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

Comparing IO-AIO/README (file contents):
Revision 1.8 by root, Sun Jul 31 17:24:05 2005 UTC vs.
Revision 1.26 by root, Thu Oct 4 12:50:35 2007 UTC

…		…
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 {	7	aio_open "/etc/passwd", O_RDONLY, 0, sub {
8	my ($fh) = @_;	8	my $fh = shift
		9	or die "/etc/passwd: $!";
9	...	10	...
10	};	11	};
11		12
12	aio_unlink "/tmp/file", sub { };	13	aio_unlink "/tmp/file", sub { };
13		14
14	aio_read $fh, 30000, 1024, $buffer, 0, sub {	15	aio_read $fh, 30000, 1024, $buffer, 0, sub {
15	$_[0] > 0 or die "read error: $!";	16	$_[0] > 0 or die "read error: $!";
16	};	17	};
17		18
18	# Event	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
		30	open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!";
		31	my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb });
		32
		33	# Event integration
19	Event->io (fd => IO::AIO::poll_fileno,	34	Event->io (fd => IO::AIO::poll_fileno,
20	poll => 'r',	35	poll => 'r',
21	cb => \&IO::AIO::poll_cb);	36	cb => \&IO::AIO::poll_cb);
22		37
23	# Glib/Gtk2	38	# Glib/Gtk2 integration
24	add_watch Glib::IO IO::AIO::poll_fileno,	39	add_watch Glib::IO IO::AIO::poll_fileno,
25	in => sub { IO::AIO::poll_cb; 1 };	40	in => sub { IO::AIO::poll_cb; 1 };
26		41
27	# Tk	42	# Tk integration
28	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",	43	Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
29	readable => \&IO::AIO::poll_cb);	44	readable => \&IO::AIO::poll_cb);
30		45
31	# Danga::Socket	46	# Danga::Socket integration
32	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>	47	Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
33	\&IO::AIO::poll_cb);	48	\&IO::AIO::poll_cb);
34		49
35	DESCRIPTION	50	DESCRIPTION
36	This module implements asynchronous I/O using whatever means your	51	This module implements asynchronous I/O using whatever means your
37	operating system supports.	52	operating system supports.
38		53
		54	Asynchronous means that operations that can normally block your program
		55	(e.g. reading from disk) will be done asynchronously: the operation will
		56	still block, but you can do something else in the meantime. This is
		57	extremely useful for programs that need to stay interactive even when
		58	doing heavy I/O (GUI programs, high performance network servers etc.),
		59	but can also be used to easily do operations in parallel that are
		60	normally done sequentially, e.g. stat'ing many files, which is much
		61	faster on a RAID volume or over NFS when you do a number of stat
		62	operations concurrently.
		63
		64	While most of this works on all types of file descriptors (for example
		65	sockets), using these functions on file descriptors that support
		66	nonblocking operation (again, sockets, pipes etc.) is very inefficient.
		67	Use an event loop for that (such as the Event module): IO::AIO will
		68	naturally fit into such an event loop itself.
		69
39	Currently, a number of threads are started that execute your read/writes	70	In this version, a number of threads are started that execute your
40	and signal their completion. You don't need thread support in your libc	71	requests and signal their completion. You don't need thread support in
41	or perl, and the threads created by this module will not be visible to	72	perl, and the threads created by this module will not be visible to
42	the pthreads library. In the future, this module might make use of the	73	perl. In the future, this module might make use of the native aio
43	native aio functions available on many operating systems. However, they	74	functions available on many operating systems. However, they are often
44	are often not well-supported (Linux doesn't allow them on normal files	75	not well-supported or restricted (GNU/Linux doesn't allow them on normal
45	currently, for example), and they would only support aio_read and	76	files currently, for example), and they would only support aio_read and
46	aio_write, so the remaining functionality would have to be implemented	77	aio_write, so the remaining functionality would have to be implemented
47	using threads anyway.	78	using threads anyway.
48		79
49	Although the module will work with in the presence of other threads, it	80	Although the module will work in the presence of other (Perl-) threads,
50	is currently not reentrant, so use appropriate locking yourself, always	81	it is currently not reentrant in any way, so use appropriate locking
51	call "poll_cb" from within the same thread, or never call "poll_cb" (or	82	yourself, always call "poll_cb" from within the same thread, or never
52	other "aio_" functions) recursively.	83	call "poll_cb" (or other "aio_" functions) recursively.
		84
		85	EXAMPLE
		86	This is a simple example that uses the Event module and loads
		87	/etc/passwd asynchronously:
		88
		89	use Fcntl;
		90	use Event;
		91	use IO::AIO;
		92
		93	# register the IO::AIO callback with Event
		94	Event->io (fd => IO::AIO::poll_fileno,
		95	poll => 'r',
		96	cb => \&IO::AIO::poll_cb);
		97
		98	# queue the request to open /etc/passwd
		99	aio_open "/etc/passwd", O_RDONLY, 0, sub {
		100	my $fh = shift
		101	or die "error while opening: $!";
		102
		103	# stat'ing filehandles is generally non-blocking
		104	my $size = -s $fh;
		105
		106	# queue a request to read the file
		107	my $contents;
		108	aio_read $fh, 0, $size, $contents, 0, sub {
		109	$_[0] == $size
		110	or die "short read: $!";
		111
		112	close $fh;
		113
		114	# file contents now in $contents
		115	print $contents;
		116
		117	# exit event loop and program
		118	Event::unloop;
		119	};
		120	};
		121
		122	# possibly queue up other requests, or open GUI windows,
		123	# check for sockets etc. etc.
		124
		125	# process events as long as there are some:
		126	Event::loop;
		127
		128	REQUEST ANATOMY AND LIFETIME
		129	Every "aio_*" function creates a request. which is a C data structure
		130	not directly visible to Perl.
