ViewVC Help

View File | Revision Log | Show Annotations | Download File

/cvs/IO-AIO/AIO.pm

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.69 by root, Tue Oct 24 03:40:25 2006 UTC vs.
Revision 1.193 by root, Thu May 26 04:15:37 2011 UTC

…		…
4		4
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", IO::AIO::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
…		…
25	$req->cancel; # cancel request if still in queue	26	$req->cancel; # cancel request if still in queue
26		27
27	my $grp = aio_group sub { print "all stats done\n" };	28	my $grp = aio_group sub { print "all stats done\n" };
28	add $grp aio_stat "..." for ...;	29	add $grp aio_stat "..." for ...;
29		30
30	# AnyEvent integration
31	open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!";
32	my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb });
33
34	# Event integration
35	Event->io (fd => IO::AIO::poll_fileno,
36	poll => 'r',
37	cb => \&IO::AIO::poll_cb);
38
39	# Glib/Gtk2 integration
40	add_watch Glib::IO IO::AIO::poll_fileno,
41	in => sub { IO::AIO::poll_cb; 1 };
42
43	# Tk integration
44	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
45	readable => \&IO::AIO::poll_cb);
46
47	# Danga::Socket integration
48	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
49	\&IO::AIO::poll_cb);
50
51	=head1 DESCRIPTION	31	=head1 DESCRIPTION
52		32
53	This module implements asynchronous I/O using whatever means your	33	This module implements asynchronous I/O using whatever means your
54	operating system supports.	34	operating system supports. It is implemented as an interface to C<libeio>
		35	(L<http://software.schmorp.de/pkg/libeio.html>).
55		36
		37	Asynchronous means that operations that can normally block your program
		38	(e.g. reading from disk) will be done asynchronously: the operation
		39	will still block, but you can do something else in the meantime. This
		40	is extremely useful for programs that need to stay interactive even
		41	when doing heavy I/O (GUI programs, high performance network servers
		42	etc.), but can also be used to easily do operations in parallel that are
		43	normally done sequentially, e.g. stat'ing many files, which is much faster
		44	on a RAID volume or over NFS when you do a number of stat operations
		45	concurrently.
		46
		47	While most of this works on all types of file descriptors (for
		48	example sockets), using these functions on file descriptors that
		49	support nonblocking operation (again, sockets, pipes etc.) is
		50	very inefficient. Use an event loop for that (such as the L<EV>
		51	module): IO::AIO will naturally fit into such an event loop itself.
		52
56	Currently, a number of threads are started that execute your read/writes	53	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	54	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	55	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	56	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	57	functions available on many operating systems. However, they are often
61	(Linux doesn't allow them on normal files currently, for example),	58	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	59	files currently, for example), and they would only support aio_read and
63	functionality would have to be implemented using threads anyway.	60	aio_write, so the remaining functionality would have to be implemented
		61	using threads anyway.
64		62
65	Although the module will work with in the presence of other threads,	63	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	64	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	65	yourself, always call C<poll_cb> from within the same thread, or never
68	call C<poll_cb> (or other C<aio_> functions) recursively.	66	call C<poll_cb> (or other C<aio_> functions) recursively.
69		67
		68	=head2 EXAMPLE
		69
		70	This is a simple example that uses the EV module and loads
		71	F</etc/passwd> asynchronously:
		72
		73	use Fcntl;
		74	use EV;
		75	use IO::AIO;
		76
		77	# register the IO::AIO callback with EV
		78	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
		79
		80	# queue the request to open /etc/passwd
		81	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
		82	my $fh = shift
		83	or die "error while opening: $!";
		84
		85	# stat'ing filehandles is generally non-blocking
		86	my $size = -s $fh;
		87
		88	# queue a request to read the file
		89	my $contents;
		90	aio_read $fh, 0, $size, $contents, 0, sub {
		91	$_[0] == $size
		92	or die "short read: $!";
		93
		94	close $fh;
		95
		96	# file contents now in $contents
		97	print $contents;
		98
		99	# exit event loop and program
		100	EV::unloop;
		101	};
		102	};
		103
		104	# possibly queue up other requests, or open GUI windows,
		105	# check for sockets etc. etc.
		106
		107	# process events as long as there are some:
		108	EV::loop;
		109
		110	=head1 REQUEST ANATOMY AND LIFETIME
		111
		112	Every C<aio_*> function creates a request. which is a C data structure not
		113	directly visible to Perl.
		114
		115	If called in non-void context, every request function returns a Perl
		116	object representing the request. In void context, nothing is returned,
		117	which saves a bit of memory.
		118
		119	The perl object is a fairly standard ref-to-hash object. The hash contents
		120	are not used by IO::AIO so you are free to store anything you like in it.
		121
		122	During their existance, aio requests travel through the following states,
		123	in order:
		124
		125	=over 4
		126
		127	=item ready
		128
		129	Immediately after a request is created it is put into the ready state,
		130	waiting for a thread to execute it.
		131
		132	=item execute
		133
		134	A thread has accepted the request for processing and is currently
		135	executing it (e.g. blocking in read).
		136
		137	=item pending
		138
		139	The request has been executed and is waiting for result processing.
		140
		141	While request submission and execution is fully asynchronous, result
		142	processing is not and relies on the perl interpreter calling C<poll_cb>
		143	(or another function with the same effect).
		144
		145	=item result
		146
		147	The request results are processed synchronously by C<poll_cb>.
		148
		149	The C<poll_cb> function will process all outstanding aio requests by
		150	calling their callbacks, freeing memory associated with them and managing
		151	any groups they are contained in.
		152
		153	=item done
		154
		155	Request has reached the end of its lifetime and holds no resources anymore
		156	(except possibly for the Perl object, but its connection to the actual
		157	aio request is severed and calling its methods will either do nothing or
		158	result in a runtime error).
		159
		160	=back
		161
70	=cut	162	=cut
71		163
72	package IO::AIO;	164	package IO::AIO;
73		165
74	no warnings;	166	use Carp ();
75	use strict 'vars';	167
		168	use common::sense;
76		169
77	use base 'Exporter';	170	use base 'Exporter';
78		171
79	BEGIN {	172	BEGIN {
80	our $VERSION = '2.0';	173	our $VERSION = '3.8';
81		174
82	our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat	175	our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close
83	aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink	176	aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx
84	aio_fsync aio_fdatasync aio_readahead aio_rename aio_link aio_move	177	aio_scandir aio_symlink aio_readlink aio_sync aio_fsync
		178	aio_fdatasync aio_sync_file_range aio_pathsync aio_readahead
		179	aio_rename aio_link aio_move aio_copy aio_group
		180	aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown
		181	aio_chmod aio_utime aio_truncate
		182	aio_msync aio_mtouch aio_mlock aio_mlockall
85	aio_group aio_nop);	183	aio_statvfs);
		184
86	our @EXPORT = (@AIO_REQ, qw(aioreq_pri));	185	our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice));
87	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush	186	our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush
88	min_parallel max_parallel max_outstanding nreqs);	187	min_parallel max_parallel max_idle idle_timeout
		188	nreqs nready npending nthreads
		189	max_poll_time max_poll_reqs
		190	sendfile fadvise madvise
		191	mmap munmap munlock munlockall);
		192
		193	push @AIO_REQ, qw(aio_busy); # not exported
89		194
90	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';	195	@IO::AIO::GRP::ISA = 'IO::AIO::REQ';
91		196
92	require XSLoader;	197	require XSLoader;
93	XSLoader::load ("IO::AIO", $VERSION);	198	XSLoader::load ("IO::AIO", $VERSION);
94	}	199	}
95		200
96	=head1 FUNCTIONS	201	=head1 FUNCTIONS
97		202
		203	=head2 QUICK OVERVIEW
		204
		205	This section simply lists the prototypes of the most important functions
		206	for quick reference. See the following sections for function-by-function
		207	documentation.
		208
		209	aio_open $pathname, $flags, $mode, $callback->($fh)
		210	aio_close $fh, $callback->($status)
		211	aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
		212	aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
		213	aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
		214	aio_readahead $fh,$offset,$length, $callback->($retval)
		215	aio_stat $fh_or_path, $callback->($status)
		216	aio_lstat $fh, $callback->($status)
		217	aio_statvfs $fh_or_path, $callback->($statvfs)
		218	aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
		219	aio_chown $fh_or_path, $uid, $gid, $callback->($status)
		220	aio_truncate $fh_or_path, $offset, $callback->($status)
		221	aio_chmod $fh_or_path, $mode, $callback->($status)
		222	aio_unlink $pathname, $callback->($status)
		223	aio_mknod $path, $mode, $dev, $callback->($status)
		224	aio_link $srcpath, $dstpath, $callback->($status)
		225	aio_symlink $srcpath, $dstpath, $callback->($status)
		226	aio_readlink $path, $callback->($link)
		227	aio_rename $srcpath, $dstpath, $callback->($status)
		228	aio_mkdir $pathname, $mode, $callback->($status)
		229	aio_rmdir $pathname, $callback->($status)
		230	aio_readdir $pathname, $callback->($entries)
		231	aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		232	IO::AIO::READDIR_DENTS IO::AIO::READDIR_DIRS_FIRST
		233	IO::AIO::READDIR_STAT_ORDER IO::AIO::READDIR_FOUND_UNKNOWN
		234	aio_load $path, $data, $callback->($status)
		235	aio_copy $srcpath, $dstpath, $callback->($status)
		236	aio_move $srcpath, $dstpath, $callback->($status)
		237	aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
		238	aio_rmtree $path, $callback->($status)
		239	aio_sync $callback->($status)
		240	aio_fsync $fh, $callback->($status)
		241	aio_fdatasync $fh, $callback->($status)
		242	aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		243	aio_pathsync $path, $callback->($status)
		244	aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		245	aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		246	aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
		247	aio_mlockall $flags, $callback->($status)
		248	aio_group $callback->(...)
