[ViewVC] Diff of: cvs/IO-AIO/README

Comparing IO-AIO/README (file contents):
Revision 1.4 by root, Sun Jul 10 21:04:46 2005 UTC vs.
Revision 1.42 by root, Thu Jan 7 20:25:57 2010 UTC

…		…
2	IO::AIO - Asynchronous Input/Output	2	IO::AIO - Asynchronous Input/Output
3		3
4	SYNOPSIS	4	SYNOPSIS
5	use IO::AIO;	5	use IO::AIO;
6		6
		7	aio_open "/etc/passwd", O_RDONLY, 0, sub {
		8	my $fh = shift
		9	or die "/etc/passwd: $!";
		10	...
		11	};
		12
		13	aio_unlink "/tmp/file", sub { };
		14
		15	aio_read $fh, 30000, 1024, $buffer, 0, sub {
		16	$_[0] > 0 or die "read error: $!";
		17	};
		18
		19	# version 2+ has request and group objects
		20	use IO::AIO 2;
		21
		22	aioreq_pri 4; # give next request a very high priority
		23	my $req = aio_unlink "/tmp/file", sub { };
		24	$req->cancel; # cancel request if still in queue
		25
		26	my $grp = aio_group sub { print "all stats done\n" };
		27	add $grp aio_stat "..." for ...;
		28
		29	# AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...)
		30	use AnyEvent::AIO;
		31
		32	# EV integration
		33	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
		34
		35	# Event integration
		36	Event->io (fd => IO::AIO::poll_fileno,
		37	poll => 'r',
		38	cb => \&IO::AIO::poll_cb);
		39
		40	# Glib/Gtk2 integration
		41	add_watch Glib::IO IO::AIO::poll_fileno,
		42	in => sub { IO::AIO::poll_cb; 1 };
		43
		44	# Tk integration
		45	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
		46	readable => \&IO::AIO::poll_cb);
		47
		48	# Danga::Socket integration
		49	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
		50	\&IO::AIO::poll_cb);
		51
7	DESCRIPTION	52	DESCRIPTION
8	This module implements asynchronous I/O using whatever means your	53	This module implements asynchronous I/O using whatever means your
9	operating system supports.	54	operating system supports. It is implemented as an interface to "libeio"
		55	(<http://software.schmorp.de/pkg/libeio.html>).
10		56
		57	Asynchronous means that operations that can normally block your program
		58	(e.g. reading from disk) will be done asynchronously: the operation will
		59	still block, but you can do something else in the meantime. This is
		60	extremely useful for programs that need to stay interactive even when
		61	doing heavy I/O (GUI programs, high performance network servers etc.),
		62	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
		64	faster on a RAID volume or over NFS when you do a number of stat
		65	operations concurrently.
		66
		67	While most of this works on all types of file descriptors (for example
		68	sockets), using these functions on file descriptors that support
		69	nonblocking operation (again, sockets, pipes etc.) is very inefficient.
		70	Use an event loop for that (such as the EV module): IO::AIO will
		71	naturally fit into such an event loop itself.
		72
11	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
12	and signal their completion. You don't need thread support in your libc	74	requests and signal their completion. You don't need thread support in
13	or perl, and the threads created by this module will not be visible to	75	perl, and the threads created by this module will not be visible to
14	the pthreads library. In the future, this module might make use of the	76	perl. In the future, this module might make use of the native aio
15	native aio functions available on many operating systems. However, they	77	functions available on many operating systems. However, they are often
16	are often not well-supported (Linux doesn't allow them on normal files	78	not well-supported or restricted (GNU/Linux doesn't allow them on normal
17	currently, for example), and they would only support aio_read and	79	files currently, for example), and they would only support aio_read and
18	aio_write, so the remaining functionality would have to be implemented	80	aio_write, so the remaining functionality would have to be implemented
19	using threads anyway.	81	using threads anyway.
20		82
21	Although the module will work with in the presence of other threads, it	83	Although the module will work in the presence of other (Perl-) threads,
22	is currently not reentrant, so use appropriate locking yourself.	84	it is currently not reentrant in any way, so use appropriate locking
		85	yourself, always call "poll_cb" from within the same thread, or never
		86	call "poll_cb" (or other "aio_" functions) recursively.
		87
		88	EXAMPLE
		89	This is a simple example that uses the EV module and loads /etc/passwd
		90	asynchronously:
		91
		92	use Fcntl;
		93	use EV;
		94	use IO::AIO;
		95
		96	# register the IO::AIO callback with EV
		97	my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
		98
		99	# queue the request to open /etc/passwd
		100	aio_open "/etc/passwd", O_RDONLY, 0, sub {
		101	my $fh = shift
		102	or die "error while opening: $!";
		103
		104	# stat'ing filehandles is generally non-blocking
		105	my $size = -s $fh;
		106
		107	# queue a request to read the file
		108	my $contents;
		109	aio_read $fh, 0, $size, $contents, 0, sub {
		110	$_[0] == $size
		111	or die "short read: $!";
		112
		113	close $fh;
		114
		115	# file contents now in $contents
		116	print $contents;
		117
		118	# exit event loop and program
		119	EV::unloop;
		120	};
		121	};
		122
		123	# possibly queue up other requests, or open GUI windows,
		124	# check for sockets etc. etc.
		125
		126	# process events as long as there are some:
		127	EV::loop;
		128
		129	REQUEST ANATOMY AND LIFETIME
		130	Every "aio_*" function creates a request. which is a C data structure
		131	not directly visible to Perl.
		132
		133	If called in non-void context, every request function returns a Perl
		134	object representing the request. In void context, nothing is returned,
		135	which saves a bit of memory.
		136
		137	The perl object is a fairly standard ref-to-hash object. The hash
		138	contents are not used by IO::AIO so you are free to store anything you
		139	like in it.
		140
		141	During their existance, aio requests travel through the following
		142	states, in order:
		143
		144	ready
		145	Immediately after a request is created it is put into the ready
		146	state, waiting for a thread to execute it.
		147
		148	execute
		149	A thread has accepted the request for processing and is currently
		150	executing it (e.g. blocking in read).
		151
		152	pending
		153	The request has been executed and is waiting for result processing.
		154
		155	While request submission and execution is fully asynchronous, result
		156	processing is not and relies on the perl interpreter calling
		157	"poll_cb" (or another function with the same effect).
		158
		159	result
		160	The request results are processed synchronously by "poll_cb".
		161
		162	The "poll_cb" function will process all outstanding aio requests by
		163	calling their callbacks, freeing memory associated with them and
		164	managing any groups they are contained in.
		165
		166	done
		167	Request has reached the end of its lifetime and holds no resources
		168	anymore (except possibly for the Perl object, but its connection to
		169	the actual aio request is severed and calling its methods will
		170	either do nothing or result in a runtime error).
