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 (even as of 2.6.12, only O_DIRECT
files are supported) and even if, it would only allow aio_read and write,
not open, stat and so on.

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.

NOTICE: the threads created by this module will automatically be killed
when the thread calling min_parallel exits. Make sure you only ever call
min_parallel from the same thread that loaded this module.

Although the module will work with in the presence of other threads, it is
not reentrant, so use appropriate locking yourself.

=head2 API NOTES

All the C<aio_*> calls are more or less thin wrappers around the syscall
with the same name (sans C<aio_>). The arguments are similar or identical,
and they all accept an additional C<$callback> argument which must be
a code reference. This code reference will get called with the syscall
return code (e.g. most syscalls return C<-1> on error, unlike perl, which
usually delivers "false") as it's sole argument when the given syscall has
been executed asynchronously.

All functions that expect a filehandle will also accept a file descriptor.

=over 4

=cut

package Linux::AIO;

use base 'Exporter';

BEGIN {
   $VERSION = 1.7;

   @EXPORT = qw(aio_read aio_write aio_open aio_close aio_stat aio_lstat aio_unlink
                aio_fsync aio_fdatasync aio_readahead);
   @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>. The default is
C<1>, which means a single asynchronous operation can be done at one time
(the number of outstanding operations, however, is unlimited).

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

Under normal circumstances you don't need to call this function, as this
module automatically starts a single async thread.

=item Linux::AIO::max_parallel $nthreads

Sets the maximum number of AIO threads to C<$nthreads>. If more than
the specified number of threads are currently running, kill them. This
function blocks until the limit is reached.

This module automatically runs C<max_parallel 0> at program end, to ensure
that all threads are killed and that there are no outstanding requests.

Under normal circumstances you don't need to call this function.

=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.

See C<poll_cb> for an example.

=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::poll_wait

Wait till the result filehandle becomes ready for reading (simply does a
select on the filehandle. This is useful if you want to synchronously wait
for some requests to finish).

See C<nreqs> for an example.

=item Linux::AIO::nreqs

Returns the number of requests currently outstanding.

Example: wait till there are no outstanding requests anymore:

   Linux::AIO::poll_wait while Linux::AIO::nreqs;

=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).

The C<$mode> argument is a bitmask. See the C<Fcntl> module for a
list. They are the same as used in C<sysopen>.

Example:

   aio_open "/etc/passwd", O_RDONLY, 0, sub {
      if ($_[0] >= 0) {
         open my $fh, "<&$_[0]";   # create a copy for perl
         aio_close $_[0], sub { }; # close the aio handle
         print "open successful, fh is $fh\n";
         ...
      } else {
         die "open failed: $!\n";
      }
   };

=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 -1 on error, just
like the syscall).

Example: Read 15 bytes at offset 7 into scalar C<$buffer>, strating at
offset C<0> within the scalar:

   aio_read $fh, 7, 15, $buffer, 0, sub {
      $_[0] >= 0 or die "read error: $!";
      print "read <$buffer>\n";
   };

=item aio_readahead $fh,$offset,$length, $callback

Asynchronously reads the specified byte range into the page cache, using
the C<readahead> syscall.

readahead() populates the page cache with data from a file so that
subsequent reads from that file will not block on disk I/O. The C<$offset>
argument specifies the starting point from which data is to be read and
C<$length> specifies the number of bytes to be read. I/O is performed in
whole pages, so that offset is effectively rounded down to a page boundary
and bytes are read up to the next page boundary greater than or equal to
(off-set+length). aio_readahead() does not read beyond the end of the
file. The current file offset of the file is left unchanged.

=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.

Example: Print the length of F</etc/passwd>:

   aio_stat "/etc/passwd", sub {
      $_[0] and die "stat failed: $!";
      print "size is ", -s _, "\n";
   };

=item aio_unlink $pathname, $callback

Asynchronously unlink (delete) a file and call the callback with the
result code.

=item aio_fsync $fh, $callback

Asynchronously call fsync on the given filehandle and call the callback
with the fsync result code.

=item aio_fdatasync $fh, $callback

Asynchronously call fdatasync on the given filehandle and call the
callback with the fdatasync result code.

