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

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.34 by root, Thu Aug 18 16:32:10 2005 UTC vs.
Revision 1.54 by root, Sun Oct 22 00:19:05 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	use IO::AIO 2; # version has aio objects
		21
		22	my $req = aio_unlink "/tmp/file", sub { };
		23	$req->cancel; # cancel request if still in queue
		24
		25	# AnyEvent
		26	open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!";
		27	my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb });
19		28
20	# Event	29	# Event
21	Event->io (fd => IO::AIO::poll_fileno,	30	Event->io (fd => IO::AIO::poll_fileno,
22	poll => 'r',	31	poll => 'r',
23	cb => \&IO::AIO::poll_cb);	32	cb => \&IO::AIO::poll_cb);
…		…
57	=cut	66	=cut
58		67
59	package IO::AIO;	68	package IO::AIO;
60		69
61	no warnings;	70	no warnings;
		71	use strict 'vars';
62		72
63	use base 'Exporter';	73	use base 'Exporter';
64		74
65	use Fcntl ();
66
67	BEGIN {	75	BEGIN {
68	$VERSION = 1.5;	76	our $VERSION = '1.99';
69		77
70	@EXPORT = qw(aio_read aio_write aio_open aio_close aio_stat aio_lstat aio_unlink	78	our @EXPORT = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat
71	aio_rmdir aio_symlink aio_fsync aio_fdatasync aio_readahead);	79	aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink
		80	aio_fsync aio_fdatasync aio_readahead aio_rename aio_link aio_move
		81	aio_group);
72	@EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs);	82	our @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs);
		83
		84	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';
73		85
74	require XSLoader;	86	require XSLoader;
75	XSLoader::load IO::AIO, $VERSION;	87	XSLoader::load ("IO::AIO", $VERSION);
76	}	88	}
77		89
78	=head1 FUNCTIONS	90	=head1 FUNCTIONS
79		91
80	=head2 AIO FUNCTIONS	92	=head2 AIO FUNCTIONS
…		…
88	syscall has been executed asynchronously.	100	syscall has been executed asynchronously.
89		101
90	All functions expecting a filehandle keep a copy of the filehandle	102	All functions expecting a filehandle keep a copy of the filehandle
91	internally until the request has finished.	103	internally until the request has finished.
92		104
		105	All non-composite requests (requests that are not broken down into
		106	multiple requests) return objects of type L<IO::AIO::REQ> that allow
		107	further manipulation of running requests.
		108
93	The pathnames you pass to these routines I<must> be absolute and	109	The pathnames you pass to these routines I<must> be absolute and
94	encoded in byte form. The reason for the former is that at the time the	110	encoded in byte form. The reason for the former is that at the time the
95	request is being executed, the current working directory could have	111	request is being executed, the current working directory could have
96	changed. Alternatively, you can make sure that you never change the	112	changed. Alternatively, you can make sure that you never change the
97	current working directory.	113	current working directory.
…		…
103	environment, d) use Glib::filename_from_unicode on unicode filenames or e)	119	environment, d) use Glib::filename_from_unicode on unicode filenames or e)
104	use something else.	120	use something else.
105		121
106	=over 4	122	=over 4
107		123
108	=item aio_open $pathname, $flags, $mode, $callback	124	=item aio_open $pathname, $flags, $mode, $callback->($fh)
109		125
110	Asynchronously open or create a file and call the callback with a newly	126	Asynchronously open or create a file and call the callback with a newly
111	created filehandle for the file.	127	created filehandle for the file.
112		128
113	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,	129	The pathname passed to C<aio_open> must be absolute. See API NOTES, above,
…		…
130	} else {	146	} else {
131	die "open failed: $!\n";	147	die "open failed: $!\n";
132	}	148	}
133	};	149	};
134		150
135	=item aio_close $fh, $callback	151	=item aio_close $fh, $callback->($status)
136		152
137	Asynchronously close a file and call the callback with the result	153	Asynchronously close a file and call the callback with the result
138	code. I<WARNING:> although accepted, you should not pass in a perl	154	code. I<WARNING:> although accepted, you should not pass in a perl
139	filehandle here, as perl will likely close the file descriptor another	155	filehandle here, as perl will likely close the file descriptor another
140	time when the filehandle is destroyed. Normally, you can safely call perls	156	time when the filehandle is destroyed. Normally, you can safely call perls
141	C<close> or just let filehandles go out of scope.	157	C<close> or just let filehandles go out of scope.
142		158
143	This is supposed to be a bug in the API, so that might change. It's	159	This is supposed to be a bug in the API, so that might change. It's
144	therefore best to avoid this function.	160	therefore best to avoid this function.
