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

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.23 by root, Fri Jul 22 08:25:22 2005 UTC vs.
Revision 1.50 by root, Sat Jun 24 16:27:02 2006 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 = '1.0';	72	$VERSION = '1.8';
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_fsync aio_fdatasync aio_readahead);	76	aio_fsync aio_fdatasync aio_readahead aio_rename aio_link aio_move);
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
…		…
88	syscall has been executed asynchronously.	94	syscall has been executed asynchronously.
89		95
90	All functions expecting a filehandle keep a copy of the filehandle	96	All functions expecting a filehandle keep a copy of the filehandle
91	internally until the request has finished.	97	internally until the request has finished.
92		98
93	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
94	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
95	working directory could have changed. Alternatively, you can make sure	101	request is being executed, the current working directory could have
96	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.
97		111
98	=over 4	112	=over 4
99		113
100	=item aio_open $pathname, $flags, $mode, $callback	114	=item aio_open $pathname, $flags, $mode, $callback->($fh)
101		115
102	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
103	created filehandle for the file.	117	created filehandle for the file.
104		118
105	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,
…		…
122	} else {	136	} else {
123	die "open failed: $!\n";	137	die "open failed: $!\n";
124	}	138	}
125	};	139	};
126		140
127	=item aio_close $fh, $callback	141	=item aio_close $fh, $callback->($status)
128		142
129	Asynchronously close a file and call the callback with the result	143	Asynchronously close a file and call the callback with the result
130	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
131	filehandle here, as perl will likely close the file descriptor another	145	filehandle here, as perl will likely close the file descriptor another
132	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
133	C<close> or just let filehandles go out of scope.	147	C<close> or just let filehandles go out of scope.
134		148
135	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
136	therefore best to avoid this function.	150	therefore best to avoid this function.
137		151
138	=item aio_read $fh,$offset,$length, $data,$dataoffset,$callback	152	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
139		153
140	=item aio_write $fh,$offset,$length, $data,$dataoffset,$callback	154	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
141		155
142	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>
143	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
144	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
145	like the syscall).	159	like the syscall).
146		160
		161	The C<$data> scalar I<MUST NOT> be modified in any way while the request
		162	is outstanding. Modifying it can result in segfaults or WW3 (if the
		163	necessary/optional hardware is installed).
		164
147	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at	165	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at
148	offset C<0> within the scalar:	166	offset C<0> within the scalar:
149		167
150	aio_read $fh, 7, 15, $buffer, 0, sub {	168	aio_read $fh, 7, 15, $buffer, 0, sub {
151	$_[0] > 0 or die "read error: $!";	169	$_[0] > 0 or die "read error: $!";
152	print "read $_[0] bytes: <$buffer>\n";	170	print "read $_[0] bytes: <$buffer>\n";
153	};	171	};
154		172
		173	=item aio_move $srcpath, $dstpath, $callback->($status)
		174
		175	[EXPERIMENTAL]
		176
		177	Try to move the I<file> (directories not supported as either source or destination)
		178	from C<$srcpath> to C<$dstpath> and call the callback with the C<0> (error) or C<-1> ok.
		179
		180	This is a composite request that tries to rename(2) the file first. If
		181	rename files with C<EXDEV>, it creates the destination file with mode 0200
		182	and copies the contents of the source file into it using C<aio_sendfile>,
		183	followed by restoring atime, mtime, access mode and uid/gid, in that
		184	order, and unlinking the C<$srcpath>.
		185
		186	If an error occurs, the partial destination file will be unlinked, if
		187	possible, except when setting atime, mtime, access mode and uid/gid, where
		188	errors are being ignored.
