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

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.71 by root, Tue Oct 24 11:57:30 2006 UTC vs.
Revision 1.113 by root, Thu Sep 20 14:06:21 2007 UTC

…		…
5	=head1 SYNOPSIS	5	=head1 SYNOPSIS
6		6
7	use IO::AIO;	7	use IO::AIO;
8		8
9	aio_open "/etc/passwd", O_RDONLY, 0, sub {	9	aio_open "/etc/passwd", O_RDONLY, 0, sub {
10	my ($fh) = @_;	10	my $fh = shift
		11	or die "/etc/passwd: $!";
11	...	12	...
12	};	13	};
13		14
14	aio_unlink "/tmp/file", sub { };	15	aio_unlink "/tmp/file", sub { };
15		16
…		…
51	=head1 DESCRIPTION	52	=head1 DESCRIPTION
52		53
53	This module implements asynchronous I/O using whatever means your	54	This module implements asynchronous I/O using whatever means your
54	operating system supports.	55	operating system supports.
55		56
		57	Asynchronous means that operations that can normally block your program
		58	(e.g. reading from disk) will be done asynchronously: the operation
		59	will still block, but you can do something else in the meantime. This
		60	is extremely useful for programs that need to stay interactive even
		61	when doing heavy I/O (GUI programs, high performance network servers
		62	etc.), but can also be used to easily do operations in parallel that are
		63	normally done sequentially, e.g. stat'ing many files, which is much faster
		64	on a RAID volume or over NFS when you do a number of stat operations
		65	concurrently.
		66
		67	While most of this works on all types of file descriptors (for
		68	example sockets), using these functions on file descriptors that
		69	support nonblocking operation (again, sockets, pipes etc.) is very
		70	inefficient. Use an event loop for that (such as the L<Event\|Event>
		71	module): IO::AIO will naturally fit into such an event loop itself.
		72
56	Currently, a number of threads are started that execute your read/writes	73	In this version, a number of threads are started that execute your
57	and signal their completion. You don't need thread support in perl, and	74	requests and signal their completion. You don't need thread support
58	the threads created by this module will not be visible to perl. In the	75	in perl, and the threads created by this module will not be visible
59	future, this module might make use of the native aio functions available	76	to perl. In the future, this module might make use of the native aio
60	on many operating systems. However, they are often not well-supported	77	functions available on many operating systems. However, they are often
61	(Linux doesn't allow them on normal files currently, for example),	78	not well-supported or restricted (GNU/Linux doesn't allow them on normal
62	and they would only support aio_read and aio_write, so the remaining	79	files currently, for example), and they would only support aio_read and
63	functionality would have to be implemented using threads anyway.	80	aio_write, so the remaining functionality would have to be implemented
		81	using threads anyway.
64		82
65	Although the module will work with in the presence of other threads,	83	Although the module will work in the presence of other (Perl-) threads,
66	it is currently not reentrant in any way, so use appropriate locking	84	it is currently not reentrant in any way, so use appropriate locking
67	yourself, always call C<poll_cb> from within the same thread, or never	85	yourself, always call C<poll_cb> from within the same thread, or never
68	call C<poll_cb> (or other C<aio_> functions) recursively.	86	call C<poll_cb> (or other C<aio_> functions) recursively.
69		87
		88	=head2 EXAMPLE
		89
		90	This is a simple example that uses the Event module and loads
		91	F</etc/passwd> asynchronously:
		92
		93	use Fcntl;
		94	use Event;
		95	use IO::AIO;
		96
		97	# register the IO::AIO callback with Event
		98	Event->io (fd => IO::AIO::poll_fileno,
		99	poll => 'r',
		100	cb => \&IO::AIO::poll_cb);
		101
		102	# queue the request to open /etc/passwd
		103	aio_open "/etc/passwd", O_RDONLY, 0, sub {
		104	my $fh = shift
		105	or die "error while opening: $!";
		106
		107	# stat'ing filehandles is generally non-blocking
		108	my $size = -s $fh;
		109
		110	# queue a request to read the file
		111	my $contents;
		112	aio_read $fh, 0, $size, $contents, 0, sub {
		113	$_[0] == $size
		114	or die "short read: $!";
		115
		116	close $fh;
		117
		118	# file contents now in $contents
		119	print $contents;
		120
		121	# exit event loop and program
		122	Event::unloop;
		123	};
		124	};
		125
		126	# possibly queue up other requests, or open GUI windows,
		127	# check for sockets etc. etc.
		128
		129	# process events as long as there are some:
		130	Event::loop;
		131
		132	=head1 REQUEST ANATOMY AND LIFETIME
		133
		134	Every C<aio_*> function creates a request. which is a C data structure not
		135	directly visible to Perl.
		136
		137	If called in non-void context, every request function returns a Perl
		138	object representing the request. In void context, nothing is returned,
		139	which saves a bit of memory.
		140
		141	The perl object is a fairly standard ref-to-hash object. The hash contents
		142	are not used by IO::AIO so you are free to store anything you like in it.
		143
		144	During their existance, aio requests travel through the following states,
		145	in order:
		146
		147	=over 4
		148
		149	=item ready
		150
		151	Immediately after a request is created it is put into the ready state,
		152	waiting for a thread to execute it.
		153
		154	=item execute
		155
		156	A thread has accepted the request for processing and is currently
		157	executing it (e.g. blocking in read).
		158
		159	=item pending
		160
		161	The request has been executed and is waiting for result processing.
		162
		163	While request submission and execution is fully asynchronous, result
		164	processing is not and relies on the perl interpreter calling C<poll_cb>
		165	(or another function with the same effect).
		166
		167	=item result
		168
		169	The request results are processed synchronously by C<poll_cb>.
		170
		171	The C<poll_cb> function will process all outstanding aio requests by
		172	calling their callbacks, freeing memory associated with them and managing
		173	any groups they are contained in.
		174
		175	=item done
		176
		177	Request has reached the end of its lifetime and holds no resources anymore
		178	(except possibly for the Perl object, but its connection to the actual
		179	aio request is severed and calling its methods will either do nothing or
		180	result in a runtime error).
