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

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.1 by root, Sun Jul 10 17:07:44 2005 UTC vs.
Revision 1.39 by root, Sun Aug 28 11:05:50 2005 UTC

…		…
4		4
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 {
		10	my ($fh) = @_;
		11	...
		12	};
		13
		14	aio_unlink "/tmp/file", sub { };
		15
		16	aio_read $fh, 30000, 1024, $buffer, 0, sub {
		17	$_[0] > 0 or die "read error: $!";
		18	};
		19
		20	# Event
		21	Event->io (fd => IO::AIO::poll_fileno,
		22	poll => 'r',
		23	cb => \&IO::AIO::poll_cb);
		24
		25	# Glib/Gtk2
		26	add_watch Glib::IO IO::AIO::poll_fileno,
		27	in => sub { IO::AIO::poll_cb; 1 };
		28
		29	# Tk
		30	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
		31	readable => \&IO::AIO::poll_cb);
		32
		33	# Danga::Socket
		34	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
		35	\&IO::AIO::poll_cb);
		36
		37
9	=head1 DESCRIPTION	38	=head1 DESCRIPTION
10		39
11	This module implements asynchronous I/O using whatever means your	40	This module implements asynchronous I/O using whatever means your
12	operating system supports. Currently, it falls back to Linux::AIO if that	41	operating system supports.
13	module is available, or uses pthreads to emulato aio functionality.
14		42
15	Currently, in this module a number of threads are started that execute	43	Currently, a number of threads are started that execute your read/writes
16	your read/writes and signal their completion. You don't need thread	44	and signal their completion. You don't need thread support in your libc or
17	support in your libc or perl, and the threads created by this module will	45	perl, and the threads created by this module will not be visible to the
18	not be visible to the pthreads library.	46	pthreads library. In the future, this module might make use of the native
		47	aio functions available on many operating systems. However, they are often
		48	not well-supported (Linux doesn't allow them on normal files currently,
		49	for example), and they would only support aio_read and aio_write, so the
		50	remaining functionality would have to be implemented using threads anyway.
19		51
20	Although the module will work with in the presence of other threads, it is	52	Although the module will work with in the presence of other threads, it is
21	not reentrant, so use appropriate locking yourself.	53	currently not reentrant, so use appropriate locking yourself, always call
22		54	C<poll_cb> from within the same thread, or never call C<poll_cb> (or other
23	=head2 API NOTES	55	C<aio_> functions) recursively.
24
25	All the C<aio_*> calls are more or less thin wrappers around the syscall
26	with the same name (sans C<aio_>). The arguments are similar or identical,
27	and they all accept an additional C<$callback> argument which must be
28	a code reference. This code reference will get called with the syscall
29	return code (e.g. most syscalls return C<-1> on error, unlike perl, which
30	usually delivers "false") as it's sole argument when the given syscall has
31	been executed asynchronously.
32
33	All functions that expect a filehandle will also accept a file descriptor.
34
35	The filenames you pass to these routines I<must> be absolute. The reason
36	is that at the time the request is being executed, the current working
37	directory could have changed. Alternatively, you can make sure that you
38	never change the current working directory.
39
40	=over 4
41		56
42	=cut	57	=cut
43		58
44	package IO::AIO;	59	package IO::AIO;
45		60
		61	no warnings;
		62
46	use base 'Exporter';	63	use base 'Exporter';
47		64
		65	use Fcntl ();
		66
48	BEGIN {	67	BEGIN {
49	$VERSION = 0.1;	68	$VERSION = 1.6;
50		69
51	@EXPORT = qw(aio_read aio_write aio_open aio_close aio_stat aio_lstat aio_unlink	70	@EXPORT = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat
		71	aio_lstat aio_unlink aio_rmdir aio_readdir aio_symlink
52	aio_fsync aio_fdatasync aio_readahead);	72	aio_fsync aio_fdatasync aio_readahead);
53	@EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel nreqs);	73	@EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel
		74	max_outstanding nreqs);
54		75
55	require XSLoader;	76	require XSLoader;
56	XSLoader::load IO::AIO, $VERSION;	77	XSLoader::load IO::AIO, $VERSION;
57	}	78	}
58		79
59	=item IO::AIO::min_parallel $nthreads	80	=head1 FUNCTIONS
60		81
61	Set the minimum number of AIO threads to C<$nthreads>. The default is	82	=head2 AIO FUNCTIONS
62	C<1>, which means a single asynchronous operation can be done at one time
63	(the number of outstanding operations, however, is unlimited).