23		171
24	FUNCTIONS	172	FUNCTIONS
25	AIO FUNCTIONS	173	AIO REQUEST FUNCTIONS
26	All the "aio_*" calls are more or less thin wrappers around the syscall	174	All the "aio_*" calls are more or less thin wrappers around the syscall
27	with the same name (sans "aio_"). The arguments are similar or	175	with the same name (sans "aio_"). The arguments are similar or
28	identical, and they all accept an additional $callback argument which	176	identical, and they all accept an additional (and optional) $callback
29	must be a code reference. This code reference will get called with the	177	argument which must be a code reference. This code reference will get
30	syscall return code (e.g. most syscalls return -1 on error, unlike perl,	178	called with the syscall return code (e.g. most syscalls return -1 on
31	which usually delivers "false") as it's sole argument when the given	179	error, unlike perl, which usually delivers "false") as its sole argument
32	syscall has been executed asynchronously.	180	after the given syscall has been executed asynchronously.
33		181
34	All functions that expect a filehandle will also accept a file	182	All functions expecting a filehandle keep a copy of the filehandle
35	descriptor.	183	internally until the request has finished.
36		184
		185	All functions return request objects of type IO::AIO::REQ that allow
		186	further manipulation of those requests while they are in-flight.
		187
37	The filenames you pass to these routines must be absolute. The reason	188	The pathnames you pass to these routines must be absolute and encoded
38	is that at the time the request is being executed, the current working	189	as octets. The reason for the former is that at the time the request is
39	directory could have changed. Alternatively, you can make sure that you	190	being executed, the current working directory could have changed.
40	never change the current working directory.	191	Alternatively, you can make sure that you never change the current
		192	working directory anywhere in the program and then use relative paths.
41		193
		194	To encode pathnames as octets, either make sure you either: a) always
		195	pass in filenames you got from outside (command line, readdir etc.)
		196	without tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module
		197	and encode your pathnames to the locale (or other) encoding in effect in
		198	the user environment, d) use Glib::filename_from_unicode on unicode
		199	filenames or e) use something else to ensure your scalar has the correct
		200	contents.
		201
		202	This works, btw. independent of the internal UTF-8 bit, which IO::AIO
		203	handles correctly whether it is set or not.
		204
		205	$prev_pri = aioreq_pri [$pri]
		206	Returns the priority value that would be used for the next request
		207	and, if $pri is given, sets the priority for the next aio request.
		208
		209	The default priority is 0, the minimum and maximum priorities are -4
		210	and 4, respectively. Requests with higher priority will be serviced
		211	first.
		212
		213	The priority will be reset to 0 after each call to one of the
		214	"aio_*" functions.
		215
		216	Example: open a file with low priority, then read something from it
		217	with higher priority so the read request is serviced before other
		218	low priority open requests (potentially spamming the cache):
		219
		220	aioreq_pri -3;
		221	aio_open ..., sub {
		222	return unless $_[0];
		223
		224	aioreq_pri -2;
		225	aio_read $_[0], ..., sub {
		226	...
		227	};
		228	};
		229
		230	aioreq_nice $pri_adjust
		231	Similar to "aioreq_pri", but subtracts the given value from the
		232	current priority, so the effect is cumulative.
		233
42	aio_open $pathname, $flags, $mode, $callback	234	aio_open $pathname, $flags, $mode, $callback->($fh)
43	Asynchronously open or create a file and call the callback with a	235	Asynchronously open or create a file and call the callback with a
44	newly created filehandle for the file.	236	newly created filehandle for the file.
45		237
46	The pathname passed to "aio_open" must be absolute. See API NOTES,	238	The pathname passed to "aio_open" must be absolute. See API NOTES,
47	above, for an explanation.	239	above, for an explanation.
48		240
49	The $mode argument is a bitmask. See the "Fcntl" module for a list.	241	The $flags argument is a bitmask. See the "Fcntl" module for a list.
50	They are the same as used in "sysopen".	242	They are the same as used by "sysopen".
		243
		244	Likewise, $mode specifies the mode of the newly created file, if it
		245	didn't exist and "O_CREAT" has been given, just like perl's
		246	"sysopen", except that it is mandatory (i.e. use 0 if you don't
		247	create new files, and 0666 or 0777 if you do). Note that the $mode
		248	will be modified by the umask in effect then the request is being
		249	executed, so better never change the umask.
51		250
52	Example:	251	Example:
53		252
54	aio_open "/etc/passwd", O_RDONLY, 0, sub {	253	aio_open "/etc/passwd", O_RDONLY, 0, sub {
55	if ($_[0]) {	254	if ($_[0]) {
…		…
58	} else {	257	} else {
59	die "open failed: $!\n";	258	die "open failed: $!\n";
60	}	259	}
61	};	260	};
62		261
63	aio_close $fh, $callback	262	aio_close $fh, $callback->($status)
64	Asynchronously close a file and call the callback with the result	263	Asynchronously close a file and call the callback with the result
65	code. WARNING: although accepted, you should not pass in a perl	264	code.
66	filehandle here, as perl will likely close the file descriptor
67	itself when the filehandle is destroyed. Normally, you can safely
68	call perls "close" or just let filehandles go out of scope.
69		265
		266	Unfortunately, you can't do this to perl. Perl insists very
		267	strongly on closing the file descriptor associated with the
		268	filehandle itself.
		269
		270	Therefore, "aio_close" will not close the filehandle - instead it
		271	will use dup2 to overwrite the file descriptor with the write-end of
		272	a pipe (the pipe fd will be created on demand and will be cached).
		273
		274	Or in other words: the file descriptor will be closed, but it will
		275	not be free for reuse until the perl filehandle is closed.
		276
70	aio_read $fh,$offset,$length, $data,$dataoffset,$callback	277	aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
71	aio_write $fh,$offset,$length, $data,$dataoffset,$callback	278	aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
72	Reads or writes "length" bytes from the specified "fh" and "offset"	279	Reads or writes $length bytes from or to the specified $fh and
73	into the scalar given by "data" and offset "dataoffset" and calls	280	$offset into the scalar given by $data and offset $dataoffset and
74	the callback without the actual number of bytes read (or -1 on	281	calls the callback without the actual number of bytes read (or -1 on
75	error, just like the syscall).	282	error, just like the syscall).
76		283
		284	"aio_read" will, like "sysread", shrink or grow the $data scalar to
		285	offset plus the actual number of bytes read.
		286
		287	If $offset is undefined, then the current file descriptor offset
		288	will be used (and updated), otherwise the file descriptor offset
		289	will not be changed by these calls.
		290
		291	If $length is undefined in "aio_write", use the remaining length of
		292	$data.