		181
		182	=back
		183
70	=cut	184	=cut
71		185
72	package IO::AIO;	186	package IO::AIO;
73		187
74	no warnings;	188	no warnings;
75	use strict 'vars';	189	use strict 'vars';
76		190
77	use base 'Exporter';	191	use base 'Exporter';
78		192
79	BEGIN {	193	BEGIN {
80	our $VERSION = '2.0';	194	our $VERSION = '2.4';
81		195
82	our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat	196	our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat
83	aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink	197	aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink
84	aio_fsync aio_fdatasync aio_readahead aio_rename aio_link aio_move	198	aio_readlink aio_fsync aio_fdatasync aio_readahead aio_rename aio_link
85	aio_group aio_nop);	199	aio_move aio_copy aio_group aio_nop aio_mknod aio_load aio_rmtree aio_mkdir
		200	aio_chown aio_chmod aio_utime aio_truncate);
86	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice));	201	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice aio_block));
87	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush	202	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush
88	min_parallel max_parallel max_outstanding nreqs);	203	min_parallel max_parallel max_idle
		204	nreqs nready npending nthreads
		205	max_poll_time max_poll_reqs);
89		206
90	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';	207	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';
91		208
92	require XSLoader;	209	require XSLoader;
93	XSLoader::load ("IO::AIO", $VERSION);	210	XSLoader::load ("IO::AIO", $VERSION);
94	}	211	}
95		212
96	=head1 FUNCTIONS	213	=head1 FUNCTIONS
97		214
98	=head2 AIO FUNCTIONS	215	=head2 AIO REQUEST FUNCTIONS
99		216
100	All the C<aio_*> calls are more or less thin wrappers around the syscall	217	All the C<aio_*> calls are more or less thin wrappers around the syscall
101	with the same name (sans C<aio_>). The arguments are similar or identical,	218	with the same name (sans C<aio_>). The arguments are similar or identical,
102	and they all accept an additional (and optional) C<$callback> argument	219	and they all accept an additional (and optional) C<$callback> argument
103	which must be a code reference. This code reference will get called with	220	which must be a code reference. This code reference will get called with
…		…
106	syscall has been executed asynchronously.	223	syscall has been executed asynchronously.
107		224
108	All functions expecting a filehandle keep a copy of the filehandle	225	All functions expecting a filehandle keep a copy of the filehandle
109	internally until the request has finished.	226	internally until the request has finished.
110		227
111	All requests return objects of type L<IO::AIO::REQ> that allow further	228	All functions return request objects of type L<IO::AIO::REQ> that allow
112	manipulation of those requests while they are in-flight.	229	further manipulation of those requests while they are in-flight.
113		230
114	The pathnames you pass to these routines I<must> be absolute and	231	The pathnames you pass to these routines I<must> be absolute and
115	encoded in byte form. The reason for the former is that at the time the	232	encoded as octets. The reason for the former is that at the time the
116	request is being executed, the current working directory could have	233	request is being executed, the current working directory could have
117	changed. Alternatively, you can make sure that you never change the	234	changed. Alternatively, you can make sure that you never change the
118	current working directory.	235	current working directory anywhere in the program and then use relative
		236	paths.
119		237
120	To encode pathnames to byte form, either make sure you either: a)	238	To encode pathnames as octets, either make sure you either: a) always pass
121	always pass in filenames you got from outside (command line, readdir	239	in filenames you got from outside (command line, readdir etc.) without
122	etc.), b) are ASCII or ISO 8859-1, c) use the Encode module and encode	240	tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module and encode
123	your pathnames to the locale (or other) encoding in effect in the user	241	your pathnames to the locale (or other) encoding in effect in the user
124	environment, d) use Glib::filename_from_unicode on unicode filenames or e)	242	environment, d) use Glib::filename_from_unicode on unicode filenames or e)
125	use something else.	243	use something else to ensure your scalar has the correct contents.
		244
		245	This works, btw. independent of the internal UTF-8 bit, which IO::AIO
		246	handles correctly wether it is set or not.
126		247
127	=over 4	248	=over 4
128		249
129	=item aioreq_pri $pri	250	=item $prev_pri = aioreq_pri [$pri]
130		251
131	Sets the priority for the next aio request. The default priority	252	Returns the priority value that would be used for the next request and, if
		253	C<$pri> is given, sets the priority for the next aio request.
		254
132	is C<0>, the minimum and maximum priorities are C<-4> and C<4>,	255	The default priority is C<0>, the minimum and maximum priorities are C<-4>
133	respectively. Requests with higher priority will be serviced first.	256	and C<4>, respectively. Requests with higher priority will be serviced
		257	first.
134		258
135	The priority will be reset to C<0> after each call to one of the C<aio_>	259	The priority will be reset to C<0> after each call to one of the C<aio_*>
136	functions.	260	functions.
137		261
138	Example: open a file with low priority, then read something from it with	262	Example: open a file with low priority, then read something from it with
139	higher priority so the read request is serviced before other low priority	263	higher priority so the read request is serviced before other low priority
140	open requests (potentially spamming the cache):	264	open requests (potentially spamming the cache):
…		…
147	aio_read $_[0], ..., sub {	271	aio_read $_[0], ..., sub {
148	...	272	...
149	};	273	};
150	};	274	};
151		275
		276
152	=item aioreq_nice $pri_adjust	277	=item aioreq_nice $pri_adjust
153		278
154	Similar to C<aioreq_pri>, but subtracts the given value from the current	279	Similar to C<aioreq_pri>, but subtracts the given value from the current
155	priority, so effects are cumulative.	280	priority, so the effect is cumulative.
		281
156		282
157	=item aio_open $pathname, $flags, $mode, $callback->($fh)	283	=item aio_open $pathname, $flags, $mode, $callback->($fh)
158		284
159	Asynchronously open or create a file and call the callback with a newly	285	Asynchronously open or create a file and call the callback with a newly
160	created filehandle for the file.	286	created filehandle for the file.
…		…
166	list. They are the same as used by C<sysopen>.	292	list. They are the same as used by C<sysopen>.
167		293
168	Likewise, C<$mode> specifies the mode of the newly created file, if it	294	Likewise, C<$mode> specifies the mode of the newly created file, if it
169	didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,	295	didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,
170	except that it is mandatory (i.e. use C<0> if you don't create new files,	296	except that it is mandatory (i.e. use C<0> if you don't create new files,
171	and C<0666> or C<0777> if you do).	297	and C<0666> or C<0777> if you do). Note that the C<$mode> will be modified
		298	by the umask in effect then the request is being executed, so better never
		299	change the umask.
172		300
173	Example:	301	Example:
174		302
175	aio_open "/etc/passwd", O_RDONLY, 0, sub {	303	aio_open "/etc/passwd", O_RDONLY, 0, sub {
176	if ($_[0]) {	304	if ($_[0]) {
…		…
179	} else {	307	} else {
180	die "open failed: $!\n";	308	die "open failed: $!\n";
181	}	309	}
182	};	310	};
183		311
		312
184	=item aio_close $fh, $callback->($status)	313	=item aio_close $fh, $callback->($status)
185		314
186	Asynchronously close a file and call the callback with the result	315	Asynchronously close a file and call the callback with the result
187	code. I<WARNING:> although accepted, you should not pass in a perl	316	code. I<WARNING:> although accepted, you should not pass in a perl
188	filehandle here, as perl will likely close the file descriptor another	317	filehandle here, as perl will likely close the file descriptor another
…		…
190	C<close> or just let filehandles go out of scope.	319	C<close> or just let filehandles go out of scope.
191		320
192	This is supposed to be a bug in the API, so that might change. It's	321	This is supposed to be a bug in the API, so that might change. It's
193	therefore best to avoid this function.	322	therefore best to avoid this function.
