Linux-AIO/AIO.pm

=head1 NAME

Linux::AIO - linux-specific aio implemented using clone

=head1 SYNOPSIS

 use Linux::AIO;

=head1 DESCRIPTION

This module implements asynchronous i/o using the means available to linux
- clone. It does not hook into the POSIX aio_* functions because linux
does not yet support these in the kernel (and even if, it would only allow
aio_read and write, not open and stat).

Instead, in this module a number of (non-posix) threads are started that
execute your read/writes and signal their completion. You don't need
thread support in your libc or perl, and the threads created by this
module will not be visible to the pthreads library.

=over 4

=cut

package Linux::AIO;

use base 'Exporter';

BEGIN {
   $VERSION = 1.01;

   @EXPORT = qw(aio_read aio_write aio_open aio_close aio_stat aio_lstat);
   @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel nreqs);

   require XSLoader;
   XSLoader::load Linux::AIO, $VERSION;
}

=item Linux::AIO::min_parallel $nthreads

Set the minimum number of AIO threads to C<$nthreads>. You I<have> to call
this function with a positive number at least once, otherwise no threads
will be started and you aio-operations will seem to hang.

It is recommended to keep the number of threads low, as many linux
kernel versions will scale negatively with the number of threads (higher
parallelity => MUCH higher latency).

=item $fileno = Linux::AIO::poll_fileno

Return the I<request result pipe filehandle>. This filehandle must be
polled for reading by some mechanism outside this module (e.g. Event
or select, see below). If the pipe becomes readable you have to call
C<poll_cb> to check the results.

=item Linux::AIO::poll_cb

Process all outstanding events on the result pipe. You have to call this
regularly. Returns the number of events processed. Returns immediately
when no events are outstanding.

You can use Event to multiplex, e.g.:

   Event->io (fd => Linux::AIO::poll_fileno,
              poll => 'r', async => 1,
              cb => \&Linux::AIO::poll_cb );


=item Linux::AIO::nreqs

Returns the number of requests currently outstanding.

=item aio_open  $pathname, $flags, $mode, $callback

Asynchronously open or create a file and call the callback with the
filedescriptor (NOT a perl filehandle, sorry for that, but watch out, this
might change in the future).

=item aio_close $fh, $callback

Asynchronously close a file and call the callback with the result code.

=item aio_read  $fh,$offset,$length, $data,$dataoffset,$callback

=item aio_write $fh,$offset,$length, $data,$dataoffset,$callback

Reads or writes C<length> bytes from the specified C<fh> and C<offset>
into the scalar given by C<data> and offset C<dataoffset> and calls the
callback without the actual number of bytes read (or C<undef> on error).

=item aio_stat  $fh_or_path, $callback

=item aio_lstat $fh, $callback

Works like perl's C<stat> or C<lstat> in void context. The callback will
be called after the stat and the results will be available using C<stat _>
or C<-s _> etc...

Currently, the stats are always 64-bit-stats, i.e. instead of returning an
error when stat'ing a large file, the results will be silently truncated
unless perl itself is compiled with large file support.

=cut

END {
   max_parallel 0;
}

1;

=back

=head1 BUGS

This module has been extensively tested in a large and very busy webserver
for many years now.

   - aio_open gives a fd, but all other functions expect a perl filehandle.

=head1 SEE ALSO

L<Coro>.

