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

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.22 by root, Wed Jul 20 21:55:27 2005 UTC vs.
Revision 1.41 by root, Wed Sep 7 17:41:17 2005 UTC

…		…
56		56
57	=cut	57	=cut
58		58
59	package IO::AIO;	59	package IO::AIO;
60		60
		61	no warnings;
		62
61	use base 'Exporter';	63	use base 'Exporter';
62		64
63	use Fcntl ();	65	use Fcntl ();
64		66
65	BEGIN {	67	BEGIN {
66	$VERSION = 0.9;	68	$VERSION = '1.61';
67		69
68	@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_scandir aio_symlink
69	aio_fsync aio_fdatasync aio_readahead);	72	aio_fsync aio_fdatasync aio_readahead);
70	@EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs);	73	@EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel
		74	max_outstanding nreqs);
71		75
72	require XSLoader;	76	require XSLoader;
73	XSLoader::load IO::AIO, $VERSION;	77	XSLoader::load IO::AIO, $VERSION;
74	}	78	}
75		79
…		…
83	which must be a code reference. This code reference will get called with	87	which must be a code reference. This code reference will get called with
84	the syscall return code (e.g. most syscalls return C<-1> on error, unlike	88	the syscall return code (e.g. most syscalls return C<-1> on error, unlike
85	perl, which usually delivers "false") as it's sole argument when the given	89	perl, which usually delivers "false") as it's sole argument when the given
86	syscall has been executed asynchronously.	90	syscall has been executed asynchronously.
87		91
88	All functions that expect a filehandle will also accept a file descriptor.	92	All functions expecting a filehandle keep a copy of the filehandle
		93	internally until the request has finished.
89		94
90	The filenames you pass to these routines I<must> be absolute. The reason	95	The pathnames you pass to these routines I<must> be absolute and
91	for this is that at the time the request is being executed, the current	96	encoded in byte form. The reason for the former is that at the time the
92	working directory could have changed. Alternatively, you can make sure	97	request is being executed, the current working directory could have
93	that you never change the current working directory.	98	changed. Alternatively, you can make sure that you never change the
		99	current working directory.
		100
		101	To encode pathnames to byte form, either make sure you either: a)
		102	always pass in filenames you got from outside (command line, readdir
		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.
94		107
95	=over 4	108	=over 4
96		109
97	=item aio_open $pathname, $flags, $mode, $callback	110	=item aio_open $pathname, $flags, $mode, $callback->($fh)
98		111
99	Asynchronously open or create a file and call the callback with a newly	112	Asynchronously open or create a file and call the callback with a newly
100	created filehandle for the file.	113	created filehandle for the file.
101		114
102	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,
…		…
119	} else {	132	} else {
120	die "open failed: $!\n";	133	die "open failed: $!\n";
121	}	134	}
122	};	135	};
123		136
124	=item aio_close $fh, $callback	137	=item aio_close $fh, $callback->($status)
125		138
126	Asynchronously close a file and call the callback with the result	139	Asynchronously close a file and call the callback with the result
127	code. I<WARNING:> although accepted, you should not pass in a perl	140	code. I<WARNING:> although accepted, you should not pass in a perl
128	filehandle here, as perl will likely close the file descriptor another	141	filehandle here, as perl will likely close the file descriptor another
129	time when the filehandle is destroyed. Normally, you can safely call perls	142	time when the filehandle is destroyed. Normally, you can safely call perls
130	C<close> or just let filehandles go out of scope.	143	C<close> or just let filehandles go out of scope.
131		144
132	This is supposed to be a bug in the API, so that might change. It's	145	This is supposed to be a bug in the API, so that might change. It's
133	therefore best to avoid this function.	146	therefore best to avoid this function.
134		147
135	=item aio_read $fh,$offset,$length, $data,$dataoffset,$callback	148	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
136		149
137	=item aio_write $fh,$offset,$length, $data,$dataoffset,$callback	150	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
138		151
139	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>
140	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
141	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
142	like the syscall).	155	like the syscall).
143		156
		157	The C<$data> scalar I<MUST NOT> be modified in any way while the request
