1 |
root |
1.1 |
=head1 NAME |
2 |
|
|
|
3 |
|
|
IO::AIO - Asynchronous Input/Output |
4 |
|
|
|
5 |
|
|
=head1 SYNOPSIS |
6 |
|
|
|
7 |
|
|
use IO::AIO; |
8 |
|
|
|
9 |
|
|
=head1 DESCRIPTION |
10 |
|
|
|
11 |
|
|
This module implements asynchronous I/O using whatever means your |
12 |
root |
1.2 |
operating system supports. |
13 |
root |
1.1 |
|
14 |
root |
1.2 |
Currently, a number of threads are started that execute your read/writes |
15 |
|
|
and signal their completion. You don't need thread support in your libc or |
16 |
|
|
perl, and the threads created by this module will not be visible to the |
17 |
|
|
pthreads library. In the future, this module might make use of the native |
18 |
|
|
aio functions available on many operating systems. However, they are often |
19 |
|
|
not well-supported (Linux doesn't allow them on normal files currently, |
20 |
|
|
for example), and they would only support aio_read and aio_write, so the |
21 |
|
|
remaining functionality would have to be implemented using threads anyway. |
22 |
root |
1.1 |
|
23 |
|
|
Although the module will work with in the presence of other threads, it is |
24 |
root |
1.2 |
currently not reentrant, so use appropriate locking yourself. |
25 |
root |
1.1 |
|
26 |
|
|
=head2 API NOTES |
27 |
|
|
|
28 |
|
|
All the C<aio_*> calls are more or less thin wrappers around the syscall |
29 |
|
|
with the same name (sans C<aio_>). The arguments are similar or identical, |
30 |
|
|
and they all accept an additional C<$callback> argument which must be |
31 |
|
|
a code reference. This code reference will get called with the syscall |
32 |
|
|
return code (e.g. most syscalls return C<-1> on error, unlike perl, which |
33 |
|
|
usually delivers "false") as it's sole argument when the given syscall has |
34 |
|
|
been executed asynchronously. |
35 |
|
|
|
36 |
|
|
All functions that expect a filehandle will also accept a file descriptor. |
37 |
|
|
|
38 |
|
|
The filenames you pass to these routines I<must> be absolute. The reason |
39 |
|
|
is that at the time the request is being executed, the current working |
40 |
|
|
directory could have changed. Alternatively, you can make sure that you |
41 |
|
|
never change the current working directory. |
42 |
|
|
|
43 |
|
|
=over 4 |
44 |
|
|
|
45 |
|
|
=cut |
46 |
|
|
|
47 |
|
|
package IO::AIO; |
48 |
|
|
|
49 |
|
|
use base 'Exporter'; |
50 |
|
|
|
51 |
root |
1.2 |
use Fcntl (); |
52 |
|
|
|
53 |
root |
1.1 |
BEGIN { |
54 |
root |
1.3 |
$VERSION = 0.2; |
55 |
root |
1.1 |
|
56 |
|
|
@EXPORT = qw(aio_read aio_write aio_open aio_close aio_stat aio_lstat aio_unlink |
57 |
|
|
aio_fsync aio_fdatasync aio_readahead); |
58 |
root |
1.4 |
@EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs); |
59 |
root |
1.1 |
|
60 |
|
|
require XSLoader; |
61 |
|
|
XSLoader::load IO::AIO, $VERSION; |
62 |
|
|
} |
63 |
|
|
|
64 |
|
|
=item IO::AIO::min_parallel $nthreads |
65 |
|
|
|
66 |
|
|
Set the minimum number of AIO threads to C<$nthreads>. The default is |
67 |
|
|
C<1>, which means a single asynchronous operation can be done at one time |
68 |
|
|
(the number of outstanding operations, however, is unlimited). |
69 |
|
|
|
70 |
root |
1.4 |
It is recommended to keep the number of threads low, as some Linux |
71 |
root |
1.1 |
kernel versions will scale negatively with the number of threads (higher |
72 |
root |
1.4 |
parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32 |
