ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/IO-AIO/AIO.pm

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.24 by root, Sun Jul 31 18:45:48 2005 UTC vs.
Revision 1.149 by root, Sat Jun 6 18:19:35 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	# Event	21	# version 2+ has request and group objects
		22	use IO::AIO 2;
		23
		24	aioreq_pri 4; # give next request a very high priority
		25	my $req = aio_unlink "/tmp/file", sub { };
		26	$req->cancel; # cancel request if still in queue
		27
		28	my $grp = aio_group sub { print "all stats done\n" };
		29	add $grp aio_stat "..." for ...;
		30
		31	# AnyEvent integration (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
21	Event->io (fd => IO::AIO::poll_fileno,	38	Event->io (fd => IO::AIO::poll_fileno,
22	poll => 'r',	39	poll => 'r',
23	cb => \&IO::AIO::poll_cb);	40	cb => \&IO::AIO::poll_cb);
24		41
25	# Glib/Gtk2	42	# Glib/Gtk2 integration
26	add_watch Glib::IO IO::AIO::poll_fileno,	43	add_watch Glib::IO IO::AIO::poll_fileno,
27	in => sub { IO::AIO::poll_cb; 1 };	44	in => sub { IO::AIO::poll_cb; 1 };
28		45
29	# Tk	46	# Tk integration
30	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",	47	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
31	readable => \&IO::AIO::poll_cb);	48	readable => \&IO::AIO::poll_cb);
32		49
33	# Danga::Socket	50	# Danga::Socket integration
34	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>	51	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
35	\&IO::AIO::poll_cb);	52	\&IO::AIO::poll_cb);
36		53
37
38	=head1 DESCRIPTION	54	=head1 DESCRIPTION
39		55
40	This module implements asynchronous I/O using whatever means your	56	This module implements asynchronous I/O using whatever means your
41	operating system supports.	57	operating system supports.
42		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
43	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
44	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
45	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
46	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
47	aio functions available on many operating systems. However, they are often	79	functions available on many operating systems. However, they are often
48	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
49	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
50	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.
51		84
52	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,
53	currently not reentrant, so use appropriate locking yourself, always call	86	it is currently not reentrant in any way, so use appropriate locking
54	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
55	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
56		185
57	=cut	186	=cut
58		187
59	package IO::AIO;	188	package IO::AIO;
60		189
		190	use Carp ();
		191
61	no warnings;	192	no warnings;
		193	use strict 'vars';
62		194
63	use base 'Exporter';	195	use base 'Exporter';
64		196
65	use Fcntl ();
66
67	BEGIN {	197	BEGIN {
68	$VERSION = 1.1;	198	our $VERSION = '3.2';
69		199
70	@EXPORT = qw(aio_read aio_write aio_open aio_close aio_stat aio_lstat aio_unlink	200	our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close
71	aio_fsync aio_fdatasync aio_readahead);	201	aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx
72	@EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs);	202	aio_scandir aio_symlink aio_readlink aio_sync aio_fsync
		203	aio_fdatasync aio_sync_file_range aio_pathsync aio_readahead
		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';
73		217
74	require XSLoader;	218	require XSLoader;
75	XSLoader::load IO::AIO, $VERSION;	219	XSLoader::load ("IO::AIO", $VERSION);
76	}	220	}
77		221
78	=head1 FUNCTIONS	222	=head1 FUNCTIONS
79		223
80	=head2 AIO FUNCTIONS	224	=head2 AIO REQUEST FUNCTIONS
81		225
82	All the C<aio_*> calls are more or less thin wrappers around the syscall	226	All the C<aio_*> calls are more or less thin wrappers around the syscall
83	with the same name (sans C<aio_>). The arguments are similar or identical,	227	with the same name (sans C<aio_>). The arguments are similar or identical,
84	and they all accept an additional (and optional) C<$callback> argument	228	and they all accept an additional (and optional) C<$callback> argument
85	which must be a code reference. This code reference will get called with	229	which must be a code reference. This code reference will get called with
86	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
87	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
88	syscall has been executed asynchronously.	232	syscall has been executed asynchronously.
89		233
90	All functions expecting a filehandle keep a copy of the filehandle	234	All functions expecting a filehandle keep a copy of the filehandle
91	internally until the request has finished.	235	internally until the request has finished.
92		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
93	The filenames you pass to these routines I<must> be absolute. The reason	240	The pathnames you pass to these routines I<must> be absolute and
94	for this is that at the time the request is being executed, the current	241	encoded as octets. The reason for the former is that at the time the
95	working directory could have changed. Alternatively, you can make sure	242	request is being executed, the current working directory could have
96	that you never change the current working directory.	243	changed. Alternatively, you can make sure that you never change the
		244	current working directory anywhere in the program and then use relative
		245	paths.
		246
		247	To encode pathnames as octets, either make sure you either: a) always pass
		248	in filenames you got from outside (command line, readdir etc.) without
		249	tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module and encode
		250	your pathnames to the locale (or other) encoding in effect in the user
		251	environment, d) use Glib::filename_from_unicode on unicode filenames or e)
		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.
97		256
98	=over 4	257	=over 4
99		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
		291
100	=item aio_open $pathname, $flags, $mode, $callback	292	=item aio_open $pathname, $flags, $mode, $callback->($fh)
101		293
102	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
103	created filehandle for the file.	295	created filehandle for the file.
104		296
105	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,	297	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,
…		…
109	list. They are the same as used by C<sysopen>.	301	list. They are the same as used by C<sysopen>.
110		302
111	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
112	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>,
113	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,
114	and C<0666> or C<0777> if you do).	306	and C<0666> or C<0777> if you do). Note that the C<$mode> will be modified
		307	by the umask in effect then the request is being executed, so better never
		308	change the umask.
