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

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.43 by root, Mon Dec 26 18:18:32 2005 UTC vs.
Revision 1.56 by root, Sun Oct 22 00:53:47 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	20	# version 2+ has request and group objects
		21	use IO::AIO 2;
		22
		23	my $req = aio_unlink "/tmp/file", sub { };
		24	$req->cancel; # cancel request if still in queue
		25
		26	my $grp = aio_group sub { print "all stats done\n" };
		27	add $grp aio_stat "..." for ...;
		28
		29	# AnyEvent integration
21	open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!";	30	open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!";
22	my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb });	31	my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb });
23		32
24	# Event	33	# Event integration
25	Event->io (fd => IO::AIO::poll_fileno,	34	Event->io (fd => IO::AIO::poll_fileno,
26	poll => 'r',	35	poll => 'r',
27	cb => \&IO::AIO::poll_cb);	36	cb => \&IO::AIO::poll_cb);
28		37
29	# Glib/Gtk2	38	# Glib/Gtk2 integration
30	add_watch Glib::IO IO::AIO::poll_fileno,	39	add_watch Glib::IO IO::AIO::poll_fileno,
31	in => sub { IO::AIO::poll_cb; 1 };	40	in => sub { IO::AIO::poll_cb; 1 };
32		41
33	# Tk	42	# Tk integration
34	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",	43	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
35	readable => \&IO::AIO::poll_cb);	44	readable => \&IO::AIO::poll_cb);
36		45
37	# Danga::Socket	46	# Danga::Socket integration
38	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>	47	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
39	\&IO::AIO::poll_cb);	48	\&IO::AIO::poll_cb);
40
41		49
42	=head1 DESCRIPTION	50	=head1 DESCRIPTION
43		51
44	This module implements asynchronous I/O using whatever means your	52	This module implements asynchronous I/O using whatever means your
45	operating system supports.	53	operating system supports.
…		…
61	=cut	69	=cut
62		70
63	package IO::AIO;	71	package IO::AIO;
64		72
65	no warnings;	73	no warnings;
		74	use strict 'vars';
66		75
67	use base 'Exporter';	76	use base 'Exporter';
68		77
69	use Fcntl ();
70
71	BEGIN {	78	BEGIN {
72	$VERSION = '1.61';	79	our $VERSION = '2.0';
73		80
74	@EXPORT = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat	81	our @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	82	aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink
76	aio_fsync aio_fdatasync aio_readahead);	83	aio_fsync aio_fdatasync aio_readahead aio_rename aio_link aio_move
		84	aio_group);
77	@EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel	85	our @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs);
78	max_outstanding nreqs);	86
		87	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';
79		88
80	require XSLoader;	89	require XSLoader;
81	XSLoader::load IO::AIO, $VERSION;	90	XSLoader::load ("IO::AIO", $VERSION);
82	}	91	}
83		92
84	=head1 FUNCTIONS	93	=head1 FUNCTIONS
85		94
86	=head2 AIO FUNCTIONS	95	=head2 AIO FUNCTIONS
…		…
93	perl, which usually delivers "false") as it's sole argument when the given	102	perl, which usually delivers "false") as it's sole argument when the given
94	syscall has been executed asynchronously.	103	syscall has been executed asynchronously.
95		104
96	All functions expecting a filehandle keep a copy of the filehandle	105	All functions expecting a filehandle keep a copy of the filehandle
97	internally until the request has finished.	106	internally until the request has finished.
		107
		108	All requests return objects of type L<IO::AIO::REQ> that allow further
		109	manipulation of those requests while they are in-flight.
98		110
99	The pathnames you pass to these routines I<must> be absolute and	111	The pathnames you pass to these routines I<must> be absolute and
100	encoded in byte form. The reason for the former is that at the time the	112	encoded in byte form. The reason for the former is that at the time the
101	request is being executed, the current working directory could have	113	request is being executed, the current working directory could have
102	changed. Alternatively, you can make sure that you never change the	114	changed. Alternatively, you can make sure that you never change the
…		…
168	aio_read $fh, 7, 15, $buffer, 0, sub {	180	aio_read $fh, 7, 15, $buffer, 0, sub {
169	$_[0] > 0 or die "read error: $!";	181	$_[0] > 0 or die "read error: $!";
170	print "read $_[0] bytes: <$buffer>\n";	182	print "read $_[0] bytes: <$buffer>\n";
171	};	183	};
172		184
		185	=item aio_move $srcpath, $dstpath, $callback->($status)
		186
		187	Try to move the I<file> (directories not supported as either source or
		188	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		189	the C<0> (error) or C<-1> ok.
