ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/IO-AIO/AIO.pm

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.42 by root, Mon Dec 26 18:15:23 2005 UTC vs.
Revision 1.148 by root, Sat Jun 6 17:25:13 2009 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
21	open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!";	22	use IO::AIO 2;
22	my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb });
23		23
24	# Event	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 (EV, Event, Glib, Tk, POE, urxvt, pureperl...)
		32	use AnyEvent::AIO;
		33
		34	# EV integration
		35	my $w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
		36
		37	# Event integration
25	Event->io (fd => IO::AIO::poll_fileno,	38	Event->io (fd => IO::AIO::poll_fileno,
26	poll => 'r',	39	poll => 'r',
27	cb => \&IO::AIO::poll_cb);	40	cb => \&IO::AIO::poll_cb);
28		41
29	# Glib/Gtk2	42	# Glib/Gtk2 integration
30	add_watch Glib::IO IO::AIO::poll_fileno,	43	add_watch Glib::IO IO::AIO::poll_fileno,
31	in => sub { IO::AIO::poll_cb; 1 };	44	in => sub { IO::AIO::poll_cb; 1 };
32		45
33	# Tk	46	# Tk integration
34	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",	47	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
35	readable => \&IO::AIO::poll_cb);	48	readable => \&IO::AIO::poll_cb);
36		49
37	# Danga::Socket	50	# Danga::Socket integration
38	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>	51	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
39	\&IO::AIO::poll_cb);	52	\&IO::AIO::poll_cb);
40		53
41
42	=head1 DESCRIPTION	54	=head1 DESCRIPTION
43		55
44	This module implements asynchronous I/O using whatever means your	56	This module implements asynchronous I/O using whatever means your
45	operating system supports.	57	operating system supports.
46		58
		59	Asynchronous means that operations that can normally block your program
		60	(e.g. reading from disk) will be done asynchronously: the operation
		61	will still block, but you can do something else in the meantime. This
		62	is extremely useful for programs that need to stay interactive even
		63	when doing heavy I/O (GUI programs, high performance network servers
		64	etc.), but can also be used to easily do operations in parallel that are
		65	normally done sequentially, e.g. stat'ing many files, which is much faster
		66	on a RAID volume or over NFS when you do a number of stat operations
		67	concurrently.
		68
		69	While most of this works on all types of file descriptors (for
		70	example sockets), using these functions on file descriptors that
		71	support nonblocking operation (again, sockets, pipes etc.) is very
		72	inefficient. Use an event loop for that (such as the L<Event|Event>
		73	module): IO::AIO will naturally fit into such an event loop itself.
		74
47	Currently, a number of threads are started that execute your read/writes	75	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	76	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	77	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	78	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	79	functions available on many operating systems. However, they are often
52	not well-supported (Linux doesn't allow them on normal files currently,	80	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	81	files currently, for example), and they would only support aio_read and
54	remaining functionality would have to be implemented using threads anyway.	82	aio_write, so the remaining functionality would have to be implemented
		83	using threads anyway.
55		84
56	Although the module will work with in the presence of other threads, it is	85	Although the module will work in the presence of other (Perl-) threads,
57	currently not reentrant, so use appropriate locking yourself, always call	86	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	87	yourself, always call C<poll_cb> from within the same thread, or never
59	C<aio_> functions) recursively.	88	call C<poll_cb> (or other C<aio_> functions) recursively.
		89
		90	=head2 EXAMPLE
		91
		92	This is a simple example that uses the Event module and loads
		93	F</etc/passwd> asynchronously:
		94
		95	use Fcntl;
		96	use Event;
		97	use IO::AIO;
		98
		99	# register the IO::AIO callback with Event
		100	Event->io (fd => IO::AIO::poll_fileno,
		101	poll => 'r',
		102	cb => \&IO::AIO::poll_cb);
		103
		104	# queue the request to open /etc/passwd
		105	aio_open "/etc/passwd", O_RDONLY, 0, sub {
		106	my $fh = shift
		107	or die "error while opening: $!";
		108
		109	# stat'ing filehandles is generally non-blocking
		110	my $size = -s $fh;
		111
		112	# queue a request to read the file
		113	my $contents;
		114	aio_read $fh, 0, $size, $contents, 0, sub {
		115	$_[0] == $size
		116	or die "short read: $!";
		117
		118	close $fh;
		119
		120	# file contents now in $contents
		121	print $contents;
		122
		123	# exit event loop and program
		124	Event::unloop;
		125	};
		126	};
		127
		128	# possibly queue up other requests, or open GUI windows,
		129	# check for sockets etc. etc.
		130
		131	# process events as long as there are some:
		132	Event::loop;
		133
		134	=head1 REQUEST ANATOMY AND LIFETIME
		135
		136	Every C<aio_*> function creates a request. which is a C data structure not
		137	directly visible to Perl.
		138
		139	If called in non-void context, every request function returns a Perl
		140	object representing the request. In void context, nothing is returned,
		141	which saves a bit of memory.
		142
		143	The perl object is a fairly standard ref-to-hash object. The hash contents
		144	are not used by IO::AIO so you are free to store anything you like in it.
		145
		146	During their existance, aio requests travel through the following states,
		147	in order:
		148
		149	=over 4
		150
		151	=item ready
		152
		153	Immediately after a request is created it is put into the ready state,
		154	waiting for a thread to execute it.
		155
		156	=item execute
		157
		158	A thread has accepted the request for processing and is currently
		159	executing it (e.g. blocking in read).
		160
		161	=item pending
		162
		163	The request has been executed and is waiting for result processing.
		164
		165	While request submission and execution is fully asynchronous, result
		166	processing is not and relies on the perl interpreter calling C<poll_cb>
		167	(or another function with the same effect).
		168
		169	=item result
		170
		171	The request results are processed synchronously by C<poll_cb>.
		172
		173	The C<poll_cb> function will process all outstanding aio requests by
		174	calling their callbacks, freeing memory associated with them and managing
		175	any groups they are contained in.
		176
		177	=item done
		178
		179	Request has reached the end of its lifetime and holds no resources anymore
		180	(except possibly for the Perl object, but its connection to the actual
		181	aio request is severed and calling its methods will either do nothing or
		182	result in a runtime error).
		183
		184	=back
60		185
61	=cut	186	=cut
62		187
63	package IO::AIO;	188	package IO::AIO;
64		189
		190	use Carp ();
		191
65	no warnings;	192	no warnings;
		193	use strict 'vars';
66		194
67	use base 'Exporter';	195	use base 'Exporter';
68		196
69	use Fcntl ();
70
71	BEGIN {	197	BEGIN {
72	$VERSION = '1.61';	198	our $VERSION = '3.19';
73		199
74	@EXPORT = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat	200	our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close
75	aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink	201	aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx
76	aio_fsync aio_fdatasync aio_readahead);	202	aio_scandir aio_symlink aio_readlink aio_sync aio_fsync
77	@EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel	203	aio_fdatasync aio_sync_file_range aio_pathsync aio_readahead
78	max_outstanding nreqs);	204	aio_rename aio_link aio_move aio_copy aio_group
		205	aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown
		206	aio_chmod aio_utime aio_truncate);
		207
		208	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice));
		209	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush
		210	min_parallel max_parallel max_idle
		211	nreqs nready npending nthreads
		212	max_poll_time max_poll_reqs);
		213
		214	push @AIO_REQ, qw(aio_busy); # not exported
		215
		216	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';
79		217
80	require XSLoader;	218	require XSLoader;
81	XSLoader::load IO::AIO, $VERSION;	219	XSLoader::load ("IO::AIO", $VERSION);
82	}	220	}
83		221
84	=head1 FUNCTIONS	222	=head1 FUNCTIONS
85		223
86	=head2 AIO FUNCTIONS	224	=head2 AIO REQUEST FUNCTIONS
87		225
88	All the C<aio_*> calls are more or less thin wrappers around the syscall	226	All the C<aio_*> calls are more or less thin wrappers around the syscall
89	with the same name (sans C<aio_>). The arguments are similar or identical,	227	with the same name (sans C<aio_>). The arguments are similar or identical,
90	and they all accept an additional (and optional) C<$callback> argument	228	and they all accept an additional (and optional) C<$callback> argument
91	which must be a code reference. This code reference will get called with	229	which must be a code reference. This code reference will get called with
92	the syscall return code (e.g. most syscalls return C<-1> on error, unlike	230	the syscall return code (e.g. most syscalls return C<-1> on error, unlike
93	perl, which usually delivers "false") as it's sole argument when the given	231	perl, which usually delivers "false") as its sole argument after the given
94	syscall has been executed asynchronously.	232	syscall has been executed asynchronously.