115		309
116	Example:	310	Example:
117		311
118	aio_open "/etc/passwd", O_RDONLY, 0, sub {	312	aio_open "/etc/passwd", O_RDONLY, 0, sub {
119	if ($_[0]) {	313	if ($_[0]) {
…		…
122	} else {	316	} else {
123	die "open failed: $!\n";	317	die "open failed: $!\n";
124	}	318	}
125	};	319	};
126		320
		321
127	=item aio_close $fh, $callback	322	=item aio_close $fh, $callback->($status)
128		323
129	Asynchronously close a file and call the callback with the result	324	Asynchronously close a file and call the callback with the result
130	code. I<WARNING:> although accepted, you should not pass in a perl	325	code.
131	filehandle here, as perl will likely close the file descriptor another
132	time when the filehandle is destroyed. Normally, you can safely call perls
133	C<close> or just let filehandles go out of scope.
134		326
135	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
136	therefore best to avoid this function.	328	closing the file descriptor associated with the filehandle itself.
137		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
		338
138	=item aio_read $fh,$offset,$length, $data,$dataoffset,$callback	339	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
139		340
140	=item aio_write $fh,$offset,$length, $data,$dataoffset,$callback	341	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
141		342
142	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
143	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<$dataoffset>
144	callback without the actual number of bytes read (or -1 on error, just	345	and calls the callback without the actual number of bytes read (or -1 on
145	like the syscall).	346	error, just like the syscall).
		347
		348	C<aio_read> will, like C<sysread>, shrink or grow the C<$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<$data>.
		360
		361	The C<$data> scalar I<MUST NOT> be modified in any way while the request
		362	is outstanding. Modifying it can result in segfaults or World War III (if
		363	the necessary/optional hardware is installed).
146		364
147	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
148	offset C<0> within the scalar:	366	offset C<0> within the scalar:
149		367
150	aio_read $fh, 7, 15, $buffer, 0, sub {	368	aio_read $fh, 7, 15, $buffer, 0, sub {
151	$_[0] > 0 or die "read error: $!";	369	$_[0] > 0 or die "read error: $!";
152	print "read $_[0] bytes: <$buffer>\n";	370	print "read $_[0] bytes: <$buffer>\n";
153	};	371	};
154		372
		373
		374	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
		375
		376	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
		377	reading at byte offset C<$in_offset>, and starts writing at the current
		378	file offset of C<$out_fh>. Because of that, it is not safe to issue more
		379	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each
		380	other.
		381
		382	This call tries to make use of a native C<sendfile> syscall to provide
		383	zero-copy operation. For this to work, C<$out_fh> should refer to a
		384	socket, and C<$in_fh> should refer to mmap'able file.
		385
		386	If the native sendfile call fails or is not implemented, it will be
		387	emulated, so you can call C<aio_sendfile> on any type of filehandle
		388	regardless of the limitations of the operating system.
		389
		390	Please note, however, that C<aio_sendfile> can read more bytes from
		391	C<$in_fh> than are written, and there is no way to find out how many
		392	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only
		393	provides the number of bytes written to C<$out_fh>. Only if the result
		394	value equals C<$length> one can assume that C<$length> bytes have been
		395	read.
		396
		397
155	=item aio_readahead $fh,$offset,$length, $callback	398	=item aio_readahead $fh,$offset,$length, $callback->($retval)
156
157	Asynchronously reads the specified byte range into the page cache, using
158	the C<readahead> syscall. If that syscall doesn't exist (likely if your OS
159	isn't Linux) the status will be C<-1> and C<$!> is set to C<ENOSYS>.
160		399
161	C<aio_readahead> populates the page cache with data from a file so that	400	C<aio_readahead> populates the page cache with data from a file so that
162	subsequent reads from that file will not block on disk I/O. The C<$offset>	401	subsequent reads from that file will not block on disk I/O. The C<$offset>
163	argument specifies the starting point from which data is to be read and	402	argument specifies the starting point from which data is to be read and
164	C<$length> specifies the number of bytes to be read. I/O is performed in	403	C<$length> specifies the number of bytes to be read. I/O is performed in
165	whole pages, so that offset is effectively rounded down to a page boundary	404	whole pages, so that offset is effectively rounded down to a page boundary
166	and bytes are read up to the next page boundary greater than or equal to	405	and bytes are read up to the next page boundary greater than or equal to
167	(off-set+length). C<aio_readahead> does not read beyond the end of the	406	(off-set+length). C<aio_readahead> does not read beyond the end of the
168	file. The current file offset of the file is left unchanged.	407	file. The current file offset of the file is left unchanged.
169		408
		409	If that syscall doesn't exist (likely if your OS isn't Linux) it will be
		410	emulated by simply reading the data, which would have a similar effect.
		411
		412
170	=item aio_stat $fh_or_path, $callback	413	=item aio_stat $fh_or_path, $callback->($status)
171		414
172	=item aio_lstat $fh, $callback	415	=item aio_lstat $fh, $callback->($status)
173		416
174	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
175	be called after the stat and the results will be available using C<stat _>	418	be called after the stat and the results will be available using C<stat _>
176	or C<-s _> etc...	419	or C<-s _> etc...
177		420
…		…
187	aio_stat "/etc/passwd", sub {	430	aio_stat "/etc/passwd", sub {
188	$_[0] and die "stat failed: $!";	431	$_[0] and die "stat failed: $!";
189	print "size is ", -s _, "\n";	432	print "size is ", -s _, "\n";
190	};	433	};
191		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
192	=item aio_unlink $pathname, $callback	477	=item aio_unlink $pathname, $callback->($status)
193		478
194	Asynchronously unlink (delete) a file and call the callback with the	479	Asynchronously unlink (delete) a file and call the callback with the
195	result code.	480	result code.
196		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
		526	=item aio_rmdir $pathname, $callback->($status)
		527
		528	Asynchronously rmdir (delete) a directory and call the callback with the
		529	result code.
		530
		531
		532	=item aio_readdir $pathname, $callback->($entries)
		533
		534	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
		535	directory (i.e. opendir + readdir + closedir). The entries will not be
		536	sorted, and will B<NOT> include the C<.> and C<..> entries.
