[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 1.36 by root, Tue Aug 23 00:03:14 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_read aio_write aio_open aio_close aio_stat aio_lstat aio_unlink
52	aio_fsync aio_fdatasync aio_readahead);	71	aio_rmdir aio_symlink aio_fsync aio_fdatasync aio_readahead);
53	@EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel nreqs);	72	@EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs);
54		73
55	require XSLoader;	74	require XSLoader;
56	XSLoader::load IO::AIO, $VERSION;	75	XSLoader::load IO::AIO, $VERSION;
57	}	76	}
58		77
59	=item IO::AIO::min_parallel $nthreads	78	=head1 FUNCTIONS
60		79
61	Set the minimum number of AIO threads to C<$nthreads>. The default is	80	=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		81
65	It is recommended to keep the number of threads low, as some linux	82	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	83	with the same name (sans C<aio_>). The arguments are similar or identical,
67	parallelity => MUCH higher latency).	84	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
		86	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
		88	syscall has been executed asynchronously.
68		89
69	Under normal circumstances you don't need to call this function, as this	90	All functions expecting a filehandle keep a copy of the filehandle
70	module automatically starts a single async thread.	91	internally until the request has finished.
71		92
72	=item IO::AIO::max_parallel $nthreads	93	The pathnames you pass to these routines I<must> be absolute and
		94	encoded in byte form. The reason for the former is that at the time the
		95	request is being executed, the current working directory could have
		96	changed. Alternatively, you can make sure that you never change the
		97	current working directory.
73		98
74	Sets the maximum number of AIO threads to C<$nthreads>. If more than	99	To encode pathnames to byte form, either make sure you either: a)
75	the specified number of threads are currently running, kill them. This	100	always pass in filenames you got from outside (command line, readdir
76	function blocks until the limit is reached.	101	etc.), b) are ASCII or ISO 8859-1, c) use the Encode module and encode
		102	your pathnames to the locale (or other) encoding in effect in the user
		103	environment, d) use Glib::filename_from_unicode on unicode filenames or e)
		104	use something else.
77		105
78	This module automatically runs C<max_parallel 0> at program end, to ensure	106	=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		107
121	=item aio_open $pathname, $flags, $mode, $callback	108	=item aio_open $pathname, $flags, $mode, $callback
122		109
123	Asynchronously open or create a file and call the callback with the	110	Asynchronously open or create a file and call the callback with a newly
124	filedescriptor (NOT a perl filehandle, sorry for that, but watch out, this	111	created filehandle for the file.
125	might change in the future).
126		112
127	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,	113	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,
128	for an explanation.	114	for an explanation.
129		115
130	The C<$mode> argument is a bitmask. See the C<Fcntl> module for a	116	The C<$flags> argument is a bitmask. See the C<Fcntl> module for a
131	list. They are the same as used in C<sysopen>.	117	list. They are the same as used by C<sysopen>.
		118
		119	Likewise, C<$mode> specifies the mode of the newly created file, if it
		120	didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,
		121	except that it is mandatory (i.e. use C<0> if you don't create new files,
		122	and C<0666> or C<0777> if you do).
132		123
133	Example:	124	Example:
134		125
135	aio_open "/etc/passwd", O_RDONLY, 0, sub {	126	aio_open "/etc/passwd", O_RDONLY, 0, sub {
136	if ($_[0] >= 0) {	127	if ($_[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";	128	print "open successful, fh is $_[0]\n";
140	...	129	...
141	} else {	130	} else {
142	die "open failed: $!\n";	131	die "open failed: $!\n";
143	}	132	}
144	};	133	};
145		134
146	=item aio_close $fh, $callback	135	=item aio_close $fh, $callback
147		136
148	Asynchronously close a file and call the callback with the result code.	137	Asynchronously close a file and call the callback with the result
		138	code. I<WARNING:> although accepted, you should not pass in a perl
		139	filehandle here, as perl will likely close the file descriptor another
		140	time when the filehandle is destroyed. Normally, you can safely call perls
		141	C<close> or just let filehandles go out of scope.
		142
		143	This is supposed to be a bug in the API, so that might change. It's
		144	therefore best to avoid this function.
149		145
150	=item aio_read $fh,$offset,$length, $data,$dataoffset,$callback	146	=item aio_read $fh,$offset,$length, $data,$dataoffset,$callback
151		147
152	=item aio_write $fh,$offset,$length, $data,$dataoffset,$callback	148	=item aio_write $fh,$offset,$length, $data,$dataoffset,$callback
153		149
154	Reads or writes C<length> bytes from the specified C<fh> and C<offset>	150	Reads or writes C<length> bytes from the specified C<fh> and C<offset>
155	into the scalar given by C<data> and offset C<dataoffset> and calls the	151	into the scalar given by C<data> and offset C<dataoffset> and calls the
156	callback without the actual number of bytes read (or -1 on error, just	152	callback without the actual number of bytes read (or -1 on error, just
157	like the syscall).	153	like the syscall).