		158	is outstanding. Modifying it can result in segfaults or WW3 (if the
		159	necessary/optional hardware is installed).
		160
144	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at	161	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at
145	offset C<0> within the scalar:	162	offset C<0> within the scalar:
146		163
147	aio_read $fh, 7, 15, $buffer, 0, sub {	164	aio_read $fh, 7, 15, $buffer, 0, sub {
148	$_[0] > 0 or die "read error: $!";	165	$_[0] > 0 or die "read error: $!";
149	print "read $_[0] bytes: <$buffer>\n";	166	print "read $_[0] bytes: <$buffer>\n";
150	};	167	};
151		168
		169	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
		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
152	=item aio_readahead $fh,$offset,$length, $callback	192	=item aio_readahead $fh,$offset,$length, $callback->($retval)
153
154	Asynchronously reads the specified byte range into the page cache, using
155	the C<readahead> syscall. If that syscall doesn't exist (likely if your OS
156	isn't Linux) the status will be C<-1> and C<$!> is set to C<ENOSYS>.
157		193
158	C<aio_readahead> populates the page cache with data from a file so that	194	C<aio_readahead> populates the page cache with data from a file so that
159	subsequent reads from that file will not block on disk I/O. The C<$offset>	195	subsequent reads from that file will not block on disk I/O. The C<$offset>
160	argument specifies the starting point from which data is to be read and	196	argument specifies the starting point from which data is to be read and
161	C<$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
162	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
163	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
164	(off-set+length). C<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
165	file. The current file offset of the file is left unchanged.	201	file. The current file offset of the file is left unchanged.
166		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.
		205
167	=item aio_stat $fh_or_path, $callback	206	=item aio_stat $fh_or_path, $callback->($status)
168		207
169	=item aio_lstat $fh, $callback	208	=item aio_lstat $fh, $callback->($status)
170		209
171	Works like perl's C<stat> or C<lstat> in void context. The callback will	210	Works like perl's C<stat> or C<lstat> in void context. The callback will
172	be called after the stat and the results will be available using C<stat _>	211	be called after the stat and the results will be available using C<stat _>
173	or C<-s _> etc...	212	or C<-s _> etc...
174		213
…		…
184	aio_stat "/etc/passwd", sub {	223	aio_stat "/etc/passwd", sub {
185	$_[0] and die "stat failed: $!";	224	$_[0] and die "stat failed: $!";
186	print "size is ", -s _, "\n";	225	print "size is ", -s _, "\n";
187	};	226	};
188		227
189	=item aio_unlink $pathname, $callback	228	=item aio_unlink $pathname, $callback->($status)
190		229
191	Asynchronously unlink (delete) a file and call the callback with the	230	Asynchronously unlink (delete) a file and call the callback with the
192	result code.	231	result code.
193		232
		233	=item aio_rmdir $pathname, $callback->($status)
		234
		235	Asynchronously rmdir (delete) a directory and call the callback with the
		236	result code.
		237
		238	=item aio_readdir $pathname $callback->($entries)
		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
		247	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
		248
		249	Scans a directory (similar to C<aio_readdir>) and tries to separate the
		250	entries of directory C<$path> into two sets of names, ones you can recurse
		251	into (directories), and ones you cannot recurse into (everything else).
		252
		253	C<aio_scandir> is a composite request that consists of many
		254	aio-primitives. C<$maxreq> specifies the maximum number of outstanding
		255	aio requests that this function generates. If it is C<< <= 0 >>, then a
		256	suitable default will be chosen (currently 8).
		257
		258	On error, the callback is called without arguments, otherwise it receives
		259	two array-refs with path-relative entry names.
		260
		261	Example:
		262
		263	aio_scandir $dir, 0, sub {
		264	my ($dirs, $nondirs) = @_;
		265	print "real directories: @$dirs\n";
		266	print "everything else: @$nondirs\n";
		267	};
		268
		269	Implementation notes.
		270
		271	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.
		272
		273	After reading the directory, the modification time, size etc. of the
		274	directory before and after the readdir is checked, and if they match, the
		275	link count will be used to decide how many entries are directories (if
		276	>= 2). Otherwise, no knowledge of the number of subdirectories will be