145		161
146	=item aio_read $fh,$offset,$length, $data,$dataoffset,$callback	162	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
147		163
148	=item aio_write $fh,$offset,$length, $data,$dataoffset,$callback	164	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
149		165
150	Reads or writes C<length> bytes from the specified C<fh> and C<offset>	166	Reads or writes C<length> bytes from the specified C<fh> and C<offset>
151	into the scalar given by C<data> and offset C<dataoffset> and calls the	167	into the scalar given by C<data> and offset C<dataoffset> and calls the
152	callback without the actual number of bytes read (or -1 on error, just	168	callback without the actual number of bytes read (or -1 on error, just
153	like the syscall).	169	like the syscall).
…		…
162	aio_read $fh, 7, 15, $buffer, 0, sub {	178	aio_read $fh, 7, 15, $buffer, 0, sub {
163	$_[0] > 0 or die "read error: $!";	179	$_[0] > 0 or die "read error: $!";
164	print "read $_[0] bytes: <$buffer>\n";	180	print "read $_[0] bytes: <$buffer>\n";
165	};	181	};
166		182
		183	=item aio_move $srcpath, $dstpath, $callback->($status)
		184
		185	Try to move the I<file> (directories not supported as either source or
		186	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		187	the C<0> (error) or C<-1> ok.
		188
		189	This is a composite request that tries to rename(2) the file first. If
		190	rename files with C<EXDEV>, it creates the destination file with mode 0200
		191	and copies the contents of the source file into it using C<aio_sendfile>,
		192	followed by restoring atime, mtime, access mode and uid/gid, in that
		193	order, and unlinking the C<$srcpath>.
		194
		195	If an error occurs, the partial destination file will be unlinked, if
		196	possible, except when setting atime, mtime, access mode and uid/gid, where
		197	errors are being ignored.
		198
		199	=cut
		200
		201	sub aio_move($$$) {
		202	my ($src, $dst, $cb) = @_;
		203
		204	aio_rename $src, $dst, sub {
		205	if ($_[0] && $! == EXDEV) {
		206	aio_open $src, O_RDONLY, 0, sub {
		207	if (my $src_fh = $_[0]) {
		208	my @stat = stat $src_fh;
		209
		210	aio_open $dst, O_WRONLY, 0200, sub {
		211	if (my $dst_fh = $_[0]) {
		212	aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
		213	close $src_fh;
		214
		215	if ($_[0] == $stat[7]) {
		216	utime $stat[8], $stat[9], $dst;
		217	chmod $stat[2] & 07777, $dst_fh;
		218	chown $stat[4], $stat[5], $dst_fh;
		219	close $dst_fh;
		220
		221	aio_unlink $src, sub {
		222	$cb->($_[0]);
		223	};
		224	} else {
		225	my $errno = $!;
		226	aio_unlink $dst, sub {
		227	$! = $errno;
		228	$cb->(-1);
		229	};
		230	}
		231	};
		232	} else {
		233	$cb->(-1);
		234	}
		235	},
		236
		237	} else {
		238	$cb->(-1);
		239	}
		240	};
		241	} else {
		242	$cb->($_[0]);
		243	}
		244	};
		245	}
		246
		247	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
		248
		249	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
		250	reading at byte offset C<$in_offset>, and starts writing at the current
		251	file offset of C<$out_fh>. Because of that, it is not safe to issue more
		252	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each
		253	other.
		254
		255	This call tries to make use of a native C<sendfile> syscall to provide
		256	zero-copy operation. For this to work, C<$out_fh> should refer to a
		257	socket, and C<$in_fh> should refer to mmap'able file.
		258
		259	If the native sendfile call fails or is not implemented, it will be
		260	emulated, so you can call C<aio_sendfile> on any type of filehandle
		261	regardless of the limitations of the operating system.