=head1 AUTHOR

 Marc Lehmann <pcg@goof.com>
 http://www.goof.com/pcg/marc/

=cut

Revision:	1.15
Committed:	Thu May 6 12:16:48 2004 UTC (20 years ago) by root
Branch:	MAIN
Changes since 1.14:	+1 -1 lines
Log Message:	* empty log message *
#	User	Rev	Content
1	root	1.1	=head1 NAME
2
3			Linux::AIO - linux-specific aio implemented using clone
4
5			=head1 SYNOPSIS
6
7			use Linux::AIO;
8
9			=head1 DESCRIPTION
10
11	root	1.14	This module implements asynchronous i/o using the means available to linux
12			- clone. It does not hook into the POSIX aio_* functions because linux
13			does not yet support these in the kernel (and even if, it would only allow
14			aio_read and write, not open and stat).
15
16			Instead, in this module a number of (non-posix) threads are started that
17			execute your read/writes and signal their completion. You don't need
18			thread support in your libc or perl, and the threads created by this
19			module will not be visible to the pthreads library.
20	root	1.3
21	root	1.1	=over 4
22
23			=cut
24
25			package Linux::AIO;
26
27	root	1.2	use base 'Exporter';
28
29	root	1.1	BEGIN {
30	root	1.15	$VERSION = 1.01;
31	root	1.1
32	root	1.10	@EXPORT = qw(aio_read aio_write aio_open aio_close aio_stat aio_lstat);
33	root	1.2	@EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel nreqs);
34
35	root	1.1	require XSLoader;
36			XSLoader::load Linux::AIO, $VERSION;
37			}
38
39	root	1.14	=item Linux::AIO::min_parallel $nthreads
40	root	1.1
41	root	1.14	Set the minimum number of AIO threads to C<$nthreads>. You I<have> to call
42			this function with a positive number at least once, otherwise no threads
43	root	1.3	will be started and you aio-operations will seem to hang.
44	root	1.1
45	root	1.14	It is recommended to keep the number of threads low, as many linux
46			kernel versions will scale negatively with the number of threads (higher
47			parallelity => MUCH higher latency).
48
49	root	1.2	=item $fileno = Linux::AIO::poll_fileno
50
51	root	1.14	Return the I<request result pipe filehandle>. This filehandle must be
52			polled for reading by some mechanism outside this module (e.g. Event
53			or select, see below). If the pipe becomes readable you have to call
54			C<poll_cb> to check the results.
55	root	1.2
56			=item Linux::AIO::poll_cb
57
58			Process all outstanding events on the result pipe. You have to call this
59	root	1.14	regularly. Returns the number of events processed. Returns immediately
60			when no events are outstanding.
61	root	1.2
62	root	1.3	You can use Event to multiplex, e.g.:
63
64	root	1.14	Event->io (fd => Linux::AIO::poll_fileno,
65			poll => 'r', async => 1,
66			cb => \&Linux::AIO::poll_cb );
67	root	1.3
68
69	root	1.2	=item Linux::AIO::nreqs
70
71			Returns the number of requests currently outstanding.
72	root	1.4
73	root	1.14	=item aio_open $pathname, $flags, $mode, $callback
74	root	1.10
75			Asynchronously open or create a file and call the callback with the
76	root	1.14	filedescriptor (NOT a perl filehandle, sorry for that, but watch out, this
77			might change in the future).
78	root	1.10
79	root	1.14	=item aio_close $fh, $callback
80	root	1.10
81			Asynchronously close a file and call the callback with the result code.
82
83	root	1.14	=item aio_read $fh,$offset,$length, $data,$dataoffset,$callback
84	root	1.9
85	root	1.14	=item aio_write $fh,$offset,$length, $data,$dataoffset,$callback
86	root	1.4
87			Reads or writes C<length> bytes from the specified C<fh> and C<offset>
88			into the scalar given by C<data> and offset C<dataoffset> and calls the
89	root	1.14	callback without the actual number of bytes read (or C<undef> on error).
90	root	1.4
91	root	1.14	=item aio_stat $fh_or_path, $callback
92	root	1.4
93	root	1.14	=item aio_lstat $fh, $callback
94	root	1.5
95	root	1.14	Works like perl's C<stat> or C<lstat> in void context. The callback will
96			be called after the stat and the results will be available using C<stat _>
97			or C<-s _> etc...
98	root	1.5
99	root	1.10	Currently, the stats are always 64-bit-stats, i.e. instead of returning an
100			error when stat'ing a large file, the results will be silently truncated
101			unless perl itself is compiled with large file support.
102	root	1.2
103	root	1.1	=cut
104	root	1.2
105			END {
106			max_parallel 0;
107			}
108	root	1.1
109			1;
110
111			=back
112
113			=head1 BUGS
114
115	root	1.14	This module has been extensively tested in a large and very busy webserver
116			for many years now.
117	root	1.1
118	root	1.14	- aio_open gives a fd, but all other functions expect a perl filehandle.
119	root	1.6
120	root	1.1	=head1 SEE ALSO
121
122			L<Coro>.
123
124			=head1 AUTHOR
125
126			Marc Lehmann <pcg@goof.com>
127			http://www.goof.com/pcg/marc/
128
129			=cut
130