		537
		538	The callback is passed a single argument which is either C<undef> or an
		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<$type>
		574	scalars are read-only: you can not modify them.
		575
		576	=item AIO::READDIR_DIRS_FIRST
		577
		578	When this flag is set, then the names will be returned in an order where
		579	likely directories come first. This is useful when you need to quickly
		580	find directories, or you want to find all directories while avoiding to
		581	stat() each entry.
		582
		583	If the system returns type information in readdir, then this is used
		584	to find directories directly. Otherwise, likely directories are files
		585	beginning with ".", or otherwise files with no dots, of which files with
		586	short names are tried first.
		587
		588	=item AIO::READDIR_STAT_ORDER
		589
		590	When this flag is set, then the names will be returned in an order
		591	suitable for stat()'ing each one. That is, when you plan to stat()
		592	all files in the given directory, then the returned order will likely
		593	be fastest.
		594
		595	If both this flag and IO::READDIR_DIRS_FIRST are specified, then the
		596	likely dirs come first, resulting in a less optimal stat order.
		597
		598	=item AIO::READDIR_FOUND_UNKNOWN
		599
		600	This flag should not be set when calling C<aio_readdirx>. Instead, it
		601	is being set by C<aio_readdirx>, when any of the C<$type>'s found were
		602	C<AIO::DT_UNKNOWN>. The absense of this flag therefore indicates that all
		603	C<$type>'s are known, which can be used to speed up some algorithms.
		604
		605	=back
		606
		607
		608	=item aio_load $path, $data, $callback->($status)
		609
		610	This is a composite request that tries to fully load the given file into
		611	memory. Status is the same as with aio_read.
		612
		613	=cut
		614
		615	sub aio_load($$;$) {
		616	my ($path, undef, $cb) = @_;
		617	my $data = \$_[1];
		618
		619	my $pri = aioreq_pri;
		620	my $grp = aio_group $cb;
		621
		622	aioreq_pri $pri;
		623	add $grp aio_open $path, O_RDONLY, 0, sub {
		624	my $fh = shift
		625	or return $grp->result (-1);
		626
		627	aioreq_pri $pri;
		628	add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub {
		629	$grp->result ($_[0]);
		630	};
		631	};
		632
		633	$grp
		634	}
		635
		636	=item aio_copy $srcpath, $dstpath, $callback->($status)
		637
		638	Try to copy the I<file> (directories not supported as either source or
		639	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		640	the C<0> (error) or C<-1> ok.
		641
		642	This is a composite request that creates the destination file with
		643	mode 0200 and copies the contents of the source file into it using
		644	C<aio_sendfile>, followed by restoring atime, mtime, access mode and
		645	uid/gid, in that order.
		646
		647	If an error occurs, the partial destination file will be unlinked, if
		648	possible, except when setting atime, mtime, access mode and uid/gid, where
		649	errors are being ignored.
		650
		651	=cut
		652
		653	sub aio_copy($$;$) {
		654	my ($src, $dst, $cb) = @_;
		655
		656	my $pri = aioreq_pri;
		657	my $grp = aio_group $cb;
		658
		659	aioreq_pri $pri;
		660	add $grp aio_open $src, O_RDONLY, 0, sub {
		661	if (my $src_fh = $_[0]) {
		662	my @stat = stat $src_fh; # hmm, might bock over nfs?
		663
		664	aioreq_pri $pri;
		665	add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {
		666	if (my $dst_fh = $_[0]) {
		667	aioreq_pri $pri;
		668	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
		669	if ($_[0] == $stat[7]) {
		670	$grp->result (0);
		671	close $src_fh;
		672
		673	my $ch = sub {
		674	aioreq_pri $pri;
		675	add $grp aio_chmod $dst_fh, $stat[2] & 07777, sub {
		676	aioreq_pri $pri;
		677	add $grp aio_chown $dst_fh, $stat[4], $stat[5], sub {
		678	aioreq_pri $pri;
		679	add $grp aio_close $dst_fh;
		680	}
		681	};
		682	};
		683
		684	aioreq_pri $pri;
		685	add $grp aio_utime $dst_fh, $stat[8], $stat[9], sub {
		686	if ($_[0] < 0 && $! == ENOSYS) {
		687	aioreq_pri $pri;
		688	add $grp aio_utime $dst, $stat[8], $stat[9], $ch;
		689	} else {
		690	$ch->();
		691	}
		692	};
		693	} else {
		694	$grp->result (-1);
		695	close $src_fh;
		696	close $dst_fh;
		697
		698	aioreq $pri;
		699	add $grp aio_unlink $dst;
		700	}
		701	};
		702	} else {
		703	$grp->result (-1);
		704	}
		705	},
		706
		707	} else {
		708	$grp->result (-1);
		709	}
		710	};
		711
		712	$grp
		713	}
		714
		715	=item aio_move $srcpath, $dstpath, $callback->($status)
		716
		717	Try to move the I<file> (directories not supported as either source or
		718	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		719	the C<0> (error) or C<-1> ok.
		720
		721	This is a composite request that tries to rename(2) the file first; if
		722	rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if
		723	that is successful, unlinks the C<$srcpath>.
		724
		725	=cut
		726
		727	sub aio_move($$;$) {
		728	my ($src, $dst, $cb) = @_;
		729
		730	my $pri = aioreq_pri;
		731	my $grp = aio_group $cb;
		732
		733	aioreq_pri $pri;
		734	add $grp aio_rename $src, $dst, sub {
		735	if ($_[0] && $! == EXDEV) {
		736	aioreq_pri $pri;
		737	add $grp aio_copy $src, $dst, sub {
		738	$grp->result ($_[0]);
		739
		740	if (!$_[0]) {
		741	aioreq_pri $pri;
		742	add $grp aio_unlink $src;
		743	}
		744	};
		745	} else {
		746	$grp->result ($_[0]);
		747	}
		748	};
		749
		750	$grp
		751	}
		752
		753	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
		754
		755	Scans a directory (similar to C<aio_readdir>) but additionally tries to
		756	efficiently separate the entries of directory C<$path> into two sets of
		757	names, directories you can recurse into (directories), and ones you cannot
		758	recurse into (everything else, including symlinks to directories).