		131
		132	If called in non-void context, every request function returns a Perl
		133	object representing the request. In void context, nothing is returned,
		134	which saves a bit of memory.
		135
		136	The perl object is a fairly standard ref-to-hash object. The hash
		137	contents are not used by IO::AIO so you are free to store anything you
		138	like in it.
		139
		140	During their existance, aio requests travel through the following
		141	states, in order:
		142
		143	ready
		144	Immediately after a request is created it is put into the ready
		145	state, waiting for a thread to execute it.
		146
		147	execute
		148	A thread has accepted the request for processing and is currently
		149	executing it (e.g. blocking in read).
		150
		151	pending
		152	The request has been executed and is waiting for result processing.
		153
		154	While request submission and execution is fully asynchronous, result
		155	processing is not and relies on the perl interpreter calling
		156	"poll_cb" (or another function with the same effect).
		157
		158	result
		159	The request results are processed synchronously by "poll_cb".
		160
		161	The "poll_cb" function will process all outstanding aio requests by
		162	calling their callbacks, freeing memory associated with them and
		163	managing any groups they are contained in.
		164
		165	done
		166	Request has reached the end of its lifetime and holds no resources
		167	anymore (except possibly for the Perl object, but its connection to
		168	the actual aio request is severed and calling its methods will
		169	either do nothing or result in a runtime error).
53		170
54	FUNCTIONS	171	FUNCTIONS
55	AIO FUNCTIONS	172	AIO REQUEST FUNCTIONS
56	All the "aio_*" calls are more or less thin wrappers around the syscall	173	All the "aio_*" calls are more or less thin wrappers around the syscall
57	with the same name (sans "aio_"). The arguments are similar or	174	with the same name (sans "aio_"). The arguments are similar or
58	identical, and they all accept an additional (and optional) $callback	175	identical, and they all accept an additional (and optional) $callback
59	argument which must be a code reference. This code reference will get	176	argument which must be a code reference. This code reference will get
60	called with the syscall return code (e.g. most syscalls return -1 on	177	called with the syscall return code (e.g. most syscalls return -1 on
…		…
62	argument when the given syscall has been executed asynchronously.	179	argument when the given syscall has been executed asynchronously.
63		180
64	All functions expecting a filehandle keep a copy of the filehandle	181	All functions expecting a filehandle keep a copy of the filehandle
65	internally until the request has finished.	182	internally until the request has finished.
66		183
		184	All functions return request objects of type IO::AIO::REQ that allow
		185	further manipulation of those requests while they are in-flight.
		186
67	The filenames you pass to these routines must be absolute. The reason	187	The pathnames you pass to these routines must be absolute and encoded
68	for this is that at the time the request is being executed, the current	188	as octets. The reason for the former is that at the time the request is
69	working directory could have changed. Alternatively, you can make sure	189	being executed, the current working directory could have changed.
70	that you never change the current working directory.	190	Alternatively, you can make sure that you never change the current
		191	working directory anywhere in the program and then use relative paths.
71		192
		193	To encode pathnames as octets, either make sure you either: a) always
		194	pass in filenames you got from outside (command line, readdir etc.)
		195	without tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module
		196	and encode your pathnames to the locale (or other) encoding in effect in
		197	the user environment, d) use Glib::filename_from_unicode on unicode
		198	filenames or e) use something else to ensure your scalar has the correct
		199	contents.
		200
		201	This works, btw. independent of the internal UTF-8 bit, which IO::AIO
		202	handles correctly wether it is set or not.
		203
		204	$prev_pri = aioreq_pri [$pri]
		205	Returns the priority value that would be used for the next request
		206	and, if $pri is given, sets the priority for the next aio request.
		207
		208	The default priority is 0, the minimum and maximum priorities are -4
		209	and 4, respectively. Requests with higher priority will be serviced
		210	first.
		211
		212	The priority will be reset to 0 after each call to one of the
		213	"aio_*" functions.
		214
		215	Example: open a file with low priority, then read something from it
		216	with higher priority so the read request is serviced before other
		217	low priority open requests (potentially spamming the cache):
		218
		219	aioreq_pri -3;
		220	aio_open ..., sub {
		221	return unless $_[0];
		222
		223	aioreq_pri -2;
		224	aio_read $_[0], ..., sub {
		225	...
		226	};
		227	};
		228
		229	aioreq_nice $pri_adjust
		230	Similar to "aioreq_pri", but subtracts the given value from the
		231	current priority, so the effect is cumulative.
		232
72	aio_open $pathname, $flags, $mode, $callback	233	aio_open $pathname, $flags, $mode, $callback->($fh)
73	Asynchronously open or create a file and call the callback with a	234	Asynchronously open or create a file and call the callback with a
74	newly created filehandle for the file.	235	newly created filehandle for the file.
75		236
76	The pathname passed to "aio_open" must be absolute. See API NOTES,	237	The pathname passed to "aio_open" must be absolute. See API NOTES,
77	above, for an explanation.	238	above, for an explanation.
…		…
80	They are the same as used by "sysopen".	241	They are the same as used by "sysopen".
81		242
82	Likewise, $mode specifies the mode of the newly created file, if it	243	Likewise, $mode specifies the mode of the newly created file, if it
83	didn't exist and "O_CREAT" has been given, just like perl's	244	didn't exist and "O_CREAT" has been given, just like perl's
84	"sysopen", except that it is mandatory (i.e. use 0 if you don't	245	"sysopen", except that it is mandatory (i.e. use 0 if you don't
85	create new files, and 0666 or 0777 if you do).	246	create new files, and 0666 or 0777 if you do). Note that the $mode
		247	will be modified by the umask in effect then the request is being
		248	executed, so better never change the umask.