158		154
		155	The C<$data> scalar I<MUST NOT> be modified in any way while the request
		156	is outstanding. Modifying it can result in segfaults or WW3 (if the
		157	necessary/optional hardware is installed).
		158
159	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, strating at	159	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at
160	offset C<0> within the scalar:	160	offset C<0> within the scalar:
161		161
162	aio_read $fh, 7, 15, $buffer, 0, sub {	162	aio_read $fh, 7, 15, $buffer, 0, sub {
163	$_[0] >= 0 or die "read error: $!";	163	$_[0] > 0 or die "read error: $!";
164	print "read <$buffer>\n";	164	print "read $_[0] bytes: <$buffer>\n";
165	};	165	};
166		166
		167	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback
		168
		169	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
		170	reading at byte offset C<$in_offset>, and starts writing at the current
		171	file offset of C<$out_fh>. Because of that, it is not safe to issue more
		172	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each
		173	other.
		174
		175	This call tries to make use of a native C<sendfile> syscall to provide
		176	zero-copy operation. For this to work, C<$out_fh> should refer to a
		177	socket, and C<$in_fh> should refer to mmap'able file.
		178
		179	If the native sendfile call fails or is not implemented, it will be
		180	emulated, so you can call C<aio_sendfile> on any type of filehandle
		181	regardless of the limitations of the operating system.
		182
		183	Please note, however, that C<aio_sendfile> can read more bytes from
		184	C<$in_fh> than are written, and there is no way to find out how many
		185	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only
		186	provides the number of bytes written to C<$out_fh>. Only if the result
		187	value equals C<$length> one can assume that C<$length> bytes have been
		188	read.
		189
167	=item aio_readahead $fh,$offset,$length, $callback	190	=item aio_readahead $fh,$offset,$length, $callback
168		191
169	Asynchronously reads the specified byte range into the page cache, using
170	the C<readahead> syscall. If that syscall doesn't exist the status will be
171	C<-1> and C<$!> is set to ENOSYS.
172
173	readahead() populates the page cache with data from a file so that	192	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<$offset>	193	subsequent reads from that file will not block on disk I/O. The C<$offset>
175	argument specifies the starting point from which data is to be read and	194	argument specifies the starting point from which data is to be read and
176	C<$length> specifies the number of bytes to be read. I/O is performed in	195	C<$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	196	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	197	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	198	(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.	199	file. The current file offset of the file is left unchanged.
		200
		201	If that syscall doesn't exist (likely if your OS isn't Linux) it will be
		202	emulated by simply reading the data, which would have a similar effect.
181		203
182	=item aio_stat $fh_or_path, $callback	204	=item aio_stat $fh_or_path, $callback
183		205
184	=item aio_lstat $fh, $callback	206	=item aio_lstat $fh, $callback
185		207
…		…
204	=item aio_unlink $pathname, $callback	226	=item aio_unlink $pathname, $callback
205		227
206	Asynchronously unlink (delete) a file and call the callback with the	228	Asynchronously unlink (delete) a file and call the callback with the
207	result code.	229	result code.
208		230
		231	=item aio_rmdir $pathname, $callback
		232
		233	Asynchronously rmdir (delete) a directory and call the callback with the
		234	result code.
		235
209	=item aio_fsync $fh, $callback	236	=item aio_fsync $fh, $callback
210		237
211	Asynchronously call fsync on the given filehandle and call the callback	238	Asynchronously call fsync on the given filehandle and call the callback
212	with the fsync result code.	239	with the fsync result code.
213		240
214	=item aio_fdatasync $fh, $callback	241	=item aio_fdatasync $fh, $callback
215		242
216	Asynchronously call fdatasync on the given filehandle and call the	243	Asynchronously call fdatasync on the given filehandle and call the
217	callback with the fdatasync result code.	244	callback with the fdatasync result code.
218		245
		246	If this call isn't available because your OS lacks it or it couldn't be
		247	detected, it will be emulated by calling C<fsync> instead.
		248
		249	=back
		250
		251	=head2 SUPPORT FUNCTIONS
		252
		253	=over 4
		254
		255	=item $fileno = IO::AIO::poll_fileno
		256
		257	Return the I<request result pipe file descriptor>. This filehandle must be
		258	polled for reading by some mechanism outside this module (e.g. Event or
		259	select, see below or the SYNOPSIS). If the pipe becomes readable you have
		260	to call C<poll_cb> to check the results.
		261
		262	See C<poll_cb> for an example.
		263
		264	=item IO::AIO::poll_cb
		265
		266	Process all outstanding events on the result pipe. You have to call this
		267	regularly. Returns the number of events processed. Returns immediately
		268	when no events are outstanding.