95		233
96	All functions expecting a filehandle keep a copy of the filehandle	234	All functions expecting a filehandle keep a copy of the filehandle
97	internally until the request has finished.	235	internally until the request has finished.
98		236
		237	All functions return request objects of type L<IO::AIO::REQ> that allow
		238	further manipulation of those requests while they are in-flight.
		239
99	The pathnames you pass to these routines I<must> be absolute and	240	The pathnames you pass to these routines I<must> be absolute and
100	encoded in byte form. The reason for the former is that at the time the	241	encoded as octets. The reason for the former is that at the time the
101	request is being executed, the current working directory could have	242	request is being executed, the current working directory could have
102	changed. Alternatively, you can make sure that you never change the	243	changed. Alternatively, you can make sure that you never change the
103	current working directory.	244	current working directory anywhere in the program and then use relative
		245	paths.
104		246
105	To encode pathnames to byte form, either make sure you either: a)	247	To encode pathnames as octets, either make sure you either: a) always pass
106	always pass in filenames you got from outside (command line, readdir	248	in filenames you got from outside (command line, readdir etc.) without
107	etc.), b) are ASCII or ISO 8859-1, c) use the Encode module and encode	249	tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module and encode
108	your pathnames to the locale (or other) encoding in effect in the user	250	your pathnames to the locale (or other) encoding in effect in the user
109	environment, d) use Glib::filename_from_unicode on unicode filenames or e)	251	environment, d) use Glib::filename_from_unicode on unicode filenames or e)
110	use something else.	252	use something else to ensure your scalar has the correct contents.
		253
		254	This works, btw. independent of the internal UTF-8 bit, which IO::AIO
		255	handles correctly whether it is set or not.
111		256
112	=over 4	257	=over 4
		258
		259	=item $prev_pri = aioreq_pri [$pri]
		260
		261	Returns the priority value that would be used for the next request and, if
		262	C<$pri> is given, sets the priority for the next aio request.
		263
		264	The default priority is C<0>, the minimum and maximum priorities are C<-4>
		265	and C<4>, respectively. Requests with higher priority will be serviced
		266	first.
		267
		268	The priority will be reset to C<0> after each call to one of the C<aio_*>
		269	functions.
		270
		271	Example: open a file with low priority, then read something from it with
		272	higher priority so the read request is serviced before other low priority
		273	open requests (potentially spamming the cache):
		274
		275	aioreq_pri -3;
		276	aio_open ..., sub {
		277	return unless $_[0];
		278
		279	aioreq_pri -2;
		280	aio_read $_[0], ..., sub {
		281	...
		282	};
		283	};
		284
		285
		286	=item aioreq_nice $pri_adjust
		287
		288	Similar to C<aioreq_pri>, but subtracts the given value from the current
		289	priority, so the effect is cumulative.
		290
113		291
114	=item aio_open $pathname, $flags, $mode, $callback->($fh)	292	=item aio_open $pathname, $flags, $mode, $callback->($fh)
115		293
116	Asynchronously open or create a file and call the callback with a newly	294	Asynchronously open or create a file and call the callback with a newly
117	created filehandle for the file.	295	created filehandle for the file.
…		…
123	list. They are the same as used by C<sysopen>.	301	list. They are the same as used by C<sysopen>.
124		302
125	Likewise, C<$mode> specifies the mode of the newly created file, if it	303	Likewise, C<$mode> specifies the mode of the newly created file, if it
126	didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,	304	didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,
127	except that it is mandatory (i.e. use C<0> if you don't create new files,	305	except that it is mandatory (i.e. use C<0> if you don't create new files,
128	and C<0666> or C<0777> if you do).	306	and C<0666> or C<0777> if you do). Note that the C<$mode> will be modified
		307	by the umask in effect then the request is being executed, so better never
		308	change the umask.
129		309
130	Example:	310	Example:
131		311
132	aio_open "/etc/passwd", O_RDONLY, 0, sub {	312	aio_open "/etc/passwd", O_RDONLY, 0, sub {
133	if ($_[0]) {	313	if ($_[0]) {
…		…
136	} else {	316	} else {
137	die "open failed: $!\n";	317	die "open failed: $!\n";
138	}	318	}
139	};	319	};
140		320
		321
141	=item aio_close $fh, $callback->($status)	322	=item aio_close $fh, $callback->($status)
142		323
143	Asynchronously close a file and call the callback with the result	324	Asynchronously close a file and call the callback with the result
144	code. I<WARNING:> although accepted, you should not pass in a perl	325	code.
145	filehandle here, as perl will likely close the file descriptor another
146	time when the filehandle is destroyed. Normally, you can safely call perls
147	C<close> or just let filehandles go out of scope.
148		326
149	This is supposed to be a bug in the API, so that might change. It's	327	Unfortunately, you can't do this to perl. Perl I<insists> very strongly on
150	therefore best to avoid this function.	328	closing the file descriptor associated with the filehandle itself.
		329
		330	Therefore, C<aio_close> will not close the filehandle - instead it will
		331	use dup2 to overwrite the file descriptor with the write-end of a pipe
		332	(the pipe fd will be created on demand and will be cached).
		333
		334	Or in other words: the file descriptor will be closed, but it will not be
		335	free for reuse until the perl filehandle is closed.
		336
		337	=cut
151		338
152	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	339	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
153		340
154	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	341	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
155		342
156	Reads or writes C<length> bytes from the specified C<fh> and C<offset>	343	Reads or writes C<$length> bytes from or to the specified C<$fh> and
157	into the scalar given by C<data> and offset C<dataoffset> and calls the	344	C<$offset> into the scalar given by C<$data> and offset C<$dataoffset>
158	callback without the actual number of bytes read (or -1 on error, just	345	and calls the callback without the actual number of bytes read (or -1 on
159	like the syscall).	346	error, just like the syscall).
		347
		348	C<aio_read> will, like C<sysread>, shrink or grow the C<$data> scalar to
		349	offset plus the actual number of bytes read.
		350
		351	If C<$offset> is undefined, then the current file descriptor offset will
		352	be used (and updated), otherwise the file descriptor offset will not be
		353	changed by these calls.
		354
		355	If C<$length> is undefined in C<aio_write>, use the remaining length of
		356	C<$data>.
		357
		358	If C<$dataoffset> is less than zero, it will be counted from the end of
		359	C<$data>.
160		360
161	The C<$data> scalar I<MUST NOT> be modified in any way while the request	361	The C<$data> scalar I<MUST NOT> be modified in any way while the request
162	is outstanding. Modifying it can result in segfaults or WW3 (if the	362	is outstanding. Modifying it can result in segfaults or World War III (if
163	necessary/optional hardware is installed).	363	the necessary/optional hardware is installed).