86		249
87	Example:	250	Example:
88		251
89	aio_open "/etc/passwd", O_RDONLY, 0, sub {	252	aio_open "/etc/passwd", O_RDONLY, 0, sub {
90	if ($_[0]) {	253	if ($_[0]) {
…		…
93	} else {	256	} else {
94	die "open failed: $!\n";	257	die "open failed: $!\n";
95	}	258	}
96	};	259	};
97		260
98	aio_close $fh, $callback	261	aio_close $fh, $callback->($status)
99	Asynchronously close a file and call the callback with the result	262	Asynchronously close a file and call the callback with the result
100	code. WARNING: although accepted, you should not pass in a perl	263	code.
101	filehandle here, as perl will likely close the file descriptor
102	another time when the filehandle is destroyed. Normally, you can
103	safely call perls "close" or just let filehandles go out of scope.
104		264
105	This is supposed to be a bug in the API, so that might change. It's	265	Unlike the other functions operating on files, this function uses
106	therefore best to avoid this function.	266	the PerlIO layer to close the filehandle. The reason is that the
		267	PerlIO API insists on closing the underlying fd itself, no matter
		268	what, and doesn't allow modifications to the fd. Unfortunately, it
		269	is not clear that you can call PerlIO from different threads
		270	(actually, its quite clear that this won't work in some cases), so
		271	while it likely works perfectly with simple file handles (such as
		272	the ones created by "aio_open") it might fail in interesting ways
		273	for others.
107		274
		275	Having said that, aio_close tries to clean up the filehandle as much
		276	as possible before handing it to an io thread, and generally does
		277	work.
		278
108	aio_read $fh,$offset,$length, $data,$dataoffset,$callback	279	aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
109	aio_write $fh,$offset,$length, $data,$dataoffset,$callback	280	aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
110	Reads or writes "length" bytes from the specified "fh" and "offset"	281	Reads or writes $length bytes from the specified $fh and $offset
111	into the scalar given by "data" and offset "dataoffset" and calls	282	into the scalar given by $data and offset $dataoffset and calls the
112	the callback without the actual number of bytes read (or -1 on	283	callback without the actual number of bytes read (or -1 on error,
113	error, just like the syscall).	284	just like the syscall).
		285
		286	If $offset is undefined, then the current file descriptor offset
		287	will be used (and updated), otherwise the file descriptor offset
		288	will not be changed by these calls.
		289
		290	If $length is undefined in "aio_write", use the remaining length of
		291	$data.
		292
		293	If $dataoffset is less than zero, it will be counted from the end of
		294	$data.
		295
		296	The $data scalar MUST NOT be modified in any way while the request
		297	is outstanding. Modifying it can result in segfaults or World War
		298	III (if the necessary/optional hardware is installed).
114		299
115	Example: Read 15 bytes at offset 7 into scalar $buffer, starting at	300	Example: Read 15 bytes at offset 7 into scalar $buffer, starting at
116	offset 0 within the scalar:	301	offset 0 within the scalar:
117		302
118	aio_read $fh, 7, 15, $buffer, 0, sub {	303	aio_read $fh, 7, 15, $buffer, 0, sub {
119	$_[0] > 0 or die "read error: $!";	304	$_[0] > 0 or die "read error: $!";
120	print "read $_[0] bytes: <$buffer>\n";	305	print "read $_[0] bytes: <$buffer>\n";
121	};	306	};
122		307
		308	aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
		309	Tries to copy $length bytes from $in_fh to $out_fh. It starts
		310	reading at byte offset $in_offset, and starts writing at the current
		311	file offset of $out_fh. Because of that, it is not safe to issue
		312	more than one "aio_sendfile" per $out_fh, as they will interfere
		313	with each other.
		314
		315	This call tries to make use of a native "sendfile" syscall to
		316	provide zero-copy operation. For this to work, $out_fh should refer
		317	to a socket, and $in_fh should refer to mmap'able file.
		318
		319	If the native sendfile call fails or is not implemented, it will be
		320	emulated, so you can call "aio_sendfile" on any type of filehandle
		321	regardless of the limitations of the operating system.
		322
		323	Please note, however, that "aio_sendfile" can read more bytes from
		324	$in_fh than are written, and there is no way to find out how many
		325	bytes have been read from "aio_sendfile" alone, as "aio_sendfile"
		326	only provides the number of bytes written to $out_fh. Only if the
		327	result value equals $length one can assume that $length bytes have
		328	been read.
		329
123	aio_readahead $fh,$offset,$length, $callback	330	aio_readahead $fh,$offset,$length, $callback->($retval)
124	Asynchronously reads the specified byte range into the page cache,
125	using the "readahead" syscall. If that syscall doesn't exist (likely
126	if your OS isn't Linux) the status will be -1 and $! is set to
127	"ENOSYS".
128
129	"aio_readahead" populates the page cache with data from a file so	331	"aio_readahead" populates the page cache with data from a file so
130	that subsequent reads from that file will not block on disk I/O. The	332	that subsequent reads from that file will not block on disk I/O. The
131	$offset argument specifies the starting point from which data is to	333	$offset argument specifies the starting point from which data is to
132	be read and $length specifies the number of bytes to be read. I/O is	334	be read and $length specifies the number of bytes to be read. I/O is
133	performed in whole pages, so that offset is effectively rounded down	335	performed in whole pages, so that offset is effectively rounded down
134	to a page boundary and bytes are read up to the next page boundary	336	to a page boundary and bytes are read up to the next page boundary
135	greater than or equal to (off-set+length). "aio_readahead" does not	337	greater than or equal to (off-set+length). "aio_readahead" does not
136	read beyond the end of the file. The current file offset of the file	338	read beyond the end of the file. The current file offset of the file
137	is left unchanged.	339	is left unchanged.