194		323
		324
195	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	325	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
196		326
197	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	327	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
198		328
199	Reads or writes C<length> bytes from the specified C<fh> and C<offset>	329	Reads or writes C<$length> bytes from the specified C<$fh> and C<$offset>
200	into the scalar given by C<data> and offset C<dataoffset> and calls the	330	into the scalar given by C<$data> and offset C<$dataoffset> and calls the
201	callback without the actual number of bytes read (or -1 on error, just	331	callback without the actual number of bytes read (or -1 on error, just
202	like the syscall).	332	like the syscall).
203		333
		334	If C<$offset> is undefined, then the current file descriptor offset will
		335	be used (and updated), otherwise the file descriptor offset will not be
		336	changed by these calls.
		337
		338	If C<$length> is undefined in C<aio_write>, use the remaining length of C<$data>.
		339
		340	If C<$dataoffset> is less than zero, it will be counted from the end of
		341	C<$data>.
		342
204	The C<$data> scalar I<MUST NOT> be modified in any way while the request	343	The C<$data> scalar I<MUST NOT> be modified in any way while the request
205	is outstanding. Modifying it can result in segfaults or WW3 (if the	344	is outstanding. Modifying it can result in segfaults or World War III (if
206	necessary/optional hardware is installed).	345	the necessary/optional hardware is installed).
207		346
208	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at	347	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at
209	offset C<0> within the scalar:	348	offset C<0> within the scalar:
210		349
211	aio_read $fh, 7, 15, $buffer, 0, sub {	350	aio_read $fh, 7, 15, $buffer, 0, sub {
212	$_[0] > 0 or die "read error: $!";	351	$_[0] > 0 or die "read error: $!";
213	print "read $_[0] bytes: <$buffer>\n";	352	print "read $_[0] bytes: <$buffer>\n";
214	};	353	};
215		354
216	=item aio_move $srcpath, $dstpath, $callback->($status)
217
218	Try to move the I<file> (directories not supported as either source or
219	destination) from C<$srcpath> to C<$dstpath> and call the callback with
220	the C<0> (error) or C<-1> ok.
221
222	This is a composite request that tries to rename(2) the file first. If
223	rename files with C<EXDEV>, it creates the destination file with mode 0200
224	and copies the contents of the source file into it using C<aio_sendfile>,
225	followed by restoring atime, mtime, access mode and uid/gid, in that
226	order, and unlinking the C<$srcpath>.
227
228	If an error occurs, the partial destination file will be unlinked, if
229	possible, except when setting atime, mtime, access mode and uid/gid, where
230	errors are being ignored.
231
232	=cut
233
234	sub aio_move($$$) {
235	my ($src, $dst, $cb) = @_;
236
237	my $grp = aio_group $cb;
238
239	add $grp aio_rename $src, $dst, sub {
240	if ($_[0] && $! == EXDEV) {
241	add $grp aio_open $src, O_RDONLY, 0, sub {
242	if (my $src_fh = $_[0]) {
243	my @stat = stat $src_fh;
244
245	add $grp aio_open $dst, O_WRONLY, 0200, sub {
246	if (my $dst_fh = $_[0]) {
247	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
248	close $src_fh;
249
250	if ($_[0] == $stat[7]) {
251	utime $stat[8], $stat[9], $dst;
252	chmod $stat[2] & 07777, $dst_fh;
253	chown $stat[4], $stat[5], $dst_fh;
254	close $dst_fh;
255
256	add $grp aio_unlink $src, sub {
257	$grp->result ($_[0]);
258	};
259	} else {
260	my $errno = $!;
261	add $grp aio_unlink $dst, sub {
262	$! = $errno;
263	$grp->result (-1);
264	};
265	}
266	};
267	} else {
268	$grp->result (-1);
269	}
270	},
271
272	} else {
273	$grp->result (-1);
274	}
275	};
276	} else {
277	$grp->result ($_[0]);
278	}
279	};
280
281	$grp
282	}
283		355
284	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)	356	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
285		357
286	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts	358	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
287	reading at byte offset C<$in_offset>, and starts writing at the current	359	reading at byte offset C<$in_offset>, and starts writing at the current
…		…
301	C<$in_fh> than are written, and there is no way to find out how many	373	C<$in_fh> than are written, and there is no way to find out how many
302	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only	374	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only
303	provides the number of bytes written to C<$out_fh>. Only if the result	375	provides the number of bytes written to C<$out_fh>. Only if the result
304	value equals C<$length> one can assume that C<$length> bytes have been	376	value equals C<$length> one can assume that C<$length> bytes have been
305	read.	377	read.
		378
306		379
307	=item aio_readahead $fh,$offset,$length, $callback->($retval)	380	=item aio_readahead $fh,$offset,$length, $callback->($retval)
308		381
309	C<aio_readahead> populates the page cache with data from a file so that	382	C<aio_readahead> populates the page cache with data from a file so that
310	subsequent reads from that file will not block on disk I/O. The C<$offset>	383	subsequent reads from that file will not block on disk I/O. The C<$offset>
…		…
316	file. The current file offset of the file is left unchanged.	389	file. The current file offset of the file is left unchanged.
317		390
318	If that syscall doesn't exist (likely if your OS isn't Linux) it will be	391	If that syscall doesn't exist (likely if your OS isn't Linux) it will be
319	emulated by simply reading the data, which would have a similar effect.	392	emulated by simply reading the data, which would have a similar effect.
320		393
		394
321	=item aio_stat $fh_or_path, $callback->($status)	395	=item aio_stat $fh_or_path, $callback->($status)
322		396
323	=item aio_lstat $fh, $callback->($status)	397	=item aio_lstat $fh, $callback->($status)
324		398
325	Works like perl's C<stat> or C<lstat> in void context. The callback will	399	Works like perl's C<stat> or C<lstat> in void context. The callback will
…		…
338	aio_stat "/etc/passwd", sub {	412	aio_stat "/etc/passwd", sub {
339	$_[0] and die "stat failed: $!";	413	$_[0] and die "stat failed: $!";
340	print "size is ", -s _, "\n";	414	print "size is ", -s _, "\n";
341	};	415	};
342		416
		417
		418	=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
		419
		420	Works like perl's C<utime> function (including the special case of $atime
		421	and $mtime being undef). Fractional times are supported if the underlying
		422	syscalls support them.
		423
		424	When called with a pathname, uses utimes(2) if available, otherwise
		425	utime(2). If called on a file descriptor, uses futimes(2) if available,
		426	otherwise returns ENOSYS, so this is not portable.
		427
		428	Examples:
		429
		430	# set atime and mtime to current time (basically touch(1)):
		431	aio_utime "path", undef, undef;
		432	# set atime to current time and mtime to beginning of the epoch:
		433	aio_utime "path", time, undef; # undef==0
		434
		435
		436	=item aio_chown $fh_or_path, $uid, $gid, $callback->($status)
		437
		438	Works like perl's C<chown> function, except that C<undef> for either $uid
		439	or $gid is being interpreted as "do not change" (but -1 can also be used).