		293
		294	If $dataoffset is less than zero, it will be counted from the end of
		295	$data.
		296
		297	The $data scalar MUST NOT be modified in any way while the request
		298	is outstanding. Modifying it can result in segfaults or World War
		299	III (if the necessary/optional hardware is installed).
		300
77	Example: Read 15 bytes at offset 7 into scalar $buffer, strating at	301	Example: Read 15 bytes at offset 7 into scalar $buffer, starting at
78	offset 0 within the scalar:	302	offset 0 within the scalar:
79		303
80	aio_read $fh, 7, 15, $buffer, 0, sub {	304	aio_read $fh, 7, 15, $buffer, 0, sub {
81	$_[0] >= 0 or die "read error: $!";	305	$_[0] > 0 or die "read error: $!";
82	print "read <$buffer>\n";	306	print "read $_[0] bytes: <$buffer>\n";
83	};	307	};
84		308
		309	aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
		310	Tries to copy $length bytes from $in_fh to $out_fh. It starts
		311	reading at byte offset $in_offset, and starts writing at the current
		312	file offset of $out_fh. Because of that, it is not safe to issue
		313	more than one "aio_sendfile" per $out_fh, as they will interfere
		314	with each other.
		315
		316	This call tries to make use of a native "sendfile" syscall to
		317	provide zero-copy operation. For this to work, $out_fh should refer
		318	to a socket, and $in_fh should refer to mmap'able file.
		319
		320	If a native sendfile cannot be found or it fails with "ENOSYS",
		321	"ENOTSUP", "EOPNOTSUPP", "EAFNOSUPPORT", "EPROTOTYPE" or "ENOTSOCK",
		322	it will be emulated, so you can call "aio_sendfile" on any type of
		323	filehandle regardless of the limitations of the operating system.
		324
		325	Please note, however, that "aio_sendfile" can read more bytes from
		326	$in_fh than are written, and there is no way to find out how many
		327	bytes have been read from "aio_sendfile" alone, as "aio_sendfile"
		328	only provides the number of bytes written to $out_fh. Only if the
		329	result value equals $length one can assume that $length bytes have
		330	been read.
		331
85	aio_readahead $fh,$offset,$length, $callback	332	aio_readahead $fh,$offset,$length, $callback->($retval)
86	Asynchronously reads the specified byte range into the page cache,
87	using the "readahead" syscall. If that syscall doesn't exist the
88	status will be -1 and $! is set to ENOSYS.
89
90	readahead() populates the page cache with data from a file so that	333	"aio_readahead" populates the page cache with data from a file so
91	subsequent reads from that file will not block on disk I/O. The	334	that subsequent reads from that file will not block on disk I/O. The
92	$offset argument specifies the starting point from which data is to	335	$offset argument specifies the starting point from which data is to
93	be read and $length specifies the number of bytes to be read. I/O is	336	be read and $length specifies the number of bytes to be read. I/O is
94	performed in whole pages, so that offset is effectively rounded down	337	performed in whole pages, so that offset is effectively rounded down
95	to a page boundary and bytes are read up to the next page boundary	338	to a page boundary and bytes are read up to the next page boundary
96	greater than or equal to (off-set+length). aio_readahead() does not	339	greater than or equal to (off-set+length). "aio_readahead" does not
97	read beyond the end of the file. The current file offset of the file	340	read beyond the end of the file. The current file offset of the file
98	is left unchanged.	341	is left unchanged.
99		342
		343	If that syscall doesn't exist (likely if your OS isn't Linux) it
		344	will be emulated by simply reading the data, which would have a
		345	similar effect.
		346
100	aio_stat $fh_or_path, $callback	347	aio_stat $fh_or_path, $callback->($status)
101	aio_lstat $fh, $callback	348	aio_lstat $fh, $callback->($status)
102	Works like perl's "stat" or "lstat" in void context. The callback	349	Works like perl's "stat" or "lstat" in void context. The callback
103	will be called after the stat and the results will be available	350	will be called after the stat and the results will be available
104	using "stat _" or "-s _" etc...	351	using "stat _" or "-s _" etc...
105		352
106	The pathname passed to "aio_stat" must be absolute. See API NOTES,	353	The pathname passed to "aio_stat" must be absolute. See API NOTES,
…		…
116	aio_stat "/etc/passwd", sub {	363	aio_stat "/etc/passwd", sub {
117	$_[0] and die "stat failed: $!";	364	$_[0] and die "stat failed: $!";
118	print "size is ", -s _, "\n";	365	print "size is ", -s _, "\n";
119	};	366	};
120		367
		368	aio_statvfs $fh_or_path, $callback->($statvfs)
		369	Works like the POSIX "statvfs" or "fstatvfs" syscalls, depending on
		370	whether a file handle or path was passed.
		371
		372	On success, the callback is passed a hash reference with the
		373	following members: "bsize", "frsize", "blocks", "bfree", "bavail",
		374	"files", "ffree", "favail", "fsid", "flag" and "namemax". On
		375	failure, "undef" is passed.
		376
		377	The following POSIX IO::AIO::ST_* constants are defined: "ST_RDONLY"
		378	and "ST_NOSUID".
		379
		380	The following non-POSIX IO::AIO::ST_* flag masks are defined to
		381	their correct value when available, or to 0 on systems that do not
		382	support them: "ST_NODEV", "ST_NOEXEC", "ST_SYNCHRONOUS",
		383	"ST_MANDLOCK", "ST_WRITE", "ST_APPEND", "ST_IMMUTABLE",
		384	"ST_NOATIME", "ST_NODIRATIME" and "ST_RELATIME".
		385
		386	Example: stat "/wd" and dump out the data if successful.
		387
		388	aio_statvfs "/wd", sub {
		389	my $f = $_[0]
		390	or die "statvfs: $!";
		391
		392	use Data::Dumper;
		393	say Dumper $f;
		394	};
		395
		396	# result:
		397	{
		398	bsize => 1024,
		399	bfree => 4333064312,
		400	blocks => 10253828096,
		401	files => 2050765568,
		402	flag => 4096,
		403	favail => 2042092649,
		404	bavail => 4333064312,
		405	ffree => 2042092649,
		406	namemax => 255,
		407	frsize => 1024,
		408	fsid => 1810
		409	}
		410
		411	aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
		412	Works like perl's "utime" function (including the special case of
		413	$atime and $mtime being undef). Fractional times are supported if
		414	the underlying syscalls support them.
		415
		416	When called with a pathname, uses utimes(2) if available, otherwise
		417	utime(2). If called on a file descriptor, uses futimes(2) if
		418	available, otherwise returns ENOSYS, so this is not portable.
