatever means your
36	operating system supports.	54	operating system supports.
37		55
		56	Asynchronous means that operations that can normally block your program
		57	(e.g. reading from disk) will be done asynchronously: the operation
		58	will still block, but you can do something else in the meantime. This
		59	is extremely useful for programs that need to stay interactive even
		60	when doing heavy I/O (GUI programs, high performance network servers
		61	etc.), but can also be used to easily do operations in parallel that are
		62	normally done sequentially, e.g. stat'ing many files, which is much faster
		63	on a RAID volume or over NFS when you do a number of stat operations
		64	concurrently.
		65
		66	While this works on all types of file descriptors (for example sockets),
		67	using these functions on file descriptors that support nonblocking
		68	operation (again, sockets, pipes etc.) is very inefficient. Use an event
		69	loop for that (such as the L<Event\|Event> module): IO::AIO will naturally
		70	fit into such an event loop itself.
		71
38	Currently, a number of threads are started that execute your read/writes	72	In this version, a number of threads are started that execute your
39	and signal their completion. You don't need thread support in your libc or	73	requests and signal their completion. You don't need thread support
40	perl, and the threads created by this module will not be visible to the	74	in perl, and the threads created by this module will not be visible
41	pthreads library. In the future, this module might make use of the native	75	to perl. In the future, this module might make use of the native aio
42	aio functions available on many operating systems. However, they are often	76	functions available on many operating systems. However, they are often
43	not well-supported (Linux doesn't allow them on normal files currently,	77	not well-supported or restricted (GNU/Linux doesn't allow them on normal
44	for example), and they would only support aio_read and aio_write, so the	78	files currently, for example), and they would only support aio_read and
45	remaining functionality would have to be implemented using threads anyway.	79	aio_write, so the remaining functionality would have to be implemented
		80	using threads anyway.
46		81
47	Although the module will work with in the presence of other threads, it is	82	Although the module will work with in the presence of other (Perl-)
48	currently not reentrant, so use appropriate locking yourself.	83	threads, it is currently not reentrant in any way, so use appropriate
		84	locking yourself, always call C<poll_cb> from within the same thread, or
		85	never call C<poll_cb> (or other C<aio_> functions) recursively.
		86
		87	=head2 EXAMPLE
		88
		89	This is a simple example that uses the Event module and loads
		90	F</etc/passwd> asynchronously:
		91
		92	use Fcntl;
		93	use Event;
		94	use IO::AIO;
		95
		96	# register the IO::AIO callback with Event
		97	Event->io (fd => IO::AIO::poll_fileno,
		98	poll => 'r',
		99	cb => \&IO::AIO::poll_cb);
		100
		101	# queue the request to open /etc/passwd
		102	aio_open "/etc/passwd", O_RDONLY, 0, sub {
		103	my $fh = $_[0]
		104	or die "error while opening: $!";
		105
		106	# stat'ing filehandles is generally non-blocking
		107	my $size = -s $fh;
		108
		109	# queue a request to read the file
		110	my $contents;
		111	aio_read $fh, 0, $size, $contents, 0, sub {
		112	$_[0] == $size
		113	or die "short read: $!";
		114
		115	close $fh;
		116
		117	# file contents now in $contents
		118	print $contents;
		119
		120	# exit event loop and program
		121	Event::unloop;
		122	};
		123	};
		124
		125	# possibly queue up other requests, or open GUI windows,
		126	# check for sockets etc. etc.
		127
		128	# process events as long as there are some:
		129	Event::loop;
		130
		131	=head1 REQUEST ANATOMY AND LIFETIME
		132
		133	Every C<aio_*> function creates a request. which is a C data structure not
		134	directly visible to Perl.
		135
		136	If called in non-void context, every request function returns a Perl
		137	object representing the request. In void context, nothing is returned,
		138	which saves a bit of memory.
		139
		140	The perl object is a fairly standard ref-to-hash object. The hash contents
		141	are not used by IO::AIO so you are free to store anything you like in it.
		142
		143	During their existance, aio requests travel through the following states,
		144	in order:
		145
		146	=over 4
		147
		148	=item ready
		149
		150	Immediately after a request is created it is put into the ready state,
		151	waiting for a thread to execute it.
		152
		153	=item execute
		154
		155	A thread has accepted the request for processing and is currently
		156	executing it (e.g. blocking in read).
		157
		158	=item pending
		159
		160	The request has been executed and is waiting for result processing.
		161
		162	While request submission and execution is fully asynchronous, result
		163	processing is not and relies on the perl interpreter calling C<poll_cb>
		164	(or another function with the same effect).
		165
		166	=item result
		167
		168	The request results are processed synchronously by C<poll_cb>.
		169
		170	The C<poll_cb> function will process all outstanding aio requests by
		171	calling their callbacks, freeing memory associated with them and managing
		172	any groups they are contained in.
		173
		174	=item done
		175
		176	Request has reached the end of its lifetime and holds no resources anymore
		177	(except possibly for the Perl object, but its connection to the actual
		178	aio request is severed and calling its methods will either do nothing or
		179	result in a runtime error).