		440
		441	Examples:
		442
		443	# same as "chown root path" in the shell:
		444	aio_chown "path", 0, -1;
		445	# same as above:
		446	aio_chown "path", 0, undef;
		447
		448
		449	=item aio_truncate $fh_or_path, $offset, $callback->($status)
		450
		451	Works like truncate(2) or ftruncate(2).
		452
		453
		454	=item aio_chmod $fh_or_path, $mode, $callback->($status)
		455
		456	Works like perl's C<chmod> function.
		457
		458
343	=item aio_unlink $pathname, $callback->($status)	459	=item aio_unlink $pathname, $callback->($status)
344		460
345	Asynchronously unlink (delete) a file and call the callback with the	461	Asynchronously unlink (delete) a file and call the callback with the
346	result code.	462	result code.
347		463
		464
		465	=item aio_mknod $path, $mode, $dev, $callback->($status)
		466
		467	[EXPERIMENTAL]
		468
		469	Asynchronously create a device node (or fifo). See mknod(2).
		470
		471	The only (POSIX-) portable way of calling this function is:
		472
		473	aio_mknod $path, IO::AIO::S_IFIFO \| $mode, 0, sub { ...
		474
		475
348	=item aio_link $srcpath, $dstpath, $callback->($status)	476	=item aio_link $srcpath, $dstpath, $callback->($status)
349		477
350	Asynchronously create a new link to the existing object at C<$srcpath> at	478	Asynchronously create a new link to the existing object at C<$srcpath> at
351	the path C<$dstpath> and call the callback with the result code.	479	the path C<$dstpath> and call the callback with the result code.
352		480
		481
353	=item aio_symlink $srcpath, $dstpath, $callback->($status)	482	=item aio_symlink $srcpath, $dstpath, $callback->($status)
354		483
355	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at	484	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at
356	the path C<$dstpath> and call the callback with the result code.	485	the path C<$dstpath> and call the callback with the result code.
357		486
		487
		488	=item aio_readlink $path, $callback->($link)
		489
		490	Asynchronously read the symlink specified by C<$path> and pass it to
		491	the callback. If an error occurs, nothing or undef gets passed to the
		492	callback.
		493
		494
358	=item aio_rename $srcpath, $dstpath, $callback->($status)	495	=item aio_rename $srcpath, $dstpath, $callback->($status)
359		496
360	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as	497	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as
361	rename(2) and call the callback with the result code.	498	rename(2) and call the callback with the result code.
362		499
		500
		501	=item aio_mkdir $pathname, $mode, $callback->($status)
		502
		503	Asynchronously mkdir (create) a directory and call the callback with
		504	the result code. C<$mode> will be modified by the umask at the time the
		505	request is executed, so do not change your umask.
		506
		507
363	=item aio_rmdir $pathname, $callback->($status)	508	=item aio_rmdir $pathname, $callback->($status)
364		509
365	Asynchronously rmdir (delete) a directory and call the callback with the	510	Asynchronously rmdir (delete) a directory and call the callback with the
366	result code.	511	result code.
		512
367		513
368	=item aio_readdir $pathname, $callback->($entries)	514	=item aio_readdir $pathname, $callback->($entries)
369		515
370	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire	516	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
371	directory (i.e. opendir + readdir + closedir). The entries will not be	517	directory (i.e. opendir + readdir + closedir). The entries will not be
372	sorted, and will B<NOT> include the C<.> and C<..> entries.	518	sorted, and will B<NOT> include the C<.> and C<..> entries.
373		519
374	The callback a single argument which is either C<undef> or an array-ref	520	The callback a single argument which is either C<undef> or an array-ref
375	with the filenames.	521	with the filenames.
376		522
		523
		524	=item aio_load $path, $data, $callback->($status)
		525
		526	This is a composite request that tries to fully load the given file into
		527	memory. Status is the same as with aio_read.
		528
		529	=cut
		530
		531	sub aio_load($$;$) {
		532	aio_block {
		533	my ($path, undef, $cb) = @_;
		534	my $data = \$_[1];
		535
		536	my $pri = aioreq_pri;
		537	my $grp = aio_group $cb;
		538
		539	aioreq_pri $pri;
		540	add $grp aio_open $path, O_RDONLY, 0, sub {
		541	my $fh = shift
		542	or return $grp->result (-1);
		543
		544	aioreq_pri $pri;
		545	add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub {
		546	$grp->result ($_[0]);
		547	};
		548	};
		549
		550	$grp
		551	}
		552	}
		553
		554	=item aio_copy $srcpath, $dstpath, $callback->($status)
		555
		556	Try to copy the I<file> (directories not supported as either source or
		557	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		558	the C<0> (error) or C<-1> ok.
		559
		560	This is a composite request that it creates the destination file with
		561	mode 0200 and copies the contents of the source file into it using
		562	C<aio_sendfile>, followed by restoring atime, mtime, access mode and
		563	uid/gid, in that order.
		564
		565	If an error occurs, the partial destination file will be unlinked, if
		566	possible, except when setting atime, mtime, access mode and uid/gid, where
		567	errors are being ignored.
		568
		569	=cut
		570
		571	sub aio_copy($$;$) {
		572	aio_block {
		573	my ($src, $dst, $cb) = @_;
		574
		575	my $pri = aioreq_pri;
		576	my $grp = aio_group $cb;
		577
		578	aioreq_pri $pri;
		579	add $grp aio_open $src, O_RDONLY, 0, sub {
		580	if (my $src_fh = $_[0]) {
		581	my @stat = stat $src_fh;
		582
		583	aioreq_pri $pri;
		584	add $grp aio_open $dst, O_CREAT \| O_WRONLY \| O_TRUNC, 0200, sub {
		585	if (my $dst_fh = $_[0]) {
		586	aioreq_pri $pri;
		587	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
		588	if ($_[0] == $stat[7]) {
		589	$grp->result (0);
		590	close $src_fh;
		591
		592	# those should not normally block. should. should.
		593	utime $stat[8], $stat[9], $dst;
		594	chmod $stat[2] & 07777, $dst_fh;
		595	chown $stat[4], $stat[5], $dst_fh;
		596	close $dst_fh;
		597	} else {
		598	$grp->result (-1);
		599	close $src_fh;
		600	close $dst_fh;
		601
		602	aioreq $pri;
		603	add $grp aio_unlink $dst;
		604	}
		605	};
		606	} else {
		607	$grp->result (-1);
		608	}
		609	},
		610
		611	} else {
		612	$grp->result (-1);
		613	}
		614	};
		615
		616	$grp
		617	}
		618	}
		619
		620	=item aio_move $srcpath, $dstpath, $callback->($status)
		621
		622	Try to move the I<file> (directories not supported as either source or
		623	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		624	the C<0> (error) or C<-1> ok.