		249	aio_nop $callback->()
		250
		251	$prev_pri = aioreq_pri [$pri]
		252	aioreq_nice $pri_adjust
		253
		254	IO::AIO::poll_wait
		255	IO::AIO::poll_cb
		256	IO::AIO::poll
		257	IO::AIO::flush
		258	IO::AIO::max_poll_reqs $nreqs
		259	IO::AIO::max_poll_time $seconds
		260	IO::AIO::min_parallel $nthreads
		261	IO::AIO::max_parallel $nthreads
		262	IO::AIO::max_idle $nthreads
		263	IO::AIO::idle_timeout $seconds
		264	IO::AIO::max_outstanding $maxreqs
		265	IO::AIO::nreqs
		266	IO::AIO::nready
		267	IO::AIO::npending
		268
		269	IO::AIO::sendfile $ofh, $ifh, $offset, $count
		270	IO::AIO::fadvise $fh, $offset, $len, $advice
		271	IO::AIO::madvise $scalar, $offset, $length, $advice
		272	IO::AIO::mprotect $scalar, $offset, $length, $protect
		273	IO::AIO::munlock $scalar, $offset = 0, $length = undef
		274	IO::AIO::munlockall
		275
98	=head2 AIO FUNCTIONS	276	=head2 AIO REQUEST FUNCTIONS
99		277
100	All the C<aio_*> calls are more or less thin wrappers around the syscall	278	All the C<aio_*> calls are more or less thin wrappers around the syscall
101	with the same name (sans C<aio_>). The arguments are similar or identical,	279	with the same name (sans C<aio_>). The arguments are similar or identical,
102	and they all accept an additional (and optional) C<$callback> argument	280	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	281	which must be a code reference. This code reference will get called with
104	the syscall return code (e.g. most syscalls return C<-1> on error, unlike	282	the syscall return code (e.g. most syscalls return C<-1> on error, unlike
105	perl, which usually delivers "false") as it's sole argument when the given	283	perl, which usually delivers "false") as its sole argument after the given
106	syscall has been executed asynchronously.	284	syscall has been executed asynchronously.
107		285
108	All functions expecting a filehandle keep a copy of the filehandle	286	All functions expecting a filehandle keep a copy of the filehandle
109	internally until the request has finished.	287	internally until the request has finished.
110		288
111	All requests return objects of type L<IO::AIO::REQ> that allow further	289	All functions return request objects of type L<IO::AIO::REQ> that allow
112	manipulation of those requests while they are in-flight.	290	further manipulation of those requests while they are in-flight.
113		291
114	The pathnames you pass to these routines I<must> be absolute and	292	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	293	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	294	request is being executed, the current working directory could have
117	changed. Alternatively, you can make sure that you never change the	295	changed. Alternatively, you can make sure that you never change the
118	current working directory.	296	current working directory anywhere in the program and then use relative
		297	paths.
119		298
120	To encode pathnames to byte form, either make sure you either: a)	299	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	300	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	301	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	302	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)	303	environment, d) use Glib::filename_from_unicode on unicode filenames or e)
125	use something else.	304	use something else to ensure your scalar has the correct contents.
		305
		306	This works, btw. independent of the internal UTF-8 bit, which IO::AIO
		307	handles correctly whether it is set or not.
126		308
127	=over 4	309	=over 4
128		310
129	=item aioreq_pri $pri	311	=item $prev_pri = aioreq_pri [$pri]
130		312
131	Sets the priority for the next aio request. The default priority	313	Returns the priority value that would be used for the next request and, if
		314	C<$pri> is given, sets the priority for the next aio request.
		315
132	is C<0>, the minimum and maximum priorities are C<-4> and C<4>,	316	The default priority is C<0>, the minimum and maximum priorities are C<-4>
133	respectively. Requests with higher priority will be serviced first.	317	and C<4>, respectively. Requests with higher priority will be serviced
		318	first.
134		319
135	The priority will be reset to C<0> after each call to one of the C<aio_>	320	The priority will be reset to C<0> after each call to one of the C<aio_*>
136	functions.	321	functions.
137		322
138	Example: open a file with low priority, then read something from it with	323	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	324	higher priority so the read request is serviced before other low priority
140	open requests (potentially spamming the cache):	325	open requests (potentially spamming the cache):
…		…
147	aio_read $_[0], ..., sub {	332	aio_read $_[0], ..., sub {
148	...	333	...
149	};	334	};
150	};	335	};
151		336
		337
152	=item aioreq_nice $pri_adjust	338	=item aioreq_nice $pri_adjust
153		339
154	Similar to C<aioreq_pri>, but subtracts the given value from the current	340	Similar to C<aioreq_pri>, but subtracts the given value from the current
155	priority, so effects are cumulative.	341	priority, so the effect is cumulative.
		342
156		343
157	=item aio_open $pathname, $flags, $mode, $callback->($fh)	344	=item aio_open $pathname, $flags, $mode, $callback->($fh)
158		345
159	Asynchronously open or create a file and call the callback with a newly	346	Asynchronously open or create a file and call the callback with a newly
160	created filehandle for the file.	347	created filehandle for the file.
…		…
166	list. They are the same as used by C<sysopen>.	353	list. They are the same as used by C<sysopen>.
167		354
168	Likewise, C<$mode> specifies the mode of the newly created file, if it	355	Likewise, C<$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>,	356	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,	357	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).	358	and C<0666> or C<0777> if you do). Note that the C<$mode> will be modified
		359	by the umask in effect then the request is being executed, so better never
		360	change the umask.
172		361
173	Example:	362	Example:
174		363
175	aio_open "/etc/passwd", O_RDONLY, 0, sub {	364	aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub {
176	if ($_[0]) {	365	if ($_[0]) {
177	print "open successful, fh is $_[0]\n";	366	print "open successful, fh is $_[0]\n";
178	...	367	...
179	} else {	368	} else {
180	die "open failed: $!\n";	369	die "open failed: $!\n";
181	}	370	}
182	};	371	};
183		372
		373
184	=item aio_close $fh, $callback->($status)	374	=item aio_close $fh, $callback->($status)
185		375
186	Asynchronously close a file and call the callback with the result	376	Asynchronously close a file and call the callback with the result
187	code. I<WARNING:> although accepted, you should not pass in a perl	377	code.
188	filehandle here, as perl will likely close the file descriptor another
189	time when the filehandle is destroyed. Normally, you can safely call perls
190	C<close> or just let filehandles go out of scope.
191		378
192	This is supposed to be a bug in the API, so that might change. It's	379	Unfortunately, you can't do this to perl. Perl I<insists> very strongly on
193	therefore best to avoid this function.	380	closing the file descriptor associated with the filehandle itself.
		381
		382	Therefore, C<aio_close> will not close the filehandle - instead it will
		383	use dup2 to overwrite the file descriptor with the write-end of a pipe
		384	(the pipe fd will be created on demand and will be cached).
		385
		386	Or in other words: the file descriptor will be closed, but it will not be
		387	free for reuse until the perl filehandle is closed.
		388
		389	=cut
194		390
195	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	391	=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
196		392
197	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)	393	=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
198		394
199	Reads or writes C<length> bytes from the specified C<fh> and C<offset>	395	Reads or writes C<$length> bytes from or to the specified C<$fh> and
200	into the scalar given by C<data> and offset C<dataoffset> and calls the	396	C<$offset> into the scalar given by C<$data> and offset C<$dataoffset>
201	callback without the actual number of bytes read (or -1 on error, just	397	and calls the callback without the actual number of bytes read (or -1 on
202	like the syscall).	398	error, just like the syscall).
		399
		400	C<aio_read> will, like C<sysread>, shrink or grow the C<$data> scalar to
		401	offset plus the actual number of bytes read.
		402
		403	If C<$offset> is undefined, then the current file descriptor offset will
		404	be used (and updated), otherwise the file descriptor offset will not be
		405	changed by these calls.
		406
		407	If C<$length> is undefined in C<aio_write>, use the remaining length of
		408	C<$data>.
		409
		410	If C<$dataoffset> is less than zero, it will be counted from the end of
		411	C<$data>.
203		412
204	The C<$data> scalar I<MUST NOT> be modified in any way while the request	413	The C<$data> scalar I<MUST NOT> be modified in any way while the request
205	is outstanding. Modifying it can result in segfaults or WW3 (if the	414	is outstanding. Modifying it can result in segfaults or World War III (if
206	necessary/optional hardware is installed).	415	the necessary/optional hardware is installed).
207		416
208	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at	417	Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at
209	offset C<0> within the scalar:	418	offset C<0> within the scalar:
210		419
211	aio_read $fh, 7, 15, $buffer, 0, sub {	420	aio_read $fh, 7, 15, $buffer, 0, sub {
212	$_[0] > 0 or die "read error: $!";	421	$_[0] > 0 or die "read error: $!";
213	print "read $_[0] bytes: <$buffer>\n";	422	print "read $_[0] bytes: <$buffer>\n";
214	};	423	};
215		424
216	=item aio_move $srcpath, $dstpath, $callback->($status)
217
218	[EXPERIMENTAL due to internal aio_group use]
219
220	Try to move the I<file> (directories not supported as either source or
221	destination) from C<$srcpath> to C<$dstpath> and call the callback with
222	the C<0> (error) or C<-1> ok.
223
224	This is a composite request that tries to rename(2) the file first. If
225	rename files with C<EXDEV>, it creates the destination file with mode 0200
226	and copies the contents of the source file into it using C<aio_sendfile>,
227	followed by restoring atime, mtime, access mode and uid/gid, in that
228	order, and unlinking the C<$srcpath>.
229
230	If an error occurs, the partial destination file will be unlinked, if
231	possible, except when setting atime, mtime, access mode and uid/gid, where
232	errors are being ignored.
233
234	=cut
235
236	sub aio_move($$$) {
237	my ($src, $dst, $cb) = @_;
238
239	my $grp = aio_group $cb;
240
241	add $grp aio_rename $src, $dst, sub {
242	if ($_[0] && $! == EXDEV) {
243	add $grp aio_open $src, O_RDONLY, 0, sub {
244	if (my $src_fh = $_[0]) {
245	my @stat = stat $src_fh;
246
247	add $grp aio_open $dst, O_WRONLY, 0200, sub {
248	if (my $dst_fh = $_[0]) {
249	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
250	close $src_fh;
251
252	if ($_[0] == $stat[7]) {
253	utime $stat[8], $stat[9], $dst;
254	chmod $stat[2] & 07777, $dst_fh;
255	chown $stat[4], $stat[5], $dst_fh;
256	close $dst_fh;
257
258	add $grp aio_unlink $src, sub {
259	$grp->result ($_[0]);
260	};
261	} else {
262	my $errno = $!;
263	add $grp aio_unlink $dst, sub {
264	$! = $errno;
265	$grp->result (-1);
266	};
267	}
268	};
269	} else {
270	$grp->result (-1);
271	}
272	},
273
274	} else {
275	$grp->result (-1);
276	}
277	};
278	} else {
279	$grp->result ($_[0]);
280	}
281	};
282
283	$grp
284	}
285		425
286	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)	426	=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
287		427
288	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts	428	Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
289	reading at byte offset C<$in_offset>, and starts writing at the current	429	reading at byte offset C<$in_offset>, and starts writing at the current
290	file offset of C<$out_fh>. Because of that, it is not safe to issue more	430	file offset of C<$out_fh>. Because of that, it is not safe to issue more
291	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each	431	than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each
292	other.	432	other.
293		433
		434	Please note that C<aio_sendfile> can read more bytes from C<$in_fh> than
		435	are written, and there is no way to find out how many bytes have been read
		436	from C<aio_sendfile> alone, as C<aio_sendfile> only provides the number of
		437	bytes written to C<$out_fh>. Only if the result value equals C<$length>
		438	one can assume that C<$length> bytes have been read.