164		364
165	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at	365	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at
166	offset C<0> within the scalar:	366	offset C<0> within the scalar:
167		367
168	aio_read $fh, 7, 15, $buffer, 0, sub {	368	aio_read $fh, 7, 15, $buffer, 0, sub {
169	$_[0] > 0 or die "read error: $!";	369	$_[0] > 0 or die "read error: $!";
170	print "read $_[0] bytes: <$buffer>\n";	370	print "read $_[0] bytes: <$buffer>\n";
171	};	371	};
		372
172		373
173	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)	374	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
174		375
175	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts	376	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
176	reading at byte offset C<$in_offset>, and starts writing at the current	377	reading at byte offset C<$in_offset>, and starts writing at the current
…		…
190	C<$in_fh> than are written, and there is no way to find out how many	391	C<$in_fh> than are written, and there is no way to find out how many
191	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only	392	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only
192	provides the number of bytes written to C<$out_fh>. Only if the result	393	provides the number of bytes written to C<$out_fh>. Only if the result
193	value equals C<$length> one can assume that C<$length> bytes have been	394	value equals C<$length> one can assume that C<$length> bytes have been
194	read.	395	read.
		396
195		397
196	=item aio_readahead $fh,$offset,$length, $callback->($retval)	398	=item aio_readahead $fh,$offset,$length, $callback->($retval)
197		399
198	C<aio_readahead> populates the page cache with data from a file so that	400	C<aio_readahead> populates the page cache with data from a file so that
199	subsequent reads from that file will not block on disk I/O. The C<$offset>	401	subsequent reads from that file will not block on disk I/O. The C<$offset>
…		…
205	file. The current file offset of the file is left unchanged.	407	file. The current file offset of the file is left unchanged.
206		408
207	If that syscall doesn't exist (likely if your OS isn't Linux) it will be	409	If that syscall doesn't exist (likely if your OS isn't Linux) it will be
208	emulated by simply reading the data, which would have a similar effect.	410	emulated by simply reading the data, which would have a similar effect.
209		411
		412
210	=item aio_stat $fh_or_path, $callback->($status)	413	=item aio_stat $fh_or_path, $callback->($status)
211		414
212	=item aio_lstat $fh, $callback->($status)	415	=item aio_lstat $fh, $callback->($status)
213		416
214	Works like perl's C<stat> or C<lstat> in void context. The callback will	417	Works like perl's C<stat> or C<lstat> in void context. The callback will
…		…
227	aio_stat "/etc/passwd", sub {	430	aio_stat "/etc/passwd", sub {
228	$_[0] and die "stat failed: $!";	431	$_[0] and die "stat failed: $!";
229	print "size is ", -s _, "\n";	432	print "size is ", -s _, "\n";
230	};	433	};
231		434
		435
		436	=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
		437
		438	Works like perl's C<utime> function (including the special case of $atime
		439	and $mtime being undef). Fractional times are supported if the underlying
		440	syscalls support them.
		441
		442	When called with a pathname, uses utimes(2) if available, otherwise
		443	utime(2). If called on a file descriptor, uses futimes(2) if available,
		444	otherwise returns ENOSYS, so this is not portable.
		445
		446	Examples:
		447
		448	# set atime and mtime to current time (basically touch(1)):
		449	aio_utime "path", undef, undef;
		450	# set atime to current time and mtime to beginning of the epoch:
		451	aio_utime "path", time, undef; # undef==0
		452
		453
		454	=item aio_chown $fh_or_path, $uid, $gid, $callback->($status)
		455
		456	Works like perl's C<chown> function, except that C<undef> for either $uid
		457	or $gid is being interpreted as "do not change" (but -1 can also be used).
		458
		459	Examples:
		460
		461	# same as "chown root path" in the shell:
		462	aio_chown "path", 0, -1;
		463	# same as above:
		464	aio_chown "path", 0, undef;
		465
		466
		467	=item aio_truncate $fh_or_path, $offset, $callback->($status)
		468
		469	Works like truncate(2) or ftruncate(2).
		470
		471
		472	=item aio_chmod $fh_or_path, $mode, $callback->($status)
		473
		474	Works like perl's C<chmod> function.
		475
		476
232	=item aio_unlink $pathname, $callback->($status)	477	=item aio_unlink $pathname, $callback->($status)
233		478
234	Asynchronously unlink (delete) a file and call the callback with the	479	Asynchronously unlink (delete) a file and call the callback with the
235	result code.	480	result code.
236		481
		482
		483	=item aio_mknod $path, $mode, $dev, $callback->($status)
		484
		485	[EXPERIMENTAL]
		486
		487	Asynchronously create a device node (or fifo). See mknod(2).
		488
		489	The only (POSIX-) portable way of calling this function is:
		490
		491	aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ...
		492
		493
		494	=item aio_link $srcpath, $dstpath, $callback->($status)
		495
		496	Asynchronously create a new link to the existing object at C<$srcpath> at
		497	the path C<$dstpath> and call the callback with the result code.
		498
		499
		500	=item aio_symlink $srcpath, $dstpath, $callback->($status)
		501
		502	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at
		503	the path C<$dstpath> and call the callback with the result code.
		504
		505
		506	=item aio_readlink $path, $callback->($link)
		507
		508	Asynchronously read the symlink specified by C<$path> and pass it to
		509	the callback. If an error occurs, nothing or undef gets passed to the
		510	callback.
		511
		512
		513	=item aio_rename $srcpath, $dstpath, $callback->($status)
		514
		515	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as
		516	rename(2) and call the callback with the result code.
		517
		518
		519	=item aio_mkdir $pathname, $mode, $callback->($status)
		520
		521	Asynchronously mkdir (create) a directory and call the callback with
		522	the result code. C<$mode> will be modified by the umask at the time the
		523	request is executed, so do not change your umask.
		524
		525
237	=item aio_rmdir $pathname, $callback->($status)	526	=item aio_rmdir $pathname, $callback->($status)
238		527
239	Asynchronously rmdir (delete) a directory and call the callback with the	528	Asynchronously rmdir (delete) a directory and call the callback with the
240	result code.	529	result code.
241		530
		531
242	=item aio_readdir $pathname $callback->($entries)	532	=item aio_readdir $pathname, $callback->($entries)
243		533
244	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire	534	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
245	directory (i.e. opendir + readdir + closedir). The entries will not be	535	directory (i.e. opendir + readdir + closedir). The entries will not be
246	sorted, and will B<NOT> include the C<.> and C<..> entries.	536	sorted, and will B<NOT> include the C<.> and C<..> entries.
247		537
248	The callback a single argument which is either C<undef> or an array-ref	538	The callback is passed a single argument which is either C<undef> or an
249	with the filenames.	539	array-ref with the filenames.
		540
		541
		542	=item aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		543
		544	Quite similar to C<aio_readdir>, but the C<$flags> argument allows to tune
		545	behaviour and output format. In case of an error, C<$entries> will be
		546	C<undef>.
		547
		548	The flags are a combination of the following constants, ORed together (the
		549	flags will also be passed to the callback, possibly modified):
		550
		551	=over 4
		552
		553	=item AIO::READDIR_DENTS
		554
		555	When this flag is off, then the callback gets an arrayref with of names
		556	only (as with C<aio_readdir>), otherwise it gets an arrayref with
		557	C<[$name, $inode, $type]> arrayrefs, each describing a single directory
		558	entry in more detail.
		559
		560	C<$name> is the name of the entry.
		561
		562	C<$inode> is the inode number (which might not be exact on systems with 64
		563	bit inode numbers and 32 bit perls). On systems that do not deliver the
		564	inode information, this will always be zero.