		625
		626	This is a composite request that tries to rename(2) the file first. If
		627	rename files with C<EXDEV>, it copies the file with C<aio_copy> and, if
		628	that is successful, unlinking the C<$srcpath>.
		629
		630	=cut
		631
		632	sub aio_move($$;$) {
		633	aio_block {
		634	my ($src, $dst, $cb) = @_;
		635
		636	my $pri = aioreq_pri;
		637	my $grp = aio_group $cb;
		638
		639	aioreq_pri $pri;
		640	add $grp aio_rename $src, $dst, sub {
		641	if ($_[0] && $! == EXDEV) {
		642	aioreq_pri $pri;
		643	add $grp aio_copy $src, $dst, sub {
		644	$grp->result ($_[0]);
		645
		646	if (!$_[0]) {
		647	aioreq_pri $pri;
		648	add $grp aio_unlink $src;
		649	}
		650	};
		651	} else {
		652	$grp->result ($_[0]);
		653	}
		654	};
		655
		656	$grp
		657	}
		658	}
		659
377	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)	660	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
378		661
379	Scans a directory (similar to C<aio_readdir>) but additionally tries to	662	Scans a directory (similar to C<aio_readdir>) but additionally tries to
380	separate the entries of directory C<$path> into two sets of names, ones	663	efficiently separate the entries of directory C<$path> into two sets of
381	you can recurse into (directories or links to them), and ones you cannot	664	names, directories you can recurse into (directories), and ones you cannot
382	recurse into (everything else).	665	recurse into (everything else, including symlinks to directories).
383		666
384	C<aio_scandir> is a composite request that creates of many sub requests_	667	C<aio_scandir> is a composite request that creates of many sub requests_
385	C<$maxreq> specifies the maximum number of outstanding aio requests that	668	C<$maxreq> specifies the maximum number of outstanding aio requests that
386	this function generates. If it is C<< <= 0 >>, then a suitable default	669	this function generates. If it is C<< <= 0 >>, then a suitable default
387	will be chosen (currently 6).	670	will be chosen (currently 4).
388		671
389	On error, the callback is called without arguments, otherwise it receives	672	On error, the callback is called without arguments, otherwise it receives
390	two array-refs with path-relative entry names.	673	two array-refs with path-relative entry names.
391		674
392	Example:	675	Example:
…		…
426	as those tend to return 0 or 1 as link counts, which disables the	709	as those tend to return 0 or 1 as link counts, which disables the
427	directory counting heuristic.	710	directory counting heuristic.
428		711
429	=cut	712	=cut
430		713
431	sub aio_scandir($$$) {	714	sub aio_scandir($$;$) {
		715	aio_block {
432	my ($path, $maxreq, $cb) = @_;	716	my ($path, $maxreq, $cb) = @_;
433		717
		718	my $pri = aioreq_pri;
		719
434	my $grp = aio_group $cb;	720	my $grp = aio_group $cb;
435		721
436	$maxreq = 6 if $maxreq <= 0;	722	$maxreq = 4 if $maxreq <= 0;
437		723
438	# stat once	724	# stat once
		725	aioreq_pri $pri;
439	add $grp aio_stat $path, sub {	726	add $grp aio_stat $path, sub {
440	return $grp->result () if $_[0];	727	return $grp->result () if $_[0];
441	my $now = time;	728	my $now = time;
442	my $hash1 = join ":", (stat _)[0,1,3,7,9];	729	my $hash1 = join ":", (stat _)[0,1,3,7,9];
443		730
444	# read the directory entries	731	# read the directory entries
		732	aioreq_pri $pri;
445	add $grp aio_readdir $path, sub {	733	add $grp aio_readdir $path, sub {
446	my $entries = shift	734	my $entries = shift
447	or return $grp->result ();	735	or return $grp->result ();
448		736
449	# stat the dir another time	737	# stat the dir another time
		738	aioreq_pri $pri;
450	add $grp aio_stat $path, sub {	739	add $grp aio_stat $path, sub {
451	my $hash2 = join ":", (stat _)[0,1,3,7,9];	740	my $hash2 = join ":", (stat _)[0,1,3,7,9];
452		741
453	my $ndirs;	742	my $ndirs;
454		743
455	# take the slow route if anything looks fishy	744	# take the slow route if anything looks fishy
456	if ($hash1 ne $hash2 or (stat _)[9] == $now) {	745	if ($hash1 ne $hash2 or (stat _)[9] == $now) {
457	$ndirs = -1;	746	$ndirs = -1;
458	} else {	747	} else {
459	# if nlink == 2, we are finished	748	# if nlink == 2, we are finished
460	# on non-posix-fs's, we rely on nlink < 2	749	# on non-posix-fs's, we rely on nlink < 2
461	$ndirs = (stat _)[3] - 2	750	$ndirs = (stat _)[3] - 2
462	or return $grp->result ([], $entries);	751	or return $grp->result ([], $entries);
463	}	752	}
464		753
465	# sort into likely dirs and likely nondirs	754	# sort into likely dirs and likely nondirs
466	# dirs == files without ".", short entries first	755	# dirs == files without ".", short entries first
467	$entries = [map $_->[0],	756	$entries = [map $_->[0],
468	sort { $b->[1] cmp $a->[1] }	757	sort { $b->[1] cmp $a->[1] }
469	map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],	758	map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],
470	@$entries];	759	@$entries];
471		760
472	my (@dirs, @nondirs);	761	my (@dirs, @nondirs);
473		762
474	my ($statcb, $schedcb);
475	my $nreq = 0;
476
477	my $statgrp = add $grp aio_group;	763	my $statgrp = add $grp aio_group sub {
478
479	$schedcb = sub {
480	if (@$entries) {
481	if ($nreq < $maxreq) {
482	my $ent = pop @$entries;
483	$nreq++;
484	add $statgrp aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) };
485	}
486	} elsif (!$nreq) {
487	# finished
488	$statgrp->cancel;
489	undef $statcb;
490	undef $schedcb;
491	$grp->result (\@dirs, \@nondirs);	764	$grp->result (\@dirs, \@nondirs);
492	}	765	};
		766
		767	limit $statgrp $maxreq;
		768	feed $statgrp sub {
		769	return unless @$entries;
		770	my $entry = pop @$entries;
		771
		772	aioreq_pri $pri;
		773	add $statgrp aio_stat "$path/$entry/.", sub {
		774	if ($_[0] < 0) {
		775	push @nondirs, $entry;
		776	} else {
		777	# need to check for real directory
		778	aioreq_pri $pri;
		779	add $statgrp aio_lstat "$path/$entry", sub {
		780	if (-d _) {
		781	push @dirs, $entry;
		782
		783	unless (--$ndirs) {
		784	push @nondirs, @$entries;
		785	feed $statgrp;
		786	}
		787	} else {
		788	push @nondirs, $entry;
		789	}
		790	}
		791	}
		792	};
		793	};
493	};	794	};
494	$statcb = sub {
495	my ($status, $entry) = @_;
496
497	if ($status < 0) {
498	$nreq--;
499	push @nondirs, $entry;
500	&$schedcb;
501	} else {
502	# need to check for real directory
503	add $grp aio_lstat "$path/$entry", sub {
504	$nreq--;
505
506	if (-d _) {
507	push @dirs, $entry;
508
509	if (!--$ndirs) {
510	push @nondirs, @$entries;
511	$entries = [];
512	}
513	} else {
514	push @nondirs, $entry;
515	}
516
517	&$schedcb;
518	}
519	}
520	};
521
522	&$schedcb while @$entries && $nreq < $maxreq;
523	};	795	};
524	};	796	};
		797
		798	$grp
525	};	799	}
		800	}
526		801
		802	=item aio_rmtree $path, $callback->($status)
		803
		804	Delete a directory tree starting (and including) C<$path>, return the
		805	status of the final C<rmdir> only. This is a composite request that
		806	uses C<aio_scandir> to recurse into and rmdir directories, and unlink
		807	everything else.