		262
		263	Please note, however, that C<aio_sendfile> can read more bytes from
		264	C<$in_fh> than are written, and there is no way to find out how many
		265	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only
		266	provides the number of bytes written to C<$out_fh>. Only if the result
		267	value equals C<$length> one can assume that C<$length> bytes have been
		268	read.
		269
167	=item aio_readahead $fh,$offset,$length, $callback	270	=item aio_readahead $fh,$offset,$length, $callback->($retval)
168		271
169	C<aio_readahead> populates the page cache with data from a file so that	272	C<aio_readahead> populates the page cache with data from a file so that
170	subsequent reads from that file will not block on disk I/O. The C<$offset>	273	subsequent reads from that file will not block on disk I/O. The C<$offset>
171	argument specifies the starting point from which data is to be read and	274	argument specifies the starting point from which data is to be read and
172	C<$length> specifies the number of bytes to be read. I/O is performed in	275	C<$length> specifies the number of bytes to be read. I/O is performed in
…		…
176	file. The current file offset of the file is left unchanged.	279	file. The current file offset of the file is left unchanged.
177		280
178	If that syscall doesn't exist (likely if your OS isn't Linux) it will be	281	If that syscall doesn't exist (likely if your OS isn't Linux) it will be
179	emulated by simply reading the data, which would have a similar effect.	282	emulated by simply reading the data, which would have a similar effect.
180		283
181	=item aio_stat $fh_or_path, $callback	284	=item aio_stat $fh_or_path, $callback->($status)
182		285
183	=item aio_lstat $fh, $callback	286	=item aio_lstat $fh, $callback->($status)
184		287
185	Works like perl's C<stat> or C<lstat> in void context. The callback will	288	Works like perl's C<stat> or C<lstat> in void context. The callback will
186	be called after the stat and the results will be available using C<stat _>	289	be called after the stat and the results will be available using C<stat _>
187	or C<-s _> etc...	290	or C<-s _> etc...
188		291
…		…
198	aio_stat "/etc/passwd", sub {	301	aio_stat "/etc/passwd", sub {
199	$_[0] and die "stat failed: $!";	302	$_[0] and die "stat failed: $!";
200	print "size is ", -s _, "\n";	303	print "size is ", -s _, "\n";
201	};	304	};
202		305
203	=item aio_unlink $pathname, $callback	306	=item aio_unlink $pathname, $callback->($status)
204		307
205	Asynchronously unlink (delete) a file and call the callback with the	308	Asynchronously unlink (delete) a file and call the callback with the
206	result code.	309	result code.
207		310
		311	=item aio_link $srcpath, $dstpath, $callback->($status)
		312
		313	Asynchronously create a new link to the existing object at C<$srcpath> at
		314	the path C<$dstpath> and call the callback with the result code.
		315
		316	=item aio_symlink $srcpath, $dstpath, $callback->($status)
		317
		318	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at
		319	the path C<$dstpath> and call the callback with the result code.
		320
		321	=item aio_rename $srcpath, $dstpath, $callback->($status)
		322
		323	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as
		324	rename(2) and call the callback with the result code.
		325
208	=item aio_rmdir $pathname, $callback	326	=item aio_rmdir $pathname, $callback->($status)
209		327
210	Asynchronously rmdir (delete) a directory and call the callback with the	328	Asynchronously rmdir (delete) a directory and call the callback with the
211	result code.	329	result code.
212		330
		331	=item aio_readdir $pathname, $callback->($entries)
		332
		333	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
		334	directory (i.e. opendir + readdir + closedir). The entries will not be
		335	sorted, and will B<NOT> include the C<.> and C<..> entries.
		336
		337	The callback a single argument which is either C<undef> or an array-ref
		338	with the filenames.
		339
		340	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
		341
		342	Scans a directory (similar to C<aio_readdir>) but additionally tries to
		343	separate the entries of directory C<$path> into two sets of names, ones
		344	you can recurse into (directories or links to them), and ones you cannot
		345	recurse into (everything else).
		346
		347	C<aio_scandir> is a composite request that consists of many sub
		348	requests. C<$maxreq> specifies the maximum number of outstanding aio
		349	requests that this function generates. If it is C<< <= 0 >>, then a
		350	suitable default will be chosen (currently 8).
		351
		352	On error, the callback is called without arguments, otherwise it receives
		353	two array-refs with path-relative entry names.