		565
		566	C<$type> is one of the C<AIO::DT_xxx> constants:
		567
		568	C<AIO::DT_UNKNOWN>, C<AIO::DT_FIFO>, C<AIO::DT_CHR>, C<AIO::DT_DIR>,
		569	C<AIO::DT_BLK>, C<AIO::DT_REG>, C<AIO::DT_LNK>, C<AIO::DT_SOCK>,
		570	C<AIO::DT_WHT>.
		571
		572	C<AIO::DT_UNKNOWN> means just that: readdir does not know. If you need to
		573	know, you have to run stat yourself. Also, for speed reasons, the C<$type>
		574	scalars are read-only: you can not modify them.
		575
		576	=item AIO::READDIR_DIRS_FIRST
		577
		578	When this flag is set, then the names will be returned in an order where
		579	likely directories come first. This is useful when you need to quickly
		580	find directories, or you want to find all directories while avoiding to
		581	stat() each entry.
		582
		583	=item AIO::READDIR_STAT_ORDER
		584
		585	When this flag is set, then the names will be returned in an order
		586	suitable for stat()'ing each one. That is, when you plan to stat()
		587	all files in the given directory, then the returned order will likely
		588	be fastest.
		589
		590	If both this flag and IO::READDIR_DIRS_FIRST are specified, then the
		591	likely dirs come first, resulting in a less optimal stat order.
		592
		593	=item AIO::READDIR_FOUND_UNKNOWN
		594
		595	This flag should not be set when calling C<aio_readdirx>. Instead, it
		596	is being set by C<aio_readdirx>, when any of the C<$type>'s found were
		597	C<AIO::DT_UNKNOWN>. The absense of this flag therefore indicates that all
		598	C<$type>'s are known, which can be used to speed up some algorithms.
		599
		600	=back
		601
		602
		603	=item aio_load $path, $data, $callback->($status)
		604
		605	This is a composite request that tries to fully load the given file into
		606	memory. Status is the same as with aio_read.
		607
		608	=cut
		609
		610	sub aio_load($$;$) {
		611	my ($path, undef, $cb) = @_;
		612	my $data = \$_[1];
		613
		614	my $pri = aioreq_pri;
		615	my $grp = aio_group $cb;
		616
		617	aioreq_pri $pri;
		618	add $grp aio_open $path, O_RDONLY, 0, sub {
		619	my $fh = shift
		620	or return $grp->result (-1);
		621
		622	aioreq_pri $pri;
		623	add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub {
		624	$grp->result ($_[0]);
		625	};
		626	};
		627
		628	$grp
		629	}
		630
		631	=item aio_copy $srcpath, $dstpath, $callback->($status)
		632
		633	Try to copy the I<file> (directories not supported as either source or
		634	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		635	the C<0> (error) or C<-1> ok.
		636
		637	This is a composite request that creates the destination file with
		638	mode 0200 and copies the contents of the source file into it using
		639	C<aio_sendfile>, followed by restoring atime, mtime, access mode and
		640	uid/gid, in that order.
		641
		642	If an error occurs, the partial destination file will be unlinked, if
		643	possible, except when setting atime, mtime, access mode and uid/gid, where
		644	errors are being ignored.
		645
		646	=cut
		647
		648	sub aio_copy($$;$) {
		649	my ($src, $dst, $cb) = @_;
		650
		651	my $pri = aioreq_pri;
		652	my $grp = aio_group $cb;
		653
		654	aioreq_pri $pri;
		655	add $grp aio_open $src, O_RDONLY, 0, sub {
		656	if (my $src_fh = $_[0]) {
		657	my @stat = stat $src_fh; # hmm, might bock over nfs?
		658
		659	aioreq_pri $pri;
		660	add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {
		661	if (my $dst_fh = $_[0]) {
		662	aioreq_pri $pri;
		663	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
		664	if ($_[0] == $stat[7]) {
		665	$grp->result (0);
		666	close $src_fh;
		667
		668	my $ch = sub {
		669	aioreq_pri $pri;
		670	add $grp aio_chmod $dst_fh, $stat[2] & 07777, sub {
		671	aioreq_pri $pri;
		672	add $grp aio_chown $dst_fh, $stat[4], $stat[5], sub {
		673	aioreq_pri $pri;
		674	add $grp aio_close $dst_fh;
		675	}
		676	};
		677	};
		678
		679	aioreq_pri $pri;
		680	add $grp aio_utime $dst_fh, $stat[8], $stat[9], sub {
		681	if ($_[0] < 0 && $! == ENOSYS) {
		682	aioreq_pri $pri;
		683	add $grp aio_utime $dst, $stat[8], $stat[9], $ch;
		684	} else {
		685	$ch->();
		686	}
		687	};
		688	} else {
		689	$grp->result (-1);
		690	close $src_fh;
		691	close $dst_fh;
		692
		693	aioreq $pri;
		694	add $grp aio_unlink $dst;
		695	}
		696	};
		697	} else {
		698	$grp->result (-1);
		699	}
		700	},
		701
		702	} else {
		703	$grp->result (-1);
		704	}
		705	};
		706
		707	$grp
		708	}
		709
		710	=item aio_move $srcpath, $dstpath, $callback->($status)
		711
		712	Try to move the I<file> (directories not supported as either source or
		713	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		714	the C<0> (error) or C<-1> ok.
		715
		716	This is a composite request that tries to rename(2) the file first; if
		717	rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if
		718	that is successful, unlinks the C<$srcpath>.
		719
		720	=cut
		721
		722	sub aio_move($$;$) {
		723	my ($src, $dst, $cb) = @_;
		724
		725	my $pri = aioreq_pri;
		726	my $grp = aio_group $cb;
		727
		728	aioreq_pri $pri;
		729	add $grp aio_rename $src, $dst, sub {
		730	if ($_[0] && $! == EXDEV) {
		731	aioreq_pri $pri;
		732	add $grp aio_copy $src, $dst, sub {
		733	$grp->result ($_[0]);
		734
		735	if (!$_[0]) {
		736	aioreq_pri $pri;
		737	add $grp aio_unlink $src;
		738	}
		739	};
		740	} else {
		741	$grp->result ($_[0]);
		742	}
		743	};
		744
		745	$grp
		746	}
250		747
251	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)	748	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
252		749
253	Scans a directory (similar to C<aio_readdir>) and tries to separate the	750	Scans a directory (similar to C<aio_readdir>) but additionally tries to
254	entries of directory C<$path> into two sets of names, ones you can recurse	751	efficiently separate the entries of directory C<$path> into two sets of
255	into (directories), and ones you cannot recurse into (everything else).	752	names, directories you can recurse into (directories), and ones you cannot
		753	recurse into (everything else, including symlinks to directories).
256		754
257	C<aio_scandir> is a composite request that consists of many	755	C<aio_scandir> is a composite request that creates of many sub requests_
258	aio-primitives. C<$maxreq> specifies the maximum number of outstanding	756	C<$maxreq> specifies the maximum number of outstanding aio requests that
259	aio requests that this function generates. If it is C<< <= 0 >>, then a	757	this function generates. If it is C<< <= 0 >>, then a suitable default
260	suitable default will be chosen (currently 8).	758	will be chosen (currently 4).
261		759
262	On error, the callback is called without arguments, otherwise it receives	760	On error, the callback is called without arguments, otherwise it receives
263	two array-refs with path-relative entry names.	761	two array-refs with path-relative entry names.
264		762
265	Example:	763	Example:
…		…
273	Implementation notes.	771	Implementation notes.
274		772
275	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.	773	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.
276		774
277	After reading the directory, the modification time, size etc. of the	775	After reading the directory, the modification time, size etc. of the
278	directory before and after the readdir is checked, and if they match, the	776	directory before and after the readdir is checked, and if they match (and
279	link count will be used to decide how many entries are directories (if	777	isn't the current time), the link count will be used to decide how many
280	>= 2). Otherwise, no knowledge of the number of subdirectories will be	778	entries are directories (if >= 2). Otherwise, no knowledge of the number
281	assumed.	779	of subdirectories will be assumed.