		759
		760	C<aio_scandir> is a composite request that creates of many sub requests_
		761	C<$maxreq> specifies the maximum number of outstanding aio requests that
		762	this function generates. If it is C<< <= 0 >>, then a suitable default
		763	will be chosen (currently 4).
		764
		765	On error, the callback is called without arguments, otherwise it receives
		766	two array-refs with path-relative entry names.
		767
		768	Example:
		769
		770	aio_scandir $dir, 0, sub {
		771	my ($dirs, $nondirs) = @_;
		772	print "real directories: @$dirs\n";
		773	print "everything else: @$nondirs\n";
		774	};
		775
		776	Implementation notes.
		777
		778	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.
		779
		780	If readdir returns file type information, then this is used directly to
		781	find directories.
		782
		783	Otherwise, after reading the directory, the modification time, size etc.
		784	of the directory before and after the readdir is checked, and if they
		785	match (and isn't the current time), the link count will be used to decide
		786	how many entries are directories (if >= 2). Otherwise, no knowledge of the
		787	number of subdirectories will be assumed.
		788
		789	Then entries will be sorted into likely directories a non-initial dot
		790	currently) and likely non-directories (see C<aio_readdirx>). Then every
		791	entry plus an appended C</.> will be C<stat>'ed, likely directories first,
		792	in order of their inode numbers. If that succeeds, it assumes that the
		793	entry is a directory or a symlink to directory (which will be checked
		794	seperately). This is often faster than stat'ing the entry itself because
		795	filesystems might detect the type of the entry without reading the inode
		796	data (e.g. ext2fs filetype feature), even on systems that cannot return
		797	the filetype information on readdir.
		798
		799	If the known number of directories (link count - 2) has been reached, the
		800	rest of the entries is assumed to be non-directories.
		801
		802	This only works with certainty on POSIX (= UNIX) filesystems, which
		803	fortunately are the vast majority of filesystems around.
		804
		805	It will also likely work on non-POSIX filesystems with reduced efficiency
		806	as those tend to return 0 or 1 as link counts, which disables the
		807	directory counting heuristic.
		808
		809	=cut
		810
		811	sub aio_scandir($$;$) {
		812	my ($path, $maxreq, $cb) = @_;
		813
		814	my $pri = aioreq_pri;
		815
		816	my $grp = aio_group $cb;
		817
		818	$maxreq = 4 if $maxreq <= 0;
		819
		820	# stat once
		821	aioreq_pri $pri;
		822	add $grp aio_stat $path, sub {
		823	return $grp->result () if $_[0];
		824	my $now = time;
		825	my $hash1 = join ":", (stat _)[0,1,3,7,9];
		826
		827	# read the directory entries
		828	aioreq_pri $pri;
		829	add $grp aio_readdirx $path, READDIR_DIRS_FIRST, sub {
		830	my $entries = shift
		831	or return $grp->result ();
		832
		833	# stat the dir another time
		834	aioreq_pri $pri;
		835	add $grp aio_stat $path, sub {
		836	my $hash2 = join ":", (stat _)[0,1,3,7,9];
		837
		838	my $ndirs;
		839
		840	# take the slow route if anything looks fishy
		841	if ($hash1 ne $hash2 or (stat _)[9] == $now) {
		842	$ndirs = -1;
		843	} else {
		844	# if nlink == 2, we are finished
		845	# on non-posix-fs's, we rely on nlink < 2
		846	$ndirs = (stat _)[3] - 2
		847	or return $grp->result ([], $entries);
		848	}
		849
		850	my (@dirs, @nondirs);
		851
		852	my $statgrp = add $grp aio_group sub {
		853	$grp->result (\@dirs, \@nondirs);
		854	};
		855
		856	limit $statgrp $maxreq;
		857	feed $statgrp sub {
		858	return unless @$entries;
		859	my $entry = pop @$entries;
		860
		861	aioreq_pri $pri;
		862	add $statgrp aio_stat "$path/$entry/.", sub {
		863	if ($_[0] < 0) {
		864	push @nondirs, $entry;
		865	} else {
		866	# need to check for real directory
		867	aioreq_pri $pri;
		868	add $statgrp aio_lstat "$path/$entry", sub {
		869	if (-d _) {
		870	push @dirs, $entry;
		871
		872	unless (--$ndirs) {
		873	push @nondirs, @$entries;
		874	feed $statgrp;
		875	}
		876	} else {
		877	push @nondirs, $entry;
		878	}
		879	}
		880	}
		881	};
		882	};
		883	};
		884	};
		885	};
		886
		887	$grp
		888	}
		889
		890	=item aio_rmtree $path, $callback->($status)
		891
		892	Delete a directory tree starting (and including) C<$path>, return the
		893	status of the final C<rmdir> only. This is a composite request that
		894	uses C<aio_scandir> to recurse into and rmdir directories, and unlink
		895	everything else.
		896
		897	=cut
		898
		899	sub aio_rmtree;
		900	sub aio_rmtree($;$) {
		901	my ($path, $cb) = @_;
		902
		903	my $pri = aioreq_pri;
		904	my $grp = aio_group $cb;
		905
		906	aioreq_pri $pri;
		907	add $grp aio_scandir $path, 0, sub {
		908	my ($dirs, $nondirs) = @_;
		909
		910	my $dirgrp = aio_group sub {
		911	add $grp aio_rmdir $path, sub {
		912	$grp->result ($_[0]);
		913	};
		914	};
		915
		916	(aioreq_pri $pri), add $dirgrp aio_rmtree "$path/$_" for @$dirs;
		917	(aioreq_pri $pri), add $dirgrp aio_unlink "$path/$_" for @$nondirs;
		918
		919	add $grp $dirgrp;
		920	};
		921
		922	$grp
		923	}
		924
		925	=item aio_sync $callback->($status)
		926
		927	Asynchronously call sync and call the callback when finished.
		928
197	=item aio_fsync $fh, $callback	929	=item aio_fsync $fh, $callback->($status)
198		930
199	Asynchronously call fsync on the given filehandle and call the callback	931	Asynchronously call fsync on the given filehandle and call the callback
200	with the fsync result code.	932	with the fsync result code.
