ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/IO-AIO/AIO.pm

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.51 by root, Sat Jun 24 19:14:04 2006 UTC vs.
Revision 1.109 by root, Sun Jun 3 09:44:17 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	# AnyEvent	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
21	open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!";	32	open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!";
22	my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb });	33	my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb });
23		34
24	# Event	35	# Event integration
25	Event->io (fd => IO::AIO::poll_fileno,	36	Event->io (fd => IO::AIO::poll_fileno,
26	poll => 'r',	37	poll => 'r',
27	cb => \&IO::AIO::poll_cb);	38	cb => \&IO::AIO::poll_cb);
28		39
29	# Glib/Gtk2	40	# Glib/Gtk2 integration
30	add_watch Glib::IO IO::AIO::poll_fileno,	41	add_watch Glib::IO IO::AIO::poll_fileno,
31	in => sub { IO::AIO::poll_cb; 1 };	42	in => sub { IO::AIO::poll_cb; 1 };
32		43
33	# Tk	44	# Tk integration
34	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",	45	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
35	readable => \&IO::AIO::poll_cb);	46	readable => \&IO::AIO::poll_cb);
36		47
37	# Danga::Socket	48	# Danga::Socket integration
38	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>	49	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
39	\&IO::AIO::poll_cb);	50	\&IO::AIO::poll_cb);
40		51
41
42	=head1 DESCRIPTION	52	=head1 DESCRIPTION
43		53
44	This module implements asynchronous I/O using whatever means your	54	This module implements asynchronous I/O using whatever means your
45	operating system supports.	55	operating system supports.
46		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
		68	example sockets), using these functions on file descriptors that
		69	support nonblocking operation (again, sockets, pipes etc.) is very
		70	inefficient. Use an event loop for that (such as the L<Event|Event>
		71	module): IO::AIO will naturally fit into such an event loop itself.
		72
47	Currently, a number of threads are started that execute your read/writes	73	In this version, a number of threads are started that execute your
48	and signal their completion. You don't need thread support in your libc or	74	requests and signal their completion. You don't need thread support
49	perl, and the threads created by this module will not be visible to the	75	in perl, and the threads created by this module will not be visible
50	pthreads library. In the future, this module might make use of the native	76	to perl. In the future, this module might make use of the native aio
51	aio functions available on many operating systems. However, they are often	77	functions available on many operating systems. However, they are often
52	not well-supported (Linux doesn't allow them on normal files currently,	78	not well-supported or restricted (GNU/Linux doesn't allow them on normal
53	for example), and they would only support aio_read and aio_write, so the	79	files currently, for example), and they would only support aio_read and
54	remaining functionality would have to be implemented using threads anyway.	80	aio_write, so the remaining functionality would have to be implemented
		81	using threads anyway.
55		82
56	Although the module will work with in the presence of other threads, it is	83	Although the module will work in the presence of other (Perl-) threads,
57	currently not reentrant, so use appropriate locking yourself, always call	84	it is currently not reentrant in any way, so use appropriate locking
58	C<poll_cb> from within the same thread, or never call C<poll_cb> (or other	85	yourself, always call C<poll_cb> from within the same thread, or never
59	C<aio_> functions) recursively.	86	call C<poll_cb> (or other C<aio_> functions) recursively.
		87
		88	=head2 EXAMPLE
		89
		90	This is a simple example that uses the Event module and loads
		91	F</etc/passwd> asynchronously:
		92
		93	use Fcntl;
		94	use Event;
		95	use IO::AIO;
		96
		97	# register the IO::AIO callback with Event
		98	Event->io (fd => IO::AIO::poll_fileno,
		99	poll => 'r',
		100	cb => \&IO::AIO::poll_cb);
		101
		102	# queue the request to open /etc/passwd
		103	aio_open "/etc/passwd", O_RDONLY, 0, sub {
		104	my $fh = shift
		105	or die "error while opening: $!";
		106
		107	# stat'ing filehandles is generally non-blocking
		108	my $size = -s $fh;
		109
		110	# queue a request to read the file
		111	my $contents;
		112	aio_read $fh, 0, $size, $contents, 0, sub {
		113	$_[0] == $size
		114	or die "short read: $!";
		115
		116	close $fh;
		117
		118	# file contents now in $contents
		119	print $contents;
		120
		121	# exit event loop and program
		122	Event::unloop;
		123	};
		124	};
		125
		126	# possibly queue up other requests, or open GUI windows,
		127	# check for sockets etc. etc.
		128
		129	# process events as long as there are some:
		130	Event::loop;
		131
		132	=head1 REQUEST ANATOMY AND LIFETIME
		133
		134	Every C<aio_*> function creates a request. which is a C data structure not
		135	directly visible to Perl.
		136
		137	If called in non-void context, every request function returns a Perl
		138	object representing the request. In void context, nothing is returned,
		139	which saves a bit of memory.
		140
		141	The perl object is a fairly standard ref-to-hash object. The hash contents
		142	are not used by IO::AIO so you are free to store anything you like in it.
		143
		144	During their existance, aio requests travel through the following states,
		145	in order:
		146
		147	=over 4
		148
		149	=item ready
		150
		151	Immediately after a request is created it is put into the ready state,
		152	waiting for a thread to execute it.
		153
		154	=item execute
		155
		156	A thread has accepted the request for processing and is currently
		157	executing it (e.g. blocking in read).
		158
		159	=item pending
		160
		161	The request has been executed and is waiting for result processing.
		162
		163	While request submission and execution is fully asynchronous, result
		164	processing is not and relies on the perl interpreter calling C<poll_cb>
		165	(or another function with the same effect).
		166
		167	=item result
		168
		169	The request results are processed synchronously by C<poll_cb>.
		170
		171	The C<poll_cb> function will process all outstanding aio requests by
		172	calling their callbacks, freeing memory associated with them and managing
		173	any groups they are contained in.
		174
		175	=item done
		176
		177	Request has reached the end of its lifetime and holds no resources anymore
		178	(except possibly for the Perl object, but its connection to the actual
		179	aio request is severed and calling its methods will either do nothing or
		180	result in a runtime error).