282		780
283	Then entires will be sorted into likely directories (everything without a	781	Then entries will be sorted into likely directories (everything without
284	non-initial dot) and likely non-directories (everything else). Then every	782	a non-initial dot currently) and likely non-directories (everything
285	entry + C</.> will be C<stat>'ed, likely directories first. This is often	783	else). Then every entry plus an appended C</.> will be C<stat>'ed,
		784	likely directories first. If that succeeds, it assumes that the entry
		785	is a directory or a symlink to directory (which will be checked
		786	seperately). This is often faster than stat'ing the entry itself because
286	faster because filesystems might detect the type of the entry without	787	filesystems might detect the type of the entry without reading the inode
287	reading the inode data (e.g. ext2s filetype feature). If that succeeds,	788	data (e.g. ext2fs filetype feature).
288	it assumes that the entry is a directory or a symlink to directory (which
289	will be checked seperately).
290		789
291	If the known number of directories has been reached, the rest of the	790	If the known number of directories (link count - 2) has been reached, the
292	entries is assumed to be non-directories.	791	rest of the entries is assumed to be non-directories.
		792
		793	This only works with certainty on POSIX (= UNIX) filesystems, which
		794	fortunately are the vast majority of filesystems around.
		795
		796	It will also likely work on non-POSIX filesystems with reduced efficiency
		797	as those tend to return 0 or 1 as link counts, which disables the
		798	directory counting heuristic.
293		799
294	=cut	800	=cut
295		801
296	sub aio_scandir($$$) {	802	sub aio_scandir($$;$) {
297	my ($path, $maxreq, $cb) = @_;	803	my ($path, $maxreq, $cb) = @_;
298		804
		805	my $pri = aioreq_pri;
		806
		807	my $grp = aio_group $cb;
		808
299	$maxreq = 8 if $maxreq <= 0;	809	$maxreq = 4 if $maxreq <= 0;
300		810
301	# stat once	811	# stat once
		812	aioreq_pri $pri;
302	aio_stat $path, sub {	813	add $grp aio_stat $path, sub {
303	$cb->() if $_[0];	814	return $grp->result () if $_[0];
		815	my $now = time;
304	my $hash1 = join ":", (stat _)[0,1,3,7,9];	816	my $hash1 = join ":", (stat _)[0,1,3,7,9];
305		817
306	# read the directory entries	818	# read the directory entries
307	aio_readdir $path, sub {	819	aioreq_pri $pri;
		820	add $grp aio_readdirx $path, READDIR_DIRS_FIRST, sub {
308	my $entries = shift	821	my $entries = shift
309	or return $cb->();	822	or return $grp->result ();
310		823
311	# stat the dir another time	824	# stat the dir another time
		825	aioreq_pri $pri;
312	aio_stat $path, sub {	826	add $grp aio_stat $path, sub {
313	my $hash2 = join ":", (stat _)[0,1,3,7,9];	827	my $hash2 = join ":", (stat _)[0,1,3,7,9];
314		828
315	my $ndirs;	829	my $ndirs;
316		830
317	# take the slow route if anything looks fishy	831	# take the slow route if anything looks fishy
318	if ($hash1 ne $hash2) {	832	if ($hash1 ne $hash2 or (stat _)[9] == $now) {
319	$ndirs = -1;	833	$ndirs = -1;
320	} else {	834	} else {
321	# if nlink == 2, we are finished	835	# if nlink == 2, we are finished
322	# on non-posix-fs's, we rely on nlink < 2	836	# on non-posix-fs's, we rely on nlink < 2
323	$ndirs = (stat _)[3] - 2	837	$ndirs = (stat _)[3] - 2
324	or $cb->([], $entries);	838	or return $grp->result ([], $entries);
325	}	839	}
326		840
327	# sort into likely dirs and likely nondirs	841	# sort into likely dirs and likely nondirs
328	# dirs == files without ".", short entries first	842	# dirs == files without ".", short entries first
329	$entries = [map $_->[0],	843	$entries = [map $_->[0],
…		…
331	map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],	845	map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],
332	@$entries];	846	@$entries];
333		847
334	my (@dirs, @nondirs);	848	my (@dirs, @nondirs);
335		849
336	my ($statcb, $schedcb);	850	my $statgrp = add $grp aio_group sub {
337	my $nreq = 0;	851	$grp->result (\@dirs, \@nondirs);
		852	};
338		853
339	$schedcb = sub {	854	limit $statgrp $maxreq;
340	if (@$entries) {	855	feed $statgrp sub {
341	if ($nreq < $maxreq) {	856	return unless @$entries;
342	my $ent = pop @$entries;	857	my $entry = pop @$entries;
		858
		859	aioreq_pri $pri;
		860	add $statgrp aio_stat "$path/$entry/.", sub {
		861	if ($_[0] < 0) {
		862	push @nondirs, $entry;
		863	} else {
		864	# need to check for real directory
		865	aioreq_pri $pri;
		866	add $statgrp aio_lstat "$path/$entry", sub {
		867	if (-d _) {
		868	push @dirs, $entry;
		869
		870	unless (--$ndirs) {
		871	push @nondirs, @$entries;
		872	feed $statgrp;
		873	}
		874	} else {
		875	push @nondirs, $entry;
		876	}
343	$nreq++;	877	}
344	aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) };
345	}	878	}
346	} elsif (!$nreq) {
347	# finished
348	undef $statcb;
349	undef $schedcb;
350	$cb->(\@dirs, \@nondirs);
351	undef $cb;
352	}	879	};
353	};	880	};
354	$statcb = sub {
355	my ($status, $entry) = @_;
356
357	if ($status < 0) {
358	$nreq--;
359	push @nondirs, $entry;
360	&$schedcb;
361	} else {
362	# need to check for real directory
363	aio_lstat "$path/$entry", sub {
364	$nreq--;
365
366	if (-d _) {
367	push @dirs, $entry;
368
369	if (!--$ndirs) {
370	push @nondirs, @$entries;
371	$entries = [];
372	}
373	} else {
374	push @nondirs, $entry;
375	}
376
377	&$schedcb;
378	}
379	}
380	};
381
382	&$schedcb while @$entries && $nreq < $maxreq;
383	};	881	};
384	};	882	};
385	};	883	};
		884
		885	$grp
386	}	886	}
		887
		888	=item aio_rmtree $path, $callback->($status)
		889
		890	Delete a directory tree starting (and including) C<$path>, return the
		891	status of the final C<rmdir> only. This is a composite request that
		892	uses C<aio_scandir> to recurse into and rmdir directories, and unlink
		893	everything else.
		894
		895	=cut
		896
		897	sub aio_rmtree;
		898	sub aio_rmtree($;$) {
		899	my ($path, $cb) = @_;
		900
		901	my $pri = aioreq_pri;
		902	my $grp = aio_group $cb;
		903
		904	aioreq_pri $pri;
		905	add $grp aio_scandir $path, 0, sub {
		906	my ($dirs, $nondirs) = @_;
		907
		908	my $dirgrp = aio_group sub {
		909	add $grp aio_rmdir $path, sub {
		910	$grp->result ($_[0]);
		911	};
		912	};
		913
		914	(aioreq_pri $pri), add $dirgrp aio_rmtree "$path/$_" for @$dirs;
		915	(aioreq_pri $pri), add $dirgrp aio_unlink "$path/$_" for @$nondirs;
		916
		917	add $grp $dirgrp;
		918	};
		919
		920	$grp
		921	}
		922
		923	=item aio_sync $callback->($status)
		924
		925	Asynchronously call sync and call the callback when finished.
387		926
388	=item aio_fsync $fh, $callback->($status)	927	=item aio_fsync $fh, $callback->($status)
389		928
390	Asynchronously call fsync on the given filehandle and call the callback	929	Asynchronously call fsync on the given filehandle and call the callback
391	with the fsync result code.	930	with the fsync result code.