		354
		355	Example:
		356
		357	aio_scandir $dir, 0, sub {
		358	my ($dirs, $nondirs) = @_;
		359	print "real directories: @$dirs\n";
		360	print "everything else: @$nondirs\n";
		361	};
		362
		363	Implementation notes.
		364
		365	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.
		366
		367	After reading the directory, the modification time, size etc. of the
		368	directory before and after the readdir is checked, and if they match (and
		369	isn't the current time), the link count will be used to decide how many
		370	entries are directories (if >= 2). Otherwise, no knowledge of the number
		371	of subdirectories will be assumed.
		372
		373	Then entries will be sorted into likely directories (everything without
		374	a non-initial dot currently) and likely non-directories (everything
		375	else). Then every entry plus an appended C</.> will be C<stat>'ed,
		376	likely directories first. If that succeeds, it assumes that the entry
		377	is a directory or a symlink to directory (which will be checked
		378	seperately). This is often faster than stat'ing the entry itself because
		379	filesystems might detect the type of the entry without reading the inode
		380	data (e.g. ext2fs filetype feature).
		381
		382	If the known number of directories (link count - 2) has been reached, the
		383	rest of the entries is assumed to be non-directories.
		384
		385	This only works with certainty on POSIX (= UNIX) filesystems, which
		386	fortunately are the vast majority of filesystems around.
		387
		388	It will also likely work on non-POSIX filesystems with reduced efficiency
		389	as those tend to return 0 or 1 as link counts, which disables the
		390	directory counting heuristic.
		391
		392	=cut
		393
		394	sub aio_scandir($$$) {
		395	my ($path, $maxreq, $cb) = @_;
		396
		397	$maxreq = 8 if $maxreq <= 0;
		398
		399	# stat once
		400	aio_stat $path, sub {
		401	return $cb->() if $_[0];
		402	my $now = time;
		403	my $hash1 = join ":", (stat _)[0,1,3,7,9];
		404
		405	# read the directory entries
		406	aio_readdir $path, sub {
		407	my $entries = shift
		408	or return $cb->();
		409
		410	# stat the dir another time
		411	aio_stat $path, sub {
		412	my $hash2 = join ":", (stat _)[0,1,3,7,9];
		413
		414	my $ndirs;
		415
		416	# take the slow route if anything looks fishy
		417	if ($hash1 ne $hash2 or (stat _)[9] == $now) {
		418	$ndirs = -1;
		419	} else {
		420	# if nlink == 2, we are finished
		421	# on non-posix-fs's, we rely on nlink < 2
		422	$ndirs = (stat _)[3] - 2
		423	or return $cb->([], $entries);
		424	}
		425
		426	# sort into likely dirs and likely nondirs
		427	# dirs == files without ".", short entries first
		428	$entries = [map $_->[0],
		429	sort { $b->[1] cmp $a->[1] }
		430	map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],
		431	@$entries];
		432
		433	my (@dirs, @nondirs);
		434
		435	my ($statcb, $schedcb);
		436	my $nreq = 0;
		437
		438	$schedcb = sub {
		439	if (@$entries) {
		440	if ($nreq < $maxreq) {
		441	my $ent = pop @$entries;
		442	$nreq++;
		443	aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) };
		444	}
		445	} elsif (!$nreq) {
		446	# finished
		447	undef $statcb;
		448	undef $schedcb;
		449	$cb->(\@dirs, \@nondirs) if $cb;
		450	undef $cb;
		451	}
		452	};
		453	$statcb = sub {
		454	my ($status, $entry) = @_;
		455
		456	if ($status < 0) {
		457	$nreq--;
		458	push @nondirs, $entry;
		459	&$schedcb;
		460	} else {
		461	# need to check for real directory
		462	aio_lstat "$path/$entry", sub {
		463	$nreq--;
		464
		465	if (-d _) {
		466	push @dirs, $entry;
		467
		468	if (!--$ndirs) {
		469	push @nondirs, @$entries;
		470	$entries = [];
		471	}
		472	} else {
		473	push @nondirs, $entry;
		474	}
		475
		476	&$schedcb;
		477	}
		478	}
		479	};
		480
		481	&$schedcb while @$entries && $nreq < $maxreq;
		482	};
		483	};
		484	};
		485	}
		486
213	=item aio_fsync $fh, $callback	487	=item aio_fsync $fh, $callback->($status)
214		488
215	Asynchronously call fsync on the given filehandle and call the callback	489	Asynchronously call fsync on the given filehandle and call the callback
216	with the fsync result code.	490	with the fsync result code.