=cut

min_parallel 1;

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 <schmorp@schmorp.de>
 http://home.schmorp.de/

=cut

Revision:	1.30
Committed:	Sat Jul 9 23:30:00 2005 UTC (18 years, 10 months ago) by root
Branch:	MAIN
Changes since 1.29:	+87 -5 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	1.27	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 (even as of 2.6.12, only O_DIRECT
14			files are supported) and even if, it would only allow aio_read and write,
15			not open, stat and so on.
16	root	1.14
17			Instead, in this module a number of (non-posix) threads are started that
18			execute your read/writes and signal their completion. You don't need
19			thread support in your libc or perl, and the threads created by this
20			module will not be visible to the pthreads library.
21	root	1.3
22	root	1.17	NOTICE: the threads created by this module will automatically be killed
23			when the thread calling min_parallel exits. Make sure you only ever call
24			min_parallel from the same thread that loaded this module.
25
26	root	1.27	Although the module will work with in the presence of other threads, it is
27			not reentrant, so use appropriate locking yourself.
28	root	1.16
29	root	1.30	=head2 API NOTES
30
31			All the C<aio_*> calls are more or less thin wrappers around the syscall
32			with the same name (sans C<aio_>). The arguments are similar or identical,
33			and they all accept an additional C<$callback> argument which must be
34			a code reference. This code reference will get called with the syscall
35			return code (e.g. most syscalls return C<-1> on error, unlike perl, which
36			usually delivers "false") as it's sole argument when the given syscall has
37			been executed asynchronously.
38
39			All functions that expect a filehandle will also accept a file descriptor.
40
41	root	1.1	=over 4
42
43			=cut
44
45			package Linux::AIO;
46
47	root	1.2	use base 'Exporter';
48
49	root	1.1	BEGIN {
50	root	1.29	$VERSION = 1.7;
51	root	1.1
52	root	1.29	@EXPORT = qw(aio_read aio_write aio_open aio_close aio_stat aio_lstat aio_unlink
53			aio_fsync aio_fdatasync aio_readahead);
54	root	1.2	@EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel nreqs);
55
56	root	1.1	require XSLoader;
57			XSLoader::load Linux::AIO, $VERSION;
58			}
59
60	root	1.14	=item Linux::AIO::min_parallel $nthreads
61	root	1.1
62	root	1.16	Set the minimum number of AIO threads to C<$nthreads>. The default is
63			C<1>, which means a single asynchronous operation can be done at one time
64			(the number of outstanding operations, however, is unlimited).
65	root	1.1
66	root	1.24	It is recommended to keep the number of threads low, as some linux
67	root	1.14	kernel versions will scale negatively with the number of threads (higher
68			parallelity => MUCH higher latency).
69
70	root	1.30	Under normal circumstances you don't need to call this function, as this
71			module automatically starts a single async thread.
72
73	root	1.24	=item Linux::AIO::max_parallel $nthreads
74
75			Sets the maximum number of AIO threads to C<$nthreads>. If more than
76			the specified number of threads are currently running, kill them. This
77			function blocks until the limit is reached.
78
79			This module automatically runs C<max_parallel 0> at program end, to ensure
80			that all threads are killed and that there are no outstanding requests.
81
82	root	1.30	Under normal circumstances you don't need to call this function.
83
84	root	1.2	=item $fileno = Linux::AIO::poll_fileno
85
86	root	1.14	Return the I<request result pipe filehandle>. This filehandle must be
87			polled for reading by some mechanism outside this module (e.g. Event
88			or select, see below). If the pipe becomes readable you have to call
89			C<poll_cb> to check the results.
90	root	1.2
91	root	1.30	See C<poll_cb> for an example.
92
93	root	1.2	=item Linux::AIO::poll_cb
94
95			Process all outstanding events on the result pipe. You have to call this
96	root	1.14	regularly. Returns the number of events processed. Returns immediately
97			when no events are outstanding.
98	root	1.2
99	root	1.3	You can use Event to multiplex, e.g.:
100
101	root	1.14	Event->io (fd => Linux::AIO::poll_fileno,
102			poll => 'r', async => 1,
103	root	1.30	cb => \&Linux::AIO::poll_cb);
104	root	1.3
105	root	1.24	=item Linux::AIO::poll_wait
106
107			Wait till the result filehandle becomes ready for reading (simply does a
108			select on the filehandle. This is useful if you want to synchronously wait
109			for some requests to finish).