		419
		420	Examples:
		421
		422	# set atime and mtime to current time (basically touch(1)):
		423	aio_utime "path", undef, undef;
		424	# set atime to current time and mtime to beginning of the epoch:
		425	aio_utime "path", time, undef; # undef==0
		426
		427	aio_chown $fh_or_path, $uid, $gid, $callback->($status)
		428	Works like perl's "chown" function, except that "undef" for either
		429	$uid or $gid is being interpreted as "do not change" (but -1 can
		430	also be used).
		431
		432	Examples:
		433
		434	# same as "chown root path" in the shell:
		435	aio_chown "path", 0, -1;
		436	# same as above:
		437	aio_chown "path", 0, undef;
		438
		439	aio_truncate $fh_or_path, $offset, $callback->($status)
		440	Works like truncate(2) or ftruncate(2).
		441
		442	aio_chmod $fh_or_path, $mode, $callback->($status)
		443	Works like perl's "chmod" function.
		444
121	aio_unlink $pathname, $callback	445	aio_unlink $pathname, $callback->($status)
122	Asynchronously unlink (delete) a file and call the callback with the	446	Asynchronously unlink (delete) a file and call the callback with the
123	result code.	447	result code.
124		448
		449	aio_mknod $path, $mode, $dev, $callback->($status)
		450	[EXPERIMENTAL]
		451
		452	Asynchronously create a device node (or fifo). See mknod(2).
		453
		454	The only (POSIX-) portable way of calling this function is:
		455
		456	aio_mknod $path, IO::AIO::S_IFIFO \| $mode, 0, sub { ...
		457
		458	aio_link $srcpath, $dstpath, $callback->($status)
		459	Asynchronously create a new link to the existing object at $srcpath
		460	at the path $dstpath and call the callback with the result code.
		461
		462	aio_symlink $srcpath, $dstpath, $callback->($status)
		463	Asynchronously create a new symbolic link to the existing object at
		464	$srcpath at the path $dstpath and call the callback with the result
		465	code.
		466
		467	aio_readlink $path, $callback->($link)
		468	Asynchronously read the symlink specified by $path and pass it to
		469	the callback. If an error occurs, nothing or undef gets passed to
		470	the callback.
		471
		472	aio_rename $srcpath, $dstpath, $callback->($status)
		473	Asynchronously rename the object at $srcpath to $dstpath, just as
		474	rename(2) and call the callback with the result code.
		475
		476	aio_mkdir $pathname, $mode, $callback->($status)
		477	Asynchronously mkdir (create) a directory and call the callback with
		478	the result code. $mode will be modified by the umask at the time the
		479	request is executed, so do not change your umask.
		480
		481	aio_rmdir $pathname, $callback->($status)
		482	Asynchronously rmdir (delete) a directory and call the callback with
		483	the result code.
		484
		485	aio_readdir $pathname, $callback->($entries)
		486	Unlike the POSIX call of the same name, "aio_readdir" reads an
		487	entire directory (i.e. opendir + readdir + closedir). The entries
		488	will not be sorted, and will NOT include the "." and ".." entries.
		489
		490	The callback is passed a single argument which is either "undef" or
		491	an array-ref with the filenames.
		492
		493	aio_readdirx $pathname, $flags, $callback->($entries, $flags)
		494	Quite similar to "aio_readdir", but the $flags argument allows to
		495	tune behaviour and output format. In case of an error, $entries will
		496	be "undef".
		497
		498	The flags are a combination of the following constants, ORed
		499	together (the flags will also be passed to the callback, possibly
		500	modified):
		501
		502	IO::AIO::READDIR_DENTS
		503	When this flag is off, then the callback gets an arrayref with
		504	of names only (as with "aio_readdir"), otherwise it gets an
		505	arrayref with "[$name, $type, $inode]" arrayrefs, each
		506	describing a single directory entry in more detail.
		507
		508	$name is the name of the entry.
		509
		510	$type is one of the "IO::AIO::DT_xxx" constants:
		511
		512	"IO::AIO::DT_UNKNOWN", "IO::AIO::DT_FIFO", "IO::AIO::DT_CHR",
		513	"IO::AIO::DT_DIR", "IO::AIO::DT_BLK", "IO::AIO::DT_REG",
		514	"IO::AIO::DT_LNK", "IO::AIO::DT_SOCK", "IO::AIO::DT_WHT".
		515
		516	"IO::AIO::DT_UNKNOWN" means just that: readdir does not know. If
		517	you need to know, you have to run stat yourself. Also, for speed
		518	reasons, the $type scalars are read-only: you can not modify
		519	them.
		520
		521	$inode is the inode number (which might not be exact on systems
		522	with 64 bit inode numbers and 32 bit perls). This field has
		523	unspecified content on systems that do not deliver the inode
		524	information.
		525
		526	IO::AIO::READDIR_DIRS_FIRST
		527	When this flag is set, then the names will be returned in an
		528	order where likely directories come first. This is useful when
		529	you need to quickly find directories, or you want to find all
		530	directories while avoiding to stat() each entry.
		531
		532	If the system returns type information in readdir, then this is
		533	used to find directories directly. Otherwise, likely directories
		534	are files beginning with ".", or otherwise files with no dots,
		535	of which files with short names are tried first.
		536
		537	IO::AIO::READDIR_STAT_ORDER
		538	When this flag is set, then the names will be returned in an
		539	order suitable for stat()'ing each one. That is, when you plan
		540	to stat() all files in the given directory, then the returned
		541	order will likely be fastest.
		542
		543	If both this flag and "IO::AIO::READDIR_DIRS_FIRST" are
		544	specified, then the likely dirs come first, resulting in a less
		545	optimal stat order.
		546
		547	IO::AIO::READDIR_FOUND_UNKNOWN
		548	This flag should not be set when calling "aio_readdirx".
		549	Instead, it is being set by "aio_readdirx", when any of the
		550	$type's found were "IO::AIO::DT_UNKNOWN". The absense of this
		551	flag therefore indicates that all $type's are known, which can
		552	be used to speed up some algorithms.
		553
		554	aio_load $path, $data, $callback->($status)
		555	This is a composite request that tries to fully load the given file
		556	into memory. Status is the same as with aio_read.
		557
		558	aio_copy $srcpath, $dstpath, $callback->($status)
		559	Try to copy the file (directories not supported as either source
		560	or destination) from $srcpath to $dstpath and call the callback with
		561	a status of 0 (ok) or -1 (error, see $!).
		562
		563	This is a composite request that creates the destination file with
		564	mode 0200 and copies the contents of the source file into it using
		565	"aio_sendfile", followed by restoring atime, mtime, access mode and
		566	uid/gid, in that order.
		567
		568	If an error occurs, the partial destination file will be unlinked,
		569	if possible, except when setting atime, mtime, access mode and
		570	uid/gid, where errors are being ignored.