		181
		182	=back
60		183
61	=cut	184	=cut
62		185
63	package IO::AIO;	186	package IO::AIO;
64		187
…		…
66	use strict 'vars';	189	use strict 'vars';
67		190
68	use base 'Exporter';	191	use base 'Exporter';
69		192
70	BEGIN {	193	BEGIN {
71	our $VERSION = '1.8';	194	our $VERSION = '2.4';
72		195
73	our @EXPORT = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat	196	our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat
74	aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink	197	aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink
75	aio_fsync aio_fdatasync aio_readahead aio_rename aio_link aio_move);	198	aio_readlink aio_fsync aio_fdatasync aio_readahead aio_rename aio_link
76	our @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs);	199	aio_move aio_copy aio_group aio_nop aio_mknod aio_load aio_rmtree aio_mkdir
		200	aio_chown aio_chmod aio_utime);
		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';
77		208
78	require XSLoader;	209	require XSLoader;
79	XSLoader::load ("IO::AIO", $VERSION);	210	XSLoader::load ("IO::AIO", $VERSION);
80	}	211	}
81		212
82	=head1 FUNCTIONS	213	=head1 FUNCTIONS
83		214
84	=head2 AIO FUNCTIONS	215	=head2 AIO REQUEST FUNCTIONS
85		216
86	All the C<aio_*> calls are more or less thin wrappers around the syscall	217	All the C<aio_*> calls are more or less thin wrappers around the syscall
87	with the same name (sans C<aio_>). The arguments are similar or identical,	218	with the same name (sans C<aio_>). The arguments are similar or identical,
88	and they all accept an additional (and optional) C<$callback> argument	219	and they all accept an additional (and optional) C<$callback> argument
89	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
…		…
92	syscall has been executed asynchronously.	223	syscall has been executed asynchronously.
93		224
94	All functions expecting a filehandle keep a copy of the filehandle	225	All functions expecting a filehandle keep a copy of the filehandle
95	internally until the request has finished.	226	internally until the request has finished.
96		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
97	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
98	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
99	request is being executed, the current working directory could have	233	request is being executed, the current working directory could have
100	changed. Alternatively, you can make sure that you never change the	234	changed. Alternatively, you can make sure that you never change the
101	current working directory.	235	current working directory anywhere in the program and then use relative
		236	paths.
102		237
103	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
104	always pass in filenames you got from outside (command line, readdir	239	in filenames you got from outside (command line, readdir etc.) without
105	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
106	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
107	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)
108	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.
109		247
110	=over 4	248	=over 4
		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
		277	=item aioreq_nice $pri_adjust
		278
		279	Similar to C<aioreq_pri>, but subtracts the given value from the current
		280	priority, so the effect is cumulative.
		281
111		282
112	=item aio_open $pathname, $flags, $mode, $callback->($fh)	283	=item aio_open $pathname, $flags, $mode, $callback->($fh)
113		284
114	Asynchronously open or create a file and call the callback with a newly	285	Asynchronously open or create a file and call the callback with a newly
115	created filehandle for the file.	286	created filehandle for the file.
…		…
121	list. They are the same as used by C<sysopen>.	292	list. They are the same as used by C<sysopen>.
122		293
123	Likewise, C<$mode> specifies the mode of the newly created file, if it	294	Likewise, C<$mode> specifies the mode of the newly created file, if it
124	didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,	295	didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,
125	except that it is mandatory (i.e. use C<0> if you don't create new files,	296	except that it is mandatory (i.e. use C<0> if you don't create new files,
126	and C<0666> or C<0777> if you do).	297	and C<0666> or C<0777> if you do). Note that the C<$mode> will be modified
		298	by the umask in effect then the request is being executed, so better never
		299	change the umask.
127		300
128	Example:	301	Example:
129		302
130	aio_open "/etc/passwd", O_RDONLY, 0, sub {	303	aio_open "/etc/passwd", O_RDONLY, 0, sub {
131	if ($_[0]) {	304	if ($_[0]) {
…		…
134	} else {	307	} else {
135	die "open failed: $!\n";	308	die "open failed: $!\n";
136	}	309	}
137	};	310	};
138		311
		312
139	=item aio_close $fh, $callback->($status)	313	=item aio_close $fh, $callback->($status)
140		314
141	Asynchronously close a file and call the callback with the result	315	Asynchronously close a file and call the callback with the result
142	code. I<WARNING:> although accepted, you should not pass in a perl	316	code. I<WARNING:> although accepted, you should not pass in a perl
143	filehandle here, as perl will likely close the file descriptor another	317	filehandle here, as perl will likely close the file descriptor another
…		…
145	C<close> or just let filehandles go out of scope.	319	C<close> or just let filehandles go out of scope.
146		320
147	This is supposed to be a bug in the API, so that might change. It's	321	This is supposed to be a bug in the API, so that might change. It's
148	therefore best to avoid this function.	322	therefore best to avoid this function.
149		323
		324
150	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	325	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
151		326
152	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	327	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
153		328
154	Reads or writes C<length> bytes from the specified C<fh> and C<offset>	329	Reads or writes C<$length> bytes from the specified C<$fh> and C<$offset>
155	into the scalar given by C<data> and offset C<dataoffset> and calls the	330	into the scalar given by C<$data> and offset C<$dataoffset> and calls the
156	callback without the actual number of bytes read (or -1 on error, just	331	callback without the actual number of bytes read (or -1 on error, just
157	like the syscall).	332	like the syscall).
158		333
		334	If C<$offset> is undefined, then the current file offset will be used (and
		335	updated), otherwise the file offset will not be changed by these calls.
		336
		337	If C<$length> is undefined in C<aio_write>, use the remaining length of C<$data>.
		338
		339	If C<$dataoffset> is less than zero, it will be counted from the end of
		340	C<$data>.
		341
159	The C<$data> scalar I<MUST NOT> be modified in any way while the request	342	The C<$data> scalar I<MUST NOT> be modified in any way while the request
160	is outstanding. Modifying it can result in segfaults or WW3 (if the	343	is outstanding. Modifying it can result in segfaults or World War III (if
161	necessary/optional hardware is installed).	344	the necessary/optional hardware is installed).
162		345
163	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at	346	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at
164	offset C<0> within the scalar:	347	offset C<0> within the scalar:
165		348
166	aio_read $fh, 7, 15, $buffer, 0, sub {	349	aio_read $fh, 7, 15, $buffer, 0, sub {
167	$_[0] > 0 or die "read error: $!";	350	$_[0] > 0 or die "read error: $!";
168	print "read $_[0] bytes: <$buffer>\n";	351	print "read $_[0] bytes: <$buffer>\n";
169	};	352	};
170		353
171	=item aio_move $srcpath, $dstpath, $callback->($status)
172
173	[EXPERIMENTAL]
174
175	Try to move the I<file> (directories not supported as either source or destination)
176	from C<$srcpath> to C<$dstpath> and call the callback with the C<0> (error) or C<-1> ok.
177
178	This is a composite request that tries to rename(2) the file first. If
179	rename files with C<EXDEV>, it creates the destination file with mode 0200
180	and copies the contents of the source file into it using C<aio_sendfile>,
181	followed by restoring atime, mtime, access mode and uid/gid, in that
182	order, and unlinking the C<$srcpath>.
183
184	If an error occurs, the partial destination file will be unlinked, if
185	possible, except when setting atime, mtime, access mode and uid/gid, where
186	errors are being ignored.