49		180
50	=cut	181	=cut
51		182
52	package IO::AIO;	183	package IO::AIO;
53		184
		185	no warnings;
		186	use strict 'vars';
		187
54	use base 'Exporter';	188	use base 'Exporter';
55		189
56	use Fcntl ();
57
58	BEGIN {	190	BEGIN {
59	$VERSION = 0.2;	191	our $VERSION = '2.1';
60		192
61	@EXPORT = qw(aio_read aio_write aio_open aio_close aio_stat aio_lstat aio_unlink	193	our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat
62	aio_fsync aio_fdatasync aio_readahead);	194	aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink
63	@EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs);	195	aio_fsync aio_fdatasync aio_readahead aio_rename aio_link aio_move
		196	aio_copy aio_group aio_nop aio_mknod);
		197	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice));
		198	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush
		199	min_parallel max_parallel max_idle
		200	nreqs nready npending nthreads
		201	max_poll_time max_poll_reqs);
		202
		203	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';
64		204
65	require XSLoader;	205	require XSLoader;
66	XSLoader::load IO::AIO, $VERSION;	206	XSLoader::load ("IO::AIO", $VERSION);
67	}	207	}
68		208
69	=head1 FUNCTIONS	209	=head1 FUNCTIONS
70		210
71	=head2 AIO FUNCTIONS	211	=head2 AIO REQUEST FUNCTIONS
72		212
73	All the C<aio_*> calls are more or less thin wrappers around the syscall	213	All the C<aio_*> calls are more or less thin wrappers around the syscall
74	with the same name (sans C<aio_>). The arguments are similar or identical,	214	with the same name (sans C<aio_>). The arguments are similar or identical,
75	and they all accept an additional C<$callback> argument which must be	215	and they all accept an additional (and optional) C<$callback> argument
76	a code reference. This code reference will get called with the syscall	216	which must be a code reference. This code reference will get called with
77	return code (e.g. most syscalls return C<-1> on error, unlike perl, which	217	the syscall return code (e.g. most syscalls return C<-1> on error, unlike
78	usually delivers "false") as it's sole argument when the given syscall has	218	perl, which usually delivers "false") as it's sole argument when the given
79	been executed asynchronously.	219	syscall has been executed asynchronously.
80		220
81	All functions that expect a filehandle will also accept a file descriptor.	221	All functions expecting a filehandle keep a copy of the filehandle
		222	internally until the request has finished.
82		223
		224	All functions return request objects of type L<IO::AIO::REQ> that allow
		225	further manipulation of those requests while they are in-flight.
		226
83	The filenames you pass to these routines I<must> be absolute. The reason	227	The pathnames you pass to these routines I<must> be absolute and
84	is that at the time the request is being executed, the current working	228	encoded as octets. The reason for the former is that at the time the
85	directory could have changed. Alternatively, you can make sure that you	229	request is being executed, the current working directory could have
86	never change the current working directory.	230	changed. Alternatively, you can make sure that you never change the
		231	current working directory anywhere in the program and then use relative
		232	paths.
		233
		234	To encode pathnames as octets, either make sure you either: a) always pass
		235	in filenames you got from outside (command line, readdir etc.) without
		236	tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module and encode
		237	your pathnames to the locale (or other) encoding in effect in the user
		238	environment, d) use Glib::filename_from_unicode on unicode filenames or e)
		239	use something else to ensure your scalar has the correct contents.
		240
		241	This works, btw. independent of the internal UTF-8 bit, which IO::AIO
		242	handles correctly wether it is set or not.
87		243
88	=over 4	244	=over 4
89		245
		246	=item $prev_pri = aioreq_pri [$pri]
		247
		248	Returns the priority value that would be used for the next request and, if
		249	C<$pri> is given, sets the priority for the next aio request.
		250
		251	The default priority is C<0>, the minimum and maximum priorities are C<-4>
		252	and C<4>, respectively. Requests with higher priority will be serviced
		253	first.
		254
		255	The priority will be reset to C<0> after each call to one of the C<aio_*>
		256	functions.
		257
		258	Example: open a file with low priority, then read something from it with
		259	higher priority so the read request is serviced before other low priority
		260	open requests (potentially spamming the cache):
		261
		262	aioreq_pri -3;
		263	aio_open ..., sub {
		264	return unless $_[0];
		265
		266	aioreq_pri -2;
		267	aio_read $_[0], ..., sub {
		268	...
		269	};
		270	};
		271
		272	=item aioreq_nice $pri_adjust
		273
		274	Similar to C<aioreq_pri>, but subtracts the given value from the current
		275	priority, so the effect is cumulative.
		276
90	=item aio_open $pathname, $flags, $mode, $callback	277	=item aio_open $pathname, $flags, $mode, $callback->($fh)
91		278
92	Asynchronously open or create a file and call the callback with a newly	279	Asynchronously open or create a file and call the callback with a newly
93	created filehandle for the file.	280	created filehandle for the file.
94		281
95	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,	282	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,
96	for an explanation.	283	for an explanation.
97		284
98	The C<$mode> argument is a bitmask. See the C<Fcntl> module for a	285	The C<$flags> argument is a bitmask. See the C<Fcntl> module for a
99	list. They are the same as used in C<sysopen>.	286	list. They are the same as used by C<sysopen>.
		287
		288	Likewise, C<$mode> specifies the mode of the newly created file, if it
		289	didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,
		290	except that it is mandatory (i.e. use C<0> if you don't create new files,
		291	and C<0666> or C<0777> if you do).
100		292
101	Example:	293	Example:
102		294
103	aio_open "/etc/passwd", O_RDONLY, 0, sub {	295	aio_open "/etc/passwd", O_RDONLY, 0, sub {
104	if ($_[0]) {	296	if ($_[0]) {
…		…
107	} else {	299	} else {
108	die "open failed: $!\n";	300	die "open failed: $!\n";
109	}	301	}
110	};	302	};
111		303
112	=item aio_close $fh, $callback	304	=item aio_close $fh, $callback->($status)
113		305
114	Asynchronously close a file and call the callback with the result	306	Asynchronously close a file and call the callback with the result
115	code. I<WARNING:> although accepted, you should not pass in a perl	307	code. I<WARNING:> although accepted, you should not pass in a perl
116	filehandle here, as perl will likely close the file descriptor itself when	308	filehandle here, as perl will likely close the file descriptor another
117	the filehandle is destroyed. Normally, you can safely call perls C<close>	309	time when the filehandle is destroyed. Normally, you can safely call perls
118	or just let filehandles go out of scope.	310	C<close> or just let filehandles go out of scope.
119		311
		312	This is supposed to be a bug in the API, so that might change. It's
		313	therefore best to avoid this function.