		571
		572	aio_move $srcpath, $dstpath, $callback->($status)
		573	Try to move the file (directories not supported as either source
		574	or destination) from $srcpath to $dstpath and call the callback with
		575	a status of 0 (ok) or -1 (error, see $!).
		576
		577	This is a composite request that tries to rename(2) the file first;
		578	if rename fails with "EXDEV", it copies the file with "aio_copy"
		579	and, if that is successful, unlinks the $srcpath.
		580
		581	aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
		582	Scans a directory (similar to "aio_readdir") but additionally tries
		583	to efficiently separate the entries of directory $path into two sets
		584	of names, directories you can recurse into (directories), and ones
		585	you cannot recurse into (everything else, including symlinks to
		586	directories).
		587
		588	"aio_scandir" is a composite request that creates of many sub
		589	requests_ $maxreq specifies the maximum number of outstanding aio
		590	requests that this function generates. If it is "<= 0", then a
		591	suitable default will be chosen (currently 4).
		592
		593	On error, the callback is called without arguments, otherwise it
		594	receives two array-refs with path-relative entry names.
		595
		596	Example:
		597
		598	aio_scandir $dir, 0, sub {
		599	my ($dirs, $nondirs) = @_;
		600	print "real directories: @$dirs\n";
		601	print "everything else: @$nondirs\n";
		602	};
		603
		604	Implementation notes.
		605
		606	The "aio_readdir" cannot be avoided, but "stat()"'ing every entry
		607	can.
		608
		609	If readdir returns file type information, then this is used directly
		610	to find directories.
		611
		612	Otherwise, after reading the directory, the modification time, size
		613	etc. of the directory before and after the readdir is checked, and
		614	if they match (and isn't the current time), the link count will be
		615	used to decide how many entries are directories (if >= 2).
		616	Otherwise, no knowledge of the number of subdirectories will be
		617	assumed.
		618
		619	Then entries will be sorted into likely directories a non-initial
		620	dot currently) and likely non-directories (see "aio_readdirx"). Then
		621	every entry plus an appended "/." will be "stat"'ed, likely
		622	directories first, in order of their inode numbers. If that
		623	succeeds, it assumes that the entry is a directory or a symlink to
		624	directory (which will be checked seperately). This is often faster
		625	than stat'ing the entry itself because filesystems might detect the
		626	type of the entry without reading the inode data (e.g. ext2fs
		627	filetype feature), even on systems that cannot return the filetype
		628	information on readdir.
		629
		630	If the known number of directories (link count - 2) has been
		631	reached, the rest of the entries is assumed to be non-directories.
		632
		633	This only works with certainty on POSIX (= UNIX) filesystems, which
		634	fortunately are the vast majority of filesystems around.
		635
		636	It will also likely work on non-POSIX filesystems with reduced
		637	efficiency as those tend to return 0 or 1 as link counts, which
		638	disables the directory counting heuristic.
		639
		640	aio_rmtree $path, $callback->($status)
		641	Delete a directory tree starting (and including) $path, return the
		642	status of the final "rmdir" only. This is a composite request that
		643	uses "aio_scandir" to recurse into and rmdir directories, and unlink
		644	everything else.
		645
		646	aio_sync $callback->($status)
		647	Asynchronously call sync and call the callback when finished.
		648
125	aio_fsync $fh, $callback	649	aio_fsync $fh, $callback->($status)
126	Asynchronously call fsync on the given filehandle and call the	650	Asynchronously call fsync on the given filehandle and call the
127	callback with the fsync result code.	651	callback with the fsync result code.
128		652
129	aio_fdatasync $fh, $callback	653	aio_fdatasync $fh, $callback->($status)
130	Asynchronously call fdatasync on the given filehandle and call the	654	Asynchronously call fdatasync on the given filehandle and call the
131	callback with the fdatasync result code.	655	callback with the fdatasync result code.
132		656
		657	If this call isn't available because your OS lacks it or it couldn't
		658	be detected, it will be emulated by calling "fsync" instead.
		659
		660	aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
		661	Sync the data portion of the file specified by $offset and $length
		662	to disk (but NOT the metadata), by calling the Linux-specific
		663	sync_file_range call. If sync_file_range is not available or it
		664	returns ENOSYS, then fdatasync or fsync is being substituted.
		665
		666	$flags can be a combination of
		667	"IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE",
		668	"IO::AIO::SYNC_FILE_RANGE_WRITE" and
		669	"IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER": refer to the sync_file_range
		670	manpage for details.
		671
		672	aio_pathsync $path, $callback->($status)
		673	This request tries to open, fsync and close the given path. This is
		674	a composite request intended to sync directories after directory
		675	operations (E.g. rename). This might not work on all operating
		676	systems or have any specific effect, but usually it makes sure that
		677	directory changes get written to disc. It works for anything that
		678	can be opened for read-only, not just directories.
		679
		680	Future versions of this function might fall back to other methods
		681	when "fsync" on the directory fails (such as calling "sync").
		682
		683	Passes 0 when everything went ok, and -1 on error.
		684
		685	aio_msync $scalar, $offset = 0, $length = undef, flags = 0,
		686	$callback->($status)
		687	This is a rather advanced IO::AIO call, which only works on
		688	mmap(2)ed scalars (see the Sys::Mmap or Mmap modules for details on
		689	this, note that the scalar must only be modified in-place while an
		690	aio operation is pending on it).
		691
		692	It calls the "msync" function of your OS, if available, with the
		693	memory area starting at $offset in the string and ending $length
		694	bytes later. If $length is negative, counts from the end, and if
		695	$length is "undef", then it goes till the end of the string. The
		696	flags can be a combination of "IO::AIO::MS_ASYNC",
		697	"IO::AIO::MS_INVALIDATE" and "IO::AIO::MS_SYNC".
		698
		699	aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0,
		700	$callback->($status)
		701	This is a rather advanced IO::AIO call, which works best on
		702	mmap(2)ed scalars.
		703
		704	It touches (reads or writes) all memory pages in the specified range
		705	inside the scalar. All caveats and parameters are the same as for
		706	"aio_msync", above, except for flags, which must be either 0 (which
		707	reads all pages and ensures they are instantiated) or
		708	"IO::AIO::MT_MODIFY", which modifies the memory page s(by reading
		709	and writing an octet from it, which dirties the page).
		710
		711	aio_group $callback->(...)
		712	This is a very special aio request: Instead of doing something, it
		713	is a container for other aio requests, which is useful if you want
		714	to bundle many requests into a single, composite, request with a
		715	definite callback and the ability to cancel the whole request with
		716	its subrequests.
		717
		718	Returns an object of class IO::AIO::GRP. See its documentation below
		719	for more info.