187
188	=cut
189
190	sub aio_move($$$) {
191	my ($src, $dst, $cb) = @_;
192
193	aio_rename $src, $dst, sub {
194	if ($_[0] && $! == EXDEV) {
195	aio_open $src, O_RDONLY, 0, sub {
196	if (my $src_fh = $_[0]) {
197	my @stat = stat $src_fh;
198
199	aio_open $dst, O_WRONLY, 0200, sub {
200	if (my $dst_fh = $_[0]) {
201	aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
202	close $src_fh;
203
204	if ($_[0] == $stat[7]) {
205	utime $stat[8], $stat[9], $dst;
206	chmod $stat[2] & 07777, $dst_fh;
207	chown $stat[4], $stat[5], $dst_fh;
208	close $dst_fh;
209
210	aio_unlink $src, sub {
211	$cb->($_[0]);
212	};
213	} else {
214	my $errno = $!;
215	aio_unlink $dst, sub {
216	$! = $errno;
217	$cb->(-1);
218	};
219	}
220	};
221	} else {
222	$cb->(-1);
223	}
224	},
225
226	} else {
227	$cb->(-1);
228	}
229	};
230	} else {
231	$cb->($_[0]);
232	}
233	};
234	}
235		354
236	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)	355	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
237		356
238	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts	357	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
239	reading at byte offset C<$in_offset>, and starts writing at the current	358	reading at byte offset C<$in_offset>, and starts writing at the current
…		…
253	C<$in_fh> than are written, and there is no way to find out how many	372	C<$in_fh> than are written, and there is no way to find out how many
254	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only	373	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only
255	provides the number of bytes written to C<$out_fh>. Only if the result	374	provides the number of bytes written to C<$out_fh>. Only if the result
256	value equals C<$length> one can assume that C<$length> bytes have been	375	value equals C<$length> one can assume that C<$length> bytes have been
257	read.	376	read.
		377
258		378
259	=item aio_readahead $fh,$offset,$length, $callback->($retval)	379	=item aio_readahead $fh,$offset,$length, $callback->($retval)
260		380
261	C<aio_readahead> populates the page cache with data from a file so that	381	C<aio_readahead> populates the page cache with data from a file so that
262	subsequent reads from that file will not block on disk I/O. The C<$offset>	382	subsequent reads from that file will not block on disk I/O. The C<$offset>
…		…
268	file. The current file offset of the file is left unchanged.	388	file. The current file offset of the file is left unchanged.
269		389
270	If that syscall doesn't exist (likely if your OS isn't Linux) it will be	390	If that syscall doesn't exist (likely if your OS isn't Linux) it will be
271	emulated by simply reading the data, which would have a similar effect.	391	emulated by simply reading the data, which would have a similar effect.
272		392
		393
273	=item aio_stat $fh_or_path, $callback->($status)	394	=item aio_stat $fh_or_path, $callback->($status)
274		395
275	=item aio_lstat $fh, $callback->($status)	396	=item aio_lstat $fh, $callback->($status)
276		397
277	Works like perl's C<stat> or C<lstat> in void context. The callback will	398	Works like perl's C<stat> or C<lstat> in void context. The callback will
…		…
290	aio_stat "/etc/passwd", sub {	411	aio_stat "/etc/passwd", sub {
291	$_[0] and die "stat failed: $!";	412	$_[0] and die "stat failed: $!";
292	print "size is ", -s _, "\n";	413	print "size is ", -s _, "\n";
293	};	414	};
294		415
		416
		417	=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
		418
		419	Works like perl's C<utime> function (including the special case of $atime
		420	and $mtime being undef). Fractional times are supported if the underlying
		421	syscalls support them.
		422
		423	When called with a pathname, uses utimes(2) if available, otherwise
		424	utime(2). If called on a file descriptor, uses futimes(2) if available,
		425	otherwise returns ENOSYS, so this is not portable.
		426
		427	Examples:
		428
		429	# set atime and mtime to current time (basically touch(1)):
		430	aio_utime "path", undef, undef;
		431	# set atime to current time and mtime to beginning of the epoch:
		432	aio_utime "path", time, undef; # undef==0
		433
		434
		435	=item aio_chown $fh_or_path, $uid, $gid, $callback->($status)
		436
		437	Works like perl's C<chown> function, except that C<undef> for either $uid
		438	or $gid is being interpreted as "do not change" (but -1 can also be used).
		439
		440	Examples:
		441
		442	# same as "chown root path" in the shell:
		443	aio_chown "path", 0, -1;
		444	# same as above:
		445	aio_chown "path", 0, undef;
		446
		447
		448	=item aio_chmod $fh_or_path, $mode, $callback->($status)
		449
		450	Works like perl's C<chmod> function.
		451
		452
295	=item aio_unlink $pathname, $callback->($status)	453	=item aio_unlink $pathname, $callback->($status)
296		454
297	Asynchronously unlink (delete) a file and call the callback with the	455	Asynchronously unlink (delete) a file and call the callback with the
298	result code.	456	result code.
299		457
		458
		459	=item aio_mknod $path, $mode, $dev, $callback->($status)
		460
		461	[EXPERIMENTAL]
		462
		463	Asynchronously create a device node (or fifo). See mknod(2).
		464
		465	The only (POSIX-) portable way of calling this function is:
		466
		467	aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ...
		468
		469
300	=item aio_link $srcpath, $dstpath, $callback->($status)	470	=item aio_link $srcpath, $dstpath, $callback->($status)
301		471
302	Asynchronously create a new link to the existing object at C<$srcpath> at	472	Asynchronously create a new link to the existing object at C<$srcpath> at
303	the path C<$dstpath> and call the callback with the result code.	473	the path C<$dstpath> and call the callback with the result code.
304		474
		475
305	=item aio_symlink $srcpath, $dstpath, $callback->($status)	476	=item aio_symlink $srcpath, $dstpath, $callback->($status)
306		477
307	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at	478	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at
308	the path C<$dstpath> and call the callback with the result code.	479	the path C<$dstpath> and call the callback with the result code.
309		480
		481
		482	=item aio_readlink $path, $callback->($link)
		483
		484	Asynchronously read the symlink specified by C<$path> and pass it to
		485	the callback. If an error occurs, nothing or undef gets passed to the
		486	callback.
		487
		488
310	=item aio_rename $srcpath, $dstpath, $callback->($status)	489	=item aio_rename $srcpath, $dstpath, $callback->($status)
311		490
312	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as	491	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as
313	rename(2) and call the callback with the result code.	492	rename(2) and call the callback with the result code.
314		493
		494
		495	=item aio_mkdir $pathname, $mode, $callback->($status)
		496
		497	Asynchronously mkdir (create) a directory and call the callback with
		498	the result code. C<$mode> will be modified by the umask at the time the
		499	request is executed, so do not change your umask.
		500
		501
315	=item aio_rmdir $pathname, $callback->($status)	502	=item aio_rmdir $pathname, $callback->($status)
316		503
317	Asynchronously rmdir (delete) a directory and call the callback with the	504	Asynchronously rmdir (delete) a directory and call the callback with the
318	result code.	505	result code.