		314
120	=item aio_read $fh,$offset,$length, $data,$dataoffset,$callback	315	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
121		316
122	=item aio_write $fh,$offset,$length, $data,$dataoffset,$callback	317	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
123		318
124	Reads or writes C<length> bytes from the specified C<fh> and C<offset>	319	Reads or writes C<length> bytes from the specified C<fh> and C<offset>
125	into the scalar given by C<data> and offset C<dataoffset> and calls the	320	into the scalar given by C<data> and offset C<dataoffset> and calls the
126	callback without the actual number of bytes read (or -1 on error, just	321	callback without the actual number of bytes read (or -1 on error, just
127	like the syscall).	322	like the syscall).
128		323
		324	The C<$data> scalar I<MUST NOT> be modified in any way while the request
		325	is outstanding. Modifying it can result in segfaults or WW3 (if the
		326	necessary/optional hardware is installed).
		327
129	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, strating at	328	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at
130	offset C<0> within the scalar:	329	offset C<0> within the scalar:
131		330
132	aio_read $fh, 7, 15, $buffer, 0, sub {	331	aio_read $fh, 7, 15, $buffer, 0, sub {
133	$_[0] >= 0 or die "read error: $!";	332	$_[0] > 0 or die "read error: $!";
134	print "read <$buffer>\n";	333	print "read $_[0] bytes: <$buffer>\n";
135	};	334	};
136		335
		336	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
		337
		338	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
		339	reading at byte offset C<$in_offset>, and starts writing at the current
		340	file offset of C<$out_fh>. Because of that, it is not safe to issue more
		341	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each
		342	other.
		343
		344	This call tries to make use of a native C<sendfile> syscall to provide
		345	zero-copy operation. For this to work, C<$out_fh> should refer to a
		346	socket, and C<$in_fh> should refer to mmap'able file.
		347
		348	If the native sendfile call fails or is not implemented, it will be
		349	emulated, so you can call C<aio_sendfile> on any type of filehandle
		350	regardless of the limitations of the operating system.
		351
		352	Please note, however, that C<aio_sendfile> can read more bytes from
		353	C<$in_fh> than are written, and there is no way to find out how many
		354	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only
		355	provides the number of bytes written to C<$out_fh>. Only if the result
		356	value equals C<$length> one can assume that C<$length> bytes have been
		357	read.
		358
137	=item aio_readahead $fh,$offset,$length, $callback	359	=item aio_readahead $fh,$offset,$length, $callback->($retval)
138		360
139	Asynchronously reads the specified byte range into the page cache, using
140	the C<readahead> syscall. If that syscall doesn't exist the status will be
141	C<-1> and C<$!> is set to ENOSYS.
142
143	readahead() populates the page cache with data from a file so that	361	C<aio_readahead> populates the page cache with data from a file so that
144	subsequent reads from that file will not block on disk I/O. The C<$offset>	362	subsequent reads from that file will not block on disk I/O. The C<$offset>
145	argument specifies the starting point from which data is to be read and	363	argument specifies the starting point from which data is to be read and
146	C<$length> specifies the number of bytes to be read. I/O is performed in	364	C<$length> specifies the number of bytes to be read. I/O is performed in
147	whole pages, so that offset is effectively rounded down to a page boundary	365	whole pages, so that offset is effectively rounded down to a page boundary
148	and bytes are read up to the next page boundary greater than or equal to	366	and bytes are read up to the next page boundary greater than or equal to
149	(off-set+length). aio_readahead() does not read beyond the end of the	367	(off-set+length). C<aio_readahead> does not read beyond the end of the
150	file. The current file offset of the file is left unchanged.	368	file. The current file offset of the file is left unchanged.
151		369
		370	If that syscall doesn't exist (likely if your OS isn't Linux) it will be
		371	emulated by simply reading the data, which would have a similar effect.
		372
152	=item aio_stat $fh_or_path, $callback	373	=item aio_stat $fh_or_path, $callback->($status)
153		374
154	=item aio_lstat $fh, $callback	375	=item aio_lstat $fh, $callback->($status)
155		376
156	Works like perl's C<stat> or C<lstat> in void context. The callback will	377	Works like perl's C<stat> or C<lstat> in void context. The callback will
157	be called after the stat and the results will be available using C<stat _>	378	be called after the stat and the results will be available using C<stat _>
158	or C<-s _> etc...	379	or C<-s _> etc...
159		380
…		…
169	aio_stat "/etc/passwd", sub {	390	aio_stat "/etc/passwd", sub {
170	$_[0] and die "stat failed: $!";	391	$_[0] and die "stat failed: $!";
171	print "size is ", -s _, "\n";	392	print "size is ", -s _, "\n";
172	};	393	};
173		394
174	=item aio_unlink $pathname, $callback	395	=item aio_unlink $pathname, $callback->($status)
175		396
176	Asynchronously unlink (delete) a file and call the callback with the	397	Asynchronously unlink (delete) a file and call the callback with the
177	result code.	398	result code.
178		399
		400	=item aio_mknod $path, $mode, $dev, $callback->($status)
		401
		402	[EXPERIMENTAL]
		403
		404	Asynchronously create a device node (or fifo). See mknod(2).
		405
		406	The only (POSIX-) portable way of calling this function is:
		407
		408	aio_mknod $path, IO::AIO::S_IFIFO \| $mode, 0, sub { ...
		409
		410	=item aio_link $srcpath, $dstpath, $callback->($status)
		411
		412	Asynchronously create a new link to the existing object at C<$srcpath> at
		413	the path C<$dstpath> and call the callback with the result code.
		414
		415	=item aio_symlink $srcpath, $dstpath, $callback->($status)
		416
		417	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at
		418	the path C<$dstpath> and call the callback with the result code.
		419
		420	=item aio_rename $srcpath, $dstpath, $callback->($status)
		421
		422	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as
		423	rename(2) and call the callback with the result code.
		424
		425	=item aio_rmdir $pathname, $callback->($status)
		426
		427	Asynchronously rmdir (delete) a directory and call the callback with the
		428	result code.