64		83
65	It is recommended to keep the number of threads low, as some linux	84	All the C<aio_*> calls are more or less thin wrappers around the syscall
66	kernel versions will scale negatively with the number of threads (higher	85	with the same name (sans C<aio_>). The arguments are similar or identical,
67	parallelity => MUCH higher latency).	86	and they all accept an additional (and optional) C<$callback> argument
		87	which must be a code reference. This code reference will get called with
		88	the syscall return code (e.g. most syscalls return C<-1> on error, unlike
		89	perl, which usually delivers "false") as it's sole argument when the given
		90	syscall has been executed asynchronously.
68		91
69	Under normal circumstances you don't need to call this function, as this	92	All functions expecting a filehandle keep a copy of the filehandle
70	module automatically starts a single async thread.	93	internally until the request has finished.
71		94
72	=item IO::AIO::max_parallel $nthreads	95	The pathnames you pass to these routines I<must> be absolute and
		96	encoded in byte form. The reason for the former is that at the time the
		97	request is being executed, the current working directory could have
		98	changed. Alternatively, you can make sure that you never change the
		99	current working directory.
73		100
74	Sets the maximum number of AIO threads to C<$nthreads>. If more than	101	To encode pathnames to byte form, either make sure you either: a)
75	the specified number of threads are currently running, kill them. This	102	always pass in filenames you got from outside (command line, readdir
76	function blocks until the limit is reached.	103	etc.), b) are ASCII or ISO 8859-1, c) use the Encode module and encode
		104	your pathnames to the locale (or other) encoding in effect in the user
		105	environment, d) use Glib::filename_from_unicode on unicode filenames or e)
		106	use something else.
77		107
78	This module automatically runs C<max_parallel 0> at program end, to ensure	108	=over 4
79	that all threads are killed and that there are no outstanding requests.
80
81	Under normal circumstances you don't need to call this function.
82
83	=item $fileno = IO::AIO::poll_fileno
84
85	Return the I<request result pipe filehandle>. This filehandle must be
86	polled for reading by some mechanism outside this module (e.g. Event
87	or select, see below). If the pipe becomes readable you have to call
88	C<poll_cb> to check the results.
89
90	See C<poll_cb> for an example.
91
92	=item IO::AIO::poll_cb
93
94	Process all outstanding events on the result pipe. You have to call this
95	regularly. Returns the number of events processed. Returns immediately
96	when no events are outstanding.
97
98	You can use Event to multiplex, e.g.:
99
100	Event->io (fd => IO::AIO::poll_fileno,
101	poll => 'r', async => 1,
102	cb => \&IO::AIO::poll_cb);
103
104	=item IO::AIO::poll_wait
105
106	Wait till the result filehandle becomes ready for reading (simply does a
107	select on the filehandle. This is useful if you want to synchronously wait
108	for some requests to finish).
109
110	See C<nreqs> for an example.
111
112	=item IO::AIO::nreqs
113
114	Returns the number of requests currently outstanding.
115
116	Example: wait till there are no outstanding requests anymore:
117
118	IO::AIO::poll_wait, IO::AIO::poll_cb
119	while IO::AIO::nreqs;
120		109
121	=item aio_open $pathname, $flags, $mode, $callback	110	=item aio_open $pathname, $flags, $mode, $callback
122		111
123	Asynchronously open or create a file and call the callback with the	112	Asynchronously open or create a file and call the callback with a newly
124	filedescriptor (NOT a perl filehandle, sorry for that, but watch out, this	113	created filehandle for the file.
125	might change in the future).
126		114
127	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,	115	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,
128	for an explanation.	116	for an explanation.
129		117
130	The C<$mode> argument is a bitmask. See the C<Fcntl> module for a	118	The C<$flags> argument is a bitmask. See the C<Fcntl> module for a
131	list. They are the same as used in C<sysopen>.	119	list. They are the same as used by C<sysopen>.
		120
		121	Likewise, C<$mode> specifies the mode of the newly created file, if it
		122	didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,
		123	except that it is mandatory (i.e. use C<0> if you don't create new files,
		124	and C<0666> or C<0777> if you do).