		189
		190	=cut
		191
		192	sub aio_move($$$) {
		193	my ($src, $dst, $cb) = @_;
		194
		195	aio_rename $src, $dst, sub {
		196	if ($_[0] && $! == Errno::EXDEV) {
		197	aio_open $src, O_RDONLY, 0, sub {
		198	if (my $src_fh = $_[0]) {
		199	my @stat = stat $src_fh;
		200
		201	aio_open $dst, O_WRONLY, 0200, sub {
		202	if (my $dst_fh = $_[0]) {
		203	aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
		204	close $src_fh;
		205
		206	if ($_[0] == $stat[7]) {
		207	utime $stat[8], $stat[9], $dst;
		208	chmod $stat[2] & 07777, $dst_fh;
		209	chown $stat[4], $stat[5], $dst_fh;
		210	close $dst_fh;
		211
		212	aio_unlink $src, sub {
		213	$cb->($_[0]);
		214	};
		215	} else {
		216	my $errno = $!;
		217	aio_unlink $dst, sub {
		218	$! = $errno;
		219	$cb->(-1);
		220	};
		221	}
		222	};
		223	} else {
		224	$cb->(-1);
		225	}
		226	},
		227
		228	} else {
		229	$cb->(-1);
		230	}
		231	};
		232	} else {
		233	$cb->($_[0]);
		234	}
		235	};
		236	}
		237
		238	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
		239
		240	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
		241	reading at byte offset C<$in_offset>, and starts writing at the current
		242	file offset of C<$out_fh>. Because of that, it is not safe to issue more
		243	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each
		244	other.
		245
		246	This call tries to make use of a native C<sendfile> syscall to provide
		247	zero-copy operation. For this to work, C<$out_fh> should refer to a
		248	socket, and C<$in_fh> should refer to mmap'able file.
		249
		250	If the native sendfile call fails or is not implemented, it will be
		251	emulated, so you can call C<aio_sendfile> on any type of filehandle
		252	regardless of the limitations of the operating system.
		253
		254	Please note, however, that C<aio_sendfile> can read more bytes from
		255	C<$in_fh> than are written, and there is no way to find out how many
		256	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only
		257	provides the number of bytes written to C<$out_fh>. Only if the result
		258	value equals C<$length> one can assume that C<$length> bytes have been
		259	read.
		260
155	=item aio_readahead $fh,$offset,$length, $callback	261	=item aio_readahead $fh,$offset,$length, $callback->($retval)
156
157	Asynchronously reads the specified byte range into the page cache, using
158	the C<readahead> syscall. If that syscall doesn't exist (likely if your OS
159	isn't Linux) the status will be C<-1> and C<$!> is set to C<ENOSYS>.
160		262
161	C<aio_readahead> populates the page cache with data from a file so that	263	C<aio_readahead> populates the page cache with data from a file so that
162	subsequent reads from that file will not block on disk I/O. The C<$offset>	264	subsequent reads from that file will not block on disk I/O. The C<$offset>
163	argument specifies the starting point from which data is to be read and	265	argument specifies the starting point from which data is to be read and
164	C<$length> specifies the number of bytes to be read. I/O is performed in	266	C<$length> specifies the number of bytes to be read. I/O is performed in
165	whole pages, so that offset is effectively rounded down to a page boundary	267	whole pages, so that offset is effectively rounded down to a page boundary
166	and bytes are read up to the next page boundary greater than or equal to	268	and bytes are read up to the next page boundary greater than or equal to
167	(off-set+length). C<aio_readahead> does not read beyond the end of the	269	(off-set+length). C<aio_readahead> does not read beyond the end of the
168	file. The current file offset of the file is left unchanged.	270	file. The current file offset of the file is left unchanged.
169		271
		272	If that syscall doesn't exist (likely if your OS isn't Linux) it will be
		273	emulated by simply reading the data, which would have a similar effect.
		274
170	=item aio_stat $fh_or_path, $callback	275	=item aio_stat $fh_or_path, $callback->($status)
171		276
172	=item aio_lstat $fh, $callback	277	=item aio_lstat $fh, $callback->($status)
173		278
174	Works like perl's C<stat> or C<lstat> in void context. The callback will	279	Works like perl's C<stat> or C<lstat> in void context. The callback will
175	be called after the stat and the results will be available using C<stat _>	280	be called after the stat and the results will be available using C<stat _>
176	or C<-s _> etc...	281	or C<-s _> etc...