		506
319		507
320	=item aio_readdir $pathname, $callback->($entries)	508	=item aio_readdir $pathname, $callback->($entries)
321		509
322	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire	510	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
323	directory (i.e. opendir + readdir + closedir). The entries will not be	511	directory (i.e. opendir + readdir + closedir). The entries will not be
324	sorted, and will B<NOT> include the C<.> and C<..> entries.	512	sorted, and will B<NOT> include the C<.> and C<..> entries.
325		513
326	The callback a single argument which is either C<undef> or an array-ref	514	The callback a single argument which is either C<undef> or an array-ref
327	with the filenames.	515	with the filenames.
328		516
		517
		518	=item aio_load $path, $data, $callback->($status)
		519
		520	This is a composite request that tries to fully load the given file into
		521	memory. Status is the same as with aio_read.
		522
		523	=cut
		524
		525	sub aio_load($$;$) {
		526	aio_block {
		527	my ($path, undef, $cb) = @_;
		528	my $data = \$_[1];
		529
		530	my $pri = aioreq_pri;
		531	my $grp = aio_group $cb;
		532
		533	aioreq_pri $pri;
		534	add $grp aio_open $path, O_RDONLY, 0, sub {
		535	my $fh = shift
		536	or return $grp->result (-1);
		537
		538	aioreq_pri $pri;
		539	add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub {
		540	$grp->result ($_[0]);
		541	};
		542	};
		543
		544	$grp
		545	}
		546	}
		547
		548	=item aio_copy $srcpath, $dstpath, $callback->($status)
		549
		550	Try to copy the I<file> (directories not supported as either source or
		551	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		552	the C<0> (error) or C<-1> ok.
		553
		554	This is a composite request that it creates the destination file with
		555	mode 0200 and copies the contents of the source file into it using
		556	C<aio_sendfile>, followed by restoring atime, mtime, access mode and
		557	uid/gid, in that order.
		558
		559	If an error occurs, the partial destination file will be unlinked, if
		560	possible, except when setting atime, mtime, access mode and uid/gid, where
		561	errors are being ignored.
		562
		563	=cut
		564
		565	sub aio_copy($$;$) {
		566	aio_block {
		567	my ($src, $dst, $cb) = @_;
		568
		569	my $pri = aioreq_pri;
		570	my $grp = aio_group $cb;
		571
		572	aioreq_pri $pri;
		573	add $grp aio_open $src, O_RDONLY, 0, sub {
		574	if (my $src_fh = $_[0]) {
		575	my @stat = stat $src_fh;
		576
		577	aioreq_pri $pri;
		578	add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {
		579	if (my $dst_fh = $_[0]) {
		580	aioreq_pri $pri;
		581	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
		582	if ($_[0] == $stat[7]) {
		583	$grp->result (0);
		584	close $src_fh;
		585
		586	# those should not normally block. should. should.
		587	utime $stat[8], $stat[9], $dst;
		588	chmod $stat[2] & 07777, $dst_fh;
		589	chown $stat[4], $stat[5], $dst_fh;
		590	close $dst_fh;
		591	} else {
		592	$grp->result (-1);
		593	close $src_fh;
		594	close $dst_fh;
		595
		596	aioreq $pri;
		597	add $grp aio_unlink $dst;
		598	}
		599	};
		600	} else {
		601	$grp->result (-1);
		602	}
		603	},
		604
		605	} else {
		606	$grp->result (-1);
		607	}
		608	};
		609
		610	$grp
		611	}
		612	}
		613
		614	=item aio_move $srcpath, $dstpath, $callback->($status)
		615
		616	Try to move the I<file> (directories not supported as either source or
		617	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		618	the C<0> (error) or C<-1> ok.
		619
		620	This is a composite request that tries to rename(2) the file first. If
		621	rename files with C<EXDEV>, it copies the file with C<aio_copy> and, if
		622	that is successful, unlinking the C<$srcpath>.
		623
		624	=cut
		625
		626	sub aio_move($$;$) {
		627	aio_block {
		628	my ($src, $dst, $cb) = @_;
		629
		630	my $pri = aioreq_pri;
		631	my $grp = aio_group $cb;
		632
		633	aioreq_pri $pri;
		634	add $grp aio_rename $src, $dst, sub {
		635	if ($_[0] && $! == EXDEV) {
		636	aioreq_pri $pri;
		637	add $grp aio_copy $src, $dst, sub {
		638	$grp->result ($_[0]);
		639
		640	if (!$_[0]) {
		641	aioreq_pri $pri;
		642	add $grp aio_unlink $src;
		643	}
		644	};
		645	} else {
		646	$grp->result ($_[0]);
		647	}
		648	};
		649
		650	$grp
		651	}
		652	}
		653
329	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)	654	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
330		655
331	Scans a directory (similar to C<aio_readdir>) and tries to separate the	656	Scans a directory (similar to C<aio_readdir>) but additionally tries to
332	entries of directory C<$path> into two sets of names, ones you can recurse	657	efficiently separate the entries of directory C<$path> into two sets of
333	into (directories), and ones you cannot recurse into (everything else).	658	names, directories you can recurse into (directories), and ones you cannot
		659	recurse into (everything else, including symlinks to directories).
334		660
335	C<aio_scandir> is a composite request that consists of many	661	C<aio_scandir> is a composite request that creates of many sub requests_
336	aio-primitives. C<$maxreq> specifies the maximum number of outstanding	662	C<$maxreq> specifies the maximum number of outstanding aio requests that
337	aio requests that this function generates. If it is C<< <= 0 >>, then a	663	this function generates. If it is C<< <= 0 >>, then a suitable default
338	suitable default will be chosen (currently 8).	664	will be chosen (currently 4).
339		665
340	On error, the callback is called without arguments, otherwise it receives	666	On error, the callback is called without arguments, otherwise it receives
341	two array-refs with path-relative entry names.	667	two array-refs with path-relative entry names.
342		668
343	Example:	669	Example:
…		…
351	Implementation notes.	677	Implementation notes.
352		678
353	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.	679	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.
354		680
355	After reading the directory, the modification time, size etc. of the	681	After reading the directory, the modification time, size etc. of the
356	directory before and after the readdir is checked, and if they match, the	682	directory before and after the readdir is checked, and if they match (and
357	link count will be used to decide how many entries are directories (if	683	isn't the current time), the link count will be used to decide how many
358	>= 2). Otherwise, no knowledge of the number of subdirectories will be	684	entries are directories (if >= 2). Otherwise, no knowledge of the number
359	assumed.	685	of subdirectories will be assumed.
360		686
361	Then entires will be sorted into likely directories (everything without a	687	Then entries will be sorted into likely directories (everything without
362	non-initial dot) and likely non-directories (everything else). Then every	688	a non-initial dot currently) and likely non-directories (everything
363	entry + C</.> will be C<stat>'ed, likely directories first. This is often	689	else). Then every entry plus an appended C</.> will be C<stat>'ed,
		690	likely directories first. If that succeeds, it assumes that the entry
		691	is a directory or a symlink to directory (which will be checked
		692	seperately). This is often faster than stat'ing the entry itself because
364	faster because filesystems might detect the type of the entry without	693	filesystems might detect the type of the entry without reading the inode
365	reading the inode data (e.g. ext2fs filetype feature). If that succeeds,	694	data (e.g. ext2fs filetype feature).