…		…
396	callback with the fdatasync result code.	935	callback with the fdatasync result code.
397		936
398	If this call isn't available because your OS lacks it or it couldn't be	937	If this call isn't available because your OS lacks it or it couldn't be
399	detected, it will be emulated by calling C<fsync> instead.	938	detected, it will be emulated by calling C<fsync> instead.
400		939
		940	=item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		941
		942	Sync the data portion of the file specified by C<$offset> and C<$length>
		943	to disk (but NOT the metadata), by calling the Linux-specific
		944	sync_file_range call. If sync_file_range is not available or it returns
		945	ENOSYS, then fdatasync or fsync is being substituted.
		946
		947	C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>,
		948	C<IO::AIO::SYNC_FILE_RANGE_WRITE> and
		949	C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range
		950	manpage for details.
		951
		952	=item aio_pathsync $path, $callback->($status)
		953
		954	This request tries to open, fsync and close the given path. This is a
		955	composite request intended to sync directories after directory operations
		956	(E.g. rename). This might not work on all operating systems or have any
		957	specific effect, but usually it makes sure that directory changes get
		958	written to disc. It works for anything that can be opened for read-only,
		959	not just directories.
		960
		961	Passes C<0> when everything went ok, and C<-1> on error.
		962
		963	=cut
		964
		965	sub aio_pathsync($;$) {
		966	my ($path, $cb) = @_;
		967
		968	my $pri = aioreq_pri;
		969	my $grp = aio_group $cb;
		970
		971	aioreq_pri $pri;
		972	add $grp aio_open $path, O_RDONLY, 0, sub {
		973	my ($fh) = @_;
		974	if ($fh) {
		975	aioreq_pri $pri;
		976	add $grp aio_fsync $fh, sub {
		977	$grp->result ($_[0]);
		978
		979	aioreq_pri $pri;
		980	add $grp aio_close $fh;
		981	};
		982	} else {
		983	$grp->result (-1);
		984	}
		985	};
		986
		987	$grp
		988	}
		989
		990	=item aio_group $callback->(...)
		991
		992	This is a very special aio request: Instead of doing something, it is a
		993	container for other aio requests, which is useful if you want to bundle
		994	many requests into a single, composite, request with a definite callback
		995	and the ability to cancel the whole request with its subrequests.
		996
		997	Returns an object of class L<IO::AIO::GRP>. See its documentation below
		998	for more info.
		999
		1000	Example:
		1001
		1002	my $grp = aio_group sub {
		1003	print "all stats done\n";
		1004	};
		1005
		1006	add $grp
		1007	(aio_stat ...),
		1008	(aio_stat ...),
		1009	...;
		1010
		1011	=item aio_nop $callback->()
		1012
		1013	This is a special request - it does nothing in itself and is only used for
		1014	side effects, such as when you want to add a dummy request to a group so
		1015	that finishing the requests in the group depends on executing the given
		1016	code.
		1017
		1018	While this request does nothing, it still goes through the execution
		1019	phase and still requires a worker thread. Thus, the callback will not
		1020	be executed immediately but only after other requests in the queue have
		1021	entered their execution phase. This can be used to measure request
		1022	latency.
		1023
		1024	=item IO::AIO::aio_busy $fractional_seconds, $callback->() *NOT EXPORTED*
		1025
		1026	Mainly used for debugging and benchmarking, this aio request puts one of
		1027	the request workers to sleep for the given time.
		1028
		1029	While it is theoretically handy to have simple I/O scheduling requests
		1030	like sleep and file handle readable/writable, the overhead this creates is
		1031	immense (it blocks a thread for a long time) so do not use this function
		1032	except to put your application under artificial I/O pressure.
		1033
401	=back	1034	=back
402		1035
		1036	=head2 IO::AIO::REQ CLASS
		1037
		1038	All non-aggregate C<aio_*> functions return an object of this class when
		1039	called in non-void context.
		1040
		1041	=over 4
		1042
		1043	=item cancel $req
		1044
		1045	Cancels the request, if possible. Has the effect of skipping execution
		1046	when entering the B<execute> state and skipping calling the callback when
		1047	entering the the B<result> state, but will leave the request otherwise
		1048	untouched. That means that requests that currently execute will not be
		1049	stopped and resources held by the request will not be freed prematurely.
		1050
		1051	=item cb $req $callback->(...)
		1052
		1053	Replace (or simply set) the callback registered to the request.
		1054
		1055	=back
		1056
		1057	=head2 IO::AIO::GRP CLASS
		1058
		1059	This class is a subclass of L<IO::AIO::REQ>, so all its methods apply to
		1060	objects of this class, too.
		1061
		1062	A IO::AIO::GRP object is a special request that can contain multiple other
		1063	aio requests.
		1064
		1065	You create one by calling the C<aio_group> constructing function with a
		1066	callback that will be called when all contained requests have entered the
		1067	C<done> state:
		1068
		1069	my $grp = aio_group sub {
		1070	print "all requests are done\n";
		1071	};
		1072
		1073	You add requests by calling the C<add> method with one or more
		1074	C<IO::AIO::REQ> objects:
		1075
		1076	$grp->add (aio_unlink "...");
		1077
		1078	add $grp aio_stat "...", sub {
		1079	$_[0] or return $grp->result ("error");
		1080
		1081	# add another request dynamically, if first succeeded
		1082	add $grp aio_open "...", sub {
		1083	$grp->result ("ok");
		1084	};
		1085	};
		1086
		1087	This makes it very easy to create composite requests (see the source of
		1088	C<aio_move> for an application) that work and feel like simple requests.
		1089
		1090	=over 4
		1091
		1092	=item * The IO::AIO::GRP objects will be cleaned up during calls to
		1093	C<IO::AIO::poll_cb>, just like any other request.
		1094
		1095	=item * They can be canceled like any other request. Canceling will cancel not
		1096	only the request itself, but also all requests it contains.
		1097
		1098	=item * They can also can also be added to other IO::AIO::GRP objects.
		1099
		1100	=item * You must not add requests to a group from within the group callback (or
		1101	any later time).
		1102
		1103	=back
		1104
		1105	Their lifetime, simplified, looks like this: when they are empty, they
		1106	will finish very quickly. If they contain only requests that are in the
		1107	C<done> state, they will also finish. Otherwise they will continue to
		1108	exist.
		1109
		1110	That means after creating a group you have some time to add requests
		1111	(precisely before the callback has been invoked, which is only done within
		1112	the C<poll_cb>). And in the callbacks of those requests, you can add
		1113	further requests to the group. And only when all those requests have
		1114	finished will the the group itself finish.
		1115
		1116	=over 4
		1117
		1118	=item add $grp ...
		1119
		1120	=item $grp->add (...)
		1121
		1122	Add one or more requests to the group. Any type of L<IO::AIO::REQ> can
		1123	be added, including other groups, as long as you do not create circular
		1124	dependencies.
		1125
		1126	Returns all its arguments.
		1127
		1128	=item $grp->cancel_subs
		1129
		1130	Cancel all subrequests and clears any feeder, but not the group request
		1131	itself. Useful when you queued a lot of events but got a result early.
		1132
		1133	=item $grp->result (...)
		1134
		1135	Set the result value(s) that will be passed to the group callback when all
		1136	subrequests have finished and set the groups errno to the current value
		1137	of errno (just like calling C<errno> without an error number). By default,
		1138	no argument will be passed and errno is zero.
		1139
		1140	=item $grp->errno ([$errno])
		1141
		1142	Sets the group errno value to C<$errno>, or the current value of errno
		1143	when the argument is missing.
		1144
		1145	Every aio request has an associated errno value that is restored when
		1146	the callback is invoked. This method lets you change this value from its
		1147	default (0).