138		340
		341	If that syscall doesn't exist (likely if your OS isn't Linux) it
		342	will be emulated by simply reading the data, which would have a
		343	similar effect.
		344
139	aio_stat $fh_or_path, $callback	345	aio_stat $fh_or_path, $callback->($status)
140	aio_lstat $fh, $callback	346	aio_lstat $fh, $callback->($status)
141	Works like perl's "stat" or "lstat" in void context. The callback	347	Works like perl's "stat" or "lstat" in void context. The callback
142	will be called after the stat and the results will be available	348	will be called after the stat and the results will be available
143	using "stat _" or "-s _" etc...	349	using "stat _" or "-s _" etc...
144		350
145	The pathname passed to "aio_stat" must be absolute. See API NOTES,	351	The pathname passed to "aio_stat" must be absolute. See API NOTES,
…		…
155	aio_stat "/etc/passwd", sub {	361	aio_stat "/etc/passwd", sub {
156	$_[0] and die "stat failed: $!";	362	$_[0] and die "stat failed: $!";
157	print "size is ", -s _, "\n";	363	print "size is ", -s _, "\n";
158	};	364	};
159		365
		366	aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
		367	Works like perl's "utime" function (including the special case of
		368	$atime and $mtime being undef). Fractional times are supported if
		369	the underlying syscalls support them.
		370
		371	When called with a pathname, uses utimes(2) if available, otherwise
		372	utime(2). If called on a file descriptor, uses futimes(2) if
		373	available, otherwise returns ENOSYS, so this is not portable.
		374
		375	Examples:
		376
		377	# set atime and mtime to current time (basically touch(1)):
		378	aio_utime "path", undef, undef;
		379	# set atime to current time and mtime to beginning of the epoch:
		380	aio_utime "path", time, undef; # undef==0
		381
		382	aio_chown $fh_or_path, $uid, $gid, $callback->($status)
		383	Works like perl's "chown" function, except that "undef" for either
		384	$uid or $gid is being interpreted as "do not change" (but -1 can
		385	also be used).
		386
		387	Examples:
		388
		389	# same as "chown root path" in the shell:
		390	aio_chown "path", 0, -1;
		391	# same as above:
		392	aio_chown "path", 0, undef;
		393
		394	aio_truncate $fh_or_path, $offset, $callback->($status)
		395	Works like truncate(2) or ftruncate(2).
		396
		397	aio_chmod $fh_or_path, $mode, $callback->($status)
		398	Works like perl's "chmod" function.
		399
160	aio_unlink $pathname, $callback	400	aio_unlink $pathname, $callback->($status)
161	Asynchronously unlink (delete) a file and call the callback with the	401	Asynchronously unlink (delete) a file and call the callback with the
162	result code.	402	result code.
163		403
		404	aio_mknod $path, $mode, $dev, $callback->($status)
		405	[EXPERIMENTAL]
		406
		407	Asynchronously create a device node (or fifo). See mknod(2).
		408
		409	The only (POSIX-) portable way of calling this function is:
		410
		411	aio_mknod $path, IO::AIO::S_IFIFO \| $mode, 0, sub { ...
		412
		413	aio_link $srcpath, $dstpath, $callback->($status)
		414	Asynchronously create a new link to the existing object at $srcpath
		415	at the path $dstpath and call the callback with the result code.
		416
		417	aio_symlink $srcpath, $dstpath, $callback->($status)
		418	Asynchronously create a new symbolic link to the existing object at
		419	$srcpath at the path $dstpath and call the callback with the result
		420	code.
		421
		422	aio_readlink $path, $callback->($link)
		423	Asynchronously read the symlink specified by $path and pass it to
		424	the callback. If an error occurs, nothing or undef gets passed to
		425	the callback.
		426
		427	aio_rename $srcpath, $dstpath, $callback->($status)
		428	Asynchronously rename the object at $srcpath to $dstpath, just as
		429	rename(2) and call the callback with the result code.
		430
		431	aio_mkdir $pathname, $mode, $callback->($status)
		432	Asynchronously mkdir (create) a directory and call the callback with
		433	the result code. $mode will be modified by the umask at the time the
		434	request is executed, so do not change your umask.
		435
		436	aio_rmdir $pathname, $callback->($status)
		437	Asynchronously rmdir (delete) a directory and call the callback with
		438	the result code.
		439
		440	aio_readdir $pathname, $callback->($entries)
		441	Unlike the POSIX call of the same name, "aio_readdir" reads an
		442	entire directory (i.e. opendir + readdir + closedir). The entries
		443	will not be sorted, and will NOT include the "." and ".." entries.
		444
		445	The callback a single argument which is either "undef" or an
		446	array-ref with the filenames.
		447
		448	aio_load $path, $data, $callback->($status)
		449	This is a composite request that tries to fully load the given file
		450	into memory. Status is the same as with aio_read.
		451
		452	aio_copy $srcpath, $dstpath, $callback->($status)
		453	Try to copy the file (directories not supported as either source
		454	or destination) from $srcpath to $dstpath and call the callback with
		455	the 0 (error) or -1 ok.
		456
		457	This is a composite request that it creates the destination file
		458	with mode 0200 and copies the contents of the source file into it
		459	using "aio_sendfile", followed by restoring atime, mtime, access
		460	mode and uid/gid, in that order.
		461
		462	If an error occurs, the partial destination file will be unlinked,
		463	if possible, except when setting atime, mtime, access mode and
		464	uid/gid, where errors are being ignored.
