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

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.21 by root, Wed Jul 13 00:13:09 2005 UTC vs.
Revision 1.48 by root, Thu Feb 16 16:38:57 2006 UTC

…		…
15		15
16	aio_read $fh, 30000, 1024, $buffer, 0, sub {	16	aio_read $fh, 30000, 1024, $buffer, 0, sub {
17	$_[0] > 0 or die "read error: $!";	17	$_[0] > 0 or die "read error: $!";
18	};	18	};
19		19
		20	# AnyEvent
		21	open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!";
		22	my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb });
		23
20	# Event	24	# Event
21	Event->io (fd => IO::AIO::poll_fileno,	25	Event->io (fd => IO::AIO::poll_fileno,
22	poll => 'r',	26	poll => 'r',
23	cb => \&IO::AIO::poll_cb);	27	cb => \&IO::AIO::poll_cb);
24		28
25	# Glib/Gtk2	29	# Glib/Gtk2
26	add_watch Glib::IO IO::AIO::poll_fileno,	30	add_watch Glib::IO IO::AIO::poll_fileno,
27	in => sub { IO::AIO::poll_cb, 1 };	31	in => sub { IO::AIO::poll_cb; 1 };
28		32
29	# Tk	33	# Tk
30	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",	34	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
31	readable => \&IO::AIO::poll_cb);	35	readable => \&IO::AIO::poll_cb);
32		36
…		…
48	not well-supported (Linux doesn't allow them on normal files currently,	52	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	53	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.	54	remaining functionality would have to be implemented using threads anyway.
51		55
52	Although the module will work with in the presence of other threads, it is	56	Although the module will work with in the presence of other threads, it is
53	currently not reentrant, so use appropriate locking yourself.	57	currently not reentrant, so use appropriate locking yourself, always call
		58	C<poll_cb> from within the same thread, or never call C<poll_cb> (or other
		59	C<aio_> functions) recursively.
54		60
55	=cut	61	=cut
56		62
57	package IO::AIO;	63	package IO::AIO;
58		64
		65	no warnings;
		66
59	use base 'Exporter';	67	use base 'Exporter';
60		68
61	use Fcntl ();	69	use Fcntl ();
62		70
63	BEGIN {	71	BEGIN {
64	$VERSION = 0.9;	72	$VERSION = '1.72';
65		73
66	@EXPORT = qw(aio_read aio_write aio_open aio_close aio_stat aio_lstat aio_unlink	74	@EXPORT = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat
		75	aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink
67	aio_fsync aio_fdatasync aio_readahead);	76	aio_fsync aio_fdatasync aio_readahead);
68	@EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs);	77	@EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel
		78	max_outstanding nreqs);
69		79
70	require XSLoader;	80	require XSLoader;
71	XSLoader::load IO::AIO, $VERSION;	81	XSLoader::load IO::AIO, $VERSION;
72	}	82	}
73		83
…		…
81	which must be a code reference. This code reference will get called with	91	which must be a code reference. This code reference will get called with
82	the syscall return code (e.g. most syscalls return C<-1> on error, unlike	92	the syscall return code (e.g. most syscalls return C<-1> on error, unlike
83	perl, which usually delivers "false") as it's sole argument when the given	93	perl, which usually delivers "false") as it's sole argument when the given
84	syscall has been executed asynchronously.	94	syscall has been executed asynchronously.
85		95
86	All functions that expect a filehandle will also accept a file descriptor.	96	All functions expecting a filehandle keep a copy of the filehandle
		97	internally until the request has finished.
87		98
88	The filenames you pass to these routines I<must> be absolute. The reason	99	The pathnames you pass to these routines I<must> be absolute and
89	for this is that at the time the request is being executed, the current	100	encoded in byte form. The reason for the former is that at the time the
90	working directory could have changed. Alternatively, you can make sure	101	request is being executed, the current working directory could have
91	that you never change the current working directory.	102	changed. Alternatively, you can make sure that you never change the
		103	current working directory.
		104
		105	To encode pathnames to byte form, either make sure you either: a)
		106	always pass in filenames you got from outside (command line, readdir
		107	etc.), b) are ASCII or ISO 8859-1, c) use the Encode module and encode
		108	your pathnames to the locale (or other) encoding in effect in the user
		109	environment, d) use Glib::filename_from_unicode on unicode filenames or e)
		110	use something else.
