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

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.30 by root, Wed Aug 17 04:47:38 2005 UTC vs.
Revision 1.47 by root, Thu Dec 29 15:44:13 2005 UTC

…		…
14	aio_unlink "/tmp/file", sub { };	14	aio_unlink "/tmp/file", sub { };
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
		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 });
19		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);
…		…
63	use base 'Exporter';	67	use base 'Exporter';
64		68
65	use Fcntl ();	69	use Fcntl ();
66		70
67	BEGIN {	71	BEGIN {
68	$VERSION = 1.2;	72	$VERSION = '1.72';
69		73
70	@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
71	aio_rmdir aio_symlink aio_fsync aio_fdatasync aio_readahead);	76	aio_fsync aio_fdatasync aio_readahead);
72	@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);
73		79
74	require XSLoader;	80	require XSLoader;
75	XSLoader::load IO::AIO, $VERSION;	81	XSLoader::load IO::AIO, $VERSION;
76	}	82	}
77		83
…		…
103	environment, d) use Glib::filename_from_unicode on unicode filenames or e)	109	environment, d) use Glib::filename_from_unicode on unicode filenames or e)
104	use something else.	110	use something else.
105		111
106	=over 4	112	=over 4
107		113
108	=item aio_open $pathname, $flags, $mode, $callback	114	=item aio_open $pathname, $flags, $mode, $callback->($fh)
109		115
110	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
111	created filehandle for the file.	117	created filehandle for the file.
112		118
113	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,
…		…
130	} else {	136	} else {
131	die "open failed: $!\n";	137	die "open failed: $!\n";
132	}	138	}
133	};	139	};
134		140
135	=item aio_close $fh, $callback	141	=item aio_close $fh, $callback->($status)
136		142
137	Asynchronously close a file and call the callback with the result	143	Asynchronously close a file and call the callback with the result
138	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
139	filehandle here, as perl will likely close the file descriptor another	145	filehandle here, as perl will likely close the file descriptor another
140	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
141	C<close> or just let filehandles go out of scope.	147	C<close> or just let filehandles go out of scope.
142		148
143	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
144	therefore best to avoid this function.	150	therefore best to avoid this function.
145		151
146	=item aio_read $fh,$offset,$length, $data,$dataoffset,$callback	152	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
147		153
148	=item aio_write $fh,$offset,$length, $data,$dataoffset,$callback	154	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
149		155
150	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>
151	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
152	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
153	like the syscall).	159	like the syscall).
154		160
		161	The C<$data> scalar I<MUST NOT> be modified in any way while the request
		162	is outstanding. Modifying it can result in segfaults or WW3 (if the
		163	necessary/optional hardware is installed).
		164
155	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at	165	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at
156	offset C<0> within the scalar:	166	offset C<0> within the scalar:
157		167
158	aio_read $fh, 7, 15, $buffer, 0, sub {	168	aio_read $fh, 7, 15, $buffer, 0, sub {
159	$_[0] > 0 or die "read error: $!";	169	$_[0] > 0 or die "read error: $!";
160	print "read $_[0] bytes: <$buffer>\n";	170	print "read $_[0] bytes: <$buffer>\n";
161	};	171	};
162		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
163	=item aio_readahead $fh,$offset,$length, $callback	196	=item aio_readahead $fh,$offset,$length, $callback->($retval)
164		197
165	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
166	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>
167	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
168	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
…		…
172	file. The current file offset of the file is left unchanged.	205	file. The current file offset of the file is left unchanged.
173		206
174	If that syscall doesn't exist (likely if your OS isn't Linux) it will be	207	If that syscall doesn't exist (likely if your OS isn't Linux) it will be
175	emulated by simply reading the data, which would have a similar effect.	208	emulated by simply reading the data, which would have a similar effect.
176		209
177	=item aio_stat $fh_or_path, $callback	210	=item aio_stat $fh_or_path, $callback->($status)
178		211
179	=item aio_lstat $fh, $callback	212	=item aio_lstat $fh, $callback->($status)
180		213
181	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
182	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 _>
183	or C<-s _> etc...	216	or C<-s _> etc...
184		217
…		…
194	aio_stat "/etc/passwd", sub {	227	aio_stat "/etc/passwd", sub {
195	$_[0] and die "stat failed: $!";	228	$_[0] and die "stat failed: $!";
196	print "size is ", -s _, "\n";	229	print "size is ", -s _, "\n";
197	};	230	};
198		231
199	=item aio_unlink $pathname, $callback	232	=item aio_unlink $pathname, $callback->($status)
200		233
201	Asynchronously unlink (delete) a file and call the callback with the	234	Asynchronously unlink (delete) a file and call the callback with the
202	result code.	235	result code.