		269
		270	Example: Install an Event watcher that automatically calls
		271	IO::AIO::poll_cb with high priority:
		272
		273	Event->io (fd => IO::AIO::poll_fileno,
		274	poll => 'r', async => 1,
		275	cb => \&IO::AIO::poll_cb);
		276
		277	=item IO::AIO::poll_wait
		278
		279	Wait till the result filehandle becomes ready for reading (simply does a
		280	C<select> on the filehandle. This is useful if you want to synchronously wait
		281	for some requests to finish).
		282
		283	See C<nreqs> for an example.
		284
		285	=item IO::AIO::nreqs
		286
		287	Returns the number of requests currently outstanding (i.e. for which their
		288	callback has not been invoked yet).
		289
		290	Example: wait till there are no outstanding requests anymore:
		291
		292	IO::AIO::poll_wait, IO::AIO::poll_cb
		293	while IO::AIO::nreqs;
		294
		295	=item IO::AIO::flush
		296
		297	Wait till all outstanding AIO requests have been handled.
		298
		299	Strictly equivalent to:
		300
		301	IO::AIO::poll_wait, IO::AIO::poll_cb
		302	while IO::AIO::nreqs;
		303
		304	=item IO::AIO::poll
		305
		306	Waits until some requests have been handled.
		307
		308	Strictly equivalent to:
		309
		310	IO::AIO::poll_wait, IO::AIO::poll_cb
		311	if IO::AIO::nreqs;
		312
		313	=item IO::AIO::min_parallel $nthreads
		314
		315	Set the minimum number of AIO threads to C<$nthreads>. The current default
		316	is C<4>, which means four asynchronous operations can be done at one time
		317	(the number of outstanding operations, however, is unlimited).
		318
		319	IO::AIO starts threads only on demand, when an AIO request is queued and
		320	no free thread exists.
		321
		322	It is recommended to keep the number of threads low, as some Linux
		323	kernel versions will scale negatively with the number of threads (higher
		324	parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32
		325	threads should be fine.
		326
		327	Under most circumstances you don't need to call this function, as the
		328	module selects a default that is suitable for low to moderate load.
		329
		330	=item IO::AIO::max_parallel $nthreads
		331
		332	Sets the maximum number of AIO threads to C<$nthreads>. If more than the
		333	specified number of threads are currently running, this function kills
		334	them. This function blocks until the limit is reached.
		335
		336	While C<$nthreads> are zero, aio requests get queued but not executed
		337	until the number of threads has been increased again.
		338
		339	This module automatically runs C<max_parallel 0> at program end, to ensure
		340	that all threads are killed and that there are no outstanding requests.
		341
		342	Under normal circumstances you don't need to call this function.
		343
		344	=item $oldnreqs = IO::AIO::max_outstanding $nreqs
		345
		346	Sets the maximum number of outstanding requests to C<$nreqs>. If you
		347	try to queue up more than this number of requests, the caller will block until
		348	some requests have been handled.
		349
		350	The default is very large, so normally there is no practical limit. If you
		351	queue up many requests in a loop it often improves speed if you set
		352	this to a relatively low number, such as C<100>.
		353
		354	Under normal circumstances you don't need to call this function.
		355
		356	=back
		357
219	=cut	358	=cut
		359
		360	# support function to convert a fd into a perl filehandle
		361	sub _fd2fh {
		362	return undef if $_[0] < 0;
		363
		364	# try to generate nice filehandles
		365	my $sym = "IO::AIO::fd#$_[0]";
		366	local *$sym;
		367
		368	open *$sym, "+<&=$_[0]" # usually works under any unix
		369	or open *$sym, "<&=$_[0]" # cygwin needs this
		370	or open *$sym, ">&=$_[0]" # or this
		371	or return undef;
		372
		373	*$sym
		374	}
220		375
221	min_parallel 4;	376	min_parallel 4;
222		377
223	END {	378	END {
224	max_parallel 0;	379	max_parallel 0;
225	}	380	}
226		381
227	1;	382	1;
228		383
229	=back	384	=head2 FORK BEHAVIOUR
230		385
231	=head1 BUGS	386	Before the fork, IO::AIO enters a quiescent state where no requests
232		387	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.	388	the fork the parent simply leaves the quiescent state and continues
		389	request/result processing, while the child clears the request/result
		390	queue (so the requests started before the fork will only be handled in
		391	the parent). Threats will be started on demand until the limit ste in the
		392	parent process has been reached again.
234		393
235	=head1 SEE ALSO	394	=head1 SEE ALSO
236		395
237	L<Coro>, L<Linux::AIO>.	396	L<Coro>, L<Linux::AIO>.
238		397

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 1.36 by root, Tue Aug 23 00:03:14 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 1.36 by root, Tue Aug 23 00:03:14 2005 UTC