		720
		721	Example:
		722
		723	my $grp = aio_group sub {
		724	print "all stats done\n";
		725	};
		726
		727	add $grp
		728	(aio_stat ...),
		729	(aio_stat ...),
		730	...;
		731
		732	aio_nop $callback->()
		733	This is a special request - it does nothing in itself and is only
		734	used for side effects, such as when you want to add a dummy request
		735	to a group so that finishing the requests in the group depends on
		736	executing the given code.
		737
		738	While this request does nothing, it still goes through the execution
		739	phase and still requires a worker thread. Thus, the callback will
		740	not be executed immediately but only after other requests in the
		741	queue have entered their execution phase. This can be used to
		742	measure request latency.
		743
		744	IO::AIO::aio_busy $fractional_seconds, $callback->() NOT EXPORTED
		745	Mainly used for debugging and benchmarking, this aio request puts
		746	one of the request workers to sleep for the given time.
		747
		748	While it is theoretically handy to have simple I/O scheduling
		749	requests like sleep and file handle readable/writable, the overhead
		750	this creates is immense (it blocks a thread for a long time) so do
		751	not use this function except to put your application under
		752	artificial I/O pressure.
		753
		754	IO::AIO::REQ CLASS
		755	All non-aggregate "aio_*" functions return an object of this class when
		756	called in non-void context.
		757
		758	cancel $req
		759	Cancels the request, if possible. Has the effect of skipping
		760	execution when entering the execute state and skipping calling the
		761	callback when entering the the result state, but will leave the
		762	request otherwise untouched (with the exception of readdir). That
		763	means that requests that currently execute will not be stopped and
		764	resources held by the request will not be freed prematurely.
		765
		766	cb $req $callback->(...)
		767	Replace (or simply set) the callback registered to the request.
		768
		769	IO::AIO::GRP CLASS
		770	This class is a subclass of IO::AIO::REQ, so all its methods apply to
		771	objects of this class, too.
		772
		773	A IO::AIO::GRP object is a special request that can contain multiple
		774	other aio requests.
		775
		776	You create one by calling the "aio_group" constructing function with a
		777	callback that will be called when all contained requests have entered
		778	the "done" state:
		779
		780	my $grp = aio_group sub {
		781	print "all requests are done\n";
		782	};
		783
		784	You add requests by calling the "add" method with one or more
		785	"IO::AIO::REQ" objects:
		786
		787	$grp->add (aio_unlink "...");
		788
		789	add $grp aio_stat "...", sub {
		790	$_[0] or return $grp->result ("error");
		791
		792	# add another request dynamically, if first succeeded
		793	add $grp aio_open "...", sub {
		794	$grp->result ("ok");
		795	};
		796	};
		797
		798	This makes it very easy to create composite requests (see the source of
		799	"aio_move" for an application) that work and feel like simple requests.
		800
		801	* The IO::AIO::GRP objects will be cleaned up during calls to
		802	"IO::AIO::poll_cb", just like any other request.
		803
		804	* They can be canceled like any other request. Canceling will cancel
		805	not only the request itself, but also all requests it contains.
		806
		807	* They can also can also be added to other IO::AIO::GRP objects.
		808
		809	* You must not add requests to a group from within the group callback
		810	(or any later time).
		811
		812	Their lifetime, simplified, looks like this: when they are empty, they
		813	will finish very quickly. If they contain only requests that are in the
		814	"done" state, they will also finish. Otherwise they will continue to
		815	exist.
		816
		817	That means after creating a group you have some time to add requests
		818	(precisely before the callback has been invoked, which is only done
		819	within the "poll_cb"). And in the callbacks of those requests, you can
		820	add further requests to the group. And only when all those requests have
		821	finished will the the group itself finish.
		822
		823	add $grp ...
		824	$grp->add (...)
		825	Add one or more requests to the group. Any type of IO::AIO::REQ can
		826	be added, including other groups, as long as you do not create
		827	circular dependencies.
		828
		829	Returns all its arguments.
		830
		831	$grp->cancel_subs
		832	Cancel all subrequests and clears any feeder, but not the group
		833	request itself. Useful when you queued a lot of events but got a
		834	result early.
		835
		836	The group request will finish normally (you cannot add requests to
		837	the group).
		838
		839	$grp->result (...)
		840	Set the result value(s) that will be passed to the group callback
		841	when all subrequests have finished and set the groups errno to the
		842	current value of errno (just like calling "errno" without an error
		843	number). By default, no argument will be passed and errno is zero.
		844
		845	$grp->errno ([$errno])
		846	Sets the group errno value to $errno, or the current value of errno
		847	when the argument is missing.
		848
		849	Every aio request has an associated errno value that is restored
		850	when the callback is invoked. This method lets you change this value
		851	from its default (0).
		852
		853	Calling "result" will also set errno, so make sure you either set $!
		854	before the call to "result", or call c<errno> after it.
		855
		856	feed $grp $callback->($grp)
		857	Sets a feeder/generator on this group: every group can have an
		858	attached generator that generates requests if idle. The idea behind
		859	this is that, although you could just queue as many requests as you
		860	want in a group, this might starve other requests for a potentially
		861	long time. For example, "aio_scandir" might generate hundreds of
		862	thousands "aio_stat" requests, delaying any later requests for a
		863	long time.
		864
		865	To avoid this, and allow incremental generation of requests, you can
		866	instead a group and set a feeder on it that generates those
		867	requests. The feed callback will be called whenever there are few
		868	enough (see "limit", below) requests active in the group itself and
		869	is expected to queue more requests.
		870
		871	The feed callback can queue as many requests as it likes (i.e. "add"
		872	does not impose any limits).
		873
		874	If the feed does not queue more requests when called, it will be
		875	automatically removed from the group.
		876
		877	If the feed limit is 0 when this method is called, it will be set to
		878	2 automatically.
		879
		880	Example:
		881
		882	# stat all files in @files, but only ever use four aio requests concurrently:
		883
		884	my $grp = aio_group sub { print "finished\n" };
		885	limit $grp 4;
		886	feed $grp sub {
		887	my $file = pop @files
		888	or return;
		889
		890	add $grp aio_stat $file, sub { ... };
		891	};
		892
		893	limit $grp $num
		894	Sets the feeder limit for the group: The feeder will be called
		895	whenever the group contains less than this many requests.
		896
		897	Setting the limit to 0 will pause the feeding process.
		898
		899	The default value for the limit is 0, but note that setting a feeder
		900	automatically bumps it up to 2.
