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

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.26 by root, Sun Aug 7 03:34:07 2005 UTC vs.
Revision 1.51 by root, Sat Jun 24 19:14:04 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);
…		…
57	=cut	61	=cut
58		62
59	package IO::AIO;	63	package IO::AIO;
60		64
61	no warnings;	65	no warnings;
		66	use strict 'vars';
62		67
63	use base 'Exporter';	68	use base 'Exporter';
64		69
65	use Fcntl ();
66
67	BEGIN {	70	BEGIN {
68	$VERSION = 1.1;	71	our $VERSION = '1.8';
69		72
70	@EXPORT = qw(aio_read aio_write aio_open aio_close aio_stat aio_lstat aio_unlink	73	our @EXPORT = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat
		74	aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink
71	aio_fsync aio_fdatasync aio_readahead);	75	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);	76	our @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs);
73		77
74	require XSLoader;	78	require XSLoader;
75	XSLoader::load IO::AIO, $VERSION;	79	XSLoader::load ("IO::AIO", $VERSION);
76	}	80	}
77		81
78	=head1 FUNCTIONS	82	=head1 FUNCTIONS
79		83
80	=head2 AIO FUNCTIONS	84	=head2 AIO FUNCTIONS
…		…
88	syscall has been executed asynchronously.	92	syscall has been executed asynchronously.
89		93
90	All functions expecting a filehandle keep a copy of the filehandle	94	All functions expecting a filehandle keep a copy of the filehandle
91	internally until the request has finished.	95	internally until the request has finished.
92		96
93	The filenames you pass to these routines I<must> be absolute. The reason	97	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	98	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	99	request is being executed, the current working directory could have
96	that you never change the current working directory.	100	changed. Alternatively, you can make sure that you never change the
		101	current working directory.
		102
		103	To encode pathnames to byte form, either make sure you either: a)
		104	always pass in filenames you got from outside (command line, readdir
		105	etc.), b) are ASCII or ISO 8859-1, c) use the Encode module and encode
		106	your pathnames to the locale (or other) encoding in effect in the user
		107	environment, d) use Glib::filename_from_unicode on unicode filenames or e)
		108	use something else.
97		109
98	=over 4	110	=over 4
99		111
100	=item aio_open $pathname, $flags, $mode, $callback	112	=item aio_open $pathname, $flags, $mode, $callback->($fh)
101		113
102	Asynchronously open or create a file and call the callback with a newly	114	Asynchronously open or create a file and call the callback with a newly
103	created filehandle for the file.	115	created filehandle for the file.
104		116
105	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,	117	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,
…		…
122	} else {	134	} else {
123	die "open failed: $!\n";	135	die "open failed: $!\n";
124	}	136	}
125	};	137	};
126		138
127	=item aio_close $fh, $callback	139	=item aio_close $fh, $callback->($status)
128		140
129	Asynchronously close a file and call the callback with the result	141	Asynchronously close a file and call the callback with the result
130	code. I<WARNING:> although accepted, you should not pass in a perl	142	code. I<WARNING:> although accepted, you should not pass in a perl
131	filehandle here, as perl will likely close the file descriptor another	143	filehandle here, as perl will likely close the file descriptor another
132	time when the filehandle is destroyed. Normally, you can safely call perls	144	time when the filehandle is destroyed. Normally, you can safely call perls
133	C<close> or just let filehandles go out of scope.	145	C<close> or just let filehandles go out of scope.
134		146
135	This is supposed to be a bug in the API, so that might change. It's	147	This is supposed to be a bug in the API, so that might change. It's
136	therefore best to avoid this function.	148	therefore best to avoid this function.
137		149
138	=item aio_read $fh,$offset,$length, $data,$dataoffset,$callback	150	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
139		151
140	=item aio_write $fh,$offset,$length, $data,$dataoffset,$callback	152	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
141		153
142	Reads or writes C<length> bytes from the specified C<fh> and C<offset>	154	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	155	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	156	callback without the actual number of bytes read (or -1 on error, just
145	like the syscall).	157	like the syscall).
146		158
		159	The C<$data> scalar I<MUST NOT> be modified in any way while the request
		160	is outstanding. Modifying it can result in segfaults or WW3 (if the
		161	necessary/optional hardware is installed).