177		282
…		…
187	aio_stat "/etc/passwd", sub {	292	aio_stat "/etc/passwd", sub {
188	$_[0] and die "stat failed: $!";	293	$_[0] and die "stat failed: $!";
189	print "size is ", -s _, "\n";	294	print "size is ", -s _, "\n";
190	};	295	};
191		296
192	=item aio_unlink $pathname, $callback	297	=item aio_unlink $pathname, $callback->($status)
193		298
194	Asynchronously unlink (delete) a file and call the callback with the	299	Asynchronously unlink (delete) a file and call the callback with the
195	result code.	300	result code.
196		301
		302	=item aio_link $srcpath, $dstpath, $callback->($status)
		303
		304	Asynchronously create a new link to the existing object at C<$srcpath> at
		305	the path C<$dstpath> and call the callback with the result code.
		306
		307	=item aio_symlink $srcpath, $dstpath, $callback->($status)
		308
		309	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at
		310	the path C<$dstpath> and call the callback with the result code.
		311
		312	=item aio_rename $srcpath, $dstpath, $callback->($status)
		313
		314	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as
		315	rename(2) and call the callback with the result code.
		316
		317	=item aio_rmdir $pathname, $callback->($status)
		318
		319	Asynchronously rmdir (delete) a directory and call the callback with the
		320	result code.
		321
		322	=item aio_readdir $pathname, $callback->($entries)
		323
		324	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
		325	directory (i.e. opendir + readdir + closedir). The entries will not be
		326	sorted, and will B<NOT> include the C<.> and C<..> entries.
		327
		328	The callback a single argument which is either C<undef> or an array-ref
		329	with the filenames.
		330
		331	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
		332
		333	Scans a directory (similar to C<aio_readdir>) and tries to separate the
		334	entries of directory C<$path> into two sets of names, ones you can recurse
		335	into (directories), and ones you cannot recurse into (everything else).
		336
		337	C<aio_scandir> is a composite request that consists of many
		338	aio-primitives. C<$maxreq> specifies the maximum number of outstanding
		339	aio requests that this function generates. If it is C<< <= 0 >>, then a
		340	suitable default will be chosen (currently 8).
		341
		342	On error, the callback is called without arguments, otherwise it receives
		343	two array-refs with path-relative entry names.
		344
		345	Example:
		346
		347	aio_scandir $dir, 0, sub {
		348	my ($dirs, $nondirs) = @_;
		349	print "real directories: @$dirs\n";
		350	print "everything else: @$nondirs\n";
		351	};
		352
		353	Implementation notes.
		354
		355	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.
		356
		357	After reading the directory, the modification time, size etc. of the
		358	directory before and after the readdir is checked, and if they match, the
		359	link count will be used to decide how many entries are directories (if
		360	>= 2). Otherwise, no knowledge of the number of subdirectories will be
		361	assumed.
		362
		363	Then entires will be sorted into likely directories (everything without a
		364	non-initial dot) and likely non-directories (everything else). Then every
		365	entry + C</.> will be C<stat>'ed, likely directories first. This is often
		366	faster because filesystems might detect the type of the entry without
		367	reading the inode data (e.g. ext2fs filetype feature). If that succeeds,
		368	it assumes that the entry is a directory or a symlink to directory (which
		369	will be checked seperately).
		370
		371	If the known number of directories has been reached, the rest of the
		372	entries is assumed to be non-directories.