92		111
93	=over 4	112	=over 4
94		113
95	=item aio_open $pathname, $flags, $mode, $callback	114	=item aio_open $pathname, $flags, $mode, $callback->($fh)
96		115
97	Asynchronously open or create a file and call the callback with a newly	116	Asynchronously open or create a file and call the callback with a newly
98	created filehandle for the file.	117	created filehandle for the file.
99		118
100	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,	119	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,
…		…
117	} else {	136	} else {
118	die "open failed: $!\n";	137	die "open failed: $!\n";
119	}	138	}
120	};	139	};
121		140
122	=item aio_close $fh, $callback	141	=item aio_close $fh, $callback->($status)
123		142
124	Asynchronously close a file and call the callback with the result	143	Asynchronously close a file and call the callback with the result
125	code. I<WARNING:> although accepted, you should not pass in a perl	144	code. I<WARNING:> although accepted, you should not pass in a perl
126	filehandle here, as perl will likely close the file descriptor another	145	filehandle here, as perl will likely close the file descriptor another
127	time when the filehandle is destroyed. Normally, you can safely call perls	146	time when the filehandle is destroyed. Normally, you can safely call perls
128	C<close> or just let filehandles go out of scope.	147	C<close> or just let filehandles go out of scope.
129		148
130	This is supposed to be a bug in the API, so that might change. It's	149	This is supposed to be a bug in the API, so that might change. It's
131	therefore best to avoid this function.	150	therefore best to avoid this function.
132		151
133	=item aio_read $fh,$offset,$length, $data,$dataoffset,$callback	152	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
134		153
135	=item aio_write $fh,$offset,$length, $data,$dataoffset,$callback	154	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
136		155
137	Reads or writes C<length> bytes from the specified C<fh> and C<offset>	156	Reads or writes C<length> bytes from the specified C<fh> and C<offset>
138	into the scalar given by C<data> and offset C<dataoffset> and calls the	157	into the scalar given by C<data> and offset C<dataoffset> and calls the
139	callback without the actual number of bytes read (or -1 on error, just	158	callback without the actual number of bytes read (or -1 on error, just
140	like the syscall).	159	like the syscall).
141		160
		161	The C<$data> scalar I<MUST NOT> be modified in any way while the request
		162	is outstanding. Modifying it can result in segfaults or WW3 (if the
		163	necessary/optional hardware is installed).
		164
142	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at	165	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at
143	offset C<0> within the scalar:	166	offset C<0> within the scalar:
144		167
145	aio_read $fh, 7, 15, $buffer, 0, sub {	168	aio_read $fh, 7, 15, $buffer, 0, sub {
146	$_[0] > 0 or die "read error: $!";	169	$_[0] > 0 or die "read error: $!";
147	print "read $_[0] bytes: <$buffer>\n";	170	print "read $_[0] bytes: <$buffer>\n";
148	};	171	};
149		172
		173	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
		174
		175	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
		176	reading at byte offset C<$in_offset>, and starts writing at the current
		177	file offset of C<$out_fh>. Because of that, it is not safe to issue more
		178	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each
		179	other.
		180
		181	This call tries to make use of a native C<sendfile> syscall to provide
		182	zero-copy operation. For this to work, C<$out_fh> should refer to a
		183	socket, and C<$in_fh> should refer to mmap'able file.
		184
		185	If the native sendfile call fails or is not implemented, it will be
		186	emulated, so you can call C<aio_sendfile> on any type of filehandle
		187	regardless of the limitations of the operating system.
		188
		189	Please note, however, that C<aio_sendfile> can read more bytes from
		190	C<$in_fh> than are written, and there is no way to find out how many
		191	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only
		192	provides the number of bytes written to C<$out_fh>. Only if the result
		193	value equals C<$length> one can assume that C<$length> bytes have been
		194	read.
		195
150	=item aio_readahead $fh,$offset,$length, $callback	196	=item aio_readahead $fh,$offset,$length, $callback->($retval)
151
152	Asynchronously reads the specified byte range into the page cache, using
153	the C<readahead> syscall. If that syscall doesn't exist (likely if your OS
154	isn't Linux) the status will be C<-1> and C<$!> is set to C<ENOSYS>.