		1148
		1149	Calling C<result> will also set errno, so make sure you either set C<$!>
		1150	before the call to C<result>, or call c<errno> after it.
		1151
		1152	=item feed $grp $callback->($grp)
		1153
		1154	Sets a feeder/generator on this group: every group can have an attached
		1155	generator that generates requests if idle. The idea behind this is that,
		1156	although you could just queue as many requests as you want in a group,
		1157	this might starve other requests for a potentially long time. For example,
		1158	C<aio_scandir> might generate hundreds of thousands C<aio_stat> requests,
		1159	delaying any later requests for a long time.
		1160
		1161	To avoid this, and allow incremental generation of requests, you can
		1162	instead a group and set a feeder on it that generates those requests. The
		1163	feed callback will be called whenever there are few enough (see C<limit>,
		1164	below) requests active in the group itself and is expected to queue more
		1165	requests.
		1166
		1167	The feed callback can queue as many requests as it likes (i.e. C<add> does
		1168	not impose any limits).
		1169
		1170	If the feed does not queue more requests when called, it will be
		1171	automatically removed from the group.
		1172
		1173	If the feed limit is C<0> when this method is called, it will be set to
		1174	C<2> automatically.
		1175
		1176	Example:
		1177
		1178	# stat all files in @files, but only ever use four aio requests concurrently:
		1179
		1180	my $grp = aio_group sub { print "finished\n" };
		1181	limit $grp 4;
		1182	feed $grp sub {
		1183	my $file = pop @files
		1184	or return;
		1185
		1186	add $grp aio_stat $file, sub { ... };
		1187	};
		1188
		1189	=item limit $grp $num
		1190
		1191	Sets the feeder limit for the group: The feeder will be called whenever
		1192	the group contains less than this many requests.
		1193
		1194	Setting the limit to C<0> will pause the feeding process.
		1195
		1196	The default value for the limit is C<0>, but note that setting a feeder
		1197	automatically bumps it up to C<2>.
		1198
		1199	=back
		1200
403	=head2 SUPPORT FUNCTIONS	1201	=head2 SUPPORT FUNCTIONS
		1202
		1203	=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION
404		1204
405	=over 4	1205	=over 4
406		1206
407	=item $fileno = IO::AIO::poll_fileno	1207	=item $fileno = IO::AIO::poll_fileno
408		1208
…		…
413		1213
414	See C<poll_cb> for an example.	1214	See C<poll_cb> for an example.
415		1215
416	=item IO::AIO::poll_cb	1216	=item IO::AIO::poll_cb
417		1217
418	Process all outstanding events on the result pipe. You have to call this	1218	Process some outstanding events on the result pipe. You have to call this
419	regularly. Returns the number of events processed. Returns immediately	1219	regularly. Returns C<0> if all events could be processed, or C<-1> if it
420	when no events are outstanding.	1220	returned earlier for whatever reason. Returns immediately when no events
		1221	are outstanding. The amount of events processed depends on the settings of
		1222	C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>.
		1223
		1224	If not all requests were processed for whatever reason, the filehandle
		1225	will still be ready when C<poll_cb> returns, so normally you don't have to
		1226	do anything special to have it called later.
421		1227
422	Example: Install an Event watcher that automatically calls	1228	Example: Install an Event watcher that automatically calls
423	IO::AIO::poll_cb with high priority:	1229	IO::AIO::poll_cb with high priority:
424		1230
425	Event->io (fd => IO::AIO::poll_fileno,	1231	Event->io (fd => IO::AIO::poll_fileno,
426	poll => 'r', async => 1,	1232	poll => 'r', async => 1,
427	cb => \&IO::AIO::poll_cb);	1233	cb => \&IO::AIO::poll_cb);
428		1234
		1235	=item IO::AIO::max_poll_reqs $nreqs
		1236
		1237	=item IO::AIO::max_poll_time $seconds
		1238
		1239	These set the maximum number of requests (default C<0>, meaning infinity)
		1240	that are being processed by C<IO::AIO::poll_cb> in one call, respectively
		1241	the maximum amount of time (default C<0>, meaning infinity) spent in
		1242	C<IO::AIO::poll_cb> to process requests (more correctly the mininum amount
		1243	of time C<poll_cb> is allowed to use).
		1244
		1245	Setting C<max_poll_time> to a non-zero value creates an overhead of one
		1246	syscall per request processed, which is not normally a problem unless your
		1247	callbacks are really really fast or your OS is really really slow (I am
		1248	not mentioning Solaris here). Using C<max_poll_reqs> incurs no overhead.
		1249
		1250	Setting these is useful if you want to ensure some level of
		1251	interactiveness when perl is not fast enough to process all requests in
		1252	time.
		1253
		1254	For interactive programs, values such as C<0.01> to C<0.1> should be fine.
		1255
		1256	Example: Install an Event watcher that automatically calls
		1257	IO::AIO::poll_cb with low priority, to ensure that other parts of the
		1258	program get the CPU sometimes even under high AIO load.
		1259
		1260	# try not to spend much more than 0.1s in poll_cb
		1261	IO::AIO::max_poll_time 0.1;
		1262
		1263	# use a low priority so other tasks have priority
		1264	Event->io (fd => IO::AIO::poll_fileno,
		1265	poll => 'r', nice => 1,
		1266	cb => &IO::AIO::poll_cb);
		1267
429	=item IO::AIO::poll_wait	1268	=item IO::AIO::poll_wait
430		1269
		1270	If there are any outstanding requests and none of them in the result
431	Wait till the result filehandle becomes ready for reading (simply does a	1271	phase, wait till the result filehandle becomes ready for reading (simply
432	C<select> on the filehandle. This is useful if you want to synchronously wait	1272	does a C<select> on the filehandle. This is useful if you want to
433	for some requests to finish).	1273	synchronously wait for some requests to finish).
434		1274
435	See C<nreqs> for an example.	1275	See C<nreqs> for an example.
436		1276
		1277	=item IO::AIO::poll
		1278
		1279	Waits until some requests have been handled.
		1280
		1281	Returns the number of requests processed, but is otherwise strictly
		1282	equivalent to:
		1283
		1284	IO::AIO::poll_wait, IO::AIO::poll_cb
		1285
437	=item IO::AIO::nreqs	1286	=item IO::AIO::flush
438		1287
439	Returns the number of requests currently outstanding (i.e. for which their	1288	Wait till all outstanding AIO requests have been handled.
440	callback has not been invoked yet).
441		1289
442	Example: wait till there are no outstanding requests anymore:	1290	Strictly equivalent to:
443		1291
444	IO::AIO::poll_wait, IO::AIO::poll_cb	1292	IO::AIO::poll_wait, IO::AIO::poll_cb
445	while IO::AIO::nreqs;	1293	while IO::AIO::nreqs;
446		1294
447	=item IO::AIO::flush	1295	=back
448		1296
449	Wait till all outstanding AIO requests have been handled.	1297	=head3 CONTROLLING THE NUMBER OF THREADS
450		1298
451	Strictly equivalent to:	1299	=over
452
453	IO::AIO::poll_wait, IO::AIO::poll_cb
454	while IO::AIO::nreqs;
455
456	=item IO::AIO::poll
457
458	Waits until some requests have been handled.
459
460	Strictly equivalent to:
461
462	IO::AIO::poll_wait, IO::AIO::poll_cb
463	if IO::AIO::nreqs;
464		1300
465	=item IO::AIO::min_parallel $nthreads	1301	=item IO::AIO::min_parallel $nthreads
466		1302
467	Set the minimum number of AIO threads to C<$nthreads>. The current default	1303	Set the minimum number of AIO threads to C<$nthreads>. The current
468	is C<4>, which means four asynchronous operations can be done at one time	1304	default is C<8>, which means eight asynchronous operations can execute
469	(the number of outstanding operations, however, is unlimited).	1305	concurrently at any one time (the number of outstanding requests,
		1306	however, is unlimited).