		439
		440	Unlike with other C<aio_> functions, it makes a lot of sense to use
		441	C<aio_sendfile> on non-blocking sockets, as long as one end (typically
		442	the C<$in_fh>) is a file - the file I/O will then be asynchronous, while
		443	the socket I/O will be non-blocking. Note, however, that you can run into
		444	a trap where C<aio_sendfile> reads some data with readahead, then fails
		445	to write all data, and when the socket is ready the next time, the data
		446	in the cache is already lost, forcing C<aio_sendfile> to again hit the
		447	disk. Explicit C<aio_read> + C<aio_write> let's you control resource usage
		448	much better.
		449
294	This call tries to make use of a native C<sendfile> syscall to provide	450	This call tries to make use of a native C<sendfile> syscall to provide
295	zero-copy operation. For this to work, C<$out_fh> should refer to a	451	zero-copy operation. For this to work, C<$out_fh> should refer to a
296	socket, and C<$in_fh> should refer to mmap'able file.	452	socket, and C<$in_fh> should refer to an mmap'able file.
297		453
298	If the native sendfile call fails or is not implemented, it will be	454	If a native sendfile cannot be found or it fails with C<ENOSYS>,
		455	C<ENOTSUP>, C<EOPNOTSUPP>, C<EAFNOSUPPORT>, C<EPROTOTYPE> or C<ENOTSOCK>,
299	emulated, so you can call C<aio_sendfile> on any type of filehandle	456	it will be emulated, so you can call C<aio_sendfile> on any type of
300	regardless of the limitations of the operating system.	457	filehandle regardless of the limitations of the operating system.
301		458
302	Please note, however, that C<aio_sendfile> can read more bytes from
303	C<$in_fh> than are written, and there is no way to find out how many
304	bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only
305	provides the number of bytes written to C<$out_fh>. Only if the result
306	value equals C<$length> one can assume that C<$length> bytes have been
307	read.
308		459
309	=item aio_readahead $fh,$offset,$length, $callback->($retval)	460	=item aio_readahead $fh,$offset,$length, $callback->($retval)
310		461
311	C<aio_readahead> populates the page cache with data from a file so that	462	C<aio_readahead> populates the page cache with data from a file so that
312	subsequent reads from that file will not block on disk I/O. The C<$offset>	463	subsequent reads from that file will not block on disk I/O. The C<$offset>
…		…
318	file. The current file offset of the file is left unchanged.	469	file. The current file offset of the file is left unchanged.
319		470
320	If that syscall doesn't exist (likely if your OS isn't Linux) it will be	471	If that syscall doesn't exist (likely if your OS isn't Linux) it will be
321	emulated by simply reading the data, which would have a similar effect.	472	emulated by simply reading the data, which would have a similar effect.
322		473
		474
323	=item aio_stat $fh_or_path, $callback->($status)	475	=item aio_stat $fh_or_path, $callback->($status)
324		476
325	=item aio_lstat $fh, $callback->($status)	477	=item aio_lstat $fh, $callback->($status)
326		478
327	Works like perl's C<stat> or C<lstat> in void context. The callback will	479	Works like perl's C<stat> or C<lstat> in void context. The callback will
…		…
332	for an explanation.	484	for an explanation.
333		485
334	Currently, the stats are always 64-bit-stats, i.e. instead of returning an	486	Currently, the stats are always 64-bit-stats, i.e. instead of returning an
335	error when stat'ing a large file, the results will be silently truncated	487	error when stat'ing a large file, the results will be silently truncated
336	unless perl itself is compiled with large file support.	488	unless perl itself is compiled with large file support.
		489
		490	To help interpret the mode and dev/rdev stat values, IO::AIO offers the
		491	following constants and functions (if not implemented, the constants will
		492	be C<0> and the functions will either C<croak> or fall back on traditional
		493	behaviour).
		494
		495	C<S_IFMT>, C<S_IFIFO>, C<S_IFCHR>, C<S_IFBLK>, C<S_IFLNK>, C<S_IFREG>,
		496	C<S_IFDIR>, C<S_IFWHT>, C<S_IFSOCK>, C<IO::AIO::major $dev_t>,
		497	C<IO::AIO::minor $dev_t>, C<IO::AIO::makedev $major, $minor>.
337		498
338	Example: Print the length of F</etc/passwd>:	499	Example: Print the length of F</etc/passwd>:
339		500
340	aio_stat "/etc/passwd", sub {	501	aio_stat "/etc/passwd", sub {
341	$_[0] and die "stat failed: $!";	502	$_[0] and die "stat failed: $!";
342	print "size is ", -s _, "\n";	503	print "size is ", -s _, "\n";
343	};	504	};
344		505
		506
		507	=item aio_statvfs $fh_or_path, $callback->($statvfs)
		508
		509	Works like the POSIX C<statvfs> or C<fstatvfs> syscalls, depending on
		510	whether a file handle or path was passed.
		511
		512	On success, the callback is passed a hash reference with the following
		513	members: C<bsize>, C<frsize>, C<blocks>, C<bfree>, C<bavail>, C<files>,
		514	C<ffree>, C<favail>, C<fsid>, C<flag> and C<namemax>. On failure, C<undef>
		515	is passed.
		516
		517	The following POSIX IO::AIO::ST_* constants are defined: C<ST_RDONLY> and
		518	C<ST_NOSUID>.
		519
		520	The following non-POSIX IO::AIO::ST_* flag masks are defined to
		521	their correct value when available, or to C<0> on systems that do
		522	not support them: C<ST_NODEV>, C<ST_NOEXEC>, C<ST_SYNCHRONOUS>,
		523	C<ST_MANDLOCK>, C<ST_WRITE>, C<ST_APPEND>, C<ST_IMMUTABLE>, C<ST_NOATIME>,
		524	C<ST_NODIRATIME> and C<ST_RELATIME>.
		525
		526	Example: stat C</wd> and dump out the data if successful.
		527
		528	aio_statvfs "/wd", sub {
		529	my $f = $_[0]
		530	or die "statvfs: $!";
		531
		532	use Data::Dumper;
		533	say Dumper $f;
		534	};
		535
		536	# result:
		537	{
		538	bsize => 1024,
		539	bfree => 4333064312,
		540	blocks => 10253828096,
		541	files => 2050765568,
		542	flag => 4096,
		543	favail => 2042092649,
		544	bavail => 4333064312,
		545	ffree => 2042092649,
		546	namemax => 255,
		547	frsize => 1024,
		548	fsid => 1810
		549	}
		550
		551
		552	=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
		553
		554	Works like perl's C<utime> function (including the special case of $atime
		555	and $mtime being undef). Fractional times are supported if the underlying
		556	syscalls support them.
		557
		558	When called with a pathname, uses utimes(2) if available, otherwise
		559	utime(2). If called on a file descriptor, uses futimes(2) if available,
		560	otherwise returns ENOSYS, so this is not portable.
		561
		562	Examples:
		563
		564	# set atime and mtime to current time (basically touch(1)):
		565	aio_utime "path", undef, undef;
		566	# set atime to current time and mtime to beginning of the epoch:
		567	aio_utime "path", time, undef; # undef==0
		568
		569
		570	=item aio_chown $fh_or_path, $uid, $gid, $callback->($status)
		571
		572	Works like perl's C<chown> function, except that C<undef> for either $uid
		573	or $gid is being interpreted as "do not change" (but -1 can also be used).
		574
		575	Examples:
		576
		577	# same as "chown root path" in the shell:
		578	aio_chown "path", 0, -1;
		579	# same as above:
		580	aio_chown "path", 0, undef;
		581
		582
		583	=item aio_truncate $fh_or_path, $offset, $callback->($status)
		584
		585	Works like truncate(2) or ftruncate(2).
		586
		587
		588	=item aio_chmod $fh_or_path, $mode, $callback->($status)
		589
		590	Works like perl's C<chmod> function.
		591
		592
345	=item aio_unlink $pathname, $callback->($status)	593	=item aio_unlink $pathname, $callback->($status)
346		594
347	Asynchronously unlink (delete) a file and call the callback with the	595	Asynchronously unlink (delete) a file and call the callback with the
348	result code.	596	result code.
349		597
		598
		599	=item aio_mknod $path, $mode, $dev, $callback->($status)
		600
		601	[EXPERIMENTAL]
		602
		603	Asynchronously create a device node (or fifo). See mknod(2).
		604
		605	The only (POSIX-) portable way of calling this function is:
		606
		607	aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ...
		608
		609	See C<aio_stat> for info about some potentially helpful extra constants
		610	and functions.
		611
350	=item aio_link $srcpath, $dstpath, $callback->($status)	612	=item aio_link $srcpath, $dstpath, $callback->($status)
351		613
352	Asynchronously create a new link to the existing object at C<$srcpath> at	614	Asynchronously create a new link to the existing object at C<$srcpath> at
353	the path C<$dstpath> and call the callback with the result code.	615	the path C<$dstpath> and call the callback with the result code.
354		616
		617
355	=item aio_symlink $srcpath, $dstpath, $callback->($status)	618	=item aio_symlink $srcpath, $dstpath, $callback->($status)
356		619
357	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at	620	Asynchronously create a new symbolic link to the existing object at C<$srcpath> at
358	the path C<$dstpath> and call the callback with the result code.	621	the path C<$dstpath> and call the callback with the result code.
359		622
		623
		624	=item aio_readlink $path, $callback->($link)
		625
		626	Asynchronously read the symlink specified by C<$path> and pass it to
		627	the callback. If an error occurs, nothing or undef gets passed to the
		628	callback.
		629
		630
360	=item aio_rename $srcpath, $dstpath, $callback->($status)	631	=item aio_rename $srcpath, $dstpath, $callback->($status)
361		632
362	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as	633	Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as
363	rename(2) and call the callback with the result code.	634	rename(2) and call the callback with the result code.
364		635
		636
		637	=item aio_mkdir $pathname, $mode, $callback->($status)
		638
		639	Asynchronously mkdir (create) a directory and call the callback with
		640	the result code. C<$mode> will be modified by the umask at the time the
		641	request is executed, so do not change your umask.
		642
		643
365	=item aio_rmdir $pathname, $callback->($status)	644	=item aio_rmdir $pathname, $callback->($status)
366		645
367	Asynchronously rmdir (delete) a directory and call the callback with the	646	Asynchronously rmdir (delete) a directory and call the callback with the
368	result code.	647	result code.
		648
369		649
370	=item aio_readdir $pathname, $callback->($entries)	650	=item aio_readdir $pathname, $callback->($entries)
371		651
372	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire	652	Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
373	directory (i.e. opendir + readdir + closedir). The entries will not be	653	directory (i.e. opendir + readdir + closedir). The entries will not be
374	sorted, and will B<NOT> include the C<.> and C<..> entries.	654	sorted, and will B<NOT> include the C<.> and C<..> entries.