201		933
202	=item aio_fdatasync $fh, $callback	934	=item aio_fdatasync $fh, $callback->($status)
203		935
204	Asynchronously call fdatasync on the given filehandle and call the	936	Asynchronously call fdatasync on the given filehandle and call the
205	callback with the fdatasync result code. Might set C<$!> to C<ENOSYS> if	937	callback with the fdatasync result code.
206	C<fdatasync> is not available.	938
		939	If this call isn't available because your OS lacks it or it couldn't be
		940	detected, it will be emulated by calling C<fsync> instead.
		941
		942	=item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		943
		944	Sync the data portion of the file specified by C<$offset> and C<$length>
		945	to disk (but NOT the metadata), by calling the Linux-specific
		946	sync_file_range call. If sync_file_range is not available or it returns
		947	ENOSYS, then fdatasync or fsync is being substituted.
		948
		949	C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>,
		950	C<IO::AIO::SYNC_FILE_RANGE_WRITE> and
		951	C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range
		952	manpage for details.
		953
		954	=item aio_pathsync $path, $callback->($status)
		955
		956	This request tries to open, fsync and close the given path. This is a
		957	composite request intended to sync directories after directory operations
		958	(E.g. rename). This might not work on all operating systems or have any
		959	specific effect, but usually it makes sure that directory changes get
		960	written to disc. It works for anything that can be opened for read-only,
		961	not just directories.
		962
		963	Passes C<0> when everything went ok, and C<-1> on error.
		964
		965	=cut
		966
		967	sub aio_pathsync($;$) {
		968	my ($path, $cb) = @_;
		969
		970	my $pri = aioreq_pri;
		971	my $grp = aio_group $cb;
		972
		973	aioreq_pri $pri;
		974	add $grp aio_open $path, O_RDONLY, 0, sub {
		975	my ($fh) = @_;
		976	if ($fh) {
		977	aioreq_pri $pri;
		978	add $grp aio_fsync $fh, sub {
		979	$grp->result ($_[0]);
		980
		981	aioreq_pri $pri;
		982	add $grp aio_close $fh;
		983	};
		984	} else {
		985	$grp->result (-1);
		986	}
		987	};
		988
		989	$grp
		990	}
		991
		992	=item aio_group $callback->(...)
		993
		994	This is a very special aio request: Instead of doing something, it is a
		995	container for other aio requests, which is useful if you want to bundle
		996	many requests into a single, composite, request with a definite callback
		997	and the ability to cancel the whole request with its subrequests.
		998
		999	Returns an object of class L<IO::AIO::GRP>. See its documentation below
		1000	for more info.
		1001
		1002	Example:
		1003
		1004	my $grp = aio_group sub {
		1005	print "all stats done\n";
		1006	};
		1007
		1008	add $grp
		1009	(aio_stat ...),
		1010	(aio_stat ...),
		1011	...;
		1012
		1013	=item aio_nop $callback->()
		1014
		1015	This is a special request - it does nothing in itself and is only used for
		1016	side effects, such as when you want to add a dummy request to a group so
		1017	that finishing the requests in the group depends on executing the given
		1018	code.
		1019
		1020	While this request does nothing, it still goes through the execution
		1021	phase and still requires a worker thread. Thus, the callback will not
		1022	be executed immediately but only after other requests in the queue have
		1023	entered their execution phase. This can be used to measure request
		1024	latency.
		1025
		1026	=item IO::AIO::aio_busy $fractional_seconds, $callback->() *NOT EXPORTED*
		1027
		1028	Mainly used for debugging and benchmarking, this aio request puts one of
		1029	the request workers to sleep for the given time.
		1030
		1031	While it is theoretically handy to have simple I/O scheduling requests
		1032	like sleep and file handle readable/writable, the overhead this creates is
		1033	immense (it blocks a thread for a long time) so do not use this function
		1034	except to put your application under artificial I/O pressure.
207		1035
208	=back	1036	=back
209		1037
		1038	=head2 IO::AIO::REQ CLASS
		1039
		1040	All non-aggregate C<aio_*> functions return an object of this class when
		1041	called in non-void context.
		1042
		1043	=over 4
		1044
		1045	=item cancel $req
		1046
		1047	Cancels the request, if possible. Has the effect of skipping execution
		1048	when entering the B<execute> state and skipping calling the callback when
		1049	entering the the B<result> state, but will leave the request otherwise
		1050	untouched. That means that requests that currently execute will not be
		1051	stopped and resources held by the request will not be freed prematurely.
		1052
		1053	=item cb $req $callback->(...)
		1054
		1055	Replace (or simply set) the callback registered to the request.
		1056
		1057	=back
		1058
		1059	=head2 IO::AIO::GRP CLASS
		1060
		1061	This class is a subclass of L<IO::AIO::REQ>, so all its methods apply to
		1062	objects of this class, too.
		1063
		1064	A IO::AIO::GRP object is a special request that can contain multiple other
		1065	aio requests.
		1066
		1067	You create one by calling the C<aio_group> constructing function with a
		1068	callback that will be called when all contained requests have entered the
		1069	C<done> state:
		1070
		1071	my $grp = aio_group sub {
		1072	print "all requests are done\n";
		1073	};
		1074
		1075	You add requests by calling the C<add> method with one or more
		1076	C<IO::AIO::REQ> objects:
		1077
		1078	$grp->add (aio_unlink "...");
		1079
		1080	add $grp aio_stat "...", sub {
		1081	$_[0] or return $grp->result ("error");
		1082
		1083	# add another request dynamically, if first succeeded
		1084	add $grp aio_open "...", sub {
		1085	$grp->result ("ok");
		1086	};
		1087	};
		1088
		1089	This makes it very easy to create composite requests (see the source of
		1090	C<aio_move> for an application) that work and feel like simple requests.
		1091
		1092	=over 4
		1093
		1094	=item * The IO::AIO::GRP objects will be cleaned up during calls to
		1095	C<IO::AIO::poll_cb>, just like any other request.
		1096
		1097	=item * They can be canceled like any other request. Canceling will cancel not
		1098	only the request itself, but also all requests it contains.