		373
		374	=cut
		375
		376	sub aio_scandir($$$) {
		377	my ($path, $maxreq, $cb) = @_;
		378
		379	$maxreq = 8 if $maxreq <= 0;
		380
		381	# stat once
		382	aio_stat $path, sub {
		383	return $cb->() if $_[0];
		384	my $hash1 = join ":", (stat _)[0,1,3,7,9];
		385
		386	# read the directory entries
		387	aio_readdir $path, sub {
		388	my $entries = shift
		389	or return $cb->();
		390
		391	# stat the dir another time
		392	aio_stat $path, sub {
		393	my $hash2 = join ":", (stat _)[0,1,3,7,9];
		394
		395	my $ndirs;
		396
		397	# take the slow route if anything looks fishy
		398	if ($hash1 ne $hash2) {
		399	$ndirs = -1;
		400	} else {
		401	# if nlink == 2, we are finished
		402	# on non-posix-fs's, we rely on nlink < 2
		403	$ndirs = (stat _)[3] - 2
		404	or return $cb->([], $entries);
		405	}
		406
		407	# sort into likely dirs and likely nondirs
		408	# dirs == files without ".", short entries first
		409	$entries = [map $_->[0],
		410	sort { $b->[1] cmp $a->[1] }
		411	map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],
		412	@$entries];
		413
		414	my (@dirs, @nondirs);
		415
		416	my ($statcb, $schedcb);
		417	my $nreq = 0;
		418
		419	$schedcb = sub {
		420	if (@$entries) {
		421	if ($nreq < $maxreq) {
		422	my $ent = pop @$entries;
		423	$nreq++;
		424	aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) };
		425	}
		426	} elsif (!$nreq) {
		427	# finished
		428	undef $statcb;
		429	undef $schedcb;
		430	$cb->(\@dirs, \@nondirs) if $cb;
		431	undef $cb;
		432	}
		433	};
		434	$statcb = sub {
		435	my ($status, $entry) = @_;
		436
		437	if ($status < 0) {
		438	$nreq--;
		439	push @nondirs, $entry;
		440	&$schedcb;
		441	} else {
		442	# need to check for real directory
		443	aio_lstat "$path/$entry", sub {
		444	$nreq--;
		445
		446	if (-d _) {
		447	push @dirs, $entry;
		448
		449	if (!--$ndirs) {
		450	push @nondirs, @$entries;
		451	$entries = [];
		452	}
		453	} else {
		454	push @nondirs, $entry;
		455	}
		456
		457	&$schedcb;
		458	}
		459	}
		460	};
		461
		462	&$schedcb while @$entries && $nreq < $maxreq;
		463	};
		464	};
		465	};
		466	}
		467
197	=item aio_fsync $fh, $callback	468	=item aio_fsync $fh, $callback->($status)
198		469
199	Asynchronously call fsync on the given filehandle and call the callback	470	Asynchronously call fsync on the given filehandle and call the callback
200	with the fsync result code.	471	with the fsync result code.
201		472
202	=item aio_fdatasync $fh, $callback	473	=item aio_fdatasync $fh, $callback->($status)
203		474
204	Asynchronously call fdatasync on the given filehandle and call the	475	Asynchronously call fdatasync on the given filehandle and call the
205	callback with the fdatasync result code. Might set C<$!> to C<ENOSYS> if	476	callback with the fdatasync result code.
206	C<fdatasync> is not available.	477
		478	If this call isn't available because your OS lacks it or it couldn't be
		479	detected, it will be emulated by calling C<fsync> instead.
207		480
208	=back	481	=back
209		482
210	=head2 SUPPORT FUNCTIONS	483	=head2 SUPPORT FUNCTIONS
211		484
…		…
269	IO::AIO::poll_wait, IO::AIO::poll_cb	542	IO::AIO::poll_wait, IO::AIO::poll_cb
270	if IO::AIO::nreqs;	543	if IO::AIO::nreqs;
271		544
272	=item IO::AIO::min_parallel $nthreads	545	=item IO::AIO::min_parallel $nthreads
273		546
274	Set the minimum number of AIO threads to C<$nthreads>. The default is	547	Set the minimum number of AIO threads to C<$nthreads>. The current default
275	C<1>, which means a single asynchronous operation can be done at one time	548	is C<4>, which means four asynchronous operations can be done at one time
276	(the number of outstanding operations, however, is unlimited).	549	(the number of outstanding operations, however, is unlimited).
		550
		551	IO::AIO starts threads only on demand, when an AIO request is queued and
		552	no free thread exists.
277		553
278	It is recommended to keep the number of threads low, as some Linux	554	It is recommended to keep the number of threads low, as some Linux
279	kernel versions will scale negatively with the number of threads (higher	555	kernel versions will scale negatively with the number of threads (higher
280	parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32	556	parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32
281	threads should be fine.	557	threads should be fine.