366	it assumes that the entry is a directory or a symlink to directory (which
367	will be checked seperately).
368		695
369	If the known number of directories has been reached, the rest of the	696	If the known number of directories (link count - 2) has been reached, the
370	entries is assumed to be non-directories.	697	rest of the entries is assumed to be non-directories.
		698
		699	This only works with certainty on POSIX (= UNIX) filesystems, which
		700	fortunately are the vast majority of filesystems around.
		701
		702	It will also likely work on non-POSIX filesystems with reduced efficiency
		703	as those tend to return 0 or 1 as link counts, which disables the
		704	directory counting heuristic.
371		705
372	=cut	706	=cut
373		707
374	sub aio_scandir($$$) {	708	sub aio_scandir($$;$) {
		709	aio_block {
375	my ($path, $maxreq, $cb) = @_;	710	my ($path, $maxreq, $cb) = @_;
376		711
		712	my $pri = aioreq_pri;
		713
		714	my $grp = aio_group $cb;
		715
377	$maxreq = 8 if $maxreq <= 0;	716	$maxreq = 4 if $maxreq <= 0;
378		717
379	# stat once	718	# stat once
		719	aioreq_pri $pri;
380	aio_stat $path, sub {	720	add $grp aio_stat $path, sub {
381	return $cb->() if $_[0];	721	return $grp->result () if $_[0];
		722	my $now = time;
382	my $hash1 = join ":", (stat _)[0,1,3,7,9];	723	my $hash1 = join ":", (stat _)[0,1,3,7,9];
383		724
384	# read the directory entries	725	# read the directory entries
		726	aioreq_pri $pri;
385	aio_readdir $path, sub {	727	add $grp aio_readdir $path, sub {
386	my $entries = shift	728	my $entries = shift
387	or return $cb->();	729	or return $grp->result ();
388		730
389	# stat the dir another time	731	# stat the dir another time
		732	aioreq_pri $pri;
390	aio_stat $path, sub {	733	add $grp aio_stat $path, sub {
391	my $hash2 = join ":", (stat _)[0,1,3,7,9];	734	my $hash2 = join ":", (stat _)[0,1,3,7,9];
392		735
393	my $ndirs;	736	my $ndirs;
394		737
395	# take the slow route if anything looks fishy	738	# take the slow route if anything looks fishy
396	if ($hash1 ne $hash2) {	739	if ($hash1 ne $hash2 or (stat _)[9] == $now) {
397	$ndirs = -1;	740	$ndirs = -1;
398	} else {	741	} else {
399	# if nlink == 2, we are finished	742	# if nlink == 2, we are finished
400	# on non-posix-fs's, we rely on nlink < 2	743	# on non-posix-fs's, we rely on nlink < 2
401	$ndirs = (stat _)[3] - 2	744	$ndirs = (stat _)[3] - 2
402	or return $cb->([], $entries);	745	or return $grp->result ([], $entries);
403	}
404
405	# sort into likely dirs and likely nondirs
406	# dirs == files without ".", short entries first
407	$entries = [map $_->[0],
408	sort { $b->[1] cmp $a->[1] }
409	map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],
410	@$entries];
411
412	my (@dirs, @nondirs);
413
414	my ($statcb, $schedcb);
415	my $nreq = 0;
416
417	$schedcb = sub {
418	if (@$entries) {
419	if ($nreq < $maxreq) {
420	my $ent = pop @$entries;
421	$nreq++;
422	aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) };
423	}
424	} elsif (!$nreq) {
425	# finished
426	undef $statcb;
427	undef $schedcb;
428	$cb->(\@dirs, \@nondirs) if $cb;
429	undef $cb;
430	}	746	}
		747
		748	# sort into likely dirs and likely nondirs
		749	# dirs == files without ".", short entries first
		750	$entries = [map $_->[0],
		751	sort { $b->[1] cmp $a->[1] }
		752	map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],
		753	@$entries];
		754
		755	my (@dirs, @nondirs);
		756
		757	my $statgrp = add $grp aio_group sub {
		758	$grp->result (\@dirs, \@nondirs);
		759	};
		760
		761	limit $statgrp $maxreq;
		762	feed $statgrp sub {
		763	return unless @$entries;
		764	my $entry = pop @$entries;
		765
		766	aioreq_pri $pri;
		767	add $statgrp aio_stat "$path/$entry/.", sub {
		768	if ($_[0] < 0) {
		769	push @nondirs, $entry;
		770	} else {
		771	# need to check for real directory
		772	aioreq_pri $pri;
		773	add $statgrp aio_lstat "$path/$entry", sub {
		774	if (-d _) {
		775	push @dirs, $entry;
		776
		777	unless (--$ndirs) {
		778	push @nondirs, @$entries;
		779	feed $statgrp;
		780	}
		781	} else {
		782	push @nondirs, $entry;
		783	}
		784	}
		785	}
		786	};
		787	};
431	};	788	};
432	$statcb = sub {
433	my ($status, $entry) = @_;
434
435	if ($status < 0) {
436	$nreq--;
437	push @nondirs, $entry;
438	&$schedcb;
439	} else {
440	# need to check for real directory
441	aio_lstat "$path/$entry", sub {
442	$nreq--;
443
444	if (-d _) {
445	push @dirs, $entry;
446
447	if (!--$ndirs) {
448	push @nondirs, @$entries;
449	$entries = [];
450	}
451	} else {
452	push @nondirs, $entry;
453	}
454
455	&$schedcb;
456	}
457	}
458	};
459
460	&$schedcb while @$entries && $nreq < $maxreq;
461	};	789	};
462	};	790	};
		791
		792	$grp
463	};	793	}
		794	}
		795
		796	=item aio_rmtree $path, $callback->($status)
		797
		798	Delete a directory tree starting (and including) C<$path>, return the
		799	status of the final C<rmdir> only. This is a composite request that
		800	uses C<aio_scandir> to recurse into and rmdir directories, and unlink
		801	everything else.
		802
		803	=cut
		804
		805	sub aio_rmtree;
		806	sub aio_rmtree($;$) {
		807	aio_block {
		808	my ($path, $cb) = @_;
		809
		810	my $pri = aioreq_pri;
		811	my $grp = aio_group $cb;
		812
		813	aioreq_pri $pri;
		814	add $grp aio_scandir $path, 0, sub {
		815	my ($dirs, $nondirs) = @_;
		816
		817	my $dirgrp = aio_group sub {
		818	add $grp aio_rmdir $path, sub {
		819	$grp->result ($_[0]);
		820	};
		821	};
		822
		823	(aioreq_pri $pri), add $dirgrp aio_rmtree "$path/$_" for @$dirs;
		824	(aioreq_pri $pri), add $dirgrp aio_unlink "$path/$_" for @$nondirs;
		825
		826	add $grp $dirgrp;
		827	};
		828
		829	$grp
		830	}
464	}	831	}
465		832
466	=item aio_fsync $fh, $callback->($status)	833	=item aio_fsync $fh, $callback->($status)
467		834
468	Asynchronously call fsync on the given filehandle and call the callback	835	Asynchronously call fsync on the given filehandle and call the callback
…		…
474	callback with the fdatasync result code.	841	callback with the fdatasync result code.