132		125
133	Example:	126	Example:
134		127
135	aio_open "/etc/passwd", O_RDONLY, 0, sub {	128	aio_open "/etc/passwd", O_RDONLY, 0, sub {
136	if ($_[0] >= 0) {	129	if ($_[0]) {
137	open my $fh, "<&$_[0]"; # create a copy for perl
138	aio_close $_[0], sub { }; # close the aio handle
139	print "open successful, fh is $fh\n";	130	print "open successful, fh is $_[0]\n";
140	...	131	...
141	} else {	132	} else {
142	die "open failed: $!\n";	133	die "open failed: $!\n";
143	}	134	}
144	};	135	};
145		136
146	=item aio_close $fh, $callback	137	=item aio_close $fh, $callback
147		138
148	Asynchronously close a file and call the callback with the result code.	139	Asynchronously close a file and call the callback with the result
		140	code. I<WARNING:> although accepted, you should not pass in a perl
		141	filehandle here, as perl will likely close the file descriptor another
		142	time when the filehandle is destroyed. Normally, you can safely call perls
		143	C<close> or just let filehandles go out of scope.
		144
		145	This is supposed to be a bug in the API, so that might change. It's
		146	therefore best to avoid this function.
149		147
150	=item aio_read $fh,$offset,$length, $data,$dataoffset,$callback	148	=item aio_read $fh,$offset,$length, $data,$dataoffset,$callback
151		149
152	=item aio_write $fh,$offset,$length, $data,$dataoffset,$callback	150	=item aio_write $fh,$offset,$length, $data,$dataoffset,$callback
153		151
154	Reads or writes C<length> bytes from the specified C<fh> and C<offset>	152	Reads or writes C<length> bytes from the specified C<fh> and C<offset>
155	into the scalar given by C<data> and offset C<dataoffset> and calls the	153	into the scalar given by C<data> and offset C<dataoffset> and calls the
156	callback without the actual number of bytes read (or -1 on error, just	154	callback without the actual number of bytes read (or -1 on error, just
157	like the syscall).	155	like the syscall).
158		156
		157	The C<$data> scalar I<MUST NOT> be modified in any way while the request
		158	is outstanding. Modifying it can result in segfaults or WW3 (if the
		159	necessary/optional hardware is installed).
		160
159	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, strating at	161	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at
160	offset C<0> within the scalar:	162	offset C<0> within the scalar:
161		163
162	aio_read $fh, 7, 15, $buffer, 0, sub {	164	aio_read $fh, 7, 15, $buffer, 0, sub {
163	$_[0] >= 0 or die "read error: $!";	165	$_[0] > 0 or die "read error: $!";
164	print "read <$buffer>\n";	166	print "read $_[0] bytes: <$buffer>\n";
165	};	167	};
166		168
		169	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback
		170
		171	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
		172	reading at byte offset C<$in_offset>, and starts writing at the current
		173	file offset of C<$out_fh>. Because of that, it is not safe to issue more
		174	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each
		175	other.
		176
		177	This call tries to make use of a native C<sendfile> syscall to provide
		178	zero-copy operation. For this to work, C<$out_fh> should refer to a
		179	socket, and C<$in_fh> should refer to mmap'able file.
		180
		181	If the native sendfile call fails or is not implemented, it will be
		182	emulated, so you can call C<aio_sendfile> on any type of filehandle
		183	regardless of the limitations of the operating system.
		184
		185	Please note, however, that C<aio_sendfile> can read more bytes from
		186	C<$in_fh> than are written, and there is no way to find out how many
		187	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only
		188	provides the number of bytes written to C<$out_fh>. Only if the result
		189	value equals C<$length> one can assume that C<$length> bytes have been
		190	read.