		808
		809	=cut
		810
		811	sub aio_rmtree;
		812	sub aio_rmtree($;$) {
		813	aio_block {
		814	my ($path, $cb) = @_;
		815
		816	my $pri = aioreq_pri;
		817	my $grp = aio_group $cb;
		818
		819	aioreq_pri $pri;
		820	add $grp aio_scandir $path, 0, sub {
		821	my ($dirs, $nondirs) = @_;
		822
		823	my $dirgrp = aio_group sub {
		824	add $grp aio_rmdir $path, sub {
		825	$grp->result ($_[0]);
		826	};
		827	};
		828
		829	(aioreq_pri $pri), add $dirgrp aio_rmtree "$path/$_" for @$dirs;
		830	(aioreq_pri $pri), add $dirgrp aio_unlink "$path/$_" for @$nondirs;
		831
		832	add $grp $dirgrp;
		833	};
		834
527	$grp	835	$grp
		836	}
528	}	837	}
529		838
530	=item aio_fsync $fh, $callback->($status)	839	=item aio_fsync $fh, $callback->($status)
531		840
532	Asynchronously call fsync on the given filehandle and call the callback	841	Asynchronously call fsync on the given filehandle and call the callback
…		…
539		848
540	If this call isn't available because your OS lacks it or it couldn't be	849	If this call isn't available because your OS lacks it or it couldn't be
541	detected, it will be emulated by calling C<fsync> instead.	850	detected, it will be emulated by calling C<fsync> instead.
542		851
543	=item aio_group $callback->(...)	852	=item aio_group $callback->(...)
544
545	[EXPERIMENTAL]
546		853
547	This is a very special aio request: Instead of doing something, it is a	854	This is a very special aio request: Instead of doing something, it is a
548	container for other aio requests, which is useful if you want to bundle	855	container for other aio requests, which is useful if you want to bundle
549	many requests into a single, composite, request with a definite callback	856	many requests into a single, composite, request with a definite callback
550	and the ability to cancel the whole request with its subrequests.	857	and the ability to cancel the whole request with its subrequests.
…		…
591	=head2 IO::AIO::REQ CLASS	898	=head2 IO::AIO::REQ CLASS
592		899
593	All non-aggregate C<aio_*> functions return an object of this class when	900	All non-aggregate C<aio_*> functions return an object of this class when
594	called in non-void context.	901	called in non-void context.
595		902
596	A request always moves through the following five states in its lifetime,
597	in order: B<ready> (request has been created, but has not been executed
598	yet), B<execute> (request is currently being executed), B<pending>
599	(request has been executed but callback has not been called yet),
600	B<result> (results are being processed synchronously, includes calling the
601	callback) and B<done> (request has reached the end of its lifetime and
602	holds no resources anymore).
603
604	=over 4	903	=over 4
605		904
606	=item cancel $req	905	=item cancel $req
607		906
608	Cancels the request, if possible. Has the effect of skipping execution	907	Cancels the request, if possible. Has the effect of skipping execution
…		…
661	=item * They can also can also be added to other IO::AIO::GRP objects.	960	=item * They can also can also be added to other IO::AIO::GRP objects.
662		961
663	=item * You must not add requests to a group from within the group callback (or	962	=item * You must not add requests to a group from within the group callback (or
664	any later time).	963	any later time).
665		964
666	=item * This does not harmonise well with C<max_outstanding>, so best do
667	not combine C<aio_group> with it. Groups and feeders are recommended for
668	this kind of concurrency-limiting.
669
670	=back	965	=back
671		966
672	Their lifetime, simplified, looks like this: when they are empty, they	967	Their lifetime, simplified, looks like this: when they are empty, they
673	will finish very quickly. If they contain only requests that are in the	968	will finish very quickly. If they contain only requests that are in the
674	C<done> state, they will also finish. Otherwise they will continue to	969	C<done> state, they will also finish. Otherwise they will continue to
…		…
689	be added, including other groups, as long as you do not create circular	984	be added, including other groups, as long as you do not create circular
690	dependencies.	985	dependencies.
691		986
692	Returns all its arguments.	987	Returns all its arguments.
693		988
		989	=item $grp->cancel_subs
		990
		991	Cancel all subrequests and clears any feeder, but not the group request
		992	itself. Useful when you queued a lot of events but got a result early.
		993
694	=item $grp->result (...)	994	=item $grp->result (...)
695		995
696	Set the result value(s) that will be passed to the group callback when all	996	Set the result value(s) that will be passed to the group callback when all
697	subrequests have finished. By default, no argument will be passed.	997	subrequests have finished and set thre groups errno to the current value
		998	of errno (just like calling C<errno> without an error number). By default,
		999	no argument will be passed and errno is zero.
		1000
		1001	=item $grp->errno ([$errno])
		1002
		1003	Sets the group errno value to C<$errno>, or the current value of errno
		1004	when the argument is missing.
		1005
		1006	Every aio request has an associated errno value that is restored when
		1007	the callback is invoked. This method lets you change this value from its
		1008	default (0).
		1009
		1010	Calling C<result> will also set errno, so make sure you either set C<$!>
		1011	before the call to C<result>, or call c<errno> after it.