		901
133	SUPPORT FUNCTIONS	902	SUPPORT FUNCTIONS
		903	EVENT PROCESSING AND EVENT LOOP INTEGRATION
134	$fileno = IO::AIO::poll_fileno	904	$fileno = IO::AIO::poll_fileno
135	Return the request result pipe filehandle. This filehandle must be	905	Return the request result pipe file descriptor. This filehandle
136	polled for reading by some mechanism outside this module (e.g. Event	906	must be polled for reading by some mechanism outside this module
137	or select, see below). If the pipe becomes readable you have to call	907	(e.g. EV, Glib, select and so on, see below or the SYNOPSIS). If the
138	"poll_cb" to check the results.	908	pipe becomes readable you have to call "poll_cb" to check the
		909	results.
139		910
140	See "poll_cb" for an example.	911	See "poll_cb" for an example.
141		912
142	IO::AIO::poll_cb	913	IO::AIO::poll_cb
143	Process all outstanding events on the result pipe. You have to call	914	Process some outstanding events on the result pipe. You have to call
144	this regularly. Returns the number of events processed. Returns	915	this regularly. Returns 0 if all events could be processed, or -1 if
145	immediately when no events are outstanding.	916	it returned earlier for whatever reason. Returns immediately when no
		917	events are outstanding. The amount of events processed depends on
		918	the settings of "IO::AIO::max_poll_req" and
		919	"IO::AIO::max_poll_time".
146		920
147	You can use Event to multiplex, e.g.:	921	If not all requests were processed for whatever reason, the
		922	filehandle will still be ready when "poll_cb" returns, so normally
		923	you don't have to do anything special to have it called later.
		924
		925	Example: Install an Event watcher that automatically calls
		926	IO::AIO::poll_cb with high priority (more examples can be found in
		927	the SYNOPSIS section, at the top of this document):
148		928
149	Event->io (fd => IO::AIO::poll_fileno,	929	Event->io (fd => IO::AIO::poll_fileno,
150	poll => 'r', async => 1,	930	poll => 'r', async => 1,
151	cb => \&IO::AIO::poll_cb);	931	cb => \&IO::AIO::poll_cb);
152		932
		933	IO::AIO::max_poll_reqs $nreqs
		934	IO::AIO::max_poll_time $seconds
		935	These set the maximum number of requests (default 0, meaning
		936	infinity) that are being processed by "IO::AIO::poll_cb" in one
		937	call, respectively the maximum amount of time (default 0, meaning
		938	infinity) spent in "IO::AIO::poll_cb" to process requests (more
		939	correctly the mininum amount of time "poll_cb" is allowed to use).
		940
		941	Setting "max_poll_time" to a non-zero value creates an overhead of
		942	one syscall per request processed, which is not normally a problem
		943	unless your callbacks are really really fast or your OS is really
		944	really slow (I am not mentioning Solaris here). Using
		945	"max_poll_reqs" incurs no overhead.
		946
		947	Setting these is useful if you want to ensure some level of
		948	interactiveness when perl is not fast enough to process all requests
		949	in time.
		950
		951	For interactive programs, values such as 0.01 to 0.1 should be fine.
		952
		953	Example: Install an Event watcher that automatically calls
		954	IO::AIO::poll_cb with low priority, to ensure that other parts of
		955	the program get the CPU sometimes even under high AIO load.
		956
		957	# try not to spend much more than 0.1s in poll_cb
		958	IO::AIO::max_poll_time 0.1;
		959
		960	# use a low priority so other tasks have priority
		961	Event->io (fd => IO::AIO::poll_fileno,
		962	poll => 'r', nice => 1,
		963	cb => &IO::AIO::poll_cb);
		964
153	IO::AIO::poll_wait	965	IO::AIO::poll_wait
		966	If there are any outstanding requests and none of them in the result
154	Wait till the result filehandle becomes ready for reading (simply	967	phase, wait till the result filehandle becomes ready for reading
155	does a select on the filehandle. This is useful if you want to	968	(simply does a "select" on the filehandle. This is useful if you
156	synchronously wait for some requests to finish).	969	want to synchronously wait for some requests to finish).
157		970
158	See "nreqs" for an example.	971	See "nreqs" for an example.
159		972
		973	IO::AIO::poll
		974	Waits until some requests have been handled.
		975
		976	Returns the number of requests processed, but is otherwise strictly
		977	equivalent to:
		978
		979	IO::AIO::poll_wait, IO::AIO::poll_cb
		980
160	IO::AIO::nreqs	981	IO::AIO::flush
161	Returns the number of requests currently outstanding.	982	Wait till all outstanding AIO requests have been handled.
162		983
163	Example: wait till there are no outstanding requests anymore:	984	Strictly equivalent to:
164		985
165	IO::AIO::poll_wait, IO::AIO::poll_cb	986	IO::AIO::poll_wait, IO::AIO::poll_cb
166	while IO::AIO::nreqs;	987	while IO::AIO::nreqs;
167		988
		989	CONTROLLING THE NUMBER OF THREADS
168	IO::AIO::min_parallel $nthreads	990	IO::AIO::min_parallel $nthreads
169	Set the minimum number of AIO threads to $nthreads. The default is	991	Set the minimum number of AIO threads to $nthreads. The current
170	1, which means a single asynchronous operation can be done at one	992	default is 8, which means eight asynchronous operations can execute
171	time (the number of outstanding operations, however, is unlimited).	993	concurrently at any one time (the number of outstanding requests,
		994	however, is unlimited).
172		995
		996	IO::AIO starts threads only on demand, when an AIO request is queued
		997	and no free thread exists. Please note that queueing up a hundred
		998	requests can create demand for a hundred threads, even if it turns
		999	out that everything is in the cache and could have been processed
		1000	faster by a single thread.
		1001
173	It is recommended to keep the number of threads low, as some Linux	1002	It is recommended to keep the number of threads relatively low, as
174	kernel versions will scale negatively with the number of threads	1003	some Linux kernel versions will scale negatively with the number of
175	(higher parallelity => MUCH higher latency). With current Linux 2.6	1004	threads (higher parallelity => MUCH higher latency). With current
176	versions, 4-32 threads should be fine.	1005	Linux 2.6 versions, 4-32 threads should be fine.
177		1006
178	Under normal circumstances you don't need to call this function, as	1007	Under most circumstances you don't need to call this function, as
179	this module automatically starts some threads (the exact number	1008	the module selects a default that is suitable for low to moderate
180	might change, and is currently 4).	1009	load.
181		1010
182	IO::AIO::max_parallel $nthreads	1011	IO::AIO::max_parallel $nthreads
183	Sets the maximum number of AIO threads to $nthreads. If more than	1012	Sets the maximum number of AIO threads to $nthreads. If more than
184	the specified number of threads are currently running, kill them.	1013	the specified number of threads are currently running, this function
185	This function blocks until the limit is reached.	1014	kills them. This function blocks until the limit is reached.
		1015
		1016	While $nthreads are zero, aio requests get queued but not executed
		1017	until the number of threads has been increased again.