		429
		430	=item aio_readdir $pathname, $callback->($entries)
		431
		432	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
		433	directory (i.e. opendir + readdir + closedir). The entries will not be
		434	sorted, and will B<NOT> include the C<.> and C<..> entries.
		435
		436	The callback a single argument which is either C<undef> or an array-ref
		437	with the filenames.
		438
		439	=item aio_copy $srcpath, $dstpath, $callback->($status)
		440
		441	Try to copy the I<file> (directories not supported as either source or
		442	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		443	the C<0> (error) or C<-1> ok.
		444
		445	This is a composite request that it creates the destination file with
		446	mode 0200 and copies the contents of the source file into it using
		447	C<aio_sendfile>, followed by restoring atime, mtime, access mode and
		448	uid/gid, in that order.
		449
		450	If an error occurs, the partial destination file will be unlinked, if
		451	possible, except when setting atime, mtime, access mode and uid/gid, where
		452	errors are being ignored.
		453
		454	=cut
		455
		456	sub aio_copy($$;$) {
		457	my ($src, $dst, $cb) = @_;
		458
		459	my $pri = aioreq_pri;
		460	my $grp = aio_group $cb;
		461
		462	aioreq_pri $pri;
		463	add $grp aio_open $src, O_RDONLY, 0, sub {
		464	if (my $src_fh = $_[0]) {
		465	my @stat = stat $src_fh;
		466
		467	aioreq_pri $pri;
		468	add $grp aio_open $dst, O_CREAT \| O_WRONLY \| O_TRUNC, 0200, sub {
		469	if (my $dst_fh = $_[0]) {
		470	aioreq_pri $pri;
		471	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
		472	if ($_[0] == $stat[7]) {
		473	$grp->result (0);
		474	close $src_fh;
		475
		476	# those should not normally block. should. should.
		477	utime $stat[8], $stat[9], $dst;
		478	chmod $stat[2] & 07777, $dst_fh;
		479	chown $stat[4], $stat[5], $dst_fh;
		480	close $dst_fh;
		481	} else {
		482	$grp->result (-1);
		483	close $src_fh;
		484	close $dst_fh;
		485
		486	aioreq $pri;
		487	add $grp aio_unlink $dst;
		488	}
		489	};
		490	} else {
		491	$grp->result (-1);
		492	}
		493	},
		494
		495	} else {
		496	$grp->result (-1);
		497	}
		498	};
		499
		500	$grp
		501	}
		502
		503	=item aio_move $srcpath, $dstpath, $callback->($status)
		504
		505	Try to move the I<file> (directories not supported as either source or
		506	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		507	the C<0> (error) or C<-1> ok.
		508
		509	This is a composite request that tries to rename(2) the file first. If
		510	rename files with C<EXDEV>, it copies the file with C<aio_copy> and, if
		511	that is successful, unlinking the C<$srcpath>.
		512
		513	=cut
		514
		515	sub aio_move($$;$) {
		516	my ($src, $dst, $cb) = @_;
		517
		518	my $pri = aioreq_pri;
		519	my $grp = aio_group $cb;
		520
		521	aioreq_pri $pri;
		522	add $grp aio_rename $src, $dst, sub {
		523	if ($_[0] && $! == EXDEV) {
		524	aioreq_pri $pri;
		525	add $grp aio_copy $src, $dst, sub {
		526	$grp->result ($_[0]);
		527
		528	if (!$_[0]) {
		529	aioreq_pri $pri;
		530	add $grp aio_unlink $src;
		531	}
		532	};
		533	} else {
		534	$grp->result ($_[0]);
		535	}
		536	};
		537
		538	$grp
		539	}
		540
		541	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
		542
		543	Scans a directory (similar to C<aio_readdir>) but additionally tries to
		544	efficiently separate the entries of directory C<$path> into two sets of
		545	names, directories you can recurse into (directories), and ones you cannot
		546	recurse into (everything else, including symlinks to directories).
		547
		548	C<aio_scandir> is a composite request that creates of many sub requests_
		549	C<$maxreq> specifies the maximum number of outstanding aio requests that
		550	this function generates. If it is C<< <= 0 >>, then a suitable default
		551	will be chosen (currently 4).
		552
		553	On error, the callback is called without arguments, otherwise it receives
		554	two array-refs with path-relative entry names.
		555
		556	Example:
		557
		558	aio_scandir $dir, 0, sub {
		559	my ($dirs, $nondirs) = @_;
		560	print "real directories: @$dirs\n";
		561	print "everything else: @$nondirs\n";
		562	};
		563
		564	Implementation notes.
		565
		566	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.
		567
		568	After reading the directory, the modification time, size etc. of the
		569	directory before and after the readdir is checked, and if they match (and
		570	isn't the current time), the link count will be used to decide how many
		571	entries are directories (if >= 2). Otherwise, no knowledge of the number
		572	of subdirectories will be assumed.
		573
		574	Then entries will be sorted into likely directories (everything without
		575	a non-initial dot currently) and likely non-directories (everything
		576	else). Then every entry plus an appended C</.> will be C<stat>'ed,
		577	likely directories first. If that succeeds, it assumes that the entry
		578	is a directory or a symlink to directory (which will be checked
		579	seperately). This is often faster than stat'ing the entry itself because
		580	filesystems might detect the type of the entry without reading the inode
		581	data (e.g. ext2fs filetype feature).
		582
		583	If the known number of directories (link count - 2) has been reached, the
		584	rest of the entries is assumed to be non-directories.
		585
		586	This only works with certainty on POSIX (= UNIX) filesystems, which
		587	fortunately are the vast majority of filesystems around.
		588
		589	It will also likely work on non-POSIX filesystems with reduced efficiency
		590	as those tend to return 0 or 1 as link counts, which disables the
		591	directory counting heuristic.