		191
167	=item aio_readahead $fh,$offset,$length, $callback	192	=item aio_readahead $fh,$offset,$length, $callback
168		193
169	Asynchronously reads the specified byte range into the page cache, using
170	the C<readahead> syscall. If that syscall doesn't exist the status will be
171	C<-1> and C<$!> is set to ENOSYS.
172
173	readahead() populates the page cache with data from a file so that	194	C<aio_readahead> populates the page cache with data from a file so that
174	subsequent reads from that file will not block on disk I/O. The C<$offset>	195	subsequent reads from that file will not block on disk I/O. The C<$offset>
175	argument specifies the starting point from which data is to be read and	196	argument specifies the starting point from which data is to be read and
176	C<$length> specifies the number of bytes to be read. I/O is performed in	197	C<$length> specifies the number of bytes to be read. I/O is performed in
177	whole pages, so that offset is effectively rounded down to a page boundary	198	whole pages, so that offset is effectively rounded down to a page boundary
178	and bytes are read up to the next page boundary greater than or equal to	199	and bytes are read up to the next page boundary greater than or equal to
179	(off-set+length). aio_readahead() does not read beyond the end of the	200	(off-set+length). C<aio_readahead> does not read beyond the end of the
180	file. The current file offset of the file is left unchanged.	201	file. The current file offset of the file is left unchanged.
		202
		203	If that syscall doesn't exist (likely if your OS isn't Linux) it will be
		204	emulated by simply reading the data, which would have a similar effect.
181		205
182	=item aio_stat $fh_or_path, $callback	206	=item aio_stat $fh_or_path, $callback
183		207
184	=item aio_lstat $fh, $callback	208	=item aio_lstat $fh, $callback
185		209
…		…
204	=item aio_unlink $pathname, $callback	228	=item aio_unlink $pathname, $callback
205		229
206	Asynchronously unlink (delete) a file and call the callback with the	230	Asynchronously unlink (delete) a file and call the callback with the
207	result code.	231	result code.
208		232
		233	=item aio_rmdir $pathname, $callback
		234
		235	Asynchronously rmdir (delete) a directory and call the callback with the
		236	result code.
		237
		238	=item aio_readdir $pathname $callback
		239
		240	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
		241	directory (i.e. opendir + readdir + closedir). The entries will not be
		242	sorted, and will B<NOT> include the C<.> and C<..> entries.
		243
		244	The callback a single argument which is either C<undef> or an array-ref
		245	with the filenames.
		246
209	=item aio_fsync $fh, $callback	247	=item aio_fsync $fh, $callback
210		248
211	Asynchronously call fsync on the given filehandle and call the callback	249	Asynchronously call fsync on the given filehandle and call the callback
212	with the fsync result code.	250	with the fsync result code.
213		251
214	=item aio_fdatasync $fh, $callback	252	=item aio_fdatasync $fh, $callback
215		253
216	Asynchronously call fdatasync on the given filehandle and call the	254	Asynchronously call fdatasync on the given filehandle and call the
217	callback with the fdatasync result code.	255	callback with the fdatasync result code.
218		256
		257	If this call isn't available because your OS lacks it or it couldn't be
		258	detected, it will be emulated by calling C<fsync> instead.
		259
		260	=back
		261
		262	=head2 SUPPORT FUNCTIONS
		263
		264	=over 4
		265
		266	=item $fileno = IO::AIO::poll_fileno
		267
		268	Return the I<request result pipe file descriptor>. This filehandle must be
		269	polled for reading by some mechanism outside this module (e.g. Event or
		270	select, see below or the SYNOPSIS). If the pipe becomes readable you have
		271	to call C<poll_cb> to check the results.
		272
		273	See C<poll_cb> for an example.
		274
		275	=item IO::AIO::poll_cb
		276
		277	Process all outstanding events on the result pipe. You have to call this
		278	regularly. Returns the number of events processed. Returns immediately
		279	when no events are outstanding.
		280
		281	Example: Install an Event watcher that automatically calls
		282	IO::AIO::poll_cb with high priority:
		283
		284	Event->io (fd => IO::AIO::poll_fileno,
		285	poll => 'r', async => 1,
		286	cb => \&IO::AIO::poll_cb);
		287
		288	=item IO::AIO::poll_wait
		289
		290	Wait till the result filehandle becomes ready for reading (simply does a
		291	C<select> on the filehandle. This is useful if you want to synchronously wait
		292	for some requests to finish).
		293
		294	See C<nreqs> for an example.
		295
		296	=item IO::AIO::nreqs
		297
		298	Returns the number of requests currently outstanding (i.e. for which their
		299	callback has not been invoked yet).