		277	assumed.
		278
		279	Then entires will be sorted into likely directories (everything without a
		280	non-initial dot) and likely non-directories (everything else). Then every
		281	entry + C</.> will be C<stat>'ed, likely directories first. This is often
		282	faster because filesystems might detect the type of the entry without
		283	reading the inode data (e.g. ext2s filetype feature). If that succeeds,
		284	it assumes that the entry is a directory or a symlink to directory (which
		285	will be checked seperately).
		286
		287	If the known number of directories has been reached, the rest of the
		288	entries is assumed to be non-directories.
		289
		290	=cut
		291
		292	sub aio_scandir($$$) {
		293	my ($path, $maxreq, $cb) = @_;
		294
		295	$maxreq = 8 if $maxreq <= 0;
		296
		297	# stat once
		298	aio_stat $path, sub {
		299	$cb->() if $_[0];
		300	my $hash1 = join ":", (stat _)[0,1,3,7,9];
		301
		302	# read the directory entries
		303	aio_readdir $path, sub {
		304	my $entries = shift
		305	or return $cb->();
		306
		307	# stat the dir another time
		308	aio_stat $path, sub {
		309	my $hash2 = join ":", (stat _)[0,1,3,7,9];
		310
		311	my $ndirs;
		312
		313	# take the slow route if anything looks fishy
		314	if ($hash1 ne $hash2) {
		315	$ndirs = -1;
		316	} else {
		317	# if nlink == 2, we are finished
		318	# on non-posix-fs's, we rely on nlink < 2
		319	$ndirs = (stat _)[3] - 2
		320	or $cb->([], $entries);
		321	}
		322
		323	# sort into likely dirs and likely nondirs
		324	# dirs == files without ".", short entries first
		325	$entries = [map $_->[0],
		326	sort { $b->[1] cmp $a->[1] }
		327	map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],
		328	@$entries];
		329
		330	my (@dirs, @nondirs);
		331
		332	my ($statcb, $schedcb);
		333	my $nreq = 0;
		334
		335	$schedcb = sub {
		336	if (@$entries) {
		337	if ($nreq < $maxreq) {
		338	my $ent = pop @$entries;
		339	$nreq++;
		340	aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) };
		341	}
		342	} elsif (!$nreq) {
		343	# finished
		344	undef $statcb;
		345	undef $schedcb;
		346	$cb->(\@dirs, \@nondirs);
		347	undef $cb;
		348	}
		349	};
		350	$statcb = sub {
		351	my ($status, $entry) = @_;
		352
		353	if ($status < 0) {
		354	$nreq--;
		355	push @nondirs, $entry;
		356	&$schedcb;
		357	} else {
		358	# need to check for real directory
		359	aio_lstat "$path/$entry", sub {
		360	$nreq--;
		361
		362	if (-d _) {
		363	push @dirs, $entry;
		364
		365	if (!--$ndirs) {
		366	push @nondirs, @$entries;
		367	$entries = [];
		368	}
		369	} else {
		370	push @nondirs, $entry;
		371	}
		372
		373	&$schedcb;
		374	}
		375	}
		376	};
		377
		378	&$schedcb while @$entries && $nreq < $maxreq;
		379	};
		380	};
		381	};
		382	}
		383
194	=item aio_fsync $fh, $callback	384	=item aio_fsync $fh, $callback->($status)
195		385
196	Asynchronously call fsync on the given filehandle and call the callback	386	Asynchronously call fsync on the given filehandle and call the callback
197	with the fsync result code.	387	with the fsync result code.
198		388
199	=item aio_fdatasync $fh, $callback	389	=item aio_fdatasync $fh, $callback->($status)
200		390
201	Asynchronously call fdatasync on the given filehandle and call the	391	Asynchronously call fdatasync on the given filehandle and call the
202	callback with the fdatasync result code. Might set C<$!> to C<ENOSYS> if	392	callback with the fdatasync result code.
203	C<fdatasync> is not available.	393
		394	If this call isn't available because your OS lacks it or it couldn't be
		395	detected, it will be emulated by calling C<fsync> instead.
204		396
205	=back	397	=back
206		398
207	=head2 SUPPORT FUNCTIONS	399	=head2 SUPPORT FUNCTIONS
208		400
…		…
266	IO::AIO::poll_wait, IO::AIO::poll_cb	458	IO::AIO::poll_wait, IO::AIO::poll_cb
267	if IO::AIO::nreqs;	459	if IO::AIO::nreqs;
268		460
269	=item IO::AIO::min_parallel $nthreads	461	=item IO::AIO::min_parallel $nthreads
270		462
271	Set the minimum number of AIO threads to C<$nthreads>. The default is	463	Set the minimum number of AIO threads to C<$nthreads>. The current default
272	C<1>, which means a single asynchronous operation can be done at one time	464	is C<4>, which means four asynchronous operations can be done at one time
273	(the number of outstanding operations, however, is unlimited).	465	(the number of outstanding operations, however, is unlimited).
		466
		467	IO::AIO starts threads only on demand, when an AIO request is queued and
		468	no free thread exists.
274		469
275	It is recommended to keep the number of threads low, as some Linux	470	It is recommended to keep the number of threads low, as some Linux