		592
		593	=cut
		594
		595	sub aio_scandir($$$) {
		596	my ($path, $maxreq, $cb) = @_;
		597
		598	my $pri = aioreq_pri;
		599
		600	my $grp = aio_group $cb;
		601
		602	$maxreq = 4 if $maxreq <= 0;
		603
		604	# stat once
		605	aioreq_pri $pri;
		606	add $grp aio_stat $path, sub {
		607	return $grp->result () if $_[0];
		608	my $now = time;
		609	my $hash1 = join ":", (stat _)[0,1,3,7,9];
		610
		611	# read the directory entries
		612	aioreq_pri $pri;
		613	add $grp aio_readdir $path, sub {
		614	my $entries = shift
		615	or return $grp->result ();
		616
		617	# stat the dir another time
		618	aioreq_pri $pri;
		619	add $grp aio_stat $path, sub {
		620	my $hash2 = join ":", (stat _)[0,1,3,7,9];
		621
		622	my $ndirs;
		623
		624	# take the slow route if anything looks fishy
		625	if ($hash1 ne $hash2 or (stat _)[9] == $now) {
		626	$ndirs = -1;
		627	} else {
		628	# if nlink == 2, we are finished
		629	# on non-posix-fs's, we rely on nlink < 2
		630	$ndirs = (stat _)[3] - 2
		631	or return $grp->result ([], $entries);
		632	}
		633
		634	# sort into likely dirs and likely nondirs
		635	# dirs == files without ".", short entries first
		636	$entries = [map $_->[0],
		637	sort { $b->[1] cmp $a->[1] }
		638	map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],
		639	@$entries];
		640
		641	my (@dirs, @nondirs);
		642
		643	my $statgrp = add $grp aio_group sub {
		644	$grp->result (\@dirs, \@nondirs);
		645	};
		646
		647	limit $statgrp $maxreq;
		648	feed $statgrp sub {
		649	return unless @$entries;
		650	my $entry = pop @$entries;
		651
		652	aioreq_pri $pri;
		653	add $statgrp aio_stat "$path/$entry/.", sub {
		654	if ($_[0] < 0) {
		655	push @nondirs, $entry;
		656	} else {
		657	# need to check for real directory
		658	aioreq_pri $pri;
		659	add $statgrp aio_lstat "$path/$entry", sub {
		660	if (-d _) {
		661	push @dirs, $entry;
		662
		663	unless (--$ndirs) {
		664	push @nondirs, @$entries;
		665	feed $statgrp;
		666	}
		667	} else {
		668	push @nondirs, $entry;
		669	}
		670	}
		671	}
		672	};
		673	};
		674	};
		675	};
		676	};
		677
		678	$grp
		679	}
		680
179	=item aio_fsync $fh, $callback	681	=item aio_fsync $fh, $callback->($status)
180		682
181	Asynchronously call fsync on the given filehandle and call the callback	683	Asynchronously call fsync on the given filehandle and call the callback
182	with the fsync result code.	684	with the fsync result code.
183		685
184	=item aio_fdatasync $fh, $callback	686	=item aio_fdatasync $fh, $callback->($status)
185		687
186	Asynchronously call fdatasync on the given filehandle and call the	688	Asynchronously call fdatasync on the given filehandle and call the
187	callback with the fdatasync result code.	689	callback with the fdatasync result code.
188		690
		691	If this call isn't available because your OS lacks it or it couldn't be
		692	detected, it will be emulated by calling C<fsync> instead.
		693
		694	=item aio_group $callback->(...)
		695
		696	This is a very special aio request: Instead of doing something, it is a
		697	container for other aio requests, which is useful if you want to bundle
		698	many requests into a single, composite, request with a definite callback
		699	and the ability to cancel the whole request with its subrequests.
		700
		701	Returns an object of class L<IO::AIO::GRP>. See its documentation below
		702	for more info.
		703
		704	Example:
		705
		706	my $grp = aio_group sub {
		707	print "all stats done\n";
		708	};
		709
		710	add $grp
		711	(aio_stat ...),
		712	(aio_stat ...),
		713	...;
		714
		715	=item aio_nop $callback->()
		716
		717	This is a special request - it does nothing in itself and is only used for
		718	side effects, such as when you want to add a dummy request to a group so
		719	that finishing the requests in the group depends on executing the given
		720	code.
		721
		722	While this request does nothing, it still goes through the execution
		723	phase and still requires a worker thread. Thus, the callback will not
		724	be executed immediately but only after other requests in the queue have
		725	entered their execution phase. This can be used to measure request
		726	latency.
		727
		728	=item IO::AIO::aio_busy $fractional_seconds, $callback->() NOT EXPORTED
		729
		730	Mainly used for debugging and benchmarking, this aio request puts one of
		731	the request workers to sleep for the given time.
		732
		733	While it is theoretically handy to have simple I/O scheduling requests
		734	like sleep and file handle readable/writable, the overhead this creates is
		735	immense (it blocks a thread for a long time) so do not use this function
		736	except to put your application under artificial I/O pressure.
		737
189	=back	738	=back
190		739
		740	=head2 IO::AIO::REQ CLASS
		741
		742	All non-aggregate C<aio_*> functions return an object of this class when
		743	called in non-void context.
		744
		745	=over 4
		746
		747	=item cancel $req
		748
		749	Cancels the request, if possible. Has the effect of skipping execution
		750	when entering the B<execute> state and skipping calling the callback when
		751	entering the the B<result> state, but will leave the request otherwise
		752	untouched. That means that requests that currently execute will not be
		753	stopped and resources held by the request will not be freed prematurely.
		754
		755	=item cb $req $callback->(...)
		756
		757	Replace (or simply set) the callback registered to the request.
		758
		759	=back
		760
		761	=head2 IO::AIO::GRP CLASS
		762
		763	This class is a subclass of L<IO::AIO::REQ>, so all its methods apply to
		764	objects of this class, too.
		765
		766	A IO::AIO::GRP object is a special request that can contain multiple other
		767	aio requests.