		465
		466	aio_move $srcpath, $dstpath, $callback->($status)
		467	Try to move the file (directories not supported as either source
		468	or destination) from $srcpath to $dstpath and call the callback with
		469	the 0 (error) or -1 ok.
		470
		471	This is a composite request that tries to rename(2) the file first.
		472	If rename files with "EXDEV", it copies the file with "aio_copy"
		473	and, if that is successful, unlinking the $srcpath.
		474
		475	aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
		476	Scans a directory (similar to "aio_readdir") but additionally tries
		477	to efficiently separate the entries of directory $path into two sets
		478	of names, directories you can recurse into (directories), and ones
		479	you cannot recurse into (everything else, including symlinks to
		480	directories).
		481
		482	"aio_scandir" is a composite request that creates of many sub
		483	requests_ $maxreq specifies the maximum number of outstanding aio
		484	requests that this function generates. If it is "<= 0", then a
		485	suitable default will be chosen (currently 4).
		486
		487	On error, the callback is called without arguments, otherwise it
		488	receives two array-refs with path-relative entry names.
		489
		490	Example:
		491
		492	aio_scandir $dir, 0, sub {
		493	my ($dirs, $nondirs) = @_;
		494	print "real directories: @$dirs\n";
		495	print "everything else: @$nondirs\n";
		496	};
		497
		498	Implementation notes.
		499
		500	The "aio_readdir" cannot be avoided, but "stat()"'ing every entry
		501	can.
		502
		503	After reading the directory, the modification time, size etc. of the
		504	directory before and after the readdir is checked, and if they match
		505	(and isn't the current time), the link count will be used to decide
		506	how many entries are directories (if >= 2). Otherwise, no knowledge
		507	of the number of subdirectories will be assumed.
		508
		509	Then entries will be sorted into likely directories (everything
		510	without a non-initial dot currently) and likely non-directories
		511	(everything else). Then every entry plus an appended "/." will be
		512	"stat"'ed, likely directories first. If that succeeds, it assumes
		513	that the entry is a directory or a symlink to directory (which will
		514	be checked seperately). This is often faster than stat'ing the entry
		515	itself because filesystems might detect the type of the entry
		516	without reading the inode data (e.g. ext2fs filetype feature).
		517
		518	If the known number of directories (link count - 2) has been
		519	reached, the rest of the entries is assumed to be non-directories.
		520
		521	This only works with certainty on POSIX (= UNIX) filesystems, which
		522	fortunately are the vast majority of filesystems around.
		523
		524	It will also likely work on non-POSIX filesystems with reduced
		525	efficiency as those tend to return 0 or 1 as link counts, which
		526	disables the directory counting heuristic.
		527
		528	aio_rmtree $path, $callback->($status)
		529	Delete a directory tree starting (and including) $path, return the
		530	status of the final "rmdir" only. This is a composite request that
		531	uses "aio_scandir" to recurse into and rmdir directories, and unlink
		532	everything else.
		533
164	aio_fsync $fh, $callback	534	aio_fsync $fh, $callback->($status)
165	Asynchronously call fsync on the given filehandle and call the	535	Asynchronously call fsync on the given filehandle and call the
166	callback with the fsync result code.	536	callback with the fsync result code.
167		537
168	aio_fdatasync $fh, $callback	538	aio_fdatasync $fh, $callback->($status)
169	Asynchronously call fdatasync on the given filehandle and call the	539	Asynchronously call fdatasync on the given filehandle and call the
170	callback with the fdatasync result code. Might set $! to "ENOSYS" if	540	callback with the fdatasync result code.
171	"fdatasync" is not available.	541
		542	If this call isn't available because your OS lacks it or it couldn't
		543	be detected, it will be emulated by calling "fsync" instead.
		544
		545	aio_group $callback->(...)
		546	This is a very special aio request: Instead of doing something, it
		547	is a container for other aio requests, which is useful if you want
		548	to bundle many requests into a single, composite, request with a
		549	definite callback and the ability to cancel the whole request with
		550	its subrequests.
		551
		552	Returns an object of class IO::AIO::GRP. See its documentation below
		553	for more info.
		554
		555	Example:
		556
		557	my $grp = aio_group sub {
		558	print "all stats done\n";
		559	};
		560
		561	add $grp
		562	(aio_stat ...),
		563	(aio_stat ...),
		564	...;
		565
		566	aio_nop $callback->()
		567	This is a special request - it does nothing in itself and is only
		568	used for side effects, such as when you want to add a dummy request
		569	to a group so that finishing the requests in the group depends on
		570	executing the given code.
		571
		572	While this request does nothing, it still goes through the execution
		573	phase and still requires a worker thread. Thus, the callback will
		574	not be executed immediately but only after other requests in the
		575	queue have entered their execution phase. This can be used to
		576	measure request latency.
		577
		578	IO::AIO::aio_busy $fractional_seconds, $callback->() NOT EXPORTED
		579	Mainly used for debugging and benchmarking, this aio request puts
		580	one of the request workers to sleep for the given time.
		581
		582	While it is theoretically handy to have simple I/O scheduling
		583	requests like sleep and file handle readable/writable, the overhead
		584	this creates is immense (it blocks a thread for a long time) so do
		585	not use this function except to put your application under
		586	artificial I/O pressure.
		587
		588	IO::AIO::REQ CLASS
		589	All non-aggregate "aio_*" functions return an object of this class when
		590	called in non-void context.
		591
		592	cancel $req
		593	Cancels the request, if possible. Has the effect of skipping
		594	execution when entering the execute state and skipping calling the
		595	callback when entering the the result state, but will leave the
		596	request otherwise untouched. That means that requests that currently
		597	execute will not be stopped and resources held by the request will
		598	not be freed prematurely.
		599
		600	cb $req $callback->(...)