		300
		301	Example: wait till there are no outstanding requests anymore:
		302
		303	IO::AIO::poll_wait, IO::AIO::poll_cb
		304	while IO::AIO::nreqs;
		305
		306	=item IO::AIO::flush
		307
		308	Wait till all outstanding AIO requests have been handled.
		309
		310	Strictly equivalent to:
		311
		312	IO::AIO::poll_wait, IO::AIO::poll_cb
		313	while IO::AIO::nreqs;
		314
		315	=item IO::AIO::poll
		316
		317	Waits until some requests have been handled.
		318
		319	Strictly equivalent to:
		320
		321	IO::AIO::poll_wait, IO::AIO::poll_cb
		322	if IO::AIO::nreqs;
		323
		324	=item IO::AIO::min_parallel $nthreads
		325
		326	Set the minimum number of AIO threads to C<$nthreads>. The current default
		327	is C<4>, which means four asynchronous operations can be done at one time
		328	(the number of outstanding operations, however, is unlimited).
		329
		330	IO::AIO starts threads only on demand, when an AIO request is queued and
		331	no free thread exists.
		332
		333	It is recommended to keep the number of threads low, as some Linux
		334	kernel versions will scale negatively with the number of threads (higher
		335	parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32
		336	threads should be fine.
		337
		338	Under most circumstances you don't need to call this function, as the
		339	module selects a default that is suitable for low to moderate load.
		340
		341	=item IO::AIO::max_parallel $nthreads
		342
		343	Sets the maximum number of AIO threads to C<$nthreads>. If more than the
		344	specified number of threads are currently running, this function kills
		345	them. This function blocks until the limit is reached.
		346
		347	While C<$nthreads> are zero, aio requests get queued but not executed
		348	until the number of threads has been increased again.
		349
		350	This module automatically runs C<max_parallel 0> at program end, to ensure
		351	that all threads are killed and that there are no outstanding requests.
		352
		353	Under normal circumstances you don't need to call this function.
		354
		355	=item $oldnreqs = IO::AIO::max_outstanding $nreqs
		356
		357	Sets the maximum number of outstanding requests to C<$nreqs>. If you
		358	try to queue up more than this number of requests, the caller will block until
		359	some requests have been handled.
		360
		361	The default is very large, so normally there is no practical limit. If you
		362	queue up many requests in a loop it often improves speed if you set
		363	this to a relatively low number, such as C<100>.
		364
		365	Under normal circumstances you don't need to call this function.
		366
		367	=back
		368
219	=cut	369	=cut
		370
		371	# support function to convert a fd into a perl filehandle
		372	sub _fd2fh {
		373	return undef if $_[0] < 0;
		374
		375	# try to generate nice filehandles
		376	my $sym = "IO::AIO::fd#$_[0]";
		377	local *$sym;
		378
		379	open *$sym, "+<&=$_[0]" # usually works under any unix
		380	or open *$sym, "<&=$_[0]" # cygwin needs this
		381	or open *$sym, ">&=$_[0]" # or this
		382	or return undef;
		383
		384	*$sym
		385	}
220		386
221	min_parallel 4;	387	min_parallel 4;
222		388
223	END {	389	END {
224	max_parallel 0;	390	max_parallel 0;
225	}	391	}
226		392
227	1;	393	1;
228		394
229	=back	395	=head2 FORK BEHAVIOUR
230		396
231	=head1 BUGS	397	Before the fork, IO::AIO enters a quiescent state where no requests
232		398	can be added in other threads and no results will be processed. After
233	- aio_open gives a fd, but all other functions expect a perl filehandle.	399	the fork the parent simply leaves the quiescent state and continues
		400	request/result processing, while the child clears the request/result
		401	queue (so the requests started before the fork will only be handled in
		402	the parent). Threats will be started on demand until the limit ste in the
		403	parent process has been reached again.
234		404
235	=head1 SEE ALSO	405	=head1 SEE ALSO
236		406
237	L<Coro>, L<Linux::AIO>.	407	L<Coro>, L<Linux::AIO>.
238		408

Diff Legend

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

Comparing IO-AIO/AIO.pm (file contents): Revision 1.1 by root, Sun Jul 10 17:07:44 2005 UTC vs. Revision 1.39 by root, Sun Aug 28 11:05:50 2005 UTC

Diff Legend

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.1 by root, Sun Jul 10 17:07:44 2005 UTC vs.
Revision 1.39 by root, Sun Aug 28 11:05:50 2005 UTC