375		655
376	The callback a single argument which is either C<undef> or an array-ref	656	The callback is passed a single argument which is either C<undef> or an
377	with the filenames.	657	array-ref with the filenames.
		658
		659
		660	=item aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		661
		662	Quite similar to C<aio_readdir>, but the C<$flags> argument allows to tune
		663	behaviour and output format. In case of an error, C<$entries> will be
		664	C<undef>.
		665
		666	The flags are a combination of the following constants, ORed together (the
		667	flags will also be passed to the callback, possibly modified):
		668
		669	=over 4
		670
		671	=item IO::AIO::READDIR_DENTS
		672
		673	When this flag is off, then the callback gets an arrayref consisting of
		674	names only (as with C<aio_readdir>), otherwise it gets an arrayref with
		675	C<[$name, $type, $inode]> arrayrefs, each describing a single directory
		676	entry in more detail.
		677
		678	C<$name> is the name of the entry.
		679
		680	C<$type> is one of the C<IO::AIO::DT_xxx> constants:
		681
		682	C<IO::AIO::DT_UNKNOWN>, C<IO::AIO::DT_FIFO>, C<IO::AIO::DT_CHR>, C<IO::AIO::DT_DIR>,
		683	C<IO::AIO::DT_BLK>, C<IO::AIO::DT_REG>, C<IO::AIO::DT_LNK>, C<IO::AIO::DT_SOCK>,
		684	C<IO::AIO::DT_WHT>.
		685
		686	C<IO::AIO::DT_UNKNOWN> means just that: readdir does not know. If you need to
		687	know, you have to run stat yourself. Also, for speed reasons, the C<$type>
		688	scalars are read-only: you can not modify them.
		689
		690	C<$inode> is the inode number (which might not be exact on systems with 64
		691	bit inode numbers and 32 bit perls). This field has unspecified content on
		692	systems that do not deliver the inode information.
		693
		694	=item IO::AIO::READDIR_DIRS_FIRST
		695
		696	When this flag is set, then the names will be returned in an order where
		697	likely directories come first, in optimal stat order. This is useful when
		698	you need to quickly find directories, or you want to find all directories
		699	while avoiding to stat() each entry.
		700
		701	If the system returns type information in readdir, then this is used
		702	to find directories directly. Otherwise, likely directories are names
		703	beginning with ".", or otherwise names with no dots, of which names with
		704	short names are tried first.
		705
		706	=item IO::AIO::READDIR_STAT_ORDER
		707
		708	When this flag is set, then the names will be returned in an order
		709	suitable for stat()'ing each one. That is, when you plan to stat()
		710	all files in the given directory, then the returned order will likely
		711	be fastest.
		712
		713	If both this flag and C<IO::AIO::READDIR_DIRS_FIRST> are specified, then
		714	the likely dirs come first, resulting in a less optimal stat order.
		715
		716	=item IO::AIO::READDIR_FOUND_UNKNOWN
		717
		718	This flag should not be set when calling C<aio_readdirx>. Instead, it
		719	is being set by C<aio_readdirx>, when any of the C<$type>'s found were
		720	C<IO::AIO::DT_UNKNOWN>. The absense of this flag therefore indicates that all
		721	C<$type>'s are known, which can be used to speed up some algorithms.
		722
		723	=back
		724
		725
		726	=item aio_load $path, $data, $callback->($status)
		727
		728	This is a composite request that tries to fully load the given file into
		729	memory. Status is the same as with aio_read.
		730
		731	=cut
		732
		733	sub aio_load($$;$) {
		734	my ($path, undef, $cb) = @_;
		735	my $data = \$_[1];
		736
		737	my $pri = aioreq_pri;
		738	my $grp = aio_group $cb;
		739
		740	aioreq_pri $pri;
		741	add $grp aio_open $path, O_RDONLY, 0, sub {
		742	my $fh = shift
		743	or return $grp->result (-1);
		744
		745	aioreq_pri $pri;
		746	add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub {
		747	$grp->result ($_[0]);
		748	};
		749	};
		750
		751	$grp
		752	}
		753
		754	=item aio_copy $srcpath, $dstpath, $callback->($status)
		755
		756	Try to copy the I<file> (directories not supported as either source or
		757	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		758	a status of C<0> (ok) or C<-1> (error, see C<$!>).
		759
		760	This is a composite request that creates the destination file with
		761	mode 0200 and copies the contents of the source file into it using
		762	C<aio_sendfile>, followed by restoring atime, mtime, access mode and
		763	uid/gid, in that order.
		764
		765	If an error occurs, the partial destination file will be unlinked, if
		766	possible, except when setting atime, mtime, access mode and uid/gid, where
		767	errors are being ignored.
		768
		769	=cut
		770
		771	sub aio_copy($$;$) {
		772	my ($src, $dst, $cb) = @_;
		773
		774	my $pri = aioreq_pri;
		775	my $grp = aio_group $cb;
		776
		777	aioreq_pri $pri;
		778	add $grp aio_open $src, O_RDONLY, 0, sub {
		779	if (my $src_fh = $_[0]) {
		780	my @stat = stat $src_fh; # hmm, might block over nfs?
		781
		782	aioreq_pri $pri;
		783	add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {
		784	if (my $dst_fh = $_[0]) {
		785	aioreq_pri $pri;
		786	add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
		787	if ($_[0] == $stat[7]) {
		788	$grp->result (0);
		789	close $src_fh;
		790
		791	my $ch = sub {
		792	aioreq_pri $pri;
		793	add $grp aio_chmod $dst_fh, $stat[2] & 07777, sub {
		794	aioreq_pri $pri;
		795	add $grp aio_chown $dst_fh, $stat[4], $stat[5], sub {
		796	aioreq_pri $pri;
		797	add $grp aio_close $dst_fh;
		798	}
		799	};
		800	};
		801
		802	aioreq_pri $pri;
		803	add $grp aio_utime $dst_fh, $stat[8], $stat[9], sub {
		804	if ($_[0] < 0 && $! == ENOSYS) {
		805	aioreq_pri $pri;
		806	add $grp aio_utime $dst, $stat[8], $stat[9], $ch;
		807	} else {
		808	$ch->();
		809	}
		810	};
		811	} else {
		812	$grp->result (-1);
		813	close $src_fh;
		814	close $dst_fh;
		815
		816	aioreq $pri;
		817	add $grp aio_unlink $dst;
		818	}
		819	};
		820	} else {
		821	$grp->result (-1);
		822	}
		823	},
		824
		825	} else {
		826	$grp->result (-1);
		827	}
		828	};
		829
		830	$grp
		831	}
		832
		833	=item aio_move $srcpath, $dstpath, $callback->($status)
		834
		835	Try to move the I<file> (directories not supported as either source or
		836	destination) from C<$srcpath> to C<$dstpath> and call the callback with
		837	a status of C<0> (ok) or C<-1> (error, see C<$!>).
		838
		839	This is a composite request that tries to rename(2) the file first; if
		840	rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if
		841	that is successful, unlinks the C<$srcpath>.
		842
		843	=cut
		844
		845	sub aio_move($$;$) {
		846	my ($src, $dst, $cb) = @_;
		847
		848	my $pri = aioreq_pri;
		849	my $grp = aio_group $cb;
		850
		851	aioreq_pri $pri;
		852	add $grp aio_rename $src, $dst, sub {
		853	if ($_[0] && $! == EXDEV) {
		854	aioreq_pri $pri;
		855	add $grp aio_copy $src, $dst, sub {
		856	$grp->result ($_[0]);
		857
		858	if (!$_[0]) {
		859	aioreq_pri $pri;
		860	add $grp aio_unlink $src;
		861	}
		862	};
		863	} else {
		864	$grp->result ($_[0]);
		865	}
		866	};
		867
		868	$grp
		869	}
378		870
379	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)	871	=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
380		872
381	[EXPERIMENTAL due to internal aio_group use]
382
383	Scans a directory (similar to C<aio_readdir>) but additionally tries to	873	Scans a directory (similar to C<aio_readdir>) but additionally tries to
384	separate the entries of directory C<$path> into two sets of names, ones	874	efficiently separate the entries of directory C<$path> into two sets of
385	you can recurse into (directories or links to them), and ones you cannot	875	names, directories you can recurse into (directories), and ones you cannot
386	recurse into (everything else).	876	recurse into (everything else, including symlinks to directories).
387		877
388	C<aio_scandir> is a composite request that creates of many sub requests_	878	C<aio_scandir> is a composite request that creates of many sub requests_
389	C<$maxreq> specifies the maximum number of outstanding aio requests that	879	C<$maxreq> specifies the maximum number of outstanding aio requests that
390	this function generates. If it is C<< <= 0 >>, then a suitable default	880	this function generates. If it is C<< <= 0 >>, then a suitable default
391	will be chosen (currently 6).	881	will be chosen (currently 4).
392		882
393	On error, the callback is called without arguments, otherwise it receives	883	On error, the callback is called without arguments, otherwise it receives
394	two array-refs with path-relative entry names.	884	two array-refs with path-relative entry names.
395		885
396	Example:	886	Example:
…		…
403		893
404	Implementation notes.	894	Implementation notes.
405		895
406	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.	896	The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can.
407		897
		898	If readdir returns file type information, then this is used directly to
		899	find directories.
		900
408	After reading the directory, the modification time, size etc. of the	901	Otherwise, after reading the directory, the modification time, size etc.
409	directory before and after the readdir is checked, and if they match (and	902	of the directory before and after the readdir is checked, and if they
410	isn't the current time), the link count will be used to decide how many	903	match (and isn't the current time), the link count will be used to decide
411	entries are directories (if >= 2). Otherwise, no knowledge of the number	904	how many entries are directories (if >= 2). Otherwise, no knowledge of the
412	of subdirectories will be assumed.	905	number of subdirectories will be assumed.
413		906
414	Then entries will be sorted into likely directories (everything without	907	Then entries will be sorted into likely directories a non-initial dot
415	a non-initial dot currently) and likely non-directories (everything	908	currently) and likely non-directories (see C<aio_readdirx>). Then every
416	else). Then every entry plus an appended C</.> will be C<stat>'ed,	909	entry plus an appended C</.> will be C<stat>'ed, likely directories first,
417	likely directories first. If that succeeds, it assumes that the entry	910	in order of their inode numbers. If that succeeds, it assumes that the
418	is a directory or a symlink to directory (which will be checked	911	entry is a directory or a symlink to directory (which will be checked
419	seperately). This is often faster than stat'ing the entry itself because	912	seperately). This is often faster than stat'ing the entry itself because
420	filesystems might detect the type of the entry without reading the inode	913	filesystems might detect the type of the entry without reading the inode
421	data (e.g. ext2fs filetype feature).	914	data (e.g. ext2fs filetype feature), even on systems that cannot return
		915	the filetype information on readdir.