155		197
156	C<aio_readahead> populates the page cache with data from a file so that	198	C<aio_readahead> populates the page cache with data from a file so that
157	subsequent reads from that file will not block on disk I/O. The C<$offset>	199	subsequent reads from that file will not block on disk I/O. The C<$offset>
158	argument specifies the starting point from which data is to be read and	200	argument specifies the starting point from which data is to be read and
159	C<$length> specifies the number of bytes to be read. I/O is performed in	201	C<$length> specifies the number of bytes to be read. I/O is performed in
160	whole pages, so that offset is effectively rounded down to a page boundary	202	whole pages, so that offset is effectively rounded down to a page boundary
161	and bytes are read up to the next page boundary greater than or equal to	203	and bytes are read up to the next page boundary greater than or equal to
162	(off-set+length). C<aio_readahead> does not read beyond the end of the	204	(off-set+length). C<aio_readahead> does not read beyond the end of the
163	file. The current file offset of the file is left unchanged.	205	file. The current file offset of the file is left unchanged.
164		206
		207	If that syscall doesn't exist (likely if your OS isn't Linux) it will be
		208	emulated by simply reading the data, which would have a similar effect.
		209
165	=item aio_stat $fh_or_path, $callback	210	=item aio_stat $fh_or_path, $callback->($status)
166		211
167	=item aio_lstat $fh, $callback	212	=item aio_lstat $fh, $callback->($status)
168		213
169	Works like perl's C<stat> or C<lstat> in void context. The callback will	214	Works like perl's C<stat> or C<lstat> in void context. The callback will
170	be called after the stat and the results will be available using C<stat _>	215	be called after the stat and the results will be available using C<stat _>
171	or C<-s _> etc...	216	or C<-s _> etc...
172		217
…		…
182	aio_stat "/etc/passwd", sub {	227	aio_stat "/etc/passwd", sub {
183	$_[0] and die "stat failed: $!";	228	$_[0] and die "stat failed: $!";
184	print "size is ", -s _, "\n";	229	print "size is ", -s _, "\n";
185	};	230	};
186		231
187	=item aio_unlink $pathname, $callback	232	=item aio_unlink $pathname, $callback->($status)
188		233
189	Asynchronously unlink (delete) a file and call the callback with the	234	Asynchronously unlink (delete) a file and call the callback with the
190	result code.	235	result code.
191		236
		237	=item aio_rmdir $pathname, $callback->($status)
		238
		239	Asynchronously rmdir (delete) a directory and call the callback with the
		240	result code.
		241
		242	=item aio_readdir $pathname, $callback->($entries)
		243
		244	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
		245	directory (i.e. opendir + readdir + closedir). The entries will not be
		246	sorted, and will B<NOT> include the C<.> and C<..> entries.
		247
		248	The callback a single argument which is either C<undef> or an array-ref
		249	with the filenames.
		250
		251	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
		252
		253	Scans a directory (similar to C<aio_readdir>) and tries to separate the
		254	entries of directory C<$path> into two sets of names, ones you can recurse
		255	into (directories), and ones you cannot recurse into (everything else).
		256
		257	C<aio_scandir> is a composite request that consists of many
		258	aio-primitives. C<$maxreq> specifies the maximum number of outstanding
		259	aio requests that this function generates. If it is C<< <= 0 >>, then a
		260	suitable default will be chosen (currently 8).
		261
		262	On error, the callback is called without arguments, otherwise it receives
		263	two array-refs with path-relative entry names.
		264
		265	Example:
		266
		267	aio_scandir $dir, 0, sub {
		268	my ($dirs, $nondirs) = @_;
		269	print "real directories: @$dirs\n";
		270	print "everything else: @$nondirs\n";
		271	};
		272
		273	Implementation notes.
		274
		275	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.
		276
		277	After reading the directory, the modification time, size etc. of the
		278	directory before and after the readdir is checked, and if they match, the
		279	link count will be used to decide how many entries are directories (if
		280	>= 2). Otherwise, no knowledge of the number of subdirectories will be
		281	assumed.
		282
		283	Then entires will be sorted into likely directories (everything without a
		284	non-initial dot) and likely non-directories (everything else). Then every
		285	entry + C</.> will be C<stat>'ed, likely directories first. This is often
		286	faster because filesystems might detect the type of the entry without
		287	reading the inode data (e.g. ext2fs filetype feature). If that succeeds,
		288	it assumes that the entry is a directory or a symlink to directory (which
		289	will be checked seperately).
		290
		291	If the known number of directories has been reached, the rest of the
		292	entries is assumed to be non-directories.