		1099
		1100	=item * They can also can also be added to other IO::AIO::GRP objects.
		1101
		1102	=item * You must not add requests to a group from within the group callback (or
		1103	any later time).
		1104
		1105	=back
		1106
		1107	Their lifetime, simplified, looks like this: when they are empty, they
		1108	will finish very quickly. If they contain only requests that are in the
		1109	C<done> state, they will also finish. Otherwise they will continue to
		1110	exist.
		1111
		1112	That means after creating a group you have some time to add requests
		1113	(precisely before the callback has been invoked, which is only done within
		1114	the C<poll_cb>). And in the callbacks of those requests, you can add
		1115	further requests to the group. And only when all those requests have
		1116	finished will the the group itself finish.
		1117
		1118	=over 4
		1119
		1120	=item add $grp ...
		1121
		1122	=item $grp->add (...)
		1123
		1124	Add one or more requests to the group. Any type of L<IO::AIO::REQ> can
		1125	be added, including other groups, as long as you do not create circular
		1126	dependencies.
		1127
		1128	Returns all its arguments.
		1129
		1130	=item $grp->cancel_subs
		1131
		1132	Cancel all subrequests and clears any feeder, but not the group request
		1133	itself. Useful when you queued a lot of events but got a result early.
		1134
		1135	=item $grp->result (...)
		1136
		1137	Set the result value(s) that will be passed to the group callback when all
		1138	subrequests have finished and set the groups errno to the current value
		1139	of errno (just like calling C<errno> without an error number). By default,
		1140	no argument will be passed and errno is zero.
		1141
		1142	=item $grp->errno ([$errno])
		1143
		1144	Sets the group errno value to C<$errno>, or the current value of errno
		1145	when the argument is missing.
		1146
		1147	Every aio request has an associated errno value that is restored when
		1148	the callback is invoked. This method lets you change this value from its
		1149	default (0).
		1150
		1151	Calling C<result> will also set errno, so make sure you either set C<$!>
		1152	before the call to C<result>, or call c<errno> after it.
		1153
		1154	=item feed $grp $callback->($grp)
		1155
		1156	Sets a feeder/generator on this group: every group can have an attached
		1157	generator that generates requests if idle. The idea behind this is that,
		1158	although you could just queue as many requests as you want in a group,
		1159	this might starve other requests for a potentially long time. For example,
		1160	C<aio_scandir> might generate hundreds of thousands C<aio_stat> requests,
		1161	delaying any later requests for a long time.
		1162
		1163	To avoid this, and allow incremental generation of requests, you can
		1164	instead a group and set a feeder on it that generates those requests. The
		1165	feed callback will be called whenever there are few enough (see C<limit>,
		1166	below) requests active in the group itself and is expected to queue more
		1167	requests.
		1168
		1169	The feed callback can queue as many requests as it likes (i.e. C<add> does
		1170	not impose any limits).
		1171
		1172	If the feed does not queue more requests when called, it will be
		1173	automatically removed from the group.
		1174
		1175	If the feed limit is C<0> when this method is called, it will be set to
		1176	C<2> automatically.
		1177
		1178	Example:
		1179
		1180	# stat all files in @files, but only ever use four aio requests concurrently:
		1181
		1182	my $grp = aio_group sub { print "finished\n" };
		1183	limit $grp 4;
		1184	feed $grp sub {
		1185	my $file = pop @files
		1186	or return;
		1187
		1188	add $grp aio_stat $file, sub { ... };
		1189	};
		1190
		1191	=item limit $grp $num
		1192
		1193	Sets the feeder limit for the group: The feeder will be called whenever
		1194	the group contains less than this many requests.
		1195
		1196	Setting the limit to C<0> will pause the feeding process.
		1197
		1198	The default value for the limit is C<0>, but note that setting a feeder
		1199	automatically bumps it up to C<2>.
		1200
		1201	=back
		1202
210	=head2 SUPPORT FUNCTIONS	1203	=head2 SUPPORT FUNCTIONS
		1204
		1205	=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION
211		1206
212	=over 4	1207	=over 4
213		1208
214	=item $fileno = IO::AIO::poll_fileno	1209	=item $fileno = IO::AIO::poll_fileno
215		1210
…		…
220		1215
221	See C<poll_cb> for an example.	1216	See C<poll_cb> for an example.
222		1217
223	=item IO::AIO::poll_cb	1218	=item IO::AIO::poll_cb
224		1219
225	Process all outstanding events on the result pipe. You have to call this	1220	Process some outstanding events on the result pipe. You have to call this
226	regularly. Returns the number of events processed. Returns immediately	1221	regularly. Returns C<0> if all events could be processed, or C<-1> if it
227	when no events are outstanding.	1222	returned earlier for whatever reason. Returns immediately when no events
		1223	are outstanding. The amount of events processed depends on the settings of
		1224	C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>.
		1225
		1226	If not all requests were processed for whatever reason, the filehandle
		1227	will still be ready when C<poll_cb> returns, so normally you don't have to
		1228	do anything special to have it called later.