203		236
204	=item aio_rmdir $pathname, $callback	237	=item aio_rmdir $pathname, $callback->($status)
205		238
206	Asynchronously rmdir (delete) a directory and call the callback with the	239	Asynchronously rmdir (delete) a directory and call the callback with the
207	result code.	240	result code.
208		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. ext2s 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
209	=item aio_fsync $fh, $callback	388	=item aio_fsync $fh, $callback->($status)
210		389
211	Asynchronously call fsync on the given filehandle and call the callback	390	Asynchronously call fsync on the given filehandle and call the callback
212	with the fsync result code.	391	with the fsync result code.
213		392
214	=item aio_fdatasync $fh, $callback	393	=item aio_fdatasync $fh, $callback->($status)
215		394
216	Asynchronously call fdatasync on the given filehandle and call the	395	Asynchronously call fdatasync on the given filehandle and call the
217	callback with the fdatasync result code.	396	callback with the fdatasync result code.
218		397
219	If this call isn't available because your OS lacks it or it couldn't be	398	If this call isn't available because your OS lacks it or it couldn't be
…		…
283	IO::AIO::poll_wait, IO::AIO::poll_cb	462	IO::AIO::poll_wait, IO::AIO::poll_cb
284	if IO::AIO::nreqs;	463	if IO::AIO::nreqs;
285		464
286	=item IO::AIO::min_parallel $nthreads	465	=item IO::AIO::min_parallel $nthreads
287		466
288	Set the minimum number of AIO threads to C<$nthreads>. The default is	467	Set the minimum number of AIO threads to C<$nthreads>. The current default
289	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
290	(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.
291		473
292	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
293	kernel versions will scale negatively with the number of threads (higher	475	kernel versions will scale negatively with the number of threads (higher
294	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
295	threads should be fine.	477	threads should be fine.
296		478
297	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
298	module automatically starts some threads (the exact number might change,	480	module selects a default that is suitable for low to moderate load.
299	and is currently 4).
300		481
301	=item IO::AIO::max_parallel $nthreads	482	=item IO::AIO::max_parallel $nthreads
302		483
303	Sets the maximum number of AIO threads to C<$nthreads>. If more than	484	Sets the maximum number of AIO threads to C<$nthreads>. If more than the
304	the specified number of threads are currently running, kill them. This	485	specified number of threads are currently running, this function kills
305	function blocks until the limit is reached.	486	them. This function blocks until the limit is reached.
		487
		488	While C<$nthreads> are zero, aio requests get queued but not executed
		489	until the number of threads has been increased again.
306		490
307	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
308	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.
309		493
310	Under normal circumstances you don't need to call this function.	494	Under normal circumstances you don't need to call this function.
…		…
314	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
315	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
316	some requests have been handled.	500	some requests have been handled.
317		501
318	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
319	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
320	this to a relatively low number, such as C<100>.	504	this to a relatively low number, such as C<100>.
321		505
322	Under normal circumstances you don't need to call this function.	506	Under normal circumstances you don't need to call this function.
323		507
324	=back	508	=back
…		…
349		533
350	1;	534	1;
351		535
352	=head2 FORK BEHAVIOUR	536	=head2 FORK BEHAVIOUR
353		537
354	Before the fork IO::AIO first handles all outstanding requests - if other	538	Before the fork, IO::AIO enters a quiescent state where no requests
355	threads add requests during this period, this time is prolonged. It then	539	can be added in other threads and no results will be processed. After
356	enters a quiescent state where no requests can be added in other threads	540	the fork the parent simply leaves the quiescent state and continues
357	and no results will be processed. After the fork the parent simply leaves	541	request/result processing, while the child clears the request/result
358	the quiescent state and continues request processing, while the child	542	queue (so the requests started before the fork will only be handled in
359	starts the same number of threads as were in use by the parent.	543	the parent). Threats will be started on demand until the limit ste in the
		544	parent process has been reached again.
360		545
361	=head1 SEE ALSO	546	=head1 SEE ALSO
362		547
363	L<Coro>, L<Linux::AIO>.	548	L<Coro>, L<Linux::AIO>.
364		549

Diff Legend

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

Comparing IO-AIO/AIO.pm (file contents): Revision 1.30 by root, Wed Aug 17 04:47:38 2005 UTC vs. Revision 1.47 by root, Thu Dec 29 15:44:13 2005 UTC

Diff Legend

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.30 by root, Wed Aug 17 04:47:38 2005 UTC vs.
Revision 1.47 by root, Thu Dec 29 15:44:13 2005 UTC