		190
		191	This is a composite request that tries to rename(2) the file first. If
		192	rename files with C<EXDEV>, it creates the destination file with mode 0200
		193	and copies the contents of the source file into it using C<aio_sendfile>,
		194	followed by restoring atime, mtime, access mode and uid/gid, in that
		195	order, and unlinking the C<$srcpath>.
		196
		197	If an error occurs, the partial destination file will be unlinked, if
		198	possible, except when setting atime, mtime, access mode and uid/gid, where
		199	errors are being ignored.
		200
		201	=cut
		202
		203	sub aio_move($$$) {
		204	my ($src, $dst, $cb) = @_;
		205
		206	my $grp = aio_group;
		207
		208	add $grp aio_rename $src, $dst, sub {
		209	if ($_[0] && $! == EXDEV) {
		210	add $grp aio_open $src, O_RDONLY, 0, sub {
		211	if (my $src_fh = $_[0]) {
		212	my @stat = stat $src_fh;
		213
		214	add $grp aio_open $dst, O_WRONLY, 0200, sub {
		215	if (my $dst_fh = $_[0]) {
		216	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
		217	close $src_fh;
		218
		219	if ($_[0] == $stat[7]) {
		220	utime $stat[8], $stat[9], $dst;
		221	chmod $stat[2] & 07777, $dst_fh;
		222	chown $stat[4], $stat[5], $dst_fh;
		223	close $dst_fh;
		224
		225	add $grp aio_unlink $src, sub {
		226	$cb->($_[0]);
		227	};
		228	} else {
		229	my $errno = $!;
		230	add $grp aio_unlink $dst, sub {
		231	$! = $errno;
		232	$cb->(-1);
		233	};
		234	}
		235	};
		236	} else {
		237	$cb->(-1);
		238	}
		239	},
		240
		241	} else {
		242	$cb->(-1);
		243	}
		244	};
		245	} else {
		246	$cb->($_[0]);
		247	}
		248	};
		249
		250	$grp
		251	}
		252
173	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)	253	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
174		254
175	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts	255	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	256	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	257	file offset of C<$out_fh>. Because of that, it is not safe to issue more
…		…
232	=item aio_unlink $pathname, $callback->($status)	312	=item aio_unlink $pathname, $callback->($status)
233		313
234	Asynchronously unlink (delete) a file and call the callback with the	314	Asynchronously unlink (delete) a file and call the callback with the
235	result code.	315	result code.
236		316
		317	=item aio_link $srcpath, $dstpath, $callback->($status)
		318
		319	Asynchronously create a new link to the existing object at C<$srcpath> at
		320	the path C<$dstpath> and call the callback with the result code.
		321
		322	=item aio_symlink $srcpath, $dstpath, $callback->($status)
		323
		324	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at
		325	the path C<$dstpath> and call the callback with the result code.
		326
		327	=item aio_rename $srcpath, $dstpath, $callback->($status)
		328
		329	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as
		330	rename(2) and call the callback with the result code.
		331
237	=item aio_rmdir $pathname, $callback->($status)	332	=item aio_rmdir $pathname, $callback->($status)
238		333
239	Asynchronously rmdir (delete) a directory and call the callback with the	334	Asynchronously rmdir (delete) a directory and call the callback with the
240	result code.	335	result code.
241		336
242	=item aio_readdir $pathname $callback->($entries)	337	=item aio_readdir $pathname, $callback->($entries)
243		338
244	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire	339	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	340	directory (i.e. opendir + readdir + closedir). The entries will not be
246	sorted, and will B<NOT> include the C<.> and C<..> entries.	341	sorted, and will B<NOT> include the C<.> and C<..> entries.
247		342
248	The callback a single argument which is either C<undef> or an array-ref	343	The callback a single argument which is either C<undef> or an array-ref
249	with the filenames.	344	with the filenames.
250		345
251	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)	346	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
252		347
253	Scans a directory (similar to C<aio_readdir>) and tries to separate the	348	Scans a directory (similar to C<aio_readdir>) but additionally tries to
254	entries of directory C<$path> into two sets of names, ones you can recurse	349	separate the entries of directory C<$path> into two sets of names, ones
255	into (directories), and ones you cannot recurse into (everything else).	350	you can recurse into (directories or links to them), and ones you cannot
		351	recurse into (everything else).