		768
		769	You create one by calling the C<aio_group> constructing function with a
		770	callback that will be called when all contained requests have entered the
		771	C<done> state:
		772
		773	my $grp = aio_group sub {
		774	print "all requests are done\n";
		775	};
		776
		777	You add requests by calling the C<add> method with one or more
		778	C<IO::AIO::REQ> objects:
		779
		780	$grp->add (aio_unlink "...");
		781
		782	add $grp aio_stat "...", sub {
		783	$_[0] or return $grp->result ("error");
		784
		785	# add another request dynamically, if first succeeded
		786	add $grp aio_open "...", sub {
		787	$grp->result ("ok");
		788	};
		789	};
		790
		791	This makes it very easy to create composite requests (see the source of
		792	C<aio_move> for an application) that work and feel like simple requests.
		793
		794	=over 4
		795
		796	=item * The IO::AIO::GRP objects will be cleaned up during calls to
		797	C<IO::AIO::poll_cb>, just like any other request.
		798
		799	=item * They can be canceled like any other request. Canceling will cancel not
		800	only the request itself, but also all requests it contains.
		801
		802	=item * They can also can also be added to other IO::AIO::GRP objects.
		803
		804	=item * You must not add requests to a group from within the group callback (or
		805	any later time).
		806
		807	=back
		808
		809	Their lifetime, simplified, looks like this: when they are empty, they
		810	will finish very quickly. If they contain only requests that are in the
		811	C<done> state, they will also finish. Otherwise they will continue to
		812	exist.
		813
		814	That means after creating a group you have some time to add requests. And
		815	in the callbacks of those requests, you can add further requests to the
		816	group. And only when all those requests have finished will the the group
		817	itself finish.
		818
		819	=over 4
		820
		821	=item add $grp ...
		822
		823	=item $grp->add (...)
		824
		825	Add one or more requests to the group. Any type of L<IO::AIO::REQ> can
		826	be added, including other groups, as long as you do not create circular
		827	dependencies.
		828
		829	Returns all its arguments.
		830
		831	=item $grp->cancel_subs
		832
		833	Cancel all subrequests and clears any feeder, but not the group request
		834	itself. Useful when you queued a lot of events but got a result early.
		835
		836	=item $grp->result (...)
		837
		838	Set the result value(s) that will be passed to the group callback when all
		839	subrequests have finished and set thre groups errno to the current value
		840	of errno (just like calling C<errno> without an error number). By default,
		841	no argument will be passed and errno is zero.
		842
		843	=item $grp->errno ([$errno])
		844
		845	Sets the group errno value to C<$errno>, or the current value of errno
		846	when the argument is missing.
		847
		848	Every aio request has an associated errno value that is restored when
		849	the callback is invoked. This method lets you change this value from its
		850	default (0).
		851
		852	Calling C<result> will also set errno, so make sure you either set C<$!>
		853	before the call to C<result>, or call c<errno> after it.
		854
		855	=item feed $grp $callback->($grp)
		856
		857	Sets a feeder/generator on this group: every group can have an attached
		858	generator that generates requests if idle. The idea behind this is that,
		859	although you could just queue as many requests as you want in a group,
		860	this might starve other requests for a potentially long time. For
		861	example, C<aio_scandir> might generate hundreds of thousands C<aio_stat>
		862	requests, delaying any later requests for a long time.
		863
		864	To avoid this, and allow incremental generation of requests, you can
		865	instead a group and set a feeder on it that generates those requests. The
		866	feed callback will be called whenever there are few enough (see C<limit>,
		867	below) requests active in the group itself and is expected to queue more
		868	requests.
		869
		870	The feed callback can queue as many requests as it likes (i.e. C<add> does
		871	not impose any limits).
		872
		873	If the feed does not queue more requests when called, it will be
		874	automatically removed from the group.
		875
		876	If the feed limit is C<0>, it will be set to C<2> automatically.
		877
		878	Example:
		879
		880	# stat all files in @files, but only ever use four aio requests concurrently:
		881
		882	my $grp = aio_group sub { print "finished\n" };
		883	limit $grp 4;
		884	feed $grp sub {
		885	my $file = pop @files
		886	or return;
		887
		888	add $grp aio_stat $file, sub { ... };
		889	};
		890
		891	=item limit $grp $num
		892
		893	Sets the feeder limit for the group: The feeder will be called whenever
		894	the group contains less than this many requests.
		895
		896	Setting the limit to C<0> will pause the feeding process.
		897
		898	=back
		899
191	=head2 SUPPORT FUNCTIONS	900	=head2 SUPPORT FUNCTIONS
192		901
		902	=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION
		903
193	=over 4	904	=over 4
194		905
195	=item $fileno = IO::AIO::poll_fileno	906	=item $fileno = IO::AIO::poll_fileno
196		907
197	Return the I<request result pipe filehandle>. This filehandle must be	908	Return the I<request result pipe file descriptor>. This filehandle must be
198	polled for reading by some mechanism outside this module (e.g. Event	909	polled for reading by some mechanism outside this module (e.g. Event or
199	or select, see below). If the pipe becomes readable you have to call	910	select, see below or the SYNOPSIS). If the pipe becomes readable you have
200	C<poll_cb> to check the results.	911	to call C<poll_cb> to check the results.
201		912
202	See C<poll_cb> for an example.	913	See C<poll_cb> for an example.
203		914
204	=item IO::AIO::poll_cb	915	=item IO::AIO::poll_cb
205		916
206	Process all outstanding events on the result pipe. You have to call this	917	Process some outstanding events on the result pipe. You have to call this
207	regularly. Returns the number of events processed. Returns immediately	918	regularly. Returns the number of events processed. Returns immediately
208	when no events are outstanding.	919	when no events are outstanding. The amount of events processed depends on
		920	the settings of C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>.
209		921
210	You can use Event to multiplex, e.g.:	922	If not all requests were processed for whatever reason, the filehandle
		923	will still be ready when C<poll_cb> returns.