186		1018
187	This module automatically runs "max_parallel 0" at program end, to	1019	This module automatically runs "max_parallel 0" at program end, to
188	ensure that all threads are killed and that there are no outstanding	1020	ensure that all threads are killed and that there are no outstanding
189	requests.	1021	requests.
190		1022
191	Under normal circumstances you don't need to call this function.	1023	Under normal circumstances you don't need to call this function.
192		1024
		1025	IO::AIO::max_idle $nthreads
		1026	Limit the number of threads (default: 4) that are allowed to idle
		1027	(i.e., threads that did not get a request to process within 10
		1028	seconds). That means if a thread becomes idle while $nthreads other
		1029	threads are also idle, it will free its resources and exit.
		1030
		1031	This is useful when you allow a large number of threads (e.g. 100 or
		1032	1000) to allow for extremely high load situations, but want to free
		1033	resources under normal circumstances (1000 threads can easily
		1034	consume 30MB of RAM).
		1035
		1036	The default is probably ok in most situations, especially if thread
		1037	creation is fast. If thread creation is very slow on your system you
		1038	might want to use larger values.
		1039
193	$oldnreqs = IO::AIO::max_outstanding $nreqs	1040	IO::AIO::max_outstanding $maxreqs
		1041	This is a very bad function to use in interactive programs because
		1042	it blocks, and a bad way to reduce concurrency because it is
		1043	inexact: Better use an "aio_group" together with a feed callback.
		1044
194	Sets the maximum number of outstanding requests to $nreqs. If you	1045	Sets the maximum number of outstanding requests to $nreqs. If you do
195	try to queue up more than this number of requests, the caller will	1046	queue up more than this number of requests, the next call to the
196	block until some requests have been handled.	1047	"poll_cb" (and "poll_some" and other functions calling "poll_cb")
		1048	function will block until the limit is no longer exceeded.
197		1049
198	The default is very large, so normally there is no practical limit.	1050	The default value is very large, so there is no practical limit on
199	If you queue up many requests in a loop it it often improves speed	1051	the number of outstanding requests.
200	if you set this to a relatively low number, such as 100.
201		1052
202	Under normal circumstances you don't need to call this function.	1053	You can still queue as many requests as you want. Therefore,
		1054	"max_outstanding" is mainly useful in simple scripts (with low
		1055	values) or as a stop gap to shield against fatal memory overflow
		1056	(with large values).
		1057
		1058	STATISTICAL INFORMATION
		1059	IO::AIO::nreqs
		1060	Returns the number of requests currently in the ready, execute or
		1061	pending states (i.e. for which their callback has not been invoked
		1062	yet).
		1063
		1064	Example: wait till there are no outstanding requests anymore:
		1065
		1066	IO::AIO::poll_wait, IO::AIO::poll_cb
		1067	while IO::AIO::nreqs;
		1068
		1069	IO::AIO::nready
		1070	Returns the number of requests currently in the ready state (not yet
		1071	executed).
		1072
		1073	IO::AIO::npending
		1074	Returns the number of requests currently in the pending state
		1075	(executed, but not yet processed by poll_cb).
		1076
		1077	MISCELLANEOUS FUNCTIONS
		1078	IO::AIO implements some functions that might be useful, but are not
		1079	asynchronous.
		1080
		1081	IO::AIO::sendfile $ofh, $ifh, $offset, $count
		1082	Calls the "eio_sendfile_sync" function, which is like
		1083	"aio_sendfile", but is blocking (this makes most sense if you know
		1084	the input data is likely cached already and the output filehandle is
		1085	set to non-blocking operations).
		1086
		1087	Returns the number of bytes copied, or -1 on error.
		1088
		1089	IO::AIO::fadvise $fh, $offset, $len, $advice
		1090	Simply calls the "posix_fadvise" function (see it's manpage for
		1091	details). The following advice constants are avaiable:
		1092	"IO::AIO::FADV_NORMAL", "IO::AIO::FADV_SEQUENTIAL",
		1093	"IO::AIO::FADV_RANDOM", "IO::AIO::FADV_NOREUSE",
		1094	"IO::AIO::FADV_WILLNEED", "IO::AIO::FADV_DONTNEED".
		1095
		1096	On systems that do not implement "posix_fadvise", this function
		1097	returns ENOSYS, otherwise the return value of "posix_fadvise".
		1098
		1099	FORK BEHAVIOUR
		1100	This module should do "the right thing" when the process using it forks:
		1101
		1102	Before the fork, IO::AIO enters a quiescent state where no requests can
		1103	be added in other threads and no results will be processed. After the
		1104	fork the parent simply leaves the quiescent state and continues
		1105	request/result processing, while the child frees the request/result
		1106	queue (so that the requests started before the fork will only be handled
		1107	in the parent). Threads will be started on demand until the limit set in
		1108	the parent process has been reached again.
		1109
		1110	In short: the parent will, after a short pause, continue as if fork had
		1111	not been called, while the child will act as if IO::AIO has not been
		1112	used yet.
		1113
		1114	MEMORY USAGE
		1115	Per-request usage:
		1116
		1117	Each aio request uses - depending on your architecture - around 100-200
		1118	bytes of memory. In addition, stat requests need a stat buffer (possibly
		1119	a few hundred bytes), readdir requires a result buffer and so on. Perl
		1120	scalars and other data passed into aio requests will also be locked and
		1121	will consume memory till the request has entered the done state.
		1122
		1123	This is not awfully much, so queuing lots of requests is not usually a
		1124	problem.
		1125
		1126	Per-thread usage:
		1127
		1128	In the execution phase, some aio requests require more memory for
		1129	temporary buffers, and each thread requires a stack and other data
		1130	structures (usually around 16k-128k, depending on the OS).
		1131
		1132	KNOWN BUGS
		1133	Known bugs will be fixed in the next release.
203		1134
204	SEE ALSO	1135	SEE ALSO
205	Coro, Linux::AIO.	1136	AnyEvent::AIO for easy integration into event loops, Coro::AIO for a
		1137	more natural syntax.
206		1138
207	AUTHOR	1139	AUTHOR
208	Marc Lehmann <schmorp@schmorp.de>	1140	Marc Lehmann <schmorp@schmorp.de>
209	http://home.schmorp.de/	1141	http://home.schmorp.de/
210		1142

Diff Legend

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

Comparing IO-AIO/README (file contents): Revision 1.4 by root, Sun Jul 10 21:04:46 2005 UTC vs. Revision 1.42 by root, Thu Jan 7 20:25:57 2010 UTC

Diff Legend

Comparing IO-AIO/README (file contents):
Revision 1.4 by root, Sun Jul 10 21:04:46 2005 UTC vs.
Revision 1.42 by root, Thu Jan 7 20:25:57 2010 UTC