276	kernel versions will scale negatively with the number of threads (higher	471	kernel versions will scale negatively with the number of threads (higher
277	parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32	472	parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32
278	threads should be fine.	473	threads should be fine.
279		474
280	Under normal circumstances you don't need to call this function, as this	475	Under most circumstances you don't need to call this function, as the
281	module automatically starts some threads (the exact number might change,	476	module selects a default that is suitable for low to moderate load.
282	and is currently 4).
283		477
284	=item IO::AIO::max_parallel $nthreads	478	=item IO::AIO::max_parallel $nthreads
285		479
286	Sets the maximum number of AIO threads to C<$nthreads>. If more than	480	Sets the maximum number of AIO threads to C<$nthreads>. If more than the
287	the specified number of threads are currently running, kill them. This	481	specified number of threads are currently running, this function kills
288	function blocks until the limit is reached.	482	them. This function blocks until the limit is reached.
		483
		484	While C<$nthreads> are zero, aio requests get queued but not executed
		485	until the number of threads has been increased again.
289		486
290	This module automatically runs C<max_parallel 0> at program end, to ensure	487	This module automatically runs C<max_parallel 0> at program end, to ensure
291	that all threads are killed and that there are no outstanding requests.	488	that all threads are killed and that there are no outstanding requests.
292		489
293	Under normal circumstances you don't need to call this function.	490	Under normal circumstances you don't need to call this function.
…		…
297	Sets the maximum number of outstanding requests to C<$nreqs>. If you	494	Sets the maximum number of outstanding requests to C<$nreqs>. If you
298	try to queue up more than this number of requests, the caller will block until	495	try to queue up more than this number of requests, the caller will block until
299	some requests have been handled.	496	some requests have been handled.
300		497
301	The default is very large, so normally there is no practical limit. If you	498	The default is very large, so normally there is no practical limit. If you
302	queue up many requests in a loop it it often improves speed if you set	499	queue up many requests in a loop it often improves speed if you set
303	this to a relatively low number, such as C<100>.	500	this to a relatively low number, such as C<100>.
304		501
305	Under normal circumstances you don't need to call this function.	502	Under normal circumstances you don't need to call this function.
306		503
307	=back	504	=back
…		…
310		507
311	# support function to convert a fd into a perl filehandle	508	# support function to convert a fd into a perl filehandle
312	sub _fd2fh {	509	sub _fd2fh {
313	return undef if $_[0] < 0;	510	return undef if $_[0] < 0;
314		511
315	# try to be perl5.6-compatible	512	# try to generate nice filehandles
316	local *AIO_FH;	513	my $sym = "IO::AIO::fd#$_[0]";
317	open AIO_FH, "+<&=$_[0]"	514	local *$sym;
		515
		516	open *$sym, "+<&=$_[0]" # usually works under any unix
		517	or open *$sym, "<&=$_[0]" # cygwin needs this
		518	or open *$sym, ">&=$_[0]" # or this
318	or return undef;	519	or return undef;
319		520
320	*AIO_FH	521	*$sym
321	}	522	}
322		523
323	min_parallel 4;	524	min_parallel 4;
324		525
325	END {	526	END {
326	max_parallel 0;	527	max_parallel 0;
327	}	528	}
328		529
329	1;	530	1;
330		531
		532	=head2 FORK BEHAVIOUR
		533
		534	Before the fork, IO::AIO enters a quiescent state where no requests
		535	can be added in other threads and no results will be processed. After
		536	the fork the parent simply leaves the quiescent state and continues
		537	request/result processing, while the child clears the request/result
		538	queue (so the requests started before the fork will only be handled in
		539	the parent). Threats will be started on demand until the limit ste in the
		540	parent process has been reached again.
		541
331	=head1 SEE ALSO	542	=head1 SEE ALSO
332		543
333	L<Coro>, L<Linux::AIO>.	544	L<Coro>, L<Linux::AIO>.
334		545
335	=head1 AUTHOR	546	=head1 AUTHOR

Diff Legend

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

Comparing IO-AIO/AIO.pm (file contents): Revision 1.22 by root, Wed Jul 20 21:55:27 2005 UTC vs. Revision 1.41 by root, Wed Sep 7 17:41:17 2005 UTC

Diff Legend

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.22 by root, Wed Jul 20 21:55:27 2005 UTC vs.
Revision 1.41 by root, Wed Sep 7 17:41:17 2005 UTC