		601	Replace (or simply set) the callback registered to the request.
		602
		603	IO::AIO::GRP CLASS
		604	This class is a subclass of IO::AIO::REQ, so all its methods apply to
		605	objects of this class, too.
		606
		607	A IO::AIO::GRP object is a special request that can contain multiple
		608	other aio requests.
		609
		610	You create one by calling the "aio_group" constructing function with a
		611	callback that will be called when all contained requests have entered
		612	the "done" state:
		613
		614	my $grp = aio_group sub {
		615	print "all requests are done\n";
		616	};
		617
		618	You add requests by calling the "add" method with one or more
		619	"IO::AIO::REQ" objects:
		620
		621	$grp->add (aio_unlink "...");
		622
		623	add $grp aio_stat "...", sub {
		624	$_[0] or return $grp->result ("error");
		625
		626	# add another request dynamically, if first succeeded
		627	add $grp aio_open "...", sub {
		628	$grp->result ("ok");
		629	};
		630	};
		631
		632	This makes it very easy to create composite requests (see the source of
		633	"aio_move" for an application) that work and feel like simple requests.
		634
		635	* The IO::AIO::GRP objects will be cleaned up during calls to
		636	"IO::AIO::poll_cb", just like any other request.
		637	* They can be canceled like any other request. Canceling will cancel not
		638	only the request itself, but also all requests it contains.
		639	* They can also can also be added to other IO::AIO::GRP objects.
		640	* You must not add requests to a group from within the group callback
		641	(or any later time).
		642
		643	Their lifetime, simplified, looks like this: when they are empty, they
		644	will finish very quickly. If they contain only requests that are in the
		645	"done" state, they will also finish. Otherwise they will continue to
		646	exist.
		647
		648	That means after creating a group you have some time to add requests.
		649	And in the callbacks of those requests, you can add further requests to
		650	the group. And only when all those requests have finished will the the
		651	group itself finish.
		652
		653	add $grp ...
		654	$grp->add (...)
		655	Add one or more requests to the group. Any type of IO::AIO::REQ can
		656	be added, including other groups, as long as you do not create
		657	circular dependencies.
		658
		659	Returns all its arguments.
		660
		661	$grp->cancel_subs
		662	Cancel all subrequests and clears any feeder, but not the group
		663	request itself. Useful when you queued a lot of events but got a
		664	result early.
		665
		666	$grp->result (...)
		667	Set the result value(s) that will be passed to the group callback
		668	when all subrequests have finished and set thre groups errno to the
		669	current value of errno (just like calling "errno" without an error
		670	number). By default, no argument will be passed and errno is zero.
		671
		672	$grp->errno ([$errno])
		673	Sets the group errno value to $errno, or the current value of errno
		674	when the argument is missing.
		675
		676	Every aio request has an associated errno value that is restored
		677	when the callback is invoked. This method lets you change this value
		678	from its default (0).
		679
		680	Calling "result" will also set errno, so make sure you either set $!
		681	before the call to "result", or call c<errno> after it.
		682
		683	feed $grp $callback->($grp)
		684	Sets a feeder/generator on this group: every group can have an
		685	attached generator that generates requests if idle. The idea behind
		686	this is that, although you could just queue as many requests as you
		687	want in a group, this might starve other requests for a potentially
		688	long time. For example, "aio_scandir" might generate hundreds of
		689	thousands "aio_stat" requests, delaying any later requests for a
		690	long time.
		691
		692	To avoid this, and allow incremental generation of requests, you can
		693	instead a group and set a feeder on it that generates those
		694	requests. The feed callback will be called whenever there are few
		695	enough (see "limit", below) requests active in the group itself and
		696	is expected to queue more requests.
		697
		698	The feed callback can queue as many requests as it likes (i.e. "add"
		699	does not impose any limits).
		700
		701	If the feed does not queue more requests when called, it will be
		702	automatically removed from the group.
		703
		704	If the feed limit is 0, it will be set to 2 automatically.
		705
		706	Example:
		707
		708	# stat all files in @files, but only ever use four aio requests concurrently:
		709
		710	my $grp = aio_group sub { print "finished\n" };
		711	limit $grp 4;
		712	feed $grp sub {
		713	my $file = pop @files
		714	or return;
		715
		716	add $grp aio_stat $file, sub { ... };
		717	};
		718
		719	limit $grp $num
		720	Sets the feeder limit for the group: The feeder will be called
		721	whenever the group contains less than this many requests.
		722
		723	Setting the limit to 0 will pause the feeding process.
172		724
173	SUPPORT FUNCTIONS	725	SUPPORT FUNCTIONS
		726	EVENT PROCESSING AND EVENT LOOP INTEGRATION
174	$fileno = IO::AIO::poll_fileno	727	$fileno = IO::AIO::poll_fileno
175	Return the request result pipe file descriptor. This filehandle	728	Return the request result pipe file descriptor. This filehandle
176	must be polled for reading by some mechanism outside this module	729	must be polled for reading by some mechanism outside this module
177	(e.g. Event or select, see below or the SYNOPSIS). If the pipe	730	(e.g. Event or select, see below or the SYNOPSIS). If the pipe
178	becomes readable you have to call "poll_cb" to check the results.	731	becomes readable you have to call "poll_cb" to check the results.
179		732
180	See "poll_cb" for an example.	733	See "poll_cb" for an example.
181		734
182	IO::AIO::poll_cb	735	IO::AIO::poll_cb
183	Process all outstanding events on the result pipe. You have to call	736	Process some outstanding events on the result pipe. You have to call
184	this regularly. Returns the number of events processed. Returns	737	this regularly. Returns the number of events processed. Returns
185	immediately when no events are outstanding.	738	immediately when no events are outstanding. The amount of events
		739	processed depends on the settings of "IO::AIO::max_poll_req" and
		740	"IO::AIO::max_poll_time".