		162
147	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at	163	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at
148	offset C<0> within the scalar:	164	offset C<0> within the scalar:
149		165
150	aio_read $fh, 7, 15, $buffer, 0, sub {	166	aio_read $fh, 7, 15, $buffer, 0, sub {
151	$_[0] > 0 or die "read error: $!";	167	$_[0] > 0 or die "read error: $!";
152	print "read $_[0] bytes: <$buffer>\n";	168	print "read $_[0] bytes: <$buffer>\n";
153	};	169	};
154		170
		171	=item aio_move $srcpath, $dstpath, $callback->($status)
		172
		173	[EXPERIMENTAL]
		174
		175	Try to move the I<file> (directories not supported as either source or destination)
		176	from C<$srcpath> to C<$dstpath> and call the callback with the C<0> (error) or C<-1> ok.
		177
		178	This is a composite request that tries to rename(2) the file first. If
		179	rename files with C<EXDEV>, it creates the destination file with mode 0200
		180	and copies the contents of the source file into it using C<aio_sendfile>,
		181	followed by restoring atime, mtime, access mode and uid/gid, in that
		182	order, and unlinking the C<$srcpath>.
		183
		184	If an error occurs, the partial destination file will be unlinked, if
		185	possible, except when setting atime, mtime, access mode and uid/gid, where
		186	errors are being ignored.
		187
		188	=cut
		189
		190	sub aio_move($$$) {
		191	my ($src, $dst, $cb) = @_;
		192
		193	aio_rename $src, $dst, sub {
		194	if ($_[0] && $! == EXDEV) {
		195	aio_open $src, O_RDONLY, 0, sub {
		196	if (my $src_fh = $_[0]) {
		197	my @stat = stat $src_fh;
		198
		199	aio_open $dst, O_WRONLY, 0200, sub {
		200	if (my $dst_fh = $_[0]) {
		201	aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
		202	close $src_fh;
		203
		204	if ($_[0] == $stat[7]) {
		205	utime $stat[8], $stat[9], $dst;
		206	chmod $stat[2] & 07777, $dst_fh;
		207	chown $stat[4], $stat[5], $dst_fh;
		208	close $dst_fh;
		209
		210	aio_unlink $src, sub {
		211	$cb->($_[0]);
		212	};
		213	} else {
		214	my $errno = $!;
		215	aio_unlink $dst, sub {
		216	$! = $errno;
		217	$cb->(-1);
		218	};
		219	}
		220	};
		221	} else {
		222	$cb->(-1);
		223	}
		224	},
		225
		226	} else {
		227	$cb->(-1);
		228	}
		229	};
		230	} else {
		231	$cb->($_[0]);
		232	}
		233	};
		234	}
		235
		236	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
		237
		238	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
		239	reading at byte offset C<$in_offset>, and starts writing at the current
		240	file offset of C<$out_fh>. Because of that, it is not safe to issue more
		241	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each
		242	other.
		243
		244	This call tries to make use of a native C<sendfile> syscall to provide
		245	zero-copy operation. For this to work, C<$out_fh> should refer to a
		246	socket, and C<$in_fh> should refer to mmap'able file.
		247
		248	If the native sendfile call fails or is not implemented, it will be
		249	emulated, so you can call C<aio_sendfile> on any type of filehandle
		250	regardless of the limitations of the operating system.
		251
		252	Please note, however, that C<aio_sendfile> can read more bytes from
		253	C<$in_fh> than are written, and there is no way to find out how many
		254	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only
		255	provides the number of bytes written to C<$out_fh>. Only if the result
		256	value equals C<$length> one can assume that C<$length> bytes have been
		257	read.
		258
155	=item aio_readahead $fh,$offset,$length, $callback	259	=item aio_readahead $fh,$offset,$length, $callback->($retval)
156		260
157	C<aio_readahead> populates the page cache with data from a file so that	261	C<aio_readahead> populates the page cache with data from a file so that
158	subsequent reads from that file will not block on disk I/O. The C<$offset>	262	subsequent reads from that file will not block on disk I/O. The C<$offset>
159	argument specifies the starting point from which data is to be read and	263	argument specifies the starting point from which data is to be read and
160	C<$length> specifies the number of bytes to be read. I/O is performed in	264	C<$length> specifies the number of bytes to be read. I/O is performed in
…		…
164	file. The current file offset of the file is left unchanged.	268	file. The current file offset of the file is left unchanged.