422		916
423	If the known number of directories (link count - 2) has been reached, the	917	If the known number of directories (link count - 2) has been reached, the
424	rest of the entries is assumed to be non-directories.	918	rest of the entries is assumed to be non-directories.
425		919
426	This only works with certainty on POSIX (= UNIX) filesystems, which	920	This only works with certainty on POSIX (= UNIX) filesystems, which
…		…
430	as those tend to return 0 or 1 as link counts, which disables the	924	as those tend to return 0 or 1 as link counts, which disables the
431	directory counting heuristic.	925	directory counting heuristic.
432		926
433	=cut	927	=cut
434		928
435	sub aio_scandir($$$) {	929	sub aio_scandir($$;$) {
436	my ($path, $maxreq, $cb) = @_;	930	my ($path, $maxreq, $cb) = @_;
437		931
		932	my $pri = aioreq_pri;
		933
438	my $grp = aio_group $cb;	934	my $grp = aio_group $cb;
439		935
440	$maxreq = 6 if $maxreq <= 0;	936	$maxreq = 4 if $maxreq <= 0;
441		937
442	# stat once	938	# stat once
		939	aioreq_pri $pri;
443	add $grp aio_stat $path, sub {	940	add $grp aio_stat $path, sub {
444	return $grp->result () if $_[0];	941	return $grp->result () if $_[0];
445	my $now = time;	942	my $now = time;
446	my $hash1 = join ":", (stat _)[0,1,3,7,9];	943	my $hash1 = join ":", (stat _)[0,1,3,7,9];
447		944
448	# read the directory entries	945	# read the directory entries
		946	aioreq_pri $pri;
449	add $grp aio_readdir $path, sub {	947	add $grp aio_readdirx $path, READDIR_DIRS_FIRST, sub {
450	my $entries = shift	948	my $entries = shift
451	or return $grp->result ();	949	or return $grp->result ();
452		950
453	# stat the dir another time	951	# stat the dir another time
		952	aioreq_pri $pri;
454	add $grp aio_stat $path, sub {	953	add $grp aio_stat $path, sub {
455	my $hash2 = join ":", (stat _)[0,1,3,7,9];	954	my $hash2 = join ":", (stat _)[0,1,3,7,9];
456		955
457	my $ndirs;	956	my $ndirs;
458		957
459	# take the slow route if anything looks fishy	958	# take the slow route if anything looks fishy
460	if ($hash1 ne $hash2 or (stat _)[9] == $now) {	959	if ($hash1 ne $hash2 or (stat _)[9] == $now) {
461	$ndirs = -1;	960	$ndirs = -1;
462	} else {	961	} else {
463	# if nlink == 2, we are finished	962	# if nlink == 2, we are finished
464	# on non-posix-fs's, we rely on nlink < 2	963	# for non-posix-fs's, we rely on nlink < 2
465	$ndirs = (stat _)[3] - 2	964	$ndirs = (stat _)[3] - 2
466	or return $grp->result ([], $entries);	965	or return $grp->result ([], $entries);
467	}	966	}
468		967
469	# sort into likely dirs and likely nondirs
470	# dirs == files without ".", short entries first
471	$entries = [map $_->[0],
472	sort { $b->[1] cmp $a->[1] }
473	map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],
474	@$entries];
475
476	my (@dirs, @nondirs);	968	my (@dirs, @nondirs);
477		969
478	my ($statcb, $schedcb);
479	my $nreq = 0;
480
481	my $statgrp = add $grp aio_group;	970	my $statgrp = add $grp aio_group sub {
		971	$grp->result (\@dirs, \@nondirs);
		972	};
482		973
483	$schedcb = sub {	974	limit $statgrp $maxreq;
484	if (@$entries) {	975	feed $statgrp sub {
485	if ($nreq < $maxreq) {	976	return unless @$entries;
486	my $ent = pop @$entries;	977	my $entry = shift @$entries;
		978
		979	aioreq_pri $pri;
		980	add $statgrp aio_stat "$path/$entry/.", sub {
		981	if ($_[0] < 0) {
		982	push @nondirs, $entry;
		983	} else {
		984	# need to check for real directory
		985	aioreq_pri $pri;
		986	add $statgrp aio_lstat "$path/$entry", sub {
		987	if (-d _) {
		988	push @dirs, $entry;
		989
		990	unless (--$ndirs) {
		991	push @nondirs, @$entries;
		992	feed $statgrp;
		993	}
		994	} else {
		995	push @nondirs, $entry;
		996	}
487	$nreq++;	997	}
488	add $statgrp aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) };
489	}	998	}
490	} elsif (!$nreq) {
491	# finished
492	$statgrp->cancel;
493	undef $statcb;
494	undef $schedcb;
495	$grp->result (\@dirs, \@nondirs);
496	}	999	};
497	};	1000	};
498	$statcb = sub {
499	my ($status, $entry) = @_;
500
501	if ($status < 0) {
502	$nreq--;
503	push @nondirs, $entry;
504	&$schedcb;
505	} else {
506	# need to check for real directory
507	add $grp aio_lstat "$path/$entry", sub {
508	$nreq--;
509
510	if (-d _) {
511	push @dirs, $entry;
512
513	if (!--$ndirs) {
514	push @nondirs, @$entries;
515	$entries = [];
516	}
517	} else {
518	push @nondirs, $entry;
519	}
520
521	&$schedcb;
522	}
523	}
524	};
525
526	&$schedcb while @$entries && $nreq < $maxreq;
527	};	1001	};
528	};	1002	};
529	};	1003	};
530		1004
531	$grp	1005	$grp
532	}	1006	}
533		1007
		1008	=item aio_rmtree $path, $callback->($status)
		1009
		1010	Delete a directory tree starting (and including) C<$path>, return the
		1011	status of the final C<rmdir> only. This is a composite request that
		1012	uses C<aio_scandir> to recurse into and rmdir directories, and unlink
		1013	everything else.
		1014
		1015	=cut
		1016
		1017	sub aio_rmtree;
		1018	sub aio_rmtree($;$) {
		1019	my ($path, $cb) = @_;
		1020
		1021	my $pri = aioreq_pri;
		1022	my $grp = aio_group $cb;
		1023
		1024	aioreq_pri $pri;
		1025	add $grp aio_scandir $path, 0, sub {
		1026	my ($dirs, $nondirs) = @_;
		1027
		1028	my $dirgrp = aio_group sub {
		1029	add $grp aio_rmdir $path, sub {
		1030	$grp->result ($_[0]);
		1031	};
		1032	};
		1033
		1034	(aioreq_pri $pri), add $dirgrp aio_rmtree "$path/$_" for @$dirs;
		1035	(aioreq_pri $pri), add $dirgrp aio_unlink "$path/$_" for @$nondirs;
		1036
		1037	add $grp $dirgrp;
		1038	};
		1039
		1040	$grp
		1041	}
		1042
		1043	=item aio_sync $callback->($status)
		1044
		1045	Asynchronously call sync and call the callback when finished.
		1046
534	=item aio_fsync $fh, $callback->($status)	1047	=item aio_fsync $fh, $callback->($status)
535		1048
536	Asynchronously call fsync on the given filehandle and call the callback	1049	Asynchronously call fsync on the given filehandle and call the callback
537	with the fsync result code.	1050	with the fsync result code.
538		1051
…		…
542	callback with the fdatasync result code.	1055	callback with the fdatasync result code.
543		1056
544	If this call isn't available because your OS lacks it or it couldn't be	1057	If this call isn't available because your OS lacks it or it couldn't be
545	detected, it will be emulated by calling C<fsync> instead.	1058	detected, it will be emulated by calling C<fsync> instead.
546		1059
		1060	=item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		1061
		1062	Sync the data portion of the file specified by C<$offset> and C<$length>
		1063	to disk (but NOT the metadata), by calling the Linux-specific
		1064	sync_file_range call. If sync_file_range is not available or it returns
		1065	ENOSYS, then fdatasync or fsync is being substituted.
		1066
		1067	C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>,
		1068	C<IO::AIO::SYNC_FILE_RANGE_WRITE> and
		1069	C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range
		1070	manpage for details.
		1071
		1072	=item aio_pathsync $path, $callback->($status)
		1073
		1074	This request tries to open, fsync and close the given path. This is a
		1075	composite request intended to sync directories after directory operations
		1076	(E.g. rename). This might not work on all operating systems or have any
		1077	specific effect, but usually it makes sure that directory changes get
		1078	written to disc. It works for anything that can be opened for read-only,
		1079	not just directories.
		1080
		1081	Future versions of this function might fall back to other methods when
		1082	C<fsync> on the directory fails (such as calling C<sync>).
		1083
		1084	Passes C<0> when everything went ok, and C<-1> on error.
		1085
		1086	=cut
		1087
		1088	sub aio_pathsync($;$) {
		1089	my ($path, $cb) = @_;
		1090
		1091	my $pri = aioreq_pri;
		1092	my $grp = aio_group $cb;
		1093
		1094	aioreq_pri $pri;
		1095	add $grp aio_open $path, O_RDONLY, 0, sub {
		1096	my ($fh) = @_;
		1097	if ($fh) {
		1098	aioreq_pri $pri;
		1099	add $grp aio_fsync $fh, sub {
		1100	$grp->result ($_[0]);
		1101
		1102	aioreq_pri $pri;
		1103	add $grp aio_close $fh;
		1104	};
		1105	} else {
		1106	$grp->result (-1);
		1107	}
		1108	};
		1109
		1110	$grp
		1111	}
		1112
		1113	=item aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		1114
		1115	This is a rather advanced IO::AIO call, which only works on mmap(2)ed
		1116	scalars (see the C<IO::AIO::mmap> function, although it also works on data
		1117	scalars managed by the L<Sys::Mmap> or L<Mmap> modules, note that the
		1118	scalar must only be modified in-place while an aio operation is pending on
		1119	it).
		1120
		1121	It calls the C<msync> function of your OS, if available, with the memory
		1122	area starting at C<$offset> in the string and ending C<$length> bytes
		1123	later. If C<$length> is negative, counts from the end, and if C<$length>
		1124	is C<undef>, then it goes till the end of the string. The flags can be
		1125	a combination of C<IO::AIO::MS_ASYNC>, C<IO::AIO::MS_INVALIDATE> and
		1126	C<IO::AIO::MS_SYNC>.
		1127
		1128	=item aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
		1129
		1130	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1131	scalars.
		1132
		1133	It touches (reads or writes) all memory pages in the specified
		1134	range inside the scalar. All caveats and parameters are the same
		1135	as for C<aio_msync>, above, except for flags, which must be either
		1136	C<0> (which reads all pages and ensures they are instantiated) or
		1137	C<IO::AIO::MT_MODIFY>, which modifies the memory page s(by reading and
		1138	writing an octet from it, which dirties the page).
		1139
		1140	=item aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status)
		1141
		1142	This is a rather advanced IO::AIO call, which works best on mmap(2)ed
		1143	scalars.