		741
		742	If not all requests were processed for whatever reason, the
		743	filehandle will still be ready when "poll_cb" returns.
186		744
187	Example: Install an Event watcher that automatically calls	745	Example: Install an Event watcher that automatically calls
188	IO::AIO::poll_cb with high priority:	746	IO::AIO::poll_cb with high priority:
189		747
190	Event->io (fd => IO::AIO::poll_fileno,	748	Event->io (fd => IO::AIO::poll_fileno,
191	poll => 'r', async => 1,	749	poll => 'r', async => 1,
192	cb => \&IO::AIO::poll_cb);	750	cb => \&IO::AIO::poll_cb);
193		751
		752	IO::AIO::max_poll_reqs $nreqs
		753	IO::AIO::max_poll_time $seconds
		754	These set the maximum number of requests (default 0, meaning
		755	infinity) that are being processed by "IO::AIO::poll_cb" in one
		756	call, respectively the maximum amount of time (default 0, meaning
		757	infinity) spent in "IO::AIO::poll_cb" to process requests (more
		758	correctly the mininum amount of time "poll_cb" is allowed to use).
		759
		760	Setting "max_poll_time" to a non-zero value creates an overhead of
		761	one syscall per request processed, which is not normally a problem
		762	unless your callbacks are really really fast or your OS is really
		763	really slow (I am not mentioning Solaris here). Using
		764	"max_poll_reqs" incurs no overhead.
		765
		766	Setting these is useful if you want to ensure some level of
		767	interactiveness when perl is not fast enough to process all requests
		768	in time.
		769
		770	For interactive programs, values such as 0.01 to 0.1 should be fine.
		771
		772	Example: Install an Event watcher that automatically calls
		773	IO::AIO::poll_cb with low priority, to ensure that other parts of
		774	the program get the CPU sometimes even under high AIO load.
		775
		776	# try not to spend much more than 0.1s in poll_cb
		777	IO::AIO::max_poll_time 0.1;
		778
		779	# use a low priority so other tasks have priority
		780	Event->io (fd => IO::AIO::poll_fileno,
		781	poll => 'r', nice => 1,
		782	cb => &IO::AIO::poll_cb);
		783
194	IO::AIO::poll_wait	784	IO::AIO::poll_wait
		785	If there are any outstanding requests and none of them in the result
195	Wait till the result filehandle becomes ready for reading (simply	786	phase, wait till the result filehandle becomes ready for reading
196	does a "select" on the filehandle. This is useful if you want to	787	(simply does a "select" on the filehandle. This is useful if you
197	synchronously wait for some requests to finish).	788	want to synchronously wait for some requests to finish).
198		789
199	See "nreqs" for an example.	790	See "nreqs" for an example.
200		791
		792	IO::AIO::poll
		793	Waits until some requests have been handled.
		794
		795	Returns the number of requests processed, but is otherwise strictly
		796	equivalent to:
		797
		798	IO::AIO::poll_wait, IO::AIO::poll_cb
		799
201	IO::AIO::nreqs	800	IO::AIO::flush
202	Returns the number of requests currently outstanding (i.e. for which	801	Wait till all outstanding AIO requests have been handled.
203	their callback has not been invoked yet).
204		802
205	Example: wait till there are no outstanding requests anymore:	803	Strictly equivalent to:
206		804
207	IO::AIO::poll_wait, IO::AIO::poll_cb	805	IO::AIO::poll_wait, IO::AIO::poll_cb
208	while IO::AIO::nreqs;	806	while IO::AIO::nreqs;
209		807
210	IO::AIO::flush	808	CONTROLLING THE NUMBER OF THREADS
211	Wait till all outstanding AIO requests have been handled.
212
213	Strictly equivalent to:
214
215	IO::AIO::poll_wait, IO::AIO::poll_cb
216	while IO::AIO::nreqs;
217
218	IO::AIO::poll
219	Waits until some requests have been handled.
220
221	Strictly equivalent to:
222
223	IO::AIO::poll_wait, IO::AIO::poll_cb
224	if IO::AIO::nreqs;
225
226	IO::AIO::min_parallel $nthreads	809	IO::AIO::min_parallel $nthreads
227	Set the minimum number of AIO threads to $nthreads. The default is	810	Set the minimum number of AIO threads to $nthreads. The current
228	1, which means a single asynchronous operation can be done at one	811	default is 8, which means eight asynchronous operations can execute
229	time (the number of outstanding operations, however, is unlimited).	812	concurrently at any one time (the number of outstanding requests,
		813	however, is unlimited).
230		814
		815	IO::AIO starts threads only on demand, when an AIO request is queued
		816	and no free thread exists. Please note that queueing up a hundred
		817	requests can create demand for a hundred threads, even if it turns
		818	out that everything is in the cache and could have been processed
		819	faster by a single thread.
		820
231	It is recommended to keep the number of threads low, as some Linux	821	It is recommended to keep the number of threads relatively low, as
232	kernel versions will scale negatively with the number of threads	822	some Linux kernel versions will scale negatively with the number of
233	(higher parallelity => MUCH higher latency). With current Linux 2.6	823	threads (higher parallelity => MUCH higher latency). With current
234	versions, 4-32 threads should be fine.	824	Linux 2.6 versions, 4-32 threads should be fine.
235		825
236	Under normal circumstances you don't need to call this function, as	826	Under most circumstances you don't need to call this function, as
237	this module automatically starts some threads (the exact number	827	the module selects a default that is suitable for low to moderate
238	might change, and is currently 4).	828	load.