228		1229
229	Example: Install an Event watcher that automatically calls	1230	Example: Install an Event watcher that automatically calls
230	IO::AIO::poll_cb with high priority:	1231	IO::AIO::poll_cb with high priority:
231		1232
232	Event->io (fd => IO::AIO::poll_fileno,	1233	Event->io (fd => IO::AIO::poll_fileno,
233	poll => 'r', async => 1,	1234	poll => 'r', async => 1,
234	cb => \&IO::AIO::poll_cb);	1235	cb => \&IO::AIO::poll_cb);
235		1236
		1237	=item IO::AIO::max_poll_reqs $nreqs
		1238
		1239	=item IO::AIO::max_poll_time $seconds
		1240
		1241	These set the maximum number of requests (default C<0>, meaning infinity)
		1242	that are being processed by C<IO::AIO::poll_cb> in one call, respectively
		1243	the maximum amount of time (default C<0>, meaning infinity) spent in
		1244	C<IO::AIO::poll_cb> to process requests (more correctly the mininum amount
		1245	of time C<poll_cb> is allowed to use).
		1246
		1247	Setting C<max_poll_time> to a non-zero value creates an overhead of one
		1248	syscall per request processed, which is not normally a problem unless your
		1249	callbacks are really really fast or your OS is really really slow (I am
		1250	not mentioning Solaris here). Using C<max_poll_reqs> incurs no overhead.
		1251
		1252	Setting these is useful if you want to ensure some level of
		1253	interactiveness when perl is not fast enough to process all requests in
		1254	time.
		1255
		1256	For interactive programs, values such as C<0.01> to C<0.1> should be fine.
		1257
		1258	Example: Install an Event watcher that automatically calls
		1259	IO::AIO::poll_cb with low priority, to ensure that other parts of the
		1260	program get the CPU sometimes even under high AIO load.
		1261
		1262	# try not to spend much more than 0.1s in poll_cb
		1263	IO::AIO::max_poll_time 0.1;
		1264
		1265	# use a low priority so other tasks have priority
		1266	Event->io (fd => IO::AIO::poll_fileno,
		1267	poll => 'r', nice => 1,
		1268	cb => &IO::AIO::poll_cb);
		1269
236	=item IO::AIO::poll_wait	1270	=item IO::AIO::poll_wait
237		1271
		1272	If there are any outstanding requests and none of them in the result
238	Wait till the result filehandle becomes ready for reading (simply does a	1273	phase, wait till the result filehandle becomes ready for reading (simply
239	C<select> on the filehandle. This is useful if you want to synchronously wait	1274	does a C<select> on the filehandle. This is useful if you want to
240	for some requests to finish).	1275	synchronously wait for some requests to finish).
241		1276
242	See C<nreqs> for an example.	1277	See C<nreqs> for an example.
243		1278
		1279	=item IO::AIO::poll
		1280
		1281	Waits until some requests have been handled.
		1282
		1283	Returns the number of requests processed, but is otherwise strictly
		1284	equivalent to:
		1285
		1286	IO::AIO::poll_wait, IO::AIO::poll_cb
		1287
244	=item IO::AIO::nreqs	1288	=item IO::AIO::flush
245		1289
246	Returns the number of requests currently outstanding (i.e. for which their	1290	Wait till all outstanding AIO requests have been handled.
247	callback has not been invoked yet).
248		1291
249	Example: wait till there are no outstanding requests anymore:	1292	Strictly equivalent to:
250		1293
251	IO::AIO::poll_wait, IO::AIO::poll_cb	1294	IO::AIO::poll_wait, IO::AIO::poll_cb
252	while IO::AIO::nreqs;	1295	while IO::AIO::nreqs;
253		1296
		1297	=back
		1298
		1299	=head3 CONTROLLING THE NUMBER OF THREADS
		1300
		1301	=over
		1302
		1303	=item IO::AIO::min_parallel $nthreads
		1304
		1305	Set the minimum number of AIO threads to C<$nthreads>. The current
		1306	default is C<8>, which means eight asynchronous operations can execute
		1307	concurrently at any one time (the number of outstanding requests,
		1308	however, is unlimited).
		1309
		1310	IO::AIO starts threads only on demand, when an AIO request is queued and
		1311	no free thread exists. Please note that queueing up a hundred requests can
		1312	create demand for a hundred threads, even if it turns out that everything
		1313	is in the cache and could have been processed faster by a single thread.
		1314
		1315	It is recommended to keep the number of threads relatively low, as some
		1316	Linux kernel versions will scale negatively with the number of threads
		1317	(higher parallelity => MUCH higher latency). With current Linux 2.6
		1318	versions, 4-32 threads should be fine.
		1319
		1320	Under most circumstances you don't need to call this function, as the
		1321	module selects a default that is suitable for low to moderate load.
		1322
		1323	=item IO::AIO::max_parallel $nthreads
		1324
		1325	Sets the maximum number of AIO threads to C<$nthreads>. If more than the
		1326	specified number of threads are currently running, this function kills
		1327	them. This function blocks until the limit is reached.
		1328
		1329	While C<$nthreads> are zero, aio requests get queued but not executed
		1330	until the number of threads has been increased again.
		1331
		1332	This module automatically runs C<max_parallel 0> at program end, to ensure
		1333	that all threads are killed and that there are no outstanding requests.
		1334
		1335	Under normal circumstances you don't need to call this function.
		1336
		1337	=item IO::AIO::max_idle $nthreads
		1338
		1339	Limit the number of threads (default: 4) that are allowed to idle (i.e.,
		1340	threads that did not get a request to process within 10 seconds). That
		1341	means if a thread becomes idle while C<$nthreads> other threads are also
		1342	idle, it will free its resources and exit.
		1343
		1344	This is useful when you allow a large number of threads (e.g. 100 or 1000)
		1345	to allow for extremely high load situations, but want to free resources
		1346	under normal circumstances (1000 threads can easily consume 30MB of RAM).
		1347
		1348	The default is probably ok in most situations, especially if thread
		1349	creation is fast. If thread creation is very slow on your system you might
		1350	want to use larger values.
		1351
		1352	=item IO::AIO::max_outstanding $maxreqs
		1353
		1354	This is a very bad function to use in interactive programs because it
		1355	blocks, and a bad way to reduce concurrency because it is inexact: Better
		1356	use an C<aio_group> together with a feed callback.