698		1012
699	=item feed $grp $callback->($grp)	1013	=item feed $grp $callback->($grp)
700
701	[VERY EXPERIMENTAL]
702		1014
703	Sets a feeder/generator on this group: every group can have an attached	1015	Sets a feeder/generator on this group: every group can have an attached
704	generator that generates requests if idle. The idea behind this is that,	1016	generator that generates requests if idle. The idea behind this is that,
705	although you could just queue as many requests as you want in a group,	1017	although you could just queue as many requests as you want in a group,
706	this might starve other requests for a potentially long time. For	1018	this might starve other requests for a potentially long time. For
…		…
743		1055
744	=back	1056	=back
745		1057
746	=head2 SUPPORT FUNCTIONS	1058	=head2 SUPPORT FUNCTIONS
747		1059
		1060	=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION
		1061
748	=over 4	1062	=over 4
749		1063
750	=item $fileno = IO::AIO::poll_fileno	1064	=item $fileno = IO::AIO::poll_fileno
751		1065
752	Return the I<request result pipe file descriptor>. This filehandle must be	1066	Return the I<request result pipe file descriptor>. This filehandle must be
…		…
756		1070
757	See C<poll_cb> for an example.	1071	See C<poll_cb> for an example.
758		1072
759	=item IO::AIO::poll_cb	1073	=item IO::AIO::poll_cb
760		1074
761	Process all outstanding events on the result pipe. You have to call this	1075	Process some outstanding events on the result pipe. You have to call this
762	regularly. Returns the number of events processed. Returns immediately	1076	regularly. Returns the number of events processed. Returns immediately
763	when no events are outstanding.	1077	when no events are outstanding. The amount of events processed depends on
		1078	the settings of C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>.
		1079
		1080	If not all requests were processed for whatever reason, the filehandle
		1081	will still be ready when C<poll_cb> returns.
764		1082
765	Example: Install an Event watcher that automatically calls	1083	Example: Install an Event watcher that automatically calls
766	IO::AIO::poll_cb with high priority:	1084	IO::AIO::poll_cb with high priority:
767		1085
768	Event->io (fd => IO::AIO::poll_fileno,	1086	Event->io (fd => IO::AIO::poll_fileno,
769	poll => 'r', async => 1,	1087	poll => 'r', async => 1,
770	cb => \&IO::AIO::poll_cb);	1088	cb => \&IO::AIO::poll_cb);
771		1089
		1090	=item IO::AIO::max_poll_reqs $nreqs
		1091
		1092	=item IO::AIO::max_poll_time $seconds
		1093
		1094	These set the maximum number of requests (default C<0>, meaning infinity)
		1095	that are being processed by C<IO::AIO::poll_cb> in one call, respectively
		1096	the maximum amount of time (default C<0>, meaning infinity) spent in
		1097	C<IO::AIO::poll_cb> to process requests (more correctly the mininum amount
		1098	of time C<poll_cb> is allowed to use).
		1099
		1100	Setting C<max_poll_time> to a non-zero value creates an overhead of one
		1101	syscall per request processed, which is not normally a problem unless your
		1102	callbacks are really really fast or your OS is really really slow (I am
		1103	not mentioning Solaris here). Using C<max_poll_reqs> incurs no overhead.
		1104
		1105	Setting these is useful if you want to ensure some level of
		1106	interactiveness when perl is not fast enough to process all requests in
		1107	time.
		1108
		1109	For interactive programs, values such as C<0.01> to C<0.1> should be fine.
		1110
		1111	Example: Install an Event watcher that automatically calls
		1112	IO::AIO::poll_cb with low priority, to ensure that other parts of the
		1113	program get the CPU sometimes even under high AIO load.
		1114
		1115	# try not to spend much more than 0.1s in poll_cb
		1116	IO::AIO::max_poll_time 0.1;
		1117
		1118	# use a low priority so other tasks have priority
		1119	Event->io (fd => IO::AIO::poll_fileno,
		1120	poll => 'r', nice => 1,
		1121	cb => &IO::AIO::poll_cb);
		1122
772	=item IO::AIO::poll_wait	1123	=item IO::AIO::poll_wait
773		1124
		1125	If there are any outstanding requests and none of them in the result
774	Wait till the result filehandle becomes ready for reading (simply does a	1126	phase, wait till the result filehandle becomes ready for reading (simply
775	C<select> on the filehandle. This is useful if you want to synchronously wait	1127	does a C<select> on the filehandle. This is useful if you want to
776	for some requests to finish).	1128	synchronously wait for some requests to finish).
777		1129
778	See C<nreqs> for an example.	1130	See C<nreqs> for an example.
779		1131
		1132	=item IO::AIO::poll
		1133
		1134	Waits until some requests have been handled.
		1135
		1136	Returns the number of requests processed, but is otherwise strictly
		1137	equivalent to:
		1138
		1139	IO::AIO::poll_wait, IO::AIO::poll_cb
		1140
780	=item IO::AIO::nreqs	1141	=item IO::AIO::flush
781		1142
782	Returns the number of requests currently outstanding (i.e. for which their	1143	Wait till all outstanding AIO requests have been handled.
783	callback has not been invoked yet).
784		1144
785	Example: wait till there are no outstanding requests anymore:	1145	Strictly equivalent to:
786		1146
787	IO::AIO::poll_wait, IO::AIO::poll_cb	1147	IO::AIO::poll_wait, IO::AIO::poll_cb
788	while IO::AIO::nreqs;	1148	while IO::AIO::nreqs;
789		1149
790	=item IO::AIO::flush	1150	=back
791		1151
792	Wait till all outstanding AIO requests have been handled.	1152	=head3 CONTROLLING THE NUMBER OF THREADS
793		1153
794	Strictly equivalent to:	1154	=over
795
796	IO::AIO::poll_wait, IO::AIO::poll_cb
797	while IO::AIO::nreqs;
798
799	=item IO::AIO::poll
800
801	Waits until some requests have been handled.
802
803	Strictly equivalent to:
804
805	IO::AIO::poll_wait, IO::AIO::poll_cb
806	if IO::AIO::nreqs;
807		1155
808	=item IO::AIO::min_parallel $nthreads	1156	=item IO::AIO::min_parallel $nthreads
809		1157
810	Set the minimum number of AIO threads to C<$nthreads>. The current	1158	Set the minimum number of AIO threads to C<$nthreads>. The current
811	default is C<8>, which means eight asynchronous operations can execute	1159	default is C<8>, which means eight asynchronous operations can execute
812	concurrently at any one time (the number of outstanding requests,	1160	concurrently at any one time (the number of outstanding requests,
813	however, is unlimited).	1161	however, is unlimited).
814		1162
815	IO::AIO starts threads only on demand, when an AIO request is queued and	1163	IO::AIO starts threads only on demand, when an AIO request is queued and
816	no free thread exists.	1164	no free thread exists. Please note that queueing up a hundred requests can
		1165	create demand for a hundred threads, even if it turns out that everything
		1166	is in the cache and could have been processed faster by a single thread.
817		1167
818	It is recommended to keep the number of threads relatively low, as some	1168	It is recommended to keep the number of threads relatively low, as some
819	Linux kernel versions will scale negatively with the number of threads	1169	Linux kernel versions will scale negatively with the number of threads
820	(higher parallelity => MUCH higher latency). With current Linux 2.6	1170	(higher parallelity => MUCH higher latency). With current Linux 2.6
821	versions, 4-32 threads should be fine.	1171	versions, 4-32 threads should be fine.