282		558
283	Under normal circumstances you don't need to call this function, as this	559	Under most circumstances you don't need to call this function, as the
284	module automatically starts some threads (the exact number might change,	560	module selects a default that is suitable for low to moderate load.
285	and is currently 4).
286		561
287	=item IO::AIO::max_parallel $nthreads	562	=item IO::AIO::max_parallel $nthreads
288		563
289	Sets the maximum number of AIO threads to C<$nthreads>. If more than	564	Sets the maximum number of AIO threads to C<$nthreads>. If more than the
290	the specified number of threads are currently running, kill them. This	565	specified number of threads are currently running, this function kills
291	function blocks until the limit is reached.	566	them. This function blocks until the limit is reached.
		567
		568	While C<$nthreads> are zero, aio requests get queued but not executed
		569	until the number of threads has been increased again.
292		570
293	This module automatically runs C<max_parallel 0> at program end, to ensure	571	This module automatically runs C<max_parallel 0> at program end, to ensure
294	that all threads are killed and that there are no outstanding requests.	572	that all threads are killed and that there are no outstanding requests.
295		573
296	Under normal circumstances you don't need to call this function.	574	Under normal circumstances you don't need to call this function.
…		…
300	Sets the maximum number of outstanding requests to C<$nreqs>. If you	578	Sets the maximum number of outstanding requests to C<$nreqs>. If you
301	try to queue up more than this number of requests, the caller will block until	579	try to queue up more than this number of requests, the caller will block until
302	some requests have been handled.	580	some requests have been handled.
303		581
304	The default is very large, so normally there is no practical limit. If you	582	The default is very large, so normally there is no practical limit. If you
305	queue up many requests in a loop it it often improves speed if you set	583	queue up many requests in a loop it often improves speed if you set
306	this to a relatively low number, such as C<100>.	584	this to a relatively low number, such as C<100>.
307		585
308	Under normal circumstances you don't need to call this function.	586	Under normal circumstances you don't need to call this function.
309		587
310	=back	588	=back
…		…
316	return undef if $_[0] < 0;	594	return undef if $_[0] < 0;
317		595
318	# try to generate nice filehandles	596	# try to generate nice filehandles
319	my $sym = "IO::AIO::fd#$_[0]";	597	my $sym = "IO::AIO::fd#$_[0]";
320	local *$sym;	598	local *$sym;
321	open *$sym, "+<&=$_[0]"	599
		600	open *$sym, "+<&=$_[0]" # usually works under any unix
		601	or open *$sym, "<&=$_[0]" # cygwin needs this
		602	or open *$sym, ">&=$_[0]" # or this
322	or return undef;	603	or return undef;
323		604
324	*$sym	605	*$sym
325	}	606	}
326		607
…		…
330	max_parallel 0;	611	max_parallel 0;
331	}	612	}
332		613
333	1;	614	1;
334		615
		616	=head2 FORK BEHAVIOUR
		617
		618	Before the fork, IO::AIO enters a quiescent state where no requests
		619	can be added in other threads and no results will be processed. After
		620	the fork the parent simply leaves the quiescent state and continues
		621	request/result processing, while the child clears the request/result
		622	queue (so the requests started before the fork will only be handled in
		623	the parent). Threats will be started on demand until the limit ste in the
		624	parent process has been reached again.
		625
335	=head1 SEE ALSO	626	=head1 SEE ALSO
336		627
337	L<Coro>, L<Linux::AIO>.	628	L<Coro>, L<Linux::AIO>.
338		629
339	=head1 AUTHOR	630	=head1 AUTHOR

Diff Legend

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

Comparing IO-AIO/AIO.pm (file contents): Revision 1.23 by root, Fri Jul 22 08:25:22 2005 UTC vs. Revision 1.50 by root, Sat Jun 24 16:27:02 2006 UTC

Diff Legend

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.23 by root, Fri Jul 22 08:25:22 2005 UTC vs.
Revision 1.50 by root, Sat Jun 24 16:27:02 2006 UTC