		293
		294	=cut
		295
		296	sub aio_scandir($$$) {
		297	my ($path, $maxreq, $cb) = @_;
		298
		299	$maxreq = 8 if $maxreq <= 0;
		300
		301	# stat once
		302	aio_stat $path, sub {
		303	return $cb->() if $_[0];
		304	my $hash1 = join ":", (stat _)[0,1,3,7,9];
		305
		306	# read the directory entries
		307	aio_readdir $path, sub {
		308	my $entries = shift
		309	or return $cb->();
		310
		311	# stat the dir another time
		312	aio_stat $path, sub {
		313	my $hash2 = join ":", (stat _)[0,1,3,7,9];
		314
		315	my $ndirs;
		316
		317	# take the slow route if anything looks fishy
		318	if ($hash1 ne $hash2) {
		319	$ndirs = -1;
		320	} else {
		321	# if nlink == 2, we are finished
		322	# on non-posix-fs's, we rely on nlink < 2
		323	$ndirs = (stat _)[3] - 2
		324	or return $cb->([], $entries);
		325	}
		326
		327	# sort into likely dirs and likely nondirs
		328	# dirs == files without ".", short entries first
		329	$entries = [map $_->[0],
		330	sort { $b->[1] cmp $a->[1] }
		331	map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],
		332	@$entries];
		333
		334	my (@dirs, @nondirs);
		335
		336	my ($statcb, $schedcb);
		337	my $nreq = 0;
		338
		339	$schedcb = sub {
		340	if (@$entries) {
		341	if ($nreq < $maxreq) {
		342	my $ent = pop @$entries;
		343	$nreq++;
		344	aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) };
		345	}
		346	} elsif (!$nreq) {
		347	# finished
		348	undef $statcb;
		349	undef $schedcb;
		350	$cb->(\@dirs, \@nondirs) if $cb;
		351	undef $cb;
		352	}
		353	};
		354	$statcb = sub {
		355	my ($status, $entry) = @_;
		356
		357	if ($status < 0) {
		358	$nreq--;
		359	push @nondirs, $entry;
		360	&$schedcb;
		361	} else {
		362	# need to check for real directory
		363	aio_lstat "$path/$entry", sub {
		364	$nreq--;
		365
		366	if (-d _) {
		367	push @dirs, $entry;
		368
		369	if (!--$ndirs) {
		370	push @nondirs, @$entries;
		371	$entries = [];
		372	}
		373	} else {
		374	push @nondirs, $entry;
		375	}
		376
		377	&$schedcb;
		378	}
		379	}
		380	};
		381
		382	&$schedcb while @$entries && $nreq < $maxreq;
		383	};
		384	};
		385	};
		386	}
		387
192	=item aio_fsync $fh, $callback	388	=item aio_fsync $fh, $callback->($status)
193		389
194	Asynchronously call fsync on the given filehandle and call the callback	390	Asynchronously call fsync on the given filehandle and call the callback
195	with the fsync result code.	391	with the fsync result code.
196		392
197	=item aio_fdatasync $fh, $callback	393	=item aio_fdatasync $fh, $callback->($status)
198		394
199	Asynchronously call fdatasync on the given filehandle and call the	395	Asynchronously call fdatasync on the given filehandle and call the
200	callback with the fdatasync result code. Might set C<$!> to C<ENOSYS> if	396	callback with the fdatasync result code.
201	C<fdatasync> is not available.	397
		398	If this call isn't available because your OS lacks it or it couldn't be
		399	detected, it will be emulated by calling C<fsync> instead.
202		400
203	=back	401	=back
204		402
205	=head2 SUPPORT FUNCTIONS	403	=head2 SUPPORT FUNCTIONS
206		404
…		…
264	IO::AIO::poll_wait, IO::AIO::poll_cb	462	IO::AIO::poll_wait, IO::AIO::poll_cb
265	if IO::AIO::nreqs;	463	if IO::AIO::nreqs;
266		464
267	=item IO::AIO::min_parallel $nthreads	465	=item IO::AIO::min_parallel $nthreads
268		466
269	Set the minimum number of AIO threads to C<$nthreads>. The default is	467	Set the minimum number of AIO threads to C<$nthreads>. The current default
270	C<1>, which means a single asynchronous operation can be done at one time	468	is C<4>, which means four asynchronous operations can be done at one time
271	(the number of outstanding operations, however, is unlimited).	469	(the number of outstanding operations, however, is unlimited).
		470
		471	IO::AIO starts threads only on demand, when an AIO request is queued and
		472	no free thread exists.