		924
		925	Example: Install an Event watcher that automatically calls
		926	IO::AIO::poll_cb with high priority:
211		927
212	Event->io (fd => IO::AIO::poll_fileno,	928	Event->io (fd => IO::AIO::poll_fileno,
213	poll => 'r', async => 1,	929	poll => 'r', async => 1,
214	cb => \&IO::AIO::poll_cb);	930	cb => \&IO::AIO::poll_cb);
215		931
		932	=item IO::AIO::max_poll_reqs $nreqs
		933
		934	=item IO::AIO::max_poll_time $seconds
		935
		936	These set the maximum number of requests (default C<0>, meaning infinity)
		937	that are being processed by C<IO::AIO::poll_cb> in one call, respectively
		938	the maximum amount of time (default C<0>, meaning infinity) spent in
		939	C<IO::AIO::poll_cb> to process requests (more correctly the mininum amount
		940	of time C<poll_cb> is allowed to use).
		941
		942	Setting these is useful if you want to ensure some level of
		943	interactiveness when perl is not fast enough to process all requests in
		944	time.
		945
		946	For interactive programs, values such as C<0.01> to C<0.1> should be fine.
		947
		948	Example: Install an Event watcher that automatically calls
		949	IO::AIO::poll_some with low priority, to ensure that other parts of the
		950	program get the CPU sometimes even under high AIO load.
		951
		952	# try not to spend much more than 0.1s in poll_cb
		953	IO::AIO::max_poll_time 0.1;
		954
		955	# use a low priority so other tasks have priority
		956	Event->io (fd => IO::AIO::poll_fileno,
		957	poll => 'r', nice => 1,
		958	cb => &IO::AIO::poll_cb);
		959
216	=item IO::AIO::poll_wait	960	=item IO::AIO::poll_wait
217		961
218	Wait till the result filehandle becomes ready for reading (simply does a	962	Wait till the result filehandle becomes ready for reading (simply does a
219	select on the filehandle. This is useful if you want to synchronously wait	963	C<select> on the filehandle. This is useful if you want to synchronously
220	for some requests to finish).	964	wait for some requests to finish).
221		965
222	See C<nreqs> for an example.	966	See C<nreqs> for an example.
223		967
		968	=item IO::AIO::poll
		969
		970	Waits until some requests have been handled.
		971
		972	Strictly equivalent to:
		973
		974	IO::AIO::poll_wait, IO::AIO::poll_cb
		975	if IO::AIO::nreqs;
		976
224	=item IO::AIO::nreqs	977	=item IO::AIO::flush
225		978
226	Returns the number of requests currently outstanding.	979	Wait till all outstanding AIO requests have been handled.
227		980
228	Example: wait till there are no outstanding requests anymore:	981	Strictly equivalent to:
229		982
230	IO::AIO::poll_wait, IO::AIO::poll_cb	983	IO::AIO::poll_wait, IO::AIO::poll_cb
231	while IO::AIO::nreqs;	984	while IO::AIO::nreqs;
232		985
		986	=head3 CONTROLLING THE NUMBER OF THREADS
		987
233	=item IO::AIO::min_parallel $nthreads	988	=item IO::AIO::min_parallel $nthreads
234		989
235	Set the minimum number of AIO threads to C<$nthreads>. The default is	990	Set the minimum number of AIO threads to C<$nthreads>. The current
236	C<1>, which means a single asynchronous operation can be done at one time	991	default is C<8>, which means eight asynchronous operations can execute
237	(the number of outstanding operations, however, is unlimited).	992	concurrently at any one time (the number of outstanding requests,
		993	however, is unlimited).
238		994
		995	IO::AIO starts threads only on demand, when an AIO request is queued and
		996	no free thread exists. Please note that queueing up a hundred requests can
		997	create demand for a hundred threads, even if it turns out that everything
		998	is in the cache and could have been processed faster by a single thread.
		999
239	It is recommended to keep the number of threads low, as some Linux	1000	It is recommended to keep the number of threads relatively low, as some
240	kernel versions will scale negatively with the number of threads (higher	1001	Linux kernel versions will scale negatively with the number of threads
241	parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32	1002	(higher parallelity => MUCH higher latency). With current Linux 2.6
242	threads should be fine.	1003	versions, 4-32 threads should be fine.
243		1004
244	Under normal circumstances you don't need to call this function, as this	1005	Under most circumstances you don't need to call this function, as the
245	module automatically starts some threads (the exact number might change,	1006	module selects a default that is suitable for low to moderate load.
246	and is currently 4).
247		1007
248	=item IO::AIO::max_parallel $nthreads	1008	=item IO::AIO::max_parallel $nthreads
249		1009
250	Sets the maximum number of AIO threads to C<$nthreads>. If more than	1010	Sets the maximum number of AIO threads to C<$nthreads>. If more than the
251	the specified number of threads are currently running, kill them. This	1011	specified number of threads are currently running, this function kills
252	function blocks until the limit is reached.	1012	them. This function blocks until the limit is reached.
		1013
		1014	While C<$nthreads> are zero, aio requests get queued but not executed
		1015	until the number of threads has been increased again.
253		1016
254	This module automatically runs C<max_parallel 0> at program end, to ensure	1017	This module automatically runs C<max_parallel 0> at program end, to ensure
255	that all threads are killed and that there are no outstanding requests.	1018	that all threads are killed and that there are no outstanding requests.
256		1019
257	Under normal circumstances you don't need to call this function.	1020	Under normal circumstances you don't need to call this function.
258		1021
		1022	=item IO::AIO::max_idle $nthreads
		1023
		1024	Limit the number of threads (default: 4) that are allowed to idle (i.e.,
		1025	threads that did not get a request to process within 10 seconds). That
		1026	means if a thread becomes idle while C<$nthreads> other threads are also
		1027	idle, it will free its resources and exit.
		1028
		1029	This is useful when you allow a large number of threads (e.g. 100 or 1000)
		1030	to allow for extremely high load situations, but want to free resources
		1031	under normal circumstances (1000 threads can easily consume 30MB of RAM).