256		352
257	C<aio_scandir> is a composite request that consists of many	353	C<aio_scandir> is a composite request that consists of many sub
258	aio-primitives. C<$maxreq> specifies the maximum number of outstanding	354	requests. C<$maxreq> specifies the maximum number of outstanding aio
259	aio requests that this function generates. If it is C<< <= 0 >>, then a	355	requests that this function generates. If it is C<< <= 0 >>, then a
260	suitable default will be chosen (currently 8).	356	suitable default will be chosen (currently 8).
261		357
262	On error, the callback is called without arguments, otherwise it receives	358	On error, the callback is called without arguments, otherwise it receives
263	two array-refs with path-relative entry names.	359	two array-refs with path-relative entry names.
264		360
…		…
273	Implementation notes.	369	Implementation notes.
274		370
275	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.	371	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.
276		372
277	After reading the directory, the modification time, size etc. of the	373	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	374	directory before and after the readdir is checked, and if they match (and
279	link count will be used to decide how many entries are directories (if	375	isn't the current time), the link count will be used to decide how many
280	>= 2). Otherwise, no knowledge of the number of subdirectories will be	376	entries are directories (if >= 2). Otherwise, no knowledge of the number
281	assumed.	377	of subdirectories will be assumed.
282		378
283	Then entires will be sorted into likely directories (everything without a	379	Then entries will be sorted into likely directories (everything without
284	non-initial dot) and likely non-directories (everything else). Then every	380	a non-initial dot currently) and likely non-directories (everything
285	entry + C</.> will be C<stat>'ed, likely directories first. This is often	381	else). Then every entry plus an appended C</.> will be C<stat>'ed,
		382	likely directories first. If that succeeds, it assumes that the entry
		383	is a directory or a symlink to directory (which will be checked
		384	seperately). This is often faster than stat'ing the entry itself because
286	faster because filesystems might detect the type of the entry without	385	filesystems might detect the type of the entry without reading the inode
287	reading the inode data (e.g. ext2s filetype feature). If that succeeds,	386	data (e.g. ext2fs filetype feature).
288	it assumes that the entry is a directory or a symlink to directory (which
289	will be checked seperately).
290		387
291	If the known number of directories has been reached, the rest of the	388	If the known number of directories (link count - 2) has been reached, the
292	entries is assumed to be non-directories.	389	rest of the entries is assumed to be non-directories.
		390
		391	This only works with certainty on POSIX (= UNIX) filesystems, which
		392	fortunately are the vast majority of filesystems around.
		393
		394	It will also likely work on non-POSIX filesystems with reduced efficiency
		395	as those tend to return 0 or 1 as link counts, which disables the
		396	directory counting heuristic.
293		397
294	=cut	398	=cut
295		399
296	sub aio_scandir($$$) {	400	sub aio_scandir($$$) {
297	my ($path, $maxreq, $cb) = @_;	401	my ($path, $maxreq, $cb) = @_;
298		402
		403	my $grp = aio_group;
		404
299	$maxreq = 8 if $maxreq <= 0;	405	$maxreq = 8 if $maxreq <= 0;
300		406
301	# stat once	407	# stat once
302	aio_stat $path, sub {	408	add $grp aio_stat $path, sub {
303	$cb->() if $_[0];	409	return $cb->() if $_[0];
		410	my $now = time;
304	my $hash1 = join ":", (stat _)[0,1,3,7,9];	411	my $hash1 = join ":", (stat _)[0,1,3,7,9];
305		412
306	# read the directory entries	413	# read the directory entries
307	aio_readdir $path, sub {	414	add $grp aio_readdir $path, sub {
308	my $entries = shift	415	my $entries = shift
309	or return $cb->();	416	or return $cb->();
310		417
311	# stat the dir another time	418	# stat the dir another time
312	aio_stat $path, sub {	419	add $grp aio_stat $path, sub {
313	my $hash2 = join ":", (stat _)[0,1,3,7,9];	420	my $hash2 = join ":", (stat _)[0,1,3,7,9];
314		421
315	my $ndirs;	422	my $ndirs;