470		1307
471	IO::AIO starts threads only on demand, when an AIO request is queued and	1308	IO::AIO starts threads only on demand, when an AIO request is queued and
472	no free thread exists.	1309	no free thread exists. Please note that queueing up a hundred requests can
		1310	create demand for a hundred threads, even if it turns out that everything
		1311	is in the cache and could have been processed faster by a single thread.
473		1312
474	It is recommended to keep the number of threads low, as some Linux	1313	It is recommended to keep the number of threads relatively low, as some
475	kernel versions will scale negatively with the number of threads (higher	1314	Linux kernel versions will scale negatively with the number of threads
476	parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32	1315	(higher parallelity => MUCH higher latency). With current Linux 2.6
477	threads should be fine.	1316	versions, 4-32 threads should be fine.
478		1317
479	Under most circumstances you don't need to call this function, as the	1318	Under most circumstances you don't need to call this function, as the
480	module selects a default that is suitable for low to moderate load.	1319	module selects a default that is suitable for low to moderate load.
481		1320
482	=item IO::AIO::max_parallel $nthreads	1321	=item IO::AIO::max_parallel $nthreads
…		…
491	This module automatically runs C<max_parallel 0> at program end, to ensure	1330	This module automatically runs C<max_parallel 0> at program end, to ensure
492	that all threads are killed and that there are no outstanding requests.	1331	that all threads are killed and that there are no outstanding requests.
493		1332
494	Under normal circumstances you don't need to call this function.	1333	Under normal circumstances you don't need to call this function.
495		1334
		1335	=item IO::AIO::max_idle $nthreads
		1336
		1337	Limit the number of threads (default: 4) that are allowed to idle (i.e.,
		1338	threads that did not get a request to process within 10 seconds). That
		1339	means if a thread becomes idle while C<$nthreads> other threads are also
		1340	idle, it will free its resources and exit.
		1341
		1342	This is useful when you allow a large number of threads (e.g. 100 or 1000)
		1343	to allow for extremely high load situations, but want to free resources
		1344	under normal circumstances (1000 threads can easily consume 30MB of RAM).
		1345
		1346	The default is probably ok in most situations, especially if thread
		1347	creation is fast. If thread creation is very slow on your system you might
		1348	want to use larger values.
		1349
496	=item $oldnreqs = IO::AIO::max_outstanding $nreqs	1350	=item IO::AIO::max_outstanding $maxreqs
		1351
		1352	This is a very bad function to use in interactive programs because it
		1353	blocks, and a bad way to reduce concurrency because it is inexact: Better
		1354	use an C<aio_group> together with a feed callback.
497		1355
498	Sets the maximum number of outstanding requests to C<$nreqs>. If you	1356	Sets the maximum number of outstanding requests to C<$nreqs>. If you
499	try to queue up more than this number of requests, the caller will block until	1357	do queue up more than this number of requests, the next call to the
500	some requests have been handled.	1358	C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>)
		1359	function will block until the limit is no longer exceeded.
501		1360
502	The default is very large, so normally there is no practical limit. If you	1361	The default value is very large, so there is no practical limit on the
503	queue up many requests in a loop it often improves speed if you set	1362	number of outstanding requests.
504	this to a relatively low number, such as C<100>.
505		1363
506	Under normal circumstances you don't need to call this function.	1364	You can still queue as many requests as you want. Therefore,
		1365	C<max_outstanding> is mainly useful in simple scripts (with low values) or
		1366	as a stop gap to shield against fatal memory overflow (with large values).
507		1367
508	=back	1368	=back
509		1369
		1370	=head3 STATISTICAL INFORMATION
		1371
		1372	=over
		1373
		1374	=item IO::AIO::nreqs
		1375
		1376	Returns the number of requests currently in the ready, execute or pending
		1377	states (i.e. for which their callback has not been invoked yet).
		1378
		1379	Example: wait till there are no outstanding requests anymore:
		1380
		1381	IO::AIO::poll_wait, IO::AIO::poll_cb
		1382	while IO::AIO::nreqs;
		1383
		1384	=item IO::AIO::nready
		1385
		1386	Returns the number of requests currently in the ready state (not yet
		1387	executed).
		1388
		1389	=item IO::AIO::npending
		1390
		1391	Returns the number of requests currently in the pending state (executed,
		1392	but not yet processed by poll_cb).
		1393
		1394	=back
		1395
510	=cut	1396	=cut
511		1397
512	# support function to convert a fd into a perl filehandle
513	sub _fd2fh {
514	return undef if $_[0] < 0;
515
516	# try to generate nice filehandles
517	my $sym = "IO::AIO::fd#$_[0]";
518	local *$sym;
519
520	open *$sym, "+<&=$_[0]" # usually works under any unix
521	or open *$sym, "<&=$_[0]" # cygwin needs this
522	or open *$sym, ">&=$_[0]" # or this
523	or return undef;
524
525	*$sym
526	}
527
528	min_parallel 4;	1398	min_parallel 8;
529		1399
530	END {	1400	END { flush }
531	max_parallel 0;
532	}
533		1401
534	1;	1402	1;
535		1403
536	=head2 FORK BEHAVIOUR	1404	=head2 FORK BEHAVIOUR
		1405
		1406	This module should do "the right thing" when the process using it forks:
537		1407
538	Before the fork, IO::AIO enters a quiescent state where no requests	1408	Before the fork, IO::AIO enters a quiescent state where no requests
539	can be added in other threads and no results will be processed. After	1409	can be added in other threads and no results will be processed. After
540	the fork the parent simply leaves the quiescent state and continues	1410	the fork the parent simply leaves the quiescent state and continues
541	request/result processing, while the child clears the request/result	1411	request/result processing, while the child frees the request/result queue
542	queue (so the requests started before the fork will only be handled in	1412	(so that the requests started before the fork will only be handled in the
543	the parent). Threats will be started on demand until the limit ste in the	1413	parent). Threads will be started on demand until the limit set in the
544	parent process has been reached again.	1414	parent process has been reached again.
545		1415
		1416	In short: the parent will, after a short pause, continue as if fork had
		1417	not been called, while the child will act as if IO::AIO has not been used
		1418	yet.
		1419
		1420	=head2 MEMORY USAGE
		1421
		1422	Per-request usage:
		1423
		1424	Each aio request uses - depending on your architecture - around 100-200
		1425	bytes of memory. In addition, stat requests need a stat buffer (possibly
		1426	a few hundred bytes), readdir requires a result buffer and so on. Perl
		1427	scalars and other data passed into aio requests will also be locked and
		1428	will consume memory till the request has entered the done state.
		1429
		1430	This is not awfully much, so queuing lots of requests is not usually a
		1431	problem.
		1432
		1433	Per-thread usage:
		1434
		1435	In the execution phase, some aio requests require more memory for
		1436	temporary buffers, and each thread requires a stack and other data
		1437	structures (usually around 16k-128k, depending on the OS).
		1438
		1439	=head1 KNOWN BUGS
		1440
		1441	Known bugs will be fixed in the next release.
		1442
546	=head1 SEE ALSO	1443	=head1 SEE ALSO
547		1444
548	L<Coro>, L<Linux::AIO>.	1445	L<AnyEvent::AIO> for easy integration into event loops, L<Coro::AIO> for a
		1446	more natural syntax.
549		1447
550	=head1 AUTHOR	1448	=head1 AUTHOR
551		1449
552	Marc Lehmann <schmorp@schmorp.de>	1450	Marc Lehmann <schmorp@schmorp.de>
553	http://home.schmorp.de/	1451	http://home.schmorp.de/

Diff Legend

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