…		…
835	This module automatically runs C<max_parallel 0> at program end, to ensure	1185	This module automatically runs C<max_parallel 0> at program end, to ensure
836	that all threads are killed and that there are no outstanding requests.	1186	that all threads are killed and that there are no outstanding requests.
837		1187
838	Under normal circumstances you don't need to call this function.	1188	Under normal circumstances you don't need to call this function.
839		1189
		1190	=item IO::AIO::max_idle $nthreads
		1191
		1192	Limit the number of threads (default: 4) that are allowed to idle (i.e.,
		1193	threads that did not get a request to process within 10 seconds). That
		1194	means if a thread becomes idle while C<$nthreads> other threads are also
		1195	idle, it will free its resources and exit.
		1196
		1197	This is useful when you allow a large number of threads (e.g. 100 or 1000)
		1198	to allow for extremely high load situations, but want to free resources
		1199	under normal circumstances (1000 threads can easily consume 30MB of RAM).
		1200
		1201	The default is probably ok in most situations, especially if thread
		1202	creation is fast. If thread creation is very slow on your system you might
		1203	want to use larger values.
		1204
840	=item $oldnreqs = IO::AIO::max_outstanding $nreqs	1205	=item $oldmaxreqs = IO::AIO::max_outstanding $maxreqs
841		1206
842	[DEPRECATED]	1207	This is a very bad function to use in interactive programs because it
		1208	blocks, and a bad way to reduce concurrency because it is inexact: Better
		1209	use an C<aio_group> together with a feed callback.
843		1210
844	Sets the maximum number of outstanding requests to C<$nreqs>. If you	1211	Sets the maximum number of outstanding requests to C<$nreqs>. If you
845	try to queue up more than this number of requests, the caller will block until	1212	do queue up more than this number of requests, the next call to the
846	some requests have been handled.	1213	C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>)
		1214	function will block until the limit is no longer exceeded.
847		1215
848	The default is very large, so normally there is no practical limit. If you	1216	The default value is very large, so there is no practical limit on the
849	queue up many requests in a loop it often improves speed if you set	1217	number of outstanding requests.
850	this to a relatively low number, such as C<100>.
851		1218
852	This function does not work well together with C<aio_group>'s, and their	1219	You can still queue as many requests as you want. Therefore,
853	feeder interface is better suited to limiting concurrency, so do not use	1220	C<max_oustsanding> is mainly useful in simple scripts (with low values) or
854	this function.	1221	as a stop gap to shield against fatal memory overflow (with large values).
855		1222
856	Under normal circumstances you don't need to call this function.	1223	=back
		1224
		1225	=head3 STATISTICAL INFORMATION
		1226
		1227	=over
		1228
		1229	=item IO::AIO::nreqs
		1230
		1231	Returns the number of requests currently in the ready, execute or pending
		1232	states (i.e. for which their callback has not been invoked yet).
		1233
		1234	Example: wait till there are no outstanding requests anymore:
		1235
		1236	IO::AIO::poll_wait, IO::AIO::poll_cb
		1237	while IO::AIO::nreqs;
		1238
		1239	=item IO::AIO::nready
		1240
		1241	Returns the number of requests currently in the ready state (not yet
		1242	executed).
		1243
		1244	=item IO::AIO::npending
		1245
		1246	Returns the number of requests currently in the pending state (executed,
		1247	but not yet processed by poll_cb).
857		1248
858	=back	1249	=back
859		1250
860	=cut	1251	=cut
861		1252
…		…
875	*$sym	1266	*$sym
876	}	1267	}
877		1268
878	min_parallel 8;	1269	min_parallel 8;
879		1270
880	END {	1271	END { flush }
881	max_parallel 0;
882	}
883		1272
884	1;	1273	1;
885		1274
886	=head2 FORK BEHAVIOUR	1275	=head2 FORK BEHAVIOUR
887		1276
888	This module should do "the right thing" when the process using it forks:	1277	This module should do "the right thing" when the process using it forks:
889		1278
890	Before the fork, IO::AIO enters a quiescent state where no requests	1279	Before the fork, IO::AIO enters a quiescent state where no requests
891	can be added in other threads and no results will be processed. After	1280	can be added in other threads and no results will be processed. After
892	the fork the parent simply leaves the quiescent state and continues	1281	the fork the parent simply leaves the quiescent state and continues
893	request/result processing, while the child clears the request/result	1282	request/result processing, while the child frees the request/result queue
894	queue (so the requests started before the fork will only be handled in	1283	(so that the requests started before the fork will only be handled in the
895	the parent). Threads will be started on demand until the limit ste in the	1284	parent). Threads will be started on demand until the limit set in the
896	parent process has been reached again.	1285	parent process has been reached again.
897		1286
898	In short: the parent will, after a short pause, continue as if fork had	1287	In short: the parent will, after a short pause, continue as if fork had
899	not been called, while the child will act as if IO::AIO has not been used	1288	not been called, while the child will act as if IO::AIO has not been used
900	yet.	1289	yet.
901		1290
902	=head2 MEMORY USAGE	1291	=head2 MEMORY USAGE
903		1292
		1293	Per-request usage:
		1294
904	Each aio request uses - depending on your architecture - around 128 bytes	1295	Each aio request uses - depending on your architecture - around 100-200
905	of memory. In addition, stat requests need a stat buffer (possibly a few	1296	bytes of memory. In addition, stat requests need a stat buffer (possibly
906	hundred bytes). Perl scalars and other data passed into aio requests will	1297	a few hundred bytes), readdir requires a result buffer and so on. Perl
907	also be locked.	1298	scalars and other data passed into aio requests will also be locked and
		1299	will consume memory till the request has entered the done state.
908		1300
909	This is now awfully much, so queuing lots of requests is not usually a	1301	This is not awfully much, so queuing lots of requests is not usually a
910	problem.	1302	problem.
911		1303
912	Each thread needs a stack area which is usually around 16k, sometimes much	1304	Per-thread usage:
913	larger, depending on the OS.	1305
		1306	In the execution phase, some aio requests require more memory for
		1307	temporary buffers, and each thread requires a stack and other data
		1308	structures (usually around 16k-128k, depending on the OS).
		1309
		1310	=head1 KNOWN BUGS
		1311
		1312	Known bugs will be fixed in the next release.
914		1313
915	=head1 SEE ALSO	1314	=head1 SEE ALSO
916		1315
917	L<Coro::AIO>.	1316	L<Coro::AIO>.
918		1317

Diff Legend

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

Comparing IO-AIO/AIO.pm (file contents): Revision 1.71 by root, Tue Oct 24 11:57:30 2006 UTC vs. Revision 1.113 by root, Thu Sep 20 14:06:21 2007 UTC

Diff Legend

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.71 by root, Tue Oct 24 11:57:30 2006 UTC vs.
Revision 1.113 by root, Thu Sep 20 14:06:21 2007 UTC