165		269
166	If that syscall doesn't exist (likely if your OS isn't Linux) it will be	270	If that syscall doesn't exist (likely if your OS isn't Linux) it will be
167	emulated by simply reading the data, which would have a similar effect.	271	emulated by simply reading the data, which would have a similar effect.
168		272
169	=item aio_stat $fh_or_path, $callback	273	=item aio_stat $fh_or_path, $callback->($status)
170		274
171	=item aio_lstat $fh, $callback	275	=item aio_lstat $fh, $callback->($status)
172		276
173	Works like perl's C<stat> or C<lstat> in void context. The callback will	277	Works like perl's C<stat> or C<lstat> in void context. The callback will
174	be called after the stat and the results will be available using C<stat _>	278	be called after the stat and the results will be available using C<stat _>
175	or C<-s _> etc...	279	or C<-s _> etc...
176		280
…		…
186	aio_stat "/etc/passwd", sub {	290	aio_stat "/etc/passwd", sub {
187	$_[0] and die "stat failed: $!";	291	$_[0] and die "stat failed: $!";
188	print "size is ", -s _, "\n";	292	print "size is ", -s _, "\n";
189	};	293	};
190		294
191	=item aio_unlink $pathname, $callback	295	=item aio_unlink $pathname, $callback->($status)
192		296
193	Asynchronously unlink (delete) a file and call the callback with the	297	Asynchronously unlink (delete) a file and call the callback with the
194	result code.	298	result code.
195		299
		300	=item aio_link $srcpath, $dstpath, $callback->($status)
		301
		302	Asynchronously create a new link to the existing object at C<$srcpath> at
		303	the path C<$dstpath> and call the callback with the result code.
		304
		305	=item aio_symlink $srcpath, $dstpath, $callback->($status)
		306
		307	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at
		308	the path C<$dstpath> and call the callback with the result code.
		309
		310	=item aio_rename $srcpath, $dstpath, $callback->($status)
		311
		312	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as
		313	rename(2) and call the callback with the result code.
		314
		315	=item aio_rmdir $pathname, $callback->($status)
		316
		317	Asynchronously rmdir (delete) a directory and call the callback with the
		318	result code.
		319
		320	=item aio_readdir $pathname, $callback->($entries)
		321
		322	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
		323	directory (i.e. opendir + readdir + closedir). The entries will not be
		324	sorted, and will B<NOT> include the C<.> and C<..> entries.
		325
		326	The callback a single argument which is either C<undef> or an array-ref
		327	with the filenames.
		328
		329	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
		330
		331	Scans a directory (similar to C<aio_readdir>) and tries to separate the
		332	entries of directory C<$path> into two sets of names, ones you can recurse
		333	into (directories), and ones you cannot recurse into (everything else).
		334
		335	C<aio_scandir> is a composite request that consists of many
		336	aio-primitives. C<$maxreq> specifies the maximum number of outstanding
		337	aio requests that this function generates. If it is C<< <= 0 >>, then a
		338	suitable default will be chosen (currently 8).
		339
		340	On error, the callback is called without arguments, otherwise it receives
		341	two array-refs with path-relative entry names.
		342
		343	Example:
		344
		345	aio_scandir $dir, 0, sub {
		346	my ($dirs, $nondirs) = @_;
		347	print "real directories: @$dirs\n";
		348	print "everything else: @$nondirs\n";
		349	};
		350
		351	Implementation notes.
		352
		353	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.
		354
		355	After reading the directory, the modification time, size etc. of the
		356	directory before and after the readdir is checked, and if they match, the
		357	link count will be used to decide how many entries are directories (if
		358	>= 2). Otherwise, no knowledge of the number of subdirectories will be
		359	assumed.
		360
		361	Then entires will be sorted into likely directories (everything without a
		362	non-initial dot) and likely non-directories (everything else). Then every
		363	entry + C</.> will be C<stat>'ed, likely directories first. This is often
		364	faster because filesystems might detect the type of the entry without
		365	reading the inode data (e.g. ext2fs filetype feature). If that succeeds,
		366	it assumes that the entry is a directory or a symlink to directory (which
		367	will be checked seperately).
		368
		369	If the known number of directories has been reached, the rest of the
		370	entries is assumed to be non-directories.