		1357
		1358	Sets the maximum number of outstanding requests to C<$nreqs>. If you
		1359	do queue up more than this number of requests, the next call to the
		1360	C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>)
		1361	function will block until the limit is no longer exceeded.
		1362
		1363	The default value is very large, so there is no practical limit on the
		1364	number of outstanding requests.
		1365
		1366	You can still queue as many requests as you want. Therefore,
		1367	C<max_outstanding> is mainly useful in simple scripts (with low values) or
		1368	as a stop gap to shield against fatal memory overflow (with large values).
		1369
		1370	=back
		1371
		1372	=head3 STATISTICAL INFORMATION
		1373
		1374	=over
		1375
254	=item IO::AIO::flush	1376	=item IO::AIO::nreqs
255		1377
256	Wait till all outstanding AIO requests have been handled.	1378	Returns the number of requests currently in the ready, execute or pending
		1379	states (i.e. for which their callback has not been invoked yet).
257		1380
258	Strictly equivalent to:	1381	Example: wait till there are no outstanding requests anymore:
259		1382
260	IO::AIO::poll_wait, IO::AIO::poll_cb	1383	IO::AIO::poll_wait, IO::AIO::poll_cb
261	while IO::AIO::nreqs;	1384	while IO::AIO::nreqs;
262		1385
		1386	=item IO::AIO::nready
		1387
		1388	Returns the number of requests currently in the ready state (not yet
		1389	executed).
		1390
263	=item IO::AIO::poll	1391	=item IO::AIO::npending
264		1392
265	Waits until some requests have been handled.	1393	Returns the number of requests currently in the pending state (executed,
266		1394	but not yet processed by poll_cb).
267	Strictly equivalent to:
268
269	IO::AIO::poll_wait, IO::AIO::poll_cb
270	if IO::AIO::nreqs;
271
272	=item IO::AIO::min_parallel $nthreads
273
274	Set the minimum number of AIO threads to C<$nthreads>. The default is
275	C<1>, which means a single asynchronous operation can be done at one time
276	(the number of outstanding operations, however, is unlimited).
277
278	It is recommended to keep the number of threads low, as some Linux
279	kernel versions will scale negatively with the number of threads (higher
280	parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32
281	threads should be fine.
282
283	Under normal circumstances you don't need to call this function, as this
284	module automatically starts some threads (the exact number might change,
285	and is currently 4).
286
287	=item IO::AIO::max_parallel $nthreads
288
289	Sets the maximum number of AIO threads to C<$nthreads>. If more than
290	the specified number of threads are currently running, kill them. This
291	function blocks until the limit is reached.
292
293	This module automatically runs C<max_parallel 0> at program end, to ensure
294	that all threads are killed and that there are no outstanding requests.
295
296	Under normal circumstances you don't need to call this function.
297
298	=item $oldnreqs = IO::AIO::max_outstanding $nreqs
299
300	Sets the maximum number of outstanding requests to C<$nreqs>. If you
301	try to queue up more than this number of requests, the caller will block until
302	some requests have been handled.
303
304	The default is very large, so normally there is no practical limit. If you
305	queue up many requests in a loop it it often improves speed if you set
306	this to a relatively low number, such as C<100>.
307
308	Under normal circumstances you don't need to call this function.
309		1395
310	=back	1396	=back
311		1397
312	=cut	1398	=cut
313		1399
314	# support function to convert a fd into a perl filehandle
315	sub _fd2fh {
316	return undef if $_[0] < 0;
317
318	# try to generate nice filehandles
319	my $sym = "IO::AIO::fd#$_[0]";
320	local *$sym;
321	open *$sym, "+<&=$_[0]"
322	or return undef;
323
324	*$sym
325	}
326
327	min_parallel 4;	1400	min_parallel 8;
328		1401
329	END {	1402	END { flush }
330	max_parallel 0;
331	}
332		1403
333	1;	1404	1;
334		1405
		1406	=head2 FORK BEHAVIOUR
		1407
		1408	This module should do "the right thing" when the process using it forks:
		1409
		1410	Before the fork, IO::AIO enters a quiescent state where no requests
		1411	can be added in other threads and no results will be processed. After
		1412	the fork the parent simply leaves the quiescent state and continues
		1413	request/result processing, while the child frees the request/result queue
		1414	(so that the requests started before the fork will only be handled in the
		1415	parent). Threads will be started on demand until the limit set in the
		1416	parent process has been reached again.
		1417
		1418	In short: the parent will, after a short pause, continue as if fork had
		1419	not been called, while the child will act as if IO::AIO has not been used
		1420	yet.
		1421
		1422	=head2 MEMORY USAGE
		1423
		1424	Per-request usage:
		1425
		1426	Each aio request uses - depending on your architecture - around 100-200
		1427	bytes of memory. In addition, stat requests need a stat buffer (possibly
		1428	a few hundred bytes), readdir requires a result buffer and so on. Perl
		1429	scalars and other data passed into aio requests will also be locked and
		1430	will consume memory till the request has entered the done state.
		1431
		1432	This is not awfully much, so queuing lots of requests is not usually a
		1433	problem.
		1434
		1435	Per-thread usage:
		1436
		1437	In the execution phase, some aio requests require more memory for
		1438	temporary buffers, and each thread requires a stack and other data
		1439	structures (usually around 16k-128k, depending on the OS).
		1440
		1441	=head1 KNOWN BUGS
		1442
		1443	Known bugs will be fixed in the next release.
		1444
335	=head1 SEE ALSO	1445	=head1 SEE ALSO
336		1446
337	L<Coro>, L<Linux::AIO>.	1447	L<AnyEvent::AIO> for easy integration into event loops, L<Coro::AIO> for a
		1448	more natural syntax.
338		1449
339	=head1 AUTHOR	1450	=head1 AUTHOR
340		1451
341	Marc Lehmann <schmorp@schmorp.de>	1452	Marc Lehmann <schmorp@schmorp.de>
342	http://home.schmorp.de/	1453	http://home.schmorp.de/

Diff Legend

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