		1032
		1033	The default is probably ok in most situations, especially if thread
		1034	creation is fast. If thread creation is very slow on your system you might
		1035	want to use larger values.
		1036
259	=item $oldnreqs = IO::AIO::max_outstanding $nreqs	1037	=item $oldmaxreqs = IO::AIO::max_outstanding $maxreqs
		1038
		1039	This is a very bad function to use in interactive programs because it
		1040	blocks, and a bad way to reduce concurrency because it is inexact: Better
		1041	use an C<aio_group> together with a feed callback.
260		1042
261	Sets the maximum number of outstanding requests to C<$nreqs>. If you	1043	Sets the maximum number of outstanding requests to C<$nreqs>. If you
262	try to queue up more than this number of requests, the caller will block until	1044	to queue up more than this number of requests, the next call to the
263	some requests have been handled.	1045	C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>)
		1046	function will block until the limit is no longer exceeded.
264		1047
265	The default is very large, so normally there is no practical limit. If you	1048	The default value is very large, so there is no practical limit on the
266	queue up many requests in a loop it it often improves speed if you set	1049	number of outstanding requests.
267	this to a relatively low number, such as C<100>.
268		1050
269	Under normal circumstances you don't need to call this function.	1051	You can still queue as many requests as you want. Therefore,
		1052	C<max_oustsanding> is mainly useful in simple scripts (with low values) or
		1053	as a stop gap to shield against fatal memory overflow (with large values).
		1054
		1055	=head3 STATISTICAL INFORMATION
		1056
		1057	=item IO::AIO::nreqs
		1058
		1059	Returns the number of requests currently in the ready, execute or pending
		1060	states (i.e. for which their callback has not been invoked yet).
		1061
		1062	Example: wait till there are no outstanding requests anymore:
		1063
		1064	IO::AIO::poll_wait, IO::AIO::poll_cb
		1065	while IO::AIO::nreqs;
		1066
		1067	=item IO::AIO::nready
		1068
		1069	Returns the number of requests currently in the ready state (not yet
		1070	executed).
		1071
		1072	=item IO::AIO::npending
		1073
		1074	Returns the number of requests currently in the pending state (executed,
		1075	but not yet processed by poll_cb).
270		1076
271	=back	1077	=back
272		1078
273	=cut	1079	=cut
274		1080
275	# support function to convert a fd into a perl filehandle	1081	# support function to convert a fd into a perl filehandle
276	sub _fd2fh {	1082	sub _fd2fh {
277	return undef if $_[0] < 0;	1083	return undef if $_[0] < 0;
278		1084
279	# try to be perl5.6-compatible	1085	# try to generate nice filehandles
280	local *AIO_FH;	1086	my $sym = "IO::AIO::fd#$_[0]";
281	open AIO_FH, "+<&=$_[0]"	1087	local *$sym;
		1088
		1089	open *$sym, "+<&=$_[0]" # usually works under any unix
		1090	or open *$sym, "<&=$_[0]" # cygwin needs this
		1091	or open *$sym, ">&=$_[0]" # or this
282	or return undef;	1092	or return undef;
283		1093
284	*AIO_FH	1094	*$sym
285	}	1095	}
286		1096
287	min_parallel 4;	1097	min_parallel 8;
288		1098
289	END {	1099	END {
290	max_parallel 0;	1100	min_parallel 1;
291	}	1101	flush;
		1102	};
292		1103
293	1;	1104	1;
294		1105
		1106	=head2 FORK BEHAVIOUR
		1107
		1108	This module should do "the right thing" when the process using it forks:
		1109
		1110	Before the fork, IO::AIO enters a quiescent state where no requests
		1111	can be added in other threads and no results will be processed. After
		1112	the fork the parent simply leaves the quiescent state and continues
		1113	request/result processing, while the child frees the request/result queue
		1114	(so that the requests started before the fork will only be handled in the
		1115	parent). Threads will be started on demand until the limit set in the
		1116	parent process has been reached again.
		1117
		1118	In short: the parent will, after a short pause, continue as if fork had
		1119	not been called, while the child will act as if IO::AIO has not been used
		1120	yet.
		1121
		1122	=head2 MEMORY USAGE
		1123
		1124	Per-request usage:
		1125
		1126	Each aio request uses - depending on your architecture - around 100-200
		1127	bytes of memory. In addition, stat requests need a stat buffer (possibly
		1128	a few hundred bytes), readdir requires a result buffer and so on. Perl
		1129	scalars and other data passed into aio requests will also be locked and
		1130	will consume memory till the request has entered the done state.
		1131
		1132	This is now awfully much, so queuing lots of requests is not usually a
		1133	problem.
		1134
		1135	Per-thread usage:
		1136
		1137	In the execution phase, some aio requests require more memory for
		1138	temporary buffers, and each thread requires a stack and other data
		1139	structures (usually around 16k-128k, depending on the OS).
		1140
		1141	=head1 KNOWN BUGS
		1142
		1143	Known bugs will be fixed in the next release.
		1144
295	=head1 SEE ALSO	1145	=head1 SEE ALSO
296		1146
297	L<Coro>, L<Linux::AIO>.	1147	L<Coro::AIO>.
298		1148
299	=head1 AUTHOR	1149	=head1 AUTHOR
300		1150
301	Marc Lehmann <schmorp@schmorp.de>	1151	Marc Lehmann <schmorp@schmorp.de>
302	http://home.schmorp.de/	1152	http://home.schmorp.de/

Diff Legend

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

Comparing IO-AIO/AIO.pm (file contents): Revision 1.6 by root, Sun Jul 10 22:19:48 2005 UTC vs. Revision 1.87 by root, Sun Oct 29 00:52:02 2006 UTC

Diff Legend

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.6 by root, Sun Jul 10 22:19:48 2005 UTC vs.
Revision 1.87 by root, Sun Oct 29 00:52:02 2006 UTC