217		491
218	=item aio_fdatasync $fh, $callback	492	=item aio_fdatasync $fh, $callback->($status)
219		493
220	Asynchronously call fdatasync on the given filehandle and call the	494	Asynchronously call fdatasync on the given filehandle and call the
221	callback with the fdatasync result code.	495	callback with the fdatasync result code.
222		496
223	If this call isn't available because your OS lacks it or it couldn't be	497	If this call isn't available because your OS lacks it or it couldn't be
224	detected, it will be emulated by calling C<fsync> instead.	498	detected, it will be emulated by calling C<fsync> instead.
		499
		500	=item aio_group $callback->()
		501
		502	=item aio_sleep $fractional_seconds, $callback->() NOT EXPORTED
		503
		504	Mainly used for debugging and benchmarking, this aio request puts one of
		505	the request workers to sleep for the given time.
		506
		507	=back
		508
		509	=head2 IO::AIO::REQ CLASS
		510
		511	All non-aggregate C<aio_*> functions return an object of this class when
		512	called in non-void context.
		513
		514	A request always moves through the following five states in its lifetime,
		515	in order: B<ready> (request has been created, but has not been executed
		516	yet), B<execute> (request is currently being executed), B<pending>
		517	(request has been executed but callback has not been called yet),
		518	B<result> (results are being processed synchronously, includes calling the
		519	callback) and B<done> (request has reached the end of its lifetime and
		520	holds no resources anymore).
		521
		522	=over 4
		523
		524	=item $req->cancel
		525
		526	Cancels the request, if possible. Has the effect of skipping execution
		527	when entering the B<execute> state and skipping calling the callback when
		528	entering the the B<result> state, but will leave the request otherwise
		529	untouched. That means that requests that currently execute will not be
		530	stopped and resources held by the request will not be freed prematurely.
225		531
226	=back	532	=back
227		533
228	=head2 SUPPORT FUNCTIONS	534	=head2 SUPPORT FUNCTIONS
229		535
…		…
357	}	663	}
358		664
359	1;	665	1;
360		666
361	=head2 FORK BEHAVIOUR	667	=head2 FORK BEHAVIOUR
		668
		669	This module should do "the right thing" when the process using it forks:
362		670
363	Before the fork, IO::AIO enters a quiescent state where no requests	671	Before the fork, IO::AIO enters a quiescent state where no requests
364	can be added in other threads and no results will be processed. After	672	can be added in other threads and no results will be processed. After
365	the fork the parent simply leaves the quiescent state and continues	673	the fork the parent simply leaves the quiescent state and continues
366	request/result processing, while the child clears the request/result	674	request/result processing, while the child clears the request/result
367	queue (so the requests started before the fork will only be handled in	675	queue (so the requests started before the fork will only be handled in
368	the parent). Threats will be started on demand until the limit ste in the	676	the parent). Threads will be started on demand until the limit ste in the
369	parent process has been reached again.	677	parent process has been reached again.
370		678
		679	In short: the parent will, after a short pause, continue as if fork had
		680	not been called, while the child will act as if IO::AIO has not been used
		681	yet.
		682
371	=head1 SEE ALSO	683	=head1 SEE ALSO
372		684
373	L<Coro>, L<Linux::AIO>.	685	L<Coro>, L<Linux::AIO> (obsolete).
374		686
375	=head1 AUTHOR	687	=head1 AUTHOR
376		688
377	Marc Lehmann <schmorp@schmorp.de>	689	Marc Lehmann <schmorp@schmorp.de>
378	http://home.schmorp.de/	690	http://home.schmorp.de/

Diff Legend

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

Comparing IO-AIO/AIO.pm (file contents): Revision 1.34 by root, Thu Aug 18 16:32:10 2005 UTC vs. Revision 1.54 by root, Sun Oct 22 00:19:05 2006 UTC

Diff Legend

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.34 by root, Thu Aug 18 16:32:10 2005 UTC vs.
Revision 1.54 by root, Sun Oct 22 00:19:05 2006 UTC