		1144
		1145	It reads in all the pages of the underlying storage into memory (if any)
		1146	and locks them, so they are not getting swapped/paged out or removed.
		1147
		1148	If C<$length> is undefined, then the scalar will be locked till the end.
		1149
		1150	On systems that do not implement C<mlock>, this function returns C<-1>
		1151	and sets errno to C<ENOSYS>.
		1152
		1153	Note that the corresponding C<munlock> is synchronous and is
		1154	documented under L<MISCELLANEOUS FUNCTIONS>.
		1155
		1156	Example: open a file, mmap and mlock it - both will be undone when
		1157	C<$data> gets destroyed.
		1158
		1159	open my $fh, "<", $path or die "$path: $!";
		1160	my $data;
		1161	IO::AIO::mmap $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh;
		1162	aio_mlock $data; # mlock in background
		1163
		1164	=item aio_mlockall $flags, $callback->($status)
		1165
		1166	Calls the C<mlockall> function with the given C<$flags> (a combination of
		1167	C<IO::AIO::MCL_CURRENT> and C<IO::AIO::MCL_FUTURE>).
		1168
		1169	On systems that do not implement C<mlockall>, this function returns C<-1>
		1170	and sets errno to C<ENOSYS>.
		1171
		1172	Note that the corresponding C<munlockall> is synchronous and is
		1173	documented under L<MISCELLANEOUS FUNCTIONS>.
		1174
		1175	Example: asynchronously lock all current and future pages into memory.
		1176
		1177	aio_mlockall IO::AIO::MCL_FUTURE;
		1178
547	=item aio_group $callback->(...)	1179	=item aio_group $callback->(...)
548
549	[EXPERIMENTAL]
550		1180
551	This is a very special aio request: Instead of doing something, it is a	1181	This is a very special aio request: Instead of doing something, it is a
552	container for other aio requests, which is useful if you want to bundle	1182	container for other aio requests, which is useful if you want to bundle
553	many requests into a single, composite, request.	1183	many requests into a single, composite, request with a definite callback
		1184	and the ability to cancel the whole request with its subrequests.
554		1185
555	Returns an object of class L<IO::AIO::GRP>. See its documentation below	1186	Returns an object of class L<IO::AIO::GRP>. See its documentation below
556	for more info.	1187	for more info.
557		1188
558	Example:	1189	Example:
…		…
577	phase and still requires a worker thread. Thus, the callback will not	1208	phase and still requires a worker thread. Thus, the callback will not
578	be executed immediately but only after other requests in the queue have	1209	be executed immediately but only after other requests in the queue have
579	entered their execution phase. This can be used to measure request	1210	entered their execution phase. This can be used to measure request
580	latency.	1211	latency.
581		1212
582	=item IO::AIO::aio_sleep $fractional_seconds, $callback->() *NOT EXPORTED*	1213	=item IO::AIO::aio_busy $fractional_seconds, $callback->() *NOT EXPORTED*
583		1214
584	Mainly used for debugging and benchmarking, this aio request puts one of	1215	Mainly used for debugging and benchmarking, this aio request puts one of
585	the request workers to sleep for the given time.	1216	the request workers to sleep for the given time.
586		1217
587	While it is theoretically handy to have simple I/O scheduling requests	1218	While it is theoretically handy to have simple I/O scheduling requests
588	like sleep and file handle readable/writable, the overhead this creates	1219	like sleep and file handle readable/writable, the overhead this creates is
589	is immense, so do not use this function except to put your application	1220	immense (it blocks a thread for a long time) so do not use this function
590	under artificial I/O pressure.	1221	except to put your application under artificial I/O pressure.
591		1222
592	=back	1223	=back
593		1224
594	=head2 IO::AIO::REQ CLASS	1225	=head2 IO::AIO::REQ CLASS
595		1226
596	All non-aggregate C<aio_*> functions return an object of this class when	1227	All non-aggregate C<aio_*> functions return an object of this class when
597	called in non-void context.	1228	called in non-void context.
598
599	A request always moves through the following five states in its lifetime,
600	in order: B<ready> (request has been created, but has not been executed
601	yet), B<execute> (request is currently being executed), B<pending>
602	(request has been executed but callback has not been called yet),
603	B<result> (results are being processed synchronously, includes calling the
604	callback) and B<done> (request has reached the end of its lifetime and
605	holds no resources anymore).
606		1229
607	=over 4	1230	=over 4
608		1231
609	=item cancel $req	1232	=item cancel $req
610		1233
611	Cancels the request, if possible. Has the effect of skipping execution	1234	Cancels the request, if possible. Has the effect of skipping execution
612	when entering the B<execute> state and skipping calling the callback when	1235	when entering the B<execute> state and skipping calling the callback when
613	entering the the B<result> state, but will leave the request otherwise	1236	entering the the B<result> state, but will leave the request otherwise
614	untouched. That means that requests that currently execute will not be	1237	untouched (with the exception of readdir). That means that requests that
615	stopped and resources held by the request will not be freed prematurely.	1238	currently execute will not be stopped and resources held by the request
		1239	will not be freed prematurely.
616		1240
617	=item cb $req $callback->(...)	1241	=item cb $req $callback->(...)
618		1242
619	Replace (or simply set) the callback registered to the request.	1243	Replace (or simply set) the callback registered to the request.
620		1244
…		…
664	=item * They can also can also be added to other IO::AIO::GRP objects.	1288	=item * They can also can also be added to other IO::AIO::GRP objects.
665		1289
666	=item * You must not add requests to a group from within the group callback (or	1290	=item * You must not add requests to a group from within the group callback (or
667	any later time).	1291	any later time).
668		1292
669	=item * This does not harmonise well with C<max_outstanding>, so best do
670	not combine C<aio_group> with it. Groups and feeders are recommended for
671	this kind of concurrency-limiting.
672
673	=back	1293	=back
674		1294
675	Their lifetime, simplified, looks like this: when they are empty, they	1295	Their lifetime, simplified, looks like this: when they are empty, they
676	will finish very quickly. If they contain only requests that are in the	1296	will finish very quickly. If they contain only requests that are in the
677	C<done> state, they will also finish. Otherwise they will continue to	1297	C<done> state, they will also finish. Otherwise they will continue to
678	exist.	1298	exist.
679		1299
680	That means after creating a group you have some time to add requests. And	1300	That means after creating a group you have some time to add requests
681	in the callbacks of those requests, you can add further requests to the	1301	(precisely before the callback has been invoked, which is only done within
682	group. And only when all those requests have finished will the the group	1302	the C<poll_cb>). And in the callbacks of those requests, you can add
683	itself finish.	1303	further requests to the group. And only when all those requests have
		1304	finished will the the group itself finish.
684		1305
685	=over 4	1306	=over 4
686		1307
687	=item add $grp ...	1308	=item add $grp ...
688		1309
…		…
692	be added, including other groups, as long as you do not create circular	1313	be added, including other groups, as long as you do not create circular
693	dependencies.	1314	dependencies.
694		1315
695	Returns all its arguments.	1316	Returns all its arguments.
696		1317
		1318	=item $grp->cancel_subs
		1319
		1320	Cancel all subrequests and clears any feeder, but not the group request
		1321	itself. Useful when you queued a lot of events but got a result early.
		1322
		1323	The group request will finish normally (you cannot add requests to the
		1324	group).
		1325
697	=item $grp->result (...)	1326	=item $grp->result (...)
698		1327
699	Set the result value(s) that will be passed to the group callback when all	1328	Set the result value(s) that will be passed to the group callback when all
700	subrequests have finished. By default, no argument will be passed.	1329	subrequests have finished and set the groups errno to the current value
		1330	of errno (just like calling C<errno> without an error number). By default,
		1331	no argument will be passed and errno is zero.
		1332
		1333	=item $grp->errno ([$errno])
		1334
		1335	Sets the group errno value to C<$errno>, or the current value of errno
		1336	when the argument is missing.
		1337
		1338	Every aio request has an associated errno value that is restored when
		1339	the callback is invoked. This method lets you change this value from its
		1340	default (0).
		1341
		1342	Calling C<result> will also set errno, so make sure you either set C<$!>
		1343	before the call to C<result>, or call c<errno> after it.
701		1344
702	=item feed $grp $callback->($grp)	1345	=item feed $grp $callback->($grp)
703
704	[VERY EXPERIMENTAL]
705		1346
706	Sets a feeder/generator on this group: every group can have an attached	1347	Sets a feeder/generator on this group: every group can have an attached
707	generator that generates requests if idle. The idea behind this is that,	1348	generator that generates requests if idle. The idea behind this is that,
708	although you could just queue as many requests as you want in a group,	1349	although you could just queue as many requests as you want in a group,
709	this might starve other requests for a potentially long time. For	1350	this might starve other requests for a potentially long time. For example,
710	example, C<aio_scandir> might generate hundreds of thousands C<aio_stat>	1351	C<aio_scandir> might generate hundreds of thousands C<aio_stat> requests,
711	requests, delaying any later requests for a long time.	1352	delaying any later requests for a long time.
712		1353
713	To avoid this, and allow incremental generation of requests, you can	1354	To avoid this, and allow incremental generation of requests, you can
714	instead a group and set a feeder on it that generates those requests. The	1355	instead a group and set a feeder on it that generates those requests. The
715	feed callback will be called whenever there are few enough (see C<limit>,	1356	feed callback will be called whenever there are few enough (see C<limit>,
716	below) requests active in the group itself and is expected to queue more	1357	below) requests active in the group itself and is expected to queue more
…		…
720	not impose any limits).	1361	not impose any limits).
721		1362
722	If the feed does not queue more requests when called, it will be	1363	If the feed does not queue more requests when called, it will be
723	automatically removed from the group.	1364	automatically removed from the group.
724		1365
725	If the feed limit is C<0>, it will be set to C<2> automatically.	1366	If the feed limit is C<0> when this method is called, it will be set to
		1367	C<2> automatically.
726		1368
727	Example:	1369	Example:
728		1370
729	# stat all files in @files, but only ever use four aio requests concurrently:	1371	# stat all files in @files, but only ever use four aio requests concurrently:
730		1372
…		…
742	Sets the feeder limit for the group: The feeder will be called whenever	1384	Sets the feeder limit for the group: The feeder will be called whenever
743	the group contains less than this many requests.	1385	the group contains less than this many requests.
744		1386
745	Setting the limit to C<0> will pause the feeding process.	1387	Setting the limit to C<0> will pause the feeding process.
746		1388
		1389	The default value for the limit is C<0>, but note that setting a feeder
		1390	automatically bumps it up to C<2>.