		371
		372	=cut
		373
		374	sub aio_scandir($$$) {
		375	my ($path, $maxreq, $cb) = @_;
		376
		377	$maxreq = 8 if $maxreq <= 0;
		378
		379	# stat once
		380	aio_stat $path, sub {
		381	return $cb->() if $_[0];
		382	my $hash1 = join ":", (stat _)[0,1,3,7,9];
		383
		384	# read the directory entries
		385	aio_readdir $path, sub {
		386	my $entries = shift
		387	or return $cb->();
		388
		389	# stat the dir another time
		390	aio_stat $path, sub {
		391	my $hash2 = join ":", (stat _)[0,1,3,7,9];
		392
		393	my $ndirs;
		394
		395	# take the slow route if anything looks fishy
		396	if ($hash1 ne $hash2) {
		397	$ndirs = -1;
		398	} else {
		399	# if nlink == 2, we are finished
		400	# on non-posix-fs's, we rely on nlink < 2
		401	$ndirs = (stat _)[3] - 2
		402	or return $cb->([], $entries);
		403	}
		404
		405	# sort into likely dirs and likely nondirs
		406	# dirs == files without ".", short entries first
		407	$entries = [map $_->[0],
		408	sort { $b->[1] cmp $a->[1] }
		409	map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],
		410	@$entries];
		411
		412	my (@dirs, @nondirs);
		413
		414	my ($statcb, $schedcb);
		415	my $nreq = 0;
		416
		417	$schedcb = sub {
		418	if (@$entries) {
		419	if ($nreq < $maxreq) {
		420	my $ent = pop @$entries;
		421	$nreq++;
		422	aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) };
		423	}
		424	} elsif (!$nreq) {
		425	# finished
		426	undef $statcb;
		427	undef $schedcb;
		428	$cb->(\@dirs, \@nondirs) if $cb;
		429	undef $cb;
		430	}
		431	};
		432	$statcb = sub {
		433	my ($status, $entry) = @_;
		434
		435	if ($status < 0) {
		436	$nreq--;
		437	push @nondirs, $entry;
		438	&$schedcb;
		439	} else {
		440	# need to check for real directory
		441	aio_lstat "$path/$entry", sub {
		442	$nreq--;
		443
		444	if (-d _) {
		445	push @dirs, $entry;
		446
		447	if (!--$ndirs) {
		448	push @nondirs, @$entries;
		449	$entries = [];
		450	}
		451	} else {
		452	push @nondirs, $entry;
		453	}
		454
		455	&$schedcb;
		456	}
		457	}
		458	};
		459
		460	&$schedcb while @$entries && $nreq < $maxreq;
		461	};
		462	};
		463	};
		464	}
		465
196	=item aio_fsync $fh, $callback	466	=item aio_fsync $fh, $callback->($status)
197		467
198	Asynchronously call fsync on the given filehandle and call the callback	468	Asynchronously call fsync on the given filehandle and call the callback
199	with the fsync result code.	469	with the fsync result code.
200		470
201	=item aio_fdatasync $fh, $callback	471	=item aio_fdatasync $fh, $callback->($status)
202		472
203	Asynchronously call fdatasync on the given filehandle and call the	473	Asynchronously call fdatasync on the given filehandle and call the
204	callback with the fdatasync result code.	474	callback with the fdatasync result code.
205		475
206	If this call isn't available because your OS lacks it or it couldn't be	476	If this call isn't available because your OS lacks it or it couldn't be
…		…
270	IO::AIO::poll_wait, IO::AIO::poll_cb	540	IO::AIO::poll_wait, IO::AIO::poll_cb
271	if IO::AIO::nreqs;	541	if IO::AIO::nreqs;
272		542
273	=item IO::AIO::min_parallel $nthreads	543	=item IO::AIO::min_parallel $nthreads
274		544
275	Set the minimum number of AIO threads to C<$nthreads>. The default is	545	Set the minimum number of AIO threads to C<$nthreads>. The current default
276	C<1>, which means a single asynchronous operation can be done at one time	546	is C<4>, which means four asynchronous operations can be done at one time
277	(the number of outstanding operations, however, is unlimited).	547	(the number of outstanding operations, however, is unlimited).
		548
		549	IO::AIO starts threads only on demand, when an AIO request is queued and
		550	no free thread exists.