475		842
476	If this call isn't available because your OS lacks it or it couldn't be	843	If this call isn't available because your OS lacks it or it couldn't be
477	detected, it will be emulated by calling C<fsync> instead.	844	detected, it will be emulated by calling C<fsync> instead.
478		845
		846	=item aio_group $callback->(...)
		847
		848	This is a very special aio request: Instead of doing something, it is a
		849	container for other aio requests, which is useful if you want to bundle
		850	many requests into a single, composite, request with a definite callback
		851	and the ability to cancel the whole request with its subrequests.
		852
		853	Returns an object of class L<IO::AIO::GRP>. See its documentation below
		854	for more info.
		855
		856	Example:
		857
		858	my $grp = aio_group sub {
		859	print "all stats done\n";
		860	};
		861
		862	add $grp
		863	(aio_stat ...),
		864	(aio_stat ...),
		865	...;
		866
		867	=item aio_nop $callback->()
		868
		869	This is a special request - it does nothing in itself and is only used for
		870	side effects, such as when you want to add a dummy request to a group so
		871	that finishing the requests in the group depends on executing the given
		872	code.
		873
		874	While this request does nothing, it still goes through the execution
		875	phase and still requires a worker thread. Thus, the callback will not
		876	be executed immediately but only after other requests in the queue have
		877	entered their execution phase. This can be used to measure request
		878	latency.
		879
		880	=item IO::AIO::aio_busy $fractional_seconds, $callback->() *NOT EXPORTED*
		881
		882	Mainly used for debugging and benchmarking, this aio request puts one of
		883	the request workers to sleep for the given time.
		884
		885	While it is theoretically handy to have simple I/O scheduling requests
		886	like sleep and file handle readable/writable, the overhead this creates is
		887	immense (it blocks a thread for a long time) so do not use this function
		888	except to put your application under artificial I/O pressure.
		889
479	=back	890	=back
480		891
		892	=head2 IO::AIO::REQ CLASS
		893
		894	All non-aggregate C<aio_*> functions return an object of this class when
		895	called in non-void context.
		896
		897	=over 4
		898
		899	=item cancel $req
		900
		901	Cancels the request, if possible. Has the effect of skipping execution
		902	when entering the B<execute> state and skipping calling the callback when
		903	entering the the B<result> state, but will leave the request otherwise
		904	untouched. That means that requests that currently execute will not be
		905	stopped and resources held by the request will not be freed prematurely.
		906
		907	=item cb $req $callback->(...)
		908
		909	Replace (or simply set) the callback registered to the request.
		910
		911	=back
		912
		913	=head2 IO::AIO::GRP CLASS
		914
		915	This class is a subclass of L<IO::AIO::REQ>, so all its methods apply to
		916	objects of this class, too.
		917
		918	A IO::AIO::GRP object is a special request that can contain multiple other
		919	aio requests.
		920
		921	You create one by calling the C<aio_group> constructing function with a
		922	callback that will be called when all contained requests have entered the
		923	C<done> state:
		924
		925	my $grp = aio_group sub {
		926	print "all requests are done\n";
		927	};
		928
		929	You add requests by calling the C<add> method with one or more
		930	C<IO::AIO::REQ> objects:
		931
		932	$grp->add (aio_unlink "...");
		933
		934	add $grp aio_stat "...", sub {
		935	$_[0] or return $grp->result ("error");
		936
		937	# add another request dynamically, if first succeeded
		938	add $grp aio_open "...", sub {
		939	$grp->result ("ok");
		940	};
		941	};
		942
		943	This makes it very easy to create composite requests (see the source of
		944	C<aio_move> for an application) that work and feel like simple requests.
		945
		946	=over 4
		947
		948	=item * The IO::AIO::GRP objects will be cleaned up during calls to
		949	C<IO::AIO::poll_cb>, just like any other request.
		950
		951	=item * They can be canceled like any other request. Canceling will cancel not
		952	only the request itself, but also all requests it contains.
		953
		954	=item * They can also can also be added to other IO::AIO::GRP objects.
		955
		956	=item * You must not add requests to a group from within the group callback (or
		957	any later time).
		958
		959	=back
		960
		961	Their lifetime, simplified, looks like this: when they are empty, they
		962	will finish very quickly. If they contain only requests that are in the
		963	C<done> state, they will also finish. Otherwise they will continue to
		964	exist.
		965
		966	That means after creating a group you have some time to add requests. And
		967	in the callbacks of those requests, you can add further requests to the
		968	group. And only when all those requests have finished will the the group
		969	itself finish.
		970
		971	=over 4
		972
		973	=item add $grp ...
		974
		975	=item $grp->add (...)
		976
		977	Add one or more requests to the group. Any type of L<IO::AIO::REQ> can
		978	be added, including other groups, as long as you do not create circular
		979	dependencies.
		980
		981	Returns all its arguments.
		982
		983	=item $grp->cancel_subs
		984
		985	Cancel all subrequests and clears any feeder, but not the group request
		986	itself. Useful when you queued a lot of events but got a result early.
		987
		988	=item $grp->result (...)
		989
		990	Set the result value(s) that will be passed to the group callback when all
		991	subrequests have finished and set thre groups errno to the current value
		992	of errno (just like calling C<errno> without an error number). By default,
		993	no argument will be passed and errno is zero.
		994
		995	=item $grp->errno ([$errno])
		996
		997	Sets the group errno value to C<$errno>, or the current value of errno
		998	when the argument is missing.
		999
		1000	Every aio request has an associated errno value that is restored when
		1001	the callback is invoked. This method lets you change this value from its
		1002	default (0).
		1003
		1004	Calling C<result> will also set errno, so make sure you either set C<$!>
		1005	before the call to C<result>, or call c<errno> after it.
		1006
		1007	=item feed $grp $callback->($grp)
		1008
		1009	Sets a feeder/generator on this group: every group can have an attached
		1010	generator that generates requests if idle. The idea behind this is that,
		1011	although you could just queue as many requests as you want in a group,
		1012	this might starve other requests for a potentially long time. For
		1013	example, C<aio_scandir> might generate hundreds of thousands C<aio_stat>
		1014	requests, delaying any later requests for a long time.
		1015
		1016	To avoid this, and allow incremental generation of requests, you can
		1017	instead a group and set a feeder on it that generates those requests. The
		1018	feed callback will be called whenever there are few enough (see C<limit>,
		1019	below) requests active in the group itself and is expected to queue more
		1020	requests.
		1021
		1022	The feed callback can queue as many requests as it likes (i.e. C<add> does
		1023	not impose any limits).