		1391
747	=back	1392	=back
748		1393
749	=head2 SUPPORT FUNCTIONS	1394	=head2 SUPPORT FUNCTIONS
750		1395
		1396	=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION
		1397
751	=over 4	1398	=over 4
752		1399
753	=item $fileno = IO::AIO::poll_fileno	1400	=item $fileno = IO::AIO::poll_fileno
754		1401
755	Return the I<request result pipe file descriptor>. This filehandle must be	1402	Return the I<request result pipe file descriptor>. This filehandle must be
756	polled for reading by some mechanism outside this module (e.g. Event or	1403	polled for reading by some mechanism outside this module (e.g. EV, Glib,
757	select, see below or the SYNOPSIS). If the pipe becomes readable you have	1404	select and so on, see below or the SYNOPSIS). If the pipe becomes readable
758	to call C<poll_cb> to check the results.	1405	you have to call C<poll_cb> to check the results.
759		1406
760	See C<poll_cb> for an example.	1407	See C<poll_cb> for an example.
761		1408
762	=item IO::AIO::poll_cb	1409	=item IO::AIO::poll_cb
763		1410
764	Process all outstanding events on the result pipe. You have to call this	1411	Process some outstanding events on the result pipe. You have to call
765	regularly. Returns the number of events processed. Returns immediately	1412	this regularly. Returns C<0> if all events could be processed (or there
766	when no events are outstanding.	1413	were no events to process), or C<-1> if it returned earlier for whatever
		1414	reason. Returns immediately when no events are outstanding. The amount of
		1415	events processed depends on the settings of C<IO::AIO::max_poll_req> and
		1416	C<IO::AIO::max_poll_time>.
		1417
		1418	If not all requests were processed for whatever reason, the filehandle
		1419	will still be ready when C<poll_cb> returns, so normally you don't have to
		1420	do anything special to have it called later.
		1421
		1422	Apart from calling C<IO::AIO::poll_cb> when the event filehandle becomes
		1423	ready, it can be beneficial to call this function from loops which submit
		1424	a lot of requests, to make sure the results get processed when they become
		1425	available and not just when the loop is finished and the event loop takes
		1426	over again. This function returns very fast when there are no outstanding
		1427	requests.
767		1428
768	Example: Install an Event watcher that automatically calls	1429	Example: Install an Event watcher that automatically calls
769	IO::AIO::poll_cb with high priority:	1430	IO::AIO::poll_cb with high priority (more examples can be found in the
		1431	SYNOPSIS section, at the top of this document):
770		1432
771	Event->io (fd => IO::AIO::poll_fileno,	1433	Event->io (fd => IO::AIO::poll_fileno,
772	poll => 'r', async => 1,	1434	poll => 'r', async => 1,
773	cb => \&IO::AIO::poll_cb);	1435	cb => \&IO::AIO::poll_cb);
774		1436
775	=item IO::AIO::poll_wait	1437	=item IO::AIO::poll_wait
776		1438
		1439	If there are any outstanding requests and none of them in the result
777	Wait till the result filehandle becomes ready for reading (simply does a	1440	phase, wait till the result filehandle becomes ready for reading (simply
778	C<select> on the filehandle. This is useful if you want to synchronously wait	1441	does a C<select> on the filehandle. This is useful if you want to
779	for some requests to finish).	1442	synchronously wait for some requests to finish).
780		1443
781	See C<nreqs> for an example.	1444	See C<nreqs> for an example.
782		1445
		1446	=item IO::AIO::poll
		1447
		1448	Waits until some requests have been handled.
		1449
		1450	Returns the number of requests processed, but is otherwise strictly
		1451	equivalent to:
		1452
		1453	IO::AIO::poll_wait, IO::AIO::poll_cb
		1454
783	=item IO::AIO::nreqs	1455	=item IO::AIO::flush
784		1456
785	Returns the number of requests currently outstanding (i.e. for which their	1457	Wait till all outstanding AIO requests have been handled.
786	callback has not been invoked yet).
787		1458
788	Example: wait till there are no outstanding requests anymore:	1459	Strictly equivalent to:
789		1460
790	IO::AIO::poll_wait, IO::AIO::poll_cb	1461	IO::AIO::poll_wait, IO::AIO::poll_cb
791	while IO::AIO::nreqs;	1462	while IO::AIO::nreqs;
792		1463
793	=item IO::AIO::flush	1464	=item IO::AIO::max_poll_reqs $nreqs
794		1465
795	Wait till all outstanding AIO requests have been handled.	1466	=item IO::AIO::max_poll_time $seconds
796		1467
797	Strictly equivalent to:	1468	These set the maximum number of requests (default C<0>, meaning infinity)
		1469	that are being processed by C<IO::AIO::poll_cb> in one call, respectively
		1470	the maximum amount of time (default C<0>, meaning infinity) spent in
		1471	C<IO::AIO::poll_cb> to process requests (more correctly the mininum amount
		1472	of time C<poll_cb> is allowed to use).
798		1473
799	IO::AIO::poll_wait, IO::AIO::poll_cb	1474	Setting C<max_poll_time> to a non-zero value creates an overhead of one
800	while IO::AIO::nreqs;	1475	syscall per request processed, which is not normally a problem unless your
		1476	callbacks are really really fast or your OS is really really slow (I am
		1477	not mentioning Solaris here). Using C<max_poll_reqs> incurs no overhead.
801		1478
802	=item IO::AIO::poll	1479	Setting these is useful if you want to ensure some level of
		1480	interactiveness when perl is not fast enough to process all requests in
		1481	time.
803		1482
804	Waits until some requests have been handled.	1483	For interactive programs, values such as C<0.01> to C<0.1> should be fine.
805		1484
806	Strictly equivalent to:	1485	Example: Install an Event watcher that automatically calls
		1486	IO::AIO::poll_cb with low priority, to ensure that other parts of the
		1487	program get the CPU sometimes even under high AIO load.
807		1488
808	IO::AIO::poll_wait, IO::AIO::poll_cb	1489	# try not to spend much more than 0.1s in poll_cb
809	if IO::AIO::nreqs;	1490	IO::AIO::max_poll_time 0.1;
		1491
		1492	# use a low priority so other tasks have priority
		1493	Event->io (fd => IO::AIO::poll_fileno,
		1494	poll => 'r', nice => 1,
		1495	cb => &IO::AIO::poll_cb);
		1496
		1497	=back
		1498
		1499	=head3 CONTROLLING THE NUMBER OF THREADS
		1500
		1501	=over
810		1502
811	=item IO::AIO::min_parallel $nthreads	1503	=item IO::AIO::min_parallel $nthreads
812		1504
813	Set the minimum number of AIO threads to C<$nthreads>. The current	1505	Set the minimum number of AIO threads to C<$nthreads>. The current
814	default is C<8>, which means eight asynchronous operations can execute	1506	default is C<8>, which means eight asynchronous operations can execute
815	concurrently at any one time (the number of outstanding requests,	1507	concurrently at any one time (the number of outstanding requests,
816	however, is unlimited).	1508	however, is unlimited).
817		1509
818	IO::AIO starts threads only on demand, when an AIO request is queued and	1510	IO::AIO starts threads only on demand, when an AIO request is queued and
819	no free thread exists.	1511	no free thread exists. Please note that queueing up a hundred requests can
		1512	create demand for a hundred threads, even if it turns out that everything
		1513	is in the cache and could have been processed faster by a single thread.
820		1514
821	It is recommended to keep the number of threads relatively low, as some	1515	It is recommended to keep the number of threads relatively low, as some
822	Linux kernel versions will scale negatively with the number of threads	1516	Linux kernel versions will scale negatively with the number of threads
823	(higher parallelity => MUCH higher latency). With current Linux 2.6	1517	(higher parallelity => MUCH higher latency). With current Linux 2.6
824	versions, 4-32 threads should be fine.	1518	versions, 4-32 threads should be fine.
…		…
838	This module automatically runs C<max_parallel 0> at program end, to ensure	1532	This module automatically runs C<max_parallel 0> at program end, to ensure
839	that all threads are killed and that there are no outstanding requests.	1533	that all threads are killed and that there are no outstanding requests.
840		1534
841	Under normal circumstances you don't need to call this function.	1535	Under normal circumstances you don't need to call this function.
842		1536
		1537	=item IO::AIO::max_idle $nthreads
		1538
		1539	Limit the number of threads (default: 4) that are allowed to idle
		1540	(i.e., threads that did not get a request to process within the idle
		1541	timeout (default: 10 seconds). That means if a thread becomes idle while
		1542	C<$nthreads> other threads are also idle, it will free its resources and
		1543	exit.
		1544
		1545	This is useful when you allow a large number of threads (e.g. 100 or 1000)
		1546	to allow for extremely high load situations, but want to free resources
		1547	under normal circumstances (1000 threads can easily consume 30MB of RAM).
		1548
		1549	The default is probably ok in most situations, especially if thread
		1550	creation is fast. If thread creation is very slow on your system you might
		1551	want to use larger values.
		1552
		1553	=item IO::AIO::idle_timeout $seconds
		1554
		1555	Sets the minimum idle timeout (default 10) after which worker threads are
		1556	allowed to exit. SEe C<IO::AIO::max_idle>.
		1557
843	=item $oldnreqs = IO::AIO::max_outstanding $nreqs	1558	=item IO::AIO::max_outstanding $maxreqs
844		1559
845	[DEPRECATED]	1560	This is a very bad function to use in interactive programs because it
		1561	blocks, and a bad way to reduce concurrency because it is inexact: Better
		1562	use an C<aio_group> together with a feed callback.
846		1563
847	Sets the maximum number of outstanding requests to C<$nreqs>. If you	1564	Sets the maximum number of outstanding requests to C<$nreqs>. If you
848	try to queue up more than this number of requests, the caller will block until	1565	do queue up more than this number of requests, the next call to the
849	some requests have been handled.	1566	C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>)
		1567	function will block until the limit is no longer exceeded.
850		1568
851	The default is very large, so normally there is no practical limit. If you	1569	The default value is very large, so there is no practical limit on the
852	queue up many requests in a loop it often improves speed if you set	1570	number of outstanding requests.
853	this to a relatively low number, such as C<100>.
854		1571
855	This function does not work well together with C<aio_group>'s, and their	1572	You can still queue as many requests as you want. Therefore,
856	feeder interface is better suited to limiting concurrency, so do not use	1573	C<max_outstanding> is mainly useful in simple scripts (with low values) or
857	this function.	1574	as a stop gap to shield against fatal memory overflow (with large values).
858
859	Under normal circumstances you don't need to call this function.
860		1575
861	=back	1576	=back
862		1577
		1578	=head3 STATISTICAL INFORMATION
		1579
		1580	=over
		1581
		1582	=item IO::AIO::nreqs
		1583
		1584	Returns the number of requests currently in the ready, execute or pending
		1585	states (i.e. for which their callback has not been invoked yet).