316		423
317	# take the slow route if anything looks fishy	424	# take the slow route if anything looks fishy
318	if ($hash1 ne $hash2) {	425	if ($hash1 ne $hash2 or (stat _)[9] == $now) {
319	$ndirs = -1;	426	$ndirs = -1;
320	} else {	427	} else {
321	# if nlink == 2, we are finished	428	# if nlink == 2, we are finished
322	# on non-posix-fs's, we rely on nlink < 2	429	# on non-posix-fs's, we rely on nlink < 2
323	$ndirs = (stat _)[3] - 2	430	$ndirs = (stat _)[3] - 2
…		…
339	$schedcb = sub {	446	$schedcb = sub {
340	if (@$entries) {	447	if (@$entries) {
341	if ($nreq < $maxreq) {	448	if ($nreq < $maxreq) {
342	my $ent = pop @$entries;	449	my $ent = pop @$entries;
343	$nreq++;	450	$nreq++;
344	aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) };	451	add $grp aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) };
345	}	452	}
346	} elsif (!$nreq) {	453	} elsif (!$nreq) {
347	# finished	454	# finished
348	undef $statcb;	455	undef $statcb;
349	undef $schedcb;	456	undef $schedcb;
350	$cb->(\@dirs, \@nondirs);	457	$cb->(\@dirs, \@nondirs) if $cb;
351	undef $cb;	458	undef $cb;
352	}	459	}
353	};	460	};
354	$statcb = sub {	461	$statcb = sub {
355	my ($status, $entry) = @_;	462	my ($status, $entry) = @_;
…		…
358	$nreq--;	465	$nreq--;
359	push @nondirs, $entry;	466	push @nondirs, $entry;
360	&$schedcb;	467	&$schedcb;
361	} else {	468	} else {
362	# need to check for real directory	469	# need to check for real directory
363	aio_lstat "$path/$entry", sub {	470	add $grp aio_lstat "$path/$entry", sub {
364	$nreq--;	471	$nreq--;
365		472
366	if (-d _) {	473	if (-d _) {
367	push @dirs, $entry;	474	push @dirs, $entry;
368		475
…		…
381		488
382	&$schedcb while @$entries && $nreq < $maxreq;	489	&$schedcb while @$entries && $nreq < $maxreq;
383	};	490	};
384	};	491	};
385	};	492	};
		493
		494	$grp
386	}	495	}
387		496
388	=item aio_fsync $fh, $callback->($status)	497	=item aio_fsync $fh, $callback->($status)
389		498
390	Asynchronously call fsync on the given filehandle and call the callback	499	Asynchronously call fsync on the given filehandle and call the callback
…		…
395	Asynchronously call fdatasync on the given filehandle and call the	504	Asynchronously call fdatasync on the given filehandle and call the
396	callback with the fdatasync result code.	505	callback with the fdatasync result code.
397		506
398	If this call isn't available because your OS lacks it or it couldn't be	507	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.	508	detected, it will be emulated by calling C<fsync> instead.
		509
		510	=item aio_group $callback->()
		511
		512	[EXPERIMENTAL]
		513
		514	This is a very special aio request: Instead of doing something, it is a
		515	container for other aio requests, which is useful if you want to bundle
		516	many requests into a single, composite, request.
		517
		518	Returns an object of class L<IO::AIO::GRP>. See its documentation below
		519	for more info.
		520
		521	Example:
		522
		523	my $grp = aio_group sub {
		524	print "all stats done\n";
		525	};
		526
		527	add $grp
		528	(aio_stat ...),
		529	(aio_stat ...),
		530	...;
		531
		532	=item IO::AIO::aio_sleep $fractional_seconds, $callback->() NOT EXPORTED
		533
		534	Mainly used for debugging and benchmarking, this aio request puts one of
		535	the request workers to sleep for the given time.
		536
		537	While it is theoretically handy to have simple I/O scheduling requests
		538	like sleep and file handle readable/writable, the overhead this creates
		539	is immense, so do not use this function except to put your application
		540	under artificial I/O pressure.
		541
		542	=back
		543
		544	=head2 IO::AIO::REQ CLASS
		545
		546	All non-aggregate C<aio_*> functions return an object of this class when
		547	called in non-void context.
		548
		549	A request always moves through the following five states in its lifetime,
		550	in order: B<ready> (request has been created, but has not been executed
		551	yet), B<execute> (request is currently being executed), B<pending>
		552	(request has been executed but callback has not been called yet),
		553	B<result> (results are being processed synchronously, includes calling the
		554	callback) and B<done> (request has reached the end of its lifetime and
		555	holds no resources anymore).