272		473
273	It is recommended to keep the number of threads low, as some Linux	474	It is recommended to keep the number of threads low, as some Linux
274	kernel versions will scale negatively with the number of threads (higher	475	kernel versions will scale negatively with the number of threads (higher
275	parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32	476	parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32
276	threads should be fine.	477	threads should be fine.
277		478
278	Under normal circumstances you don't need to call this function, as this	479	Under most circumstances you don't need to call this function, as the
279	module automatically starts some threads (the exact number might change,	480	module selects a default that is suitable for low to moderate load.
280	and is currently 4).
281		481
282	=item IO::AIO::max_parallel $nthreads	482	=item IO::AIO::max_parallel $nthreads
283		483
284	Sets the maximum number of AIO threads to C<$nthreads>. If more than	484	Sets the maximum number of AIO threads to C<$nthreads>. If more than the
285	the specified number of threads are currently running, kill them. This	485	specified number of threads are currently running, this function kills
286	function blocks until the limit is reached.	486	them. This function blocks until the limit is reached.
		487
		488	While C<$nthreads> are zero, aio requests get queued but not executed
		489	until the number of threads has been increased again.
287		490
288	This module automatically runs C<max_parallel 0> at program end, to ensure	491	This module automatically runs C<max_parallel 0> at program end, to ensure
289	that all threads are killed and that there are no outstanding requests.	492	that all threads are killed and that there are no outstanding requests.
290		493
291	Under normal circumstances you don't need to call this function.	494	Under normal circumstances you don't need to call this function.
…		…
295	Sets the maximum number of outstanding requests to C<$nreqs>. If you	498	Sets the maximum number of outstanding requests to C<$nreqs>. If you
296	try to queue up more than this number of requests, the caller will block until	499	try to queue up more than this number of requests, the caller will block until
297	some requests have been handled.	500	some requests have been handled.
298		501
299	The default is very large, so normally there is no practical limit. If you	502	The default is very large, so normally there is no practical limit. If you
300	queue up many requests in a loop it it often improves speed if you set	503	queue up many requests in a loop it often improves speed if you set
301	this to a relatively low number, such as C<100>.	504	this to a relatively low number, such as C<100>.
302		505
303	Under normal circumstances you don't need to call this function.	506	Under normal circumstances you don't need to call this function.
304		507
305	=back	508	=back
…		…
308		511
309	# support function to convert a fd into a perl filehandle	512	# support function to convert a fd into a perl filehandle
310	sub _fd2fh {	513	sub _fd2fh {
311	return undef if $_[0] < 0;	514	return undef if $_[0] < 0;
312		515
313	# try to be perl5.6-compatible	516	# try to generate nice filehandles
314	local *AIO_FH;	517	my $sym = "IO::AIO::fd#$_[0]";
315	open AIO_FH, "+<&=$_[0]"	518	local *$sym;
		519
		520	open *$sym, "+<&=$_[0]" # usually works under any unix
		521	or open *$sym, "<&=$_[0]" # cygwin needs this
		522	or open *$sym, ">&=$_[0]" # or this
316	or return undef;	523	or return undef;
317		524
318	*AIO_FH	525	*$sym
319	}	526	}
320		527
321	min_parallel 4;	528	min_parallel 4;
322		529
323	END {	530	END {
324	max_parallel 0;	531	max_parallel 0;
325	}	532	}
326		533
327	1;	534	1;
328		535
		536	=head2 FORK BEHAVIOUR
		537
		538	Before the fork, IO::AIO enters a quiescent state where no requests
		539	can be added in other threads and no results will be processed. After
		540	the fork the parent simply leaves the quiescent state and continues
		541	request/result processing, while the child clears the request/result
		542	queue (so the requests started before the fork will only be handled in
		543	the parent). Threats will be started on demand until the limit ste in the
		544	parent process has been reached again.
		545
329	=head1 SEE ALSO	546	=head1 SEE ALSO
330		547
331	L<Coro>, L<Linux::AIO>.	548	L<Coro>, L<Linux::AIO>.
332		549
333	=head1 AUTHOR	550	=head1 AUTHOR

Diff Legend

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

Comparing IO-AIO/AIO.pm (file contents): Revision 1.21 by root, Wed Jul 13 00:13:09 2005 UTC vs. Revision 1.48 by root, Thu Feb 16 16:38:57 2006 UTC

Diff Legend

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.21 by root, Wed Jul 13 00:13:09 2005 UTC vs.
Revision 1.48 by root, Thu Feb 16 16:38:57 2006 UTC