		1586
		1587	Example: wait till there are no outstanding requests anymore:
		1588
		1589	IO::AIO::poll_wait, IO::AIO::poll_cb
		1590	while IO::AIO::nreqs;
		1591
		1592	=item IO::AIO::nready
		1593
		1594	Returns the number of requests currently in the ready state (not yet
		1595	executed).
		1596
		1597	=item IO::AIO::npending
		1598
		1599	Returns the number of requests currently in the pending state (executed,
		1600	but not yet processed by poll_cb).
		1601
		1602	=back
		1603
		1604	=head3 MISCELLANEOUS FUNCTIONS
		1605
		1606	IO::AIO implements some functions that might be useful, but are not
		1607	asynchronous.
		1608
		1609	=over 4
		1610
		1611	=item IO::AIO::sendfile $ofh, $ifh, $offset, $count
		1612
		1613	Calls the C<eio_sendfile_sync> function, which is like C<aio_sendfile>,
		1614	but is blocking (this makes most sense if you know the input data is
		1615	likely cached already and the output filehandle is set to non-blocking
		1616	operations).
		1617
		1618	Returns the number of bytes copied, or C<-1> on error.
		1619
		1620	=item IO::AIO::fadvise $fh, $offset, $len, $advice
		1621
		1622	Simply calls the C<posix_fadvise> function (see its
		1623	manpage for details). The following advice constants are
		1624	avaiable: C<IO::AIO::FADV_NORMAL>, C<IO::AIO::FADV_SEQUENTIAL>,
		1625	C<IO::AIO::FADV_RANDOM>, C<IO::AIO::FADV_NOREUSE>,
		1626	C<IO::AIO::FADV_WILLNEED>, C<IO::AIO::FADV_DONTNEED>.
		1627
		1628	On systems that do not implement C<posix_fadvise>, this function returns
		1629	ENOSYS, otherwise the return value of C<posix_fadvise>.
		1630
		1631	=item IO::AIO::madvise $scalar, $offset, $len, $advice
		1632
		1633	Simply calls the C<posix_madvise> function (see its
		1634	manpage for details). The following advice constants are
		1635	avaiable: C<IO::AIO::MADV_NORMAL>, C<IO::AIO::MADV_SEQUENTIAL>,
		1636	C<IO::AIO::MADV_RANDOM>, C<IO::AIO::MADV_WILLNEED>, C<IO::AIO::MADV_DONTNEED>.
		1637
		1638	On systems that do not implement C<posix_madvise>, this function returns
		1639	ENOSYS, otherwise the return value of C<posix_madvise>.
		1640
		1641	=item IO::AIO::mprotect $scalar, $offset, $len, $protect
		1642
		1643	Simply calls the C<mprotect> function on the preferably AIO::mmap'ed
		1644	$scalar (see its manpage for details). The following protect
		1645	constants are avaiable: C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_READ>,
		1646	C<IO::AIO::PROT_WRITE>, C<IO::AIO::PROT_EXEC>.
		1647
		1648	On systems that do not implement C<mprotect>, this function returns
		1649	ENOSYS, otherwise the return value of C<mprotect>.
		1650
		1651	=item IO::AIO::mmap $scalar, $length, $prot, $flags, $fh[, $offset]
		1652
		1653	Memory-maps a file (or anonymous memory range) and attaches it to the
		1654	given C<$scalar>, which will act like a string scalar.
		1655
		1656	The only operations allowed on the scalar are C<substr>/C<vec> that don't
		1657	change the string length, and most read-only operations such as copying it
		1658	or searching it with regexes and so on.
		1659
		1660	Anything else is unsafe and will, at best, result in memory leaks.
		1661
		1662	The memory map associated with the C<$scalar> is automatically removed
		1663	when the C<$scalar> is destroyed, or when the C<IO::AIO::mmap> or
		1664	C<IO::AIO::munmap> functions are called.
		1665
		1666	This calls the C<mmap>(2) function internally. See your system's manual
		1667	page for details on the C<$length>, C<$prot> and C<$flags> parameters.
		1668
		1669	The C<$length> must be larger than zero and smaller than the actual
		1670	filesize.
		1671
		1672	C<$prot> is a combination of C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_EXEC>,
		1673	C<IO::AIO::PROT_READ> and/or C<IO::AIO::PROT_WRITE>,
		1674
		1675	C<$flags> can be a combination of C<IO::AIO::MAP_SHARED> or
		1676	C<IO::AIO::MAP_PRIVATE>, or a number of system-specific flags (when
		1677	not available, the are defined as 0): C<IO::AIO::MAP_ANONYMOUS>
		1678	(which is set to C<MAP_ANON> if your system only provides this
		1679	constant), C<IO::AIO::MAP_HUGETLB>, C<IO::AIO::MAP_LOCKED>,
		1680	C<IO::AIO::MAP_NORESERVE>, C<IO::AIO::MAP_POPULATE> or
		1681	C<IO::AIO::MAP_NONBLOCK>
		1682
		1683	If C<$fh> is C<undef>, then a file descriptor of C<-1> is passed.
		1684
		1685	C<$offset> is the offset from the start of the file - it generally must be
		1686	a multiple of C<IO::AIO::PAGESIZE> and defaults to C<0>.
		1687
		1688	Example:
		1689
		1690	use Digest::MD5;
		1691	use IO::AIO;
		1692
		1693	open my $fh, "<verybigfile"
		1694	or die "$!";
		1695
		1696	IO::AIO::mmap my $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh
		1697	or die "verybigfile: $!";
		1698
		1699	my $fast_md5 = md5 $data;
		1700
		1701	=item IO::AIO::munmap $scalar
		1702
		1703	Removes a previous mmap and undefines the C<$scalar>.
		1704
		1705	=item IO::AIO::munlock $scalar, $offset = 0, $length = undef
		1706
		1707	Calls the C<munlock> function, undoing the effects of a previous
		1708	C<aio_mlock> call (see its description for details).
		1709
		1710	=item IO::AIO::munlockall
		1711
		1712	Calls the C<munlockall> function.
		1713
		1714	On systems that do not implement C<munlockall>, this function returns
		1715	ENOSYS, otherwise the return value of C<munlockall>.
		1716
		1717	=back
		1718
863	=cut	1719	=cut
864		1720
865	# support function to convert a fd into a perl filehandle
866	sub _fd2fh {
867	return undef if $_[0] < 0;
868
869	# try to generate nice filehandles
870	my $sym = "IO::AIO::fd#$_[0]";
871	local *$sym;
872
873	open *$sym, "+<&=$_[0]" # usually works under any unix
874	or open *$sym, "<&=$_[0]" # cygwin needs this
875	or open *$sym, ">&=$_[0]" # or this
876	or return undef;
877
878	*$sym
879	}
880
881	min_parallel 8;	1721	min_parallel 8;
882		1722
883	END {	1723	END { flush }
884	max_parallel 0;
885	}
886		1724
887	1;	1725	1;
		1726
		1727	=head1 EVENT LOOP INTEGRATION
		1728
		1729	It is recommended to use L<AnyEvent::AIO> to integrate IO::AIO
		1730	automatically into many event loops:
		1731
		1732	# AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...)
		1733	use AnyEvent::AIO;
		1734
		1735	You can also integrate IO::AIO manually into many event loops, here are
		1736	some examples of how to do this:
		1737
		1738	# EV integration
		1739	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
		1740
		1741	# Event integration
		1742	Event->io (fd => IO::AIO::poll_fileno,
		1743	poll => 'r',
		1744	cb => \&IO::AIO::poll_cb);
		1745
		1746	# Glib/Gtk2 integration
		1747	add_watch Glib::IO IO::AIO::poll_fileno,
		1748	in => sub { IO::AIO::poll_cb; 1 };
		1749
		1750	# Tk integration
		1751	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
		1752	readable => \&IO::AIO::poll_cb);
		1753
		1754	# Danga::Socket integration
		1755	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
		1756	\&IO::AIO::poll_cb);
888		1757
889	=head2 FORK BEHAVIOUR	1758	=head2 FORK BEHAVIOUR
890		1759
891	This module should do "the right thing" when the process using it forks:	1760	This module should do "the right thing" when the process using it forks:
892		1761
893	Before the fork, IO::AIO enters a quiescent state where no requests	1762	Before the fork, IO::AIO enters a quiescent state where no requests
894	can be added in other threads and no results will be processed. After	1763	can be added in other threads and no results will be processed. After
895	the fork the parent simply leaves the quiescent state and continues	1764	the fork the parent simply leaves the quiescent state and continues
896	request/result processing, while the child clears the request/result	1765	request/result processing, while the child frees the request/result queue
897	queue (so the requests started before the fork will only be handled in	1766	(so that the requests started before the fork will only be handled in the
898	the parent). Threads will be started on demand until the limit ste in the	1767	parent). Threads will be started on demand until the limit set in the
899	parent process has been reached again.	1768	parent process has been reached again.
900		1769
901	In short: the parent will, after a short pause, continue as if fork had	1770	In short: the parent will, after a short pause, continue as if fork had
902	not been called, while the child will act as if IO::AIO has not been used	1771	not been called, while the child will act as if IO::AIO has not been used
903	yet.	1772	yet.
904		1773
905	=head2 MEMORY USAGE	1774	=head2 MEMORY USAGE
906		1775
		1776	Per-request usage:
		1777
907	Each aio request uses - depending on your architecture - around 128 bytes	1778	Each aio request uses - depending on your architecture - around 100-200
908	of memory. In addition, stat requests need a stat buffer (possibly a few	1779	bytes of memory. In addition, stat requests need a stat buffer (possibly
909	hundred bytes). Perl scalars and other data passed into aio requests will	1780	a few hundred bytes), readdir requires a result buffer and so on. Perl
910	also be locked.	1781	scalars and other data passed into aio requests will also be locked and
		1782	will consume memory till the request has entered the done state.
911		1783
912	This is now awfully much, so queuing lots of requests is not usually a	1784	This is not awfully much, so queuing lots of requests is not usually a
913	problem.	1785	problem.
914		1786
915	Each thread needs a stack area which is usually around 16k, sometimes much	1787	Per-thread usage:
916	larger, depending on the OS.	1788
		1789	In the execution phase, some aio requests require more memory for
		1790	temporary buffers, and each thread requires a stack and other data
		1791	structures (usually around 16k-128k, depending on the OS).
		1792
		1793	=head1 KNOWN BUGS
		1794
		1795	Known bugs will be fixed in the next release.
917		1796
918	=head1 SEE ALSO	1797	=head1 SEE ALSO
919		1798
920	L<Coro::AIO>.	1799	L<AnyEvent::AIO> for easy integration into event loops, L<Coro::AIO> for a
		1800	more natural syntax.
921		1801
922	=head1 AUTHOR	1802	=head1 AUTHOR
923		1803
924	Marc Lehmann <schmorp@schmorp.de>	1804	Marc Lehmann <schmorp@schmorp.de>
925	http://home.schmorp.de/	1805	http://home.schmorp.de/

Diff Legend

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