		556
		557	=over 4
		558
		559	=item $req->cancel
		560
		561	Cancels the request, if possible. Has the effect of skipping execution
		562	when entering the B<execute> state and skipping calling the callback when
		563	entering the the B<result> state, but will leave the request otherwise
		564	untouched. That means that requests that currently execute will not be
		565	stopped and resources held by the request will not be freed prematurely.
		566
		567	=back
		568
		569	=head2 IO::AIO::GRP CLASS
		570
		571	This class is a subclass of L<IO::AIO::REQ>, so all its methods apply to
		572	objects of this class, too.
		573
		574	A IO::AIO::GRP object is a special request that can contain multiple other
		575	aio requests.
		576
		577	You create one by calling the C<aio_group> constructing function with a
		578	callback that will be called when all contained requests have entered the
		579	C<done> state:
		580
		581	my $grp = aio_group sub {
		582	print "all requests are done\n";
		583	};
		584
		585	You add requests by calling the C<add> method with one or more
		586	C<IO::AIO::REQ> objects:
		587
		588	$grp->add (aio_unlink "...");
		589
		590	add $grp aio_stat "...", sub { ... };
		591
		592	This makes it very easy to create composite requests (see the source of
		593	C<aio_move> for an application) that work and feel like simple requests.
		594
		595	The IO::AIO::GRP objects will be cleaned up during calls to
		596	C<IO::AIO::poll_cb>, just like any other request.
		597
		598	They can be canceled like any other request. Canceling will cancel not
		599	just the request itself, but also all requests it contains.
		600
		601	They can also can also be added to other IO::AIO::GRP objects.
		602
		603	Their lifetime, simplified, looks like this: when they are empty, they
		604	will finish very quickly. If they contain only requests that are in the
		605	C<done> state, they will also finish. Otherwise they will continue to
		606	exist.
		607
		608	=over 4
		609
		610	=item $grp->add (...)
		611
		612	=item add $grp ...
		613
		614	Add one or more
		615	Cancels the request, if possible. Has the effect of skipping execution
		616	when entering the B<execute> state and skipping calling the callback when
		617	entering the the B<result> state, but will leave the request otherwise
		618	untouched. That means that requests that currently execute will not be
		619	stopped and resources held by the request will not be freed prematurely.
400		620
401	=back	621	=back
402		622
403	=head2 SUPPORT FUNCTIONS	623	=head2 SUPPORT FUNCTIONS
404		624
…		…
532	}	752	}
533		753
534	1;	754	1;
535		755
536	=head2 FORK BEHAVIOUR	756	=head2 FORK BEHAVIOUR
		757
		758	This module should do "the right thing" when the process using it forks:
537		759
538	Before the fork, IO::AIO enters a quiescent state where no requests	760	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	761	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	762	the fork the parent simply leaves the quiescent state and continues
541	request/result processing, while the child clears the request/result	763	request/result processing, while the child clears the request/result
542	queue (so the requests started before the fork will only be handled in	764	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	765	the parent). Threads will be started on demand until the limit ste in the
544	parent process has been reached again.	766	parent process has been reached again.
545		767
		768	In short: the parent will, after a short pause, continue as if fork had
		769	not been called, while the child will act as if IO::AIO has not been used
		770	yet.
		771
546	=head1 SEE ALSO	772	=head1 SEE ALSO
547		773
548	L<Coro>, L<Linux::AIO>.	774	L<Coro>, L<Linux::AIO> (obsolete).
549		775
550	=head1 AUTHOR	776	=head1 AUTHOR
551		777
552	Marc Lehmann <schmorp@schmorp.de>	778	Marc Lehmann <schmorp@schmorp.de>
553	http://home.schmorp.de/	779	http://home.schmorp.de/

Diff Legend

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

Comparing IO-AIO/AIO.pm (file contents): Revision 1.43 by root, Mon Dec 26 18:18:32 2005 UTC vs. Revision 1.56 by root, Sun Oct 22 00:53:47 2006 UTC

Diff Legend

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.43 by root, Mon Dec 26 18:18:32 2005 UTC vs.
Revision 1.56 by root, Sun Oct 22 00:53:47 2006 UTC