		1024
		1025	If the feed does not queue more requests when called, it will be
		1026	automatically removed from the group.
		1027
		1028	If the feed limit is C<0>, it will be set to C<2> automatically.
		1029
		1030	Example:
		1031
		1032	# stat all files in @files, but only ever use four aio requests concurrently:
		1033
		1034	my $grp = aio_group sub { print "finished\n" };
		1035	limit $grp 4;
		1036	feed $grp sub {
		1037	my $file = pop @files
		1038	or return;
		1039
		1040	add $grp aio_stat $file, sub { ... };
		1041	};
		1042
		1043	=item limit $grp $num
		1044
		1045	Sets the feeder limit for the group: The feeder will be called whenever
		1046	the group contains less than this many requests.
		1047
		1048	Setting the limit to C<0> will pause the feeding process.
		1049
		1050	=back
		1051
481	=head2 SUPPORT FUNCTIONS	1052	=head2 SUPPORT FUNCTIONS
		1053
		1054	=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION
482		1055
483	=over 4	1056	=over 4
484		1057
485	=item $fileno = IO::AIO::poll_fileno	1058	=item $fileno = IO::AIO::poll_fileno
486		1059
…		…
491		1064
492	See C<poll_cb> for an example.	1065	See C<poll_cb> for an example.
493		1066
494	=item IO::AIO::poll_cb	1067	=item IO::AIO::poll_cb
495		1068
496	Process all outstanding events on the result pipe. You have to call this	1069	Process some outstanding events on the result pipe. You have to call this
497	regularly. Returns the number of events processed. Returns immediately	1070	regularly. Returns the number of events processed. Returns immediately
498	when no events are outstanding.	1071	when no events are outstanding. The amount of events processed depends on
		1072	the settings of C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>.
		1073
		1074	If not all requests were processed for whatever reason, the filehandle
		1075	will still be ready when C<poll_cb> returns.
499		1076
500	Example: Install an Event watcher that automatically calls	1077	Example: Install an Event watcher that automatically calls
501	IO::AIO::poll_cb with high priority:	1078	IO::AIO::poll_cb with high priority:
502		1079
503	Event->io (fd => IO::AIO::poll_fileno,	1080	Event->io (fd => IO::AIO::poll_fileno,
504	poll => 'r', async => 1,	1081	poll => 'r', async => 1,
505	cb => \&IO::AIO::poll_cb);	1082	cb => \&IO::AIO::poll_cb);
506		1083
		1084	=item IO::AIO::max_poll_reqs $nreqs
		1085
		1086	=item IO::AIO::max_poll_time $seconds
		1087
		1088	These set the maximum number of requests (default C<0>, meaning infinity)
		1089	that are being processed by C<IO::AIO::poll_cb> in one call, respectively
		1090	the maximum amount of time (default C<0>, meaning infinity) spent in
		1091	C<IO::AIO::poll_cb> to process requests (more correctly the mininum amount
		1092	of time C<poll_cb> is allowed to use).
		1093
		1094	Setting C<max_poll_time> to a non-zero value creates an overhead of one
		1095	syscall per request processed, which is not normally a problem unless your
		1096	callbacks are really really fast or your OS is really really slow (I am
		1097	not mentioning Solaris here). Using C<max_poll_reqs> incurs no overhead.
		1098
		1099	Setting these is useful if you want to ensure some level of
		1100	interactiveness when perl is not fast enough to process all requests in
		1101	time.
		1102
		1103	For interactive programs, values such as C<0.01> to C<0.1> should be fine.
		1104
		1105	Example: Install an Event watcher that automatically calls
		1106	IO::AIO::poll_cb with low priority, to ensure that other parts of the
		1107	program get the CPU sometimes even under high AIO load.
		1108
		1109	# try not to spend much more than 0.1s in poll_cb
		1110	IO::AIO::max_poll_time 0.1;
		1111
		1112	# use a low priority so other tasks have priority
		1113	Event->io (fd => IO::AIO::poll_fileno,
		1114	poll => 'r', nice => 1,
		1115	cb => &IO::AIO::poll_cb);
		1116
507	=item IO::AIO::poll_wait	1117	=item IO::AIO::poll_wait
508		1118
		1119	If there are any outstanding requests and none of them in the result
509	Wait till the result filehandle becomes ready for reading (simply does a	1120	phase, wait till the result filehandle becomes ready for reading (simply
510	C<select> on the filehandle. This is useful if you want to synchronously wait	1121	does a C<select> on the filehandle. This is useful if you want to
511	for some requests to finish).	1122	synchronously wait for some requests to finish).
512		1123
513	See C<nreqs> for an example.	1124	See C<nreqs> for an example.
514		1125
		1126	=item IO::AIO::poll
		1127
		1128	Waits until some requests have been handled.
		1129
		1130	Returns the number of requests processed, but is otherwise strictly
		1131	equivalent to:
		1132
		1133	IO::AIO::poll_wait, IO::AIO::poll_cb
		1134
515	=item IO::AIO::nreqs	1135	=item IO::AIO::flush
516		1136
517	Returns the number of requests currently outstanding (i.e. for which their	1137	Wait till all outstanding AIO requests have been handled.
518	callback has not been invoked yet).
519		1138
520	Example: wait till there are no outstanding requests anymore:	1139	Strictly equivalent to:
521		1140
522	IO::AIO::poll_wait, IO::AIO::poll_cb	1141	IO::AIO::poll_wait, IO::AIO::poll_cb
523	while IO::AIO::nreqs;	1142	while IO::AIO::nreqs;
524		1143
525	=item IO::AIO::flush	1144	=back
526		1145
527	Wait till all outstanding AIO requests have been handled.	1146	=head3 CONTROLLING THE NUMBER OF THREADS
528		1147
529	Strictly equivalent to:	1148	=over
530
531	IO::AIO::poll_wait, IO::AIO::poll_cb
532	while IO::AIO::nreqs;
533
534	=item IO::AIO::poll
535
536	Waits until some requests have been handled.
537
538	Strictly equivalent to:
539
540	IO::AIO::poll_wait, IO::AIO::poll_cb
541	if IO::AIO::nreqs;
542		1149
543	=item IO::AIO::min_parallel $nthreads	1150	=item IO::AIO::min_parallel $nthreads
544		1151
545	Set the minimum number of AIO threads to C<$nthreads>. The current default	1152	Set the minimum number of AIO threads to C<$nthreads>. The current
546	is C<4>, which means four asynchronous operations can be done at one time	1153	default is C<8>, which means eight asynchronous operations can execute
547	(the number of outstanding operations, however, is unlimited).	1154	concurrently at any one time (the number of outstanding requests,
		1155	however, is unlimited).
548		1156
549	IO::AIO starts threads only on demand, when an AIO request is queued and	1157	IO::AIO starts threads only on demand, when an AIO request is queued and
550	no free thread exists.	1158	no free thread exists. Please note that queueing up a hundred requests can
		1159	create demand for a hundred threads, even if it turns out that everything
		1160	is in the cache and could have been processed faster by a single thread.