239		829
240	IO::AIO::max_parallel $nthreads	830	IO::AIO::max_parallel $nthreads
241	Sets the maximum number of AIO threads to $nthreads. If more than	831	Sets the maximum number of AIO threads to $nthreads. If more than
242	the specified number of threads are currently running, kill them.	832	the specified number of threads are currently running, this function
243	This function blocks until the limit is reached.	833	kills them. This function blocks until the limit is reached.
		834
		835	While $nthreads are zero, aio requests get queued but not executed
		836	until the number of threads has been increased again.
244		837
245	This module automatically runs "max_parallel 0" at program end, to	838	This module automatically runs "max_parallel 0" at program end, to
246	ensure that all threads are killed and that there are no outstanding	839	ensure that all threads are killed and that there are no outstanding
247	requests.	840	requests.
248		841
249	Under normal circumstances you don't need to call this function.	842	Under normal circumstances you don't need to call this function.
250		843
		844	IO::AIO::max_idle $nthreads
		845	Limit the number of threads (default: 4) that are allowed to idle
		846	(i.e., threads that did not get a request to process within 10
		847	seconds). That means if a thread becomes idle while $nthreads other
		848	threads are also idle, it will free its resources and exit.
		849
		850	This is useful when you allow a large number of threads (e.g. 100 or
		851	1000) to allow for extremely high load situations, but want to free
		852	resources under normal circumstances (1000 threads can easily
		853	consume 30MB of RAM).
		854
		855	The default is probably ok in most situations, especially if thread
		856	creation is fast. If thread creation is very slow on your system you
		857	might want to use larger values.
		858
251	$oldnreqs = IO::AIO::max_outstanding $nreqs	859	$oldmaxreqs = IO::AIO::max_outstanding $maxreqs
		860	This is a very bad function to use in interactive programs because
		861	it blocks, and a bad way to reduce concurrency because it is
		862	inexact: Better use an "aio_group" together with a feed callback.
		863
252	Sets the maximum number of outstanding requests to $nreqs. If you	864	Sets the maximum number of outstanding requests to $nreqs. If you do
253	try to queue up more than this number of requests, the caller will	865	queue up more than this number of requests, the next call to the
254	block until some requests have been handled.	866	"poll_cb" (and "poll_some" and other functions calling "poll_cb")
		867	function will block until the limit is no longer exceeded.
255		868
256	The default is very large, so normally there is no practical limit.	869	The default value is very large, so there is no practical limit on
257	If you queue up many requests in a loop it it often improves speed	870	the number of outstanding requests.
258	if you set this to a relatively low number, such as 100.
259		871
260	Under normal circumstances you don't need to call this function.	872	You can still queue as many requests as you want. Therefore,
		873	"max_oustsanding" is mainly useful in simple scripts (with low
		874	values) or as a stop gap to shield against fatal memory overflow
		875	(with large values).
		876
		877	STATISTICAL INFORMATION
		878	IO::AIO::nreqs
		879	Returns the number of requests currently in the ready, execute or
		880	pending states (i.e. for which their callback has not been invoked
		881	yet).
		882
		883	Example: wait till there are no outstanding requests anymore:
		884
		885	IO::AIO::poll_wait, IO::AIO::poll_cb
		886	while IO::AIO::nreqs;
		887
		888	IO::AIO::nready
		889	Returns the number of requests currently in the ready state (not yet
		890	executed).
		891
		892	IO::AIO::npending
		893	Returns the number of requests currently in the pending state
		894	(executed, but not yet processed by poll_cb).
		895
		896	FORK BEHAVIOUR
		897	This module should do "the right thing" when the process using it forks:
		898
		899	Before the fork, IO::AIO enters a quiescent state where no requests can
		900	be added in other threads and no results will be processed. After the
		901	fork the parent simply leaves the quiescent state and continues
		902	request/result processing, while the child frees the request/result
		903	queue (so that the requests started before the fork will only be handled
		904	in the parent). Threads will be started on demand until the limit set in
		905	the parent process has been reached again.
		906
		907	In short: the parent will, after a short pause, continue as if fork had
		908	not been called, while the child will act as if IO::AIO has not been
		909	used yet.
		910
		911	MEMORY USAGE
		912	Per-request usage:
		913
		914	Each aio request uses - depending on your architecture - around 100-200
		915	bytes of memory. In addition, stat requests need a stat buffer (possibly
		916	a few hundred bytes), readdir requires a result buffer and so on. Perl
		917	scalars and other data passed into aio requests will also be locked and
		918	will consume memory till the request has entered the done state.
		919
		920	This is not awfully much, so queuing lots of requests is not usually a
		921	problem.
		922
		923	Per-thread usage:
		924
		925	In the execution phase, some aio requests require more memory for
		926	temporary buffers, and each thread requires a stack and other data
		927	structures (usually around 16k-128k, depending on the OS).
		928
		929	KNOWN BUGS
		930	Known bugs will be fixed in the next release.
261		931
262	SEE ALSO	932	SEE ALSO
263	Coro, Linux::AIO.	933	Coro::AIO.
264		934
265	AUTHOR	935	AUTHOR
266	Marc Lehmann <schmorp@schmorp.de>	936	Marc Lehmann <schmorp@schmorp.de>
267	http://home.schmorp.de/	937	http://home.schmorp.de/
268		938

Diff Legend

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

Comparing IO-AIO/README (file contents): Revision 1.8 by root, Sun Jul 31 17:24:05 2005 UTC vs. Revision 1.26 by root, Thu Oct 4 12:50:35 2007 UTC

Diff Legend

Comparing IO-AIO/README (file contents):
Revision 1.8 by root, Sun Jul 31 17:24:05 2005 UTC vs.
Revision 1.26 by root, Thu Oct 4 12:50:35 2007 UTC