110
111	root	1.30	See C<nreqs> for an example.
112
113	root	1.2	=item Linux::AIO::nreqs
114
115			Returns the number of requests currently outstanding.
116	root	1.4
117	root	1.30	Example: wait till there are no outstanding requests anymore:
118
119			Linux::AIO::poll_wait while Linux::AIO::nreqs;
120
121			=item aio_open $pathname, $flags, $mode, $callback
122	root	1.10
123			Asynchronously open or create a file and call the callback with the
124	root	1.14	filedescriptor (NOT a perl filehandle, sorry for that, but watch out, this
125			might change in the future).
126	root	1.10
127	root	1.30	The C<$mode> argument is a bitmask. See the C<Fcntl> module for a
128			list. They are the same as used in C<sysopen>.
129
130			Example:
131
132			aio_open "/etc/passwd", O_RDONLY, 0, sub {
133			if ($_[0] >= 0) {
134			open my $fh, "<&$_[0]"; # create a copy for perl
135			aio_close $_[0], sub { }; # close the aio handle
136			print "open successful, fh is $fh\n";
137			...
138			} else {
139			die "open failed: $!\n";
140			}
141			};
142
143	root	1.14	=item aio_close $fh, $callback
144	root	1.10
145			Asynchronously close a file and call the callback with the result code.
146
147	root	1.14	=item aio_read $fh,$offset,$length, $data,$dataoffset,$callback
148	root	1.9
149	root	1.14	=item aio_write $fh,$offset,$length, $data,$dataoffset,$callback
150	root	1.4
151			Reads or writes C<length> bytes from the specified C<fh> and C<offset>
152			into the scalar given by C<data> and offset C<dataoffset> and calls the
153	root	1.30	callback without the actual number of bytes read (or -1 on error, just
154			like the syscall).
155
156			Example: Read 15 bytes at offset 7 into scalar C<$buffer>, strating at
157			offset C<0> within the scalar:
158
159			aio_read $fh, 7, 15, $buffer, 0, sub {
160			$_[0] >= 0 or die "read error: $!";
161			print "read <$buffer>\n";
162			};
163
164			=item aio_readahead $fh,$offset,$length, $callback
165
166			Asynchronously reads the specified byte range into the page cache, using
167			the C<readahead> syscall.
168
169			readahead() populates the page cache with data from a file so that
170			subsequent reads from that file will not block on disk I/O. The C<$offset>
171			argument specifies the starting point from which data is to be read and
172			C<$length> specifies the number of bytes to be read. I/O is performed in
173			whole pages, so that offset is effectively rounded down to a page boundary
174			and bytes are read up to the next page boundary greater than or equal to
175			(off-set+length). aio_readahead() does not read beyond the end of the
176			file. The current file offset of the file is left unchanged.
177	root	1.4
178	root	1.14	=item aio_stat $fh_or_path, $callback
179	root	1.4
180	root	1.14	=item aio_lstat $fh, $callback
181	root	1.5
182	root	1.14	Works like perl's C<stat> or C<lstat> in void context. The callback will
183			be called after the stat and the results will be available using C<stat _>
184			or C<-s _> etc...
185	root	1.5
186	root	1.10	Currently, the stats are always 64-bit-stats, i.e. instead of returning an
187			error when stat'ing a large file, the results will be silently truncated
188			unless perl itself is compiled with large file support.
189	root	1.17
190	root	1.30	Example: Print the length of F</etc/passwd>:
191
192			aio_stat "/etc/passwd", sub {
193			$_[0] and die "stat failed: $!";
194			print "size is ", -s _, "\n";
195			};
196
197			=item aio_unlink $pathname, $callback
198
199			Asynchronously unlink (delete) a file and call the callback with the
200			result code.
201
202			=item aio_fsync $fh, $callback
203
204			Asynchronously call fsync on the given filehandle and call the callback
205			with the fsync result code.
206
207			=item aio_fdatasync $fh, $callback
208	root	1.17
209	root	1.30	Asynchronously call fdatasync on the given filehandle and call the
210			callback with the fdatasync result code.
211	root	1.2
212	root	1.1	=cut
213	root	1.16
214			min_parallel 1;
215	root	1.2
216			END {
217			max_parallel 0;
218			}
219	root	1.1
220			1;
221
222			=back
223
224			=head1 BUGS
225
226	root	1.14	This module has been extensively tested in a large and very busy webserver
227			for many years now.
228	root	1.1
229	root	1.14	- aio_open gives a fd, but all other functions expect a perl filehandle.
230	root	1.6
231	root	1.1	=head1 SEE ALSO
232
233			L<Coro>.
234
235			=head1 AUTHOR
236
237	root	1.22	Marc Lehmann <schmorp@schmorp.de>
238	root	1.20	http://home.schmorp.de/
239	root	1.1
240			=cut
241