551		1161
552	It is recommended to keep the number of threads low, as some Linux	1162	It is recommended to keep the number of threads relatively low, as some
553	kernel versions will scale negatively with the number of threads (higher	1163	Linux kernel versions will scale negatively with the number of threads
554	parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32	1164	(higher parallelity => MUCH higher latency). With current Linux 2.6
555	threads should be fine.	1165	versions, 4-32 threads should be fine.
556		1166
557	Under most circumstances you don't need to call this function, as the	1167	Under most circumstances you don't need to call this function, as the
558	module selects a default that is suitable for low to moderate load.	1168	module selects a default that is suitable for low to moderate load.
559		1169
560	=item IO::AIO::max_parallel $nthreads	1170	=item IO::AIO::max_parallel $nthreads
…		…
569	This module automatically runs C<max_parallel 0> at program end, to ensure	1179	This module automatically runs C<max_parallel 0> at program end, to ensure
570	that all threads are killed and that there are no outstanding requests.	1180	that all threads are killed and that there are no outstanding requests.
571		1181
572	Under normal circumstances you don't need to call this function.	1182	Under normal circumstances you don't need to call this function.
573		1183
		1184	=item IO::AIO::max_idle $nthreads
		1185
		1186	Limit the number of threads (default: 4) that are allowed to idle (i.e.,
		1187	threads that did not get a request to process within 10 seconds). That
		1188	means if a thread becomes idle while C<$nthreads> other threads are also
		1189	idle, it will free its resources and exit.
		1190
		1191	This is useful when you allow a large number of threads (e.g. 100 or 1000)
		1192	to allow for extremely high load situations, but want to free resources
		1193	under normal circumstances (1000 threads can easily consume 30MB of RAM).
		1194
		1195	The default is probably ok in most situations, especially if thread
		1196	creation is fast. If thread creation is very slow on your system you might
		1197	want to use larger values.
		1198
574	=item $oldnreqs = IO::AIO::max_outstanding $nreqs	1199	=item $oldmaxreqs = IO::AIO::max_outstanding $maxreqs
		1200
		1201	This is a very bad function to use in interactive programs because it
		1202	blocks, and a bad way to reduce concurrency because it is inexact: Better
		1203	use an C<aio_group> together with a feed callback.
575		1204
576	Sets the maximum number of outstanding requests to C<$nreqs>. If you	1205	Sets the maximum number of outstanding requests to C<$nreqs>. If you
577	try to queue up more than this number of requests, the caller will block until	1206	to queue up more than this number of requests, the next call to the
578	some requests have been handled.	1207	C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>)
		1208	function will block until the limit is no longer exceeded.
579		1209
580	The default is very large, so normally there is no practical limit. If you	1210	The default value is very large, so there is no practical limit on the
581	queue up many requests in a loop it often improves speed if you set	1211	number of outstanding requests.
582	this to a relatively low number, such as C<100>.
583		1212
584	Under normal circumstances you don't need to call this function.	1213	You can still queue as many requests as you want. Therefore,
		1214	C<max_oustsanding> is mainly useful in simple scripts (with low values) or
		1215	as a stop gap to shield against fatal memory overflow (with large values).
		1216
		1217	=back
		1218
		1219	=head3 STATISTICAL INFORMATION
		1220
		1221	=over
		1222
		1223	=item IO::AIO::nreqs
		1224
		1225	Returns the number of requests currently in the ready, execute or pending
		1226	states (i.e. for which their callback has not been invoked yet).
		1227
		1228	Example: wait till there are no outstanding requests anymore:
		1229
		1230	IO::AIO::poll_wait, IO::AIO::poll_cb
		1231	while IO::AIO::nreqs;
		1232
		1233	=item IO::AIO::nready
		1234
		1235	Returns the number of requests currently in the ready state (not yet
		1236	executed).
		1237
		1238	=item IO::AIO::npending
		1239
		1240	Returns the number of requests currently in the pending state (executed,
		1241	but not yet processed by poll_cb).
585		1242
586	=back	1243	=back
587		1244
588	=cut	1245	=cut
589		1246
…		…
601	or return undef;	1258	or return undef;
602		1259
603	*$sym	1260	*$sym
604	}	1261	}
605		1262
606	min_parallel 4;	1263	min_parallel 8;
607		1264
608	END {	1265	END { flush }
609	max_parallel 0;
610	}
611		1266
612	1;	1267	1;
613		1268
614	=head2 FORK BEHAVIOUR	1269	=head2 FORK BEHAVIOUR
		1270
		1271	This module should do "the right thing" when the process using it forks:
615		1272
616	Before the fork, IO::AIO enters a quiescent state where no requests	1273	Before the fork, IO::AIO enters a quiescent state where no requests
617	can be added in other threads and no results will be processed. After	1274	can be added in other threads and no results will be processed. After
618	the fork the parent simply leaves the quiescent state and continues	1275	the fork the parent simply leaves the quiescent state and continues
619	request/result processing, while the child clears the request/result	1276	request/result processing, while the child frees the request/result queue
620	queue (so the requests started before the fork will only be handled in	1277	(so that the requests started before the fork will only be handled in the
621	the parent). Threats will be started on demand until the limit ste in the	1278	parent). Threads will be started on demand until the limit set in the
622	parent process has been reached again.	1279	parent process has been reached again.
623		1280
		1281	In short: the parent will, after a short pause, continue as if fork had
		1282	not been called, while the child will act as if IO::AIO has not been used
		1283	yet.
		1284
		1285	=head2 MEMORY USAGE
		1286
		1287	Per-request usage:
		1288
		1289	Each aio request uses - depending on your architecture - around 100-200
		1290	bytes of memory. In addition, stat requests need a stat buffer (possibly
		1291	a few hundred bytes), readdir requires a result buffer and so on. Perl
		1292	scalars and other data passed into aio requests will also be locked and
		1293	will consume memory till the request has entered the done state.
		1294
		1295	This is now awfully much, so queuing lots of requests is not usually a
		1296	problem.
		1297
		1298	Per-thread usage:
		1299
		1300	In the execution phase, some aio requests require more memory for
		1301	temporary buffers, and each thread requires a stack and other data
		1302	structures (usually around 16k-128k, depending on the OS).
		1303
		1304	=head1 KNOWN BUGS
		1305
		1306	Known bugs will be fixed in the next release.
		1307
624	=head1 SEE ALSO	1308	=head1 SEE ALSO
625		1309
626	L<Coro>, L<Linux::AIO>.	1310	L<Coro::AIO>.
627		1311
628	=head1 AUTHOR	1312	=head1 AUTHOR
629		1313
630	Marc Lehmann <schmorp@schmorp.de>	1314	Marc Lehmann <schmorp@schmorp.de>
631	http://home.schmorp.de/	1315	http://home.schmorp.de/

Diff Legend

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