278		551
279	It is recommended to keep the number of threads low, as some Linux	552	It is recommended to keep the number of threads low, as some Linux
280	kernel versions will scale negatively with the number of threads (higher	553	kernel versions will scale negatively with the number of threads (higher
281	parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32	554	parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32
282	threads should be fine.	555	threads should be fine.
283		556
284	Under normal circumstances you don't need to call this function, as this	557	Under most circumstances you don't need to call this function, as the
285	module automatically starts some threads (the exact number might change,	558	module selects a default that is suitable for low to moderate load.
286	and is currently 4).
287		559
288	=item IO::AIO::max_parallel $nthreads	560	=item IO::AIO::max_parallel $nthreads
289		561
290	Sets the maximum number of AIO threads to C<$nthreads>. If more than	562	Sets the maximum number of AIO threads to C<$nthreads>. If more than the
291	the specified number of threads are currently running, kill them. This	563	specified number of threads are currently running, this function kills
292	function blocks until the limit is reached.	564	them. This function blocks until the limit is reached.
		565
		566	While C<$nthreads> are zero, aio requests get queued but not executed
		567	until the number of threads has been increased again.
293		568
294	This module automatically runs C<max_parallel 0> at program end, to ensure	569	This module automatically runs C<max_parallel 0> at program end, to ensure
295	that all threads are killed and that there are no outstanding requests.	570	that all threads are killed and that there are no outstanding requests.
296		571
297	Under normal circumstances you don't need to call this function.	572	Under normal circumstances you don't need to call this function.
…		…
301	Sets the maximum number of outstanding requests to C<$nreqs>. If you	576	Sets the maximum number of outstanding requests to C<$nreqs>. If you
302	try to queue up more than this number of requests, the caller will block until	577	try to queue up more than this number of requests, the caller will block until
303	some requests have been handled.	578	some requests have been handled.
304		579
305	The default is very large, so normally there is no practical limit. If you	580	The default is very large, so normally there is no practical limit. If you
306	queue up many requests in a loop it it often improves speed if you set	581	queue up many requests in a loop it often improves speed if you set
307	this to a relatively low number, such as C<100>.	582	this to a relatively low number, such as C<100>.
308		583
309	Under normal circumstances you don't need to call this function.	584	Under normal circumstances you don't need to call this function.
310		585
311	=back	586	=back
…		…
318		593
319	# try to generate nice filehandles	594	# try to generate nice filehandles
320	my $sym = "IO::AIO::fd#$_[0]";	595	my $sym = "IO::AIO::fd#$_[0]";
321	local *$sym;	596	local *$sym;
322		597
323	open *$sym, "+<&$_[0]" # usually under any unix	598	open *$sym, "+<&=$_[0]" # usually works under any unix
324	or open *$sym, "<&$_[0]" # cygwin needs this	599	or open *$sym, "<&=$_[0]" # cygwin needs this
325	or open *$sym, ">&$_[0]" # cygwin needs this	600	or open *$sym, ">&=$_[0]" # or this
326	or return undef;	601	or return undef;
327		602
328	*$sym	603	*$sym
329	}	604	}
330		605
…		…
334	max_parallel 0;	609	max_parallel 0;
335	}	610	}
336		611
337	1;	612	1;
338		613
		614	=head2 FORK BEHAVIOUR
		615
		616	Before the fork, IO::AIO enters a quiescent state where no requests
		617	can be added in other threads and no results will be processed. After
		618	the fork the parent simply leaves the quiescent state and continues
		619	request/result processing, while the child clears the request/result
		620	queue (so the requests started before the fork will only be handled in
		621	the parent). Threats will be started on demand until the limit ste in the
		622	parent process has been reached again.
		623
339	=head1 SEE ALSO	624	=head1 SEE ALSO
340		625
341	L<Coro>, L<Linux::AIO>.	626	L<Coro>, L<Linux::AIO>.
342		627
343	=head1 AUTHOR	628	=head1 AUTHOR

Diff Legend

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

Comparing IO-AIO/AIO.pm (file contents): Revision 1.26 by root, Sun Aug 7 03:34:07 2005 UTC vs. Revision 1.51 by root, Sat Jun 24 19:14:04 2006 UTC

Diff Legend

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.26 by root, Sun Aug 7 03:34:07 2005 UTC vs.
Revision 1.51 by root, Sat Jun 24 19:14:04 2006 UTC