73 |
|
|
threads should be fine. |
74 |
root |
1.1 |
|
75 |
|
|
Under normal circumstances you don't need to call this function, as this |
76 |
root |
1.4 |
module automatically starts some threads (the exact number might change, |
77 |
|
|
and is currently 4). |
78 |
root |
1.1 |
|
79 |
|
|
=item IO::AIO::max_parallel $nthreads |
80 |
|
|
|
81 |
|
|
Sets the maximum number of AIO threads to C<$nthreads>. If more than |
82 |
|
|
the specified number of threads are currently running, kill them. This |
83 |
|
|
function blocks until the limit is reached. |
84 |
|
|
|
85 |
|
|
This module automatically runs C<max_parallel 0> at program end, to ensure |
86 |
|
|
that all threads are killed and that there are no outstanding requests. |
87 |
|
|
|
88 |
|
|
Under normal circumstances you don't need to call this function. |
89 |
|
|
|
90 |
root |
1.4 |
=item $oldnreqs = IO::AIO::max_outstanding $nreqs |
91 |
|
|
|
92 |
|
|
Sets the maximum number of outstanding requests to C<$nreqs>. If you |
93 |
|
|
try to queue up more than this number of requests, the caller will block until |
94 |
|
|
some requests have been handled. |
95 |
|
|
|
96 |
|
|
The default is very large, so normally there is no practical limit. If you |
97 |
|
|
queue up many requests in a loop it it often improves speed if you set |
98 |
|
|
this to a relatively low number, such as C<100>. |
99 |
|
|
|
100 |
|
|
Under normal circumstances you don't need to call this function. |
101 |
|
|
|
102 |
root |
1.1 |
=item $fileno = IO::AIO::poll_fileno |
103 |
|
|
|
104 |
|
|
Return the I<request result pipe filehandle>. This filehandle must be |
105 |
|
|
polled for reading by some mechanism outside this module (e.g. Event |
106 |
|
|
or select, see below). If the pipe becomes readable you have to call |
107 |
|
|
C<poll_cb> to check the results. |
108 |
|
|
|
109 |
|
|
See C<poll_cb> for an example. |
110 |
|
|
|
111 |
|
|
=item IO::AIO::poll_cb |
112 |
|
|
|
113 |
|
|
Process all outstanding events on the result pipe. You have to call this |
114 |
|
|
regularly. Returns the number of events processed. Returns immediately |
115 |
|
|
when no events are outstanding. |
116 |
|
|
|
117 |
|
|
You can use Event to multiplex, e.g.: |
118 |
|
|
|
119 |
|
|
Event->io (fd => IO::AIO::poll_fileno, |
120 |
|
|
poll => 'r', async => 1, |
121 |
|
|
cb => \&IO::AIO::poll_cb); |
122 |
|
|
|
123 |
|
|
=item IO::AIO::poll_wait |
124 |
|
|
|
125 |
|
|
Wait till the result filehandle becomes ready for reading (simply does a |
126 |
|
|
select on the filehandle. This is useful if you want to synchronously wait |
127 |
|
|
for some requests to finish). |
128 |
|
|
|
129 |
|
|
See C<nreqs> for an example. |
130 |
|
|
|
131 |
|
|
=item IO::AIO::nreqs |
132 |
|
|
|
133 |
|
|
Returns the number of requests currently outstanding. |
134 |
|
|
|
135 |
|
|
Example: wait till there are no outstanding requests anymore: |
136 |
|
|
|
137 |
|
|
IO::AIO::poll_wait, IO::AIO::poll_cb |
138 |
|
|
while IO::AIO::nreqs; |
139 |
|
|
|
140 |
|
|
=item aio_open $pathname, $flags, $mode, $callback |
141 |
|
|
|
142 |
root |
1.2 |
Asynchronously open or create a file and call the callback with a newly |
143 |
|
|
created filehandle for the file. |
144 |
root |
1.1 |
|
145 |
|
|
The pathname passed to C<aio_open> must be absolute. See API NOTES, above, |
146 |
|
|
for an explanation. |
147 |
|
|
|
148 |
|
|
The C<$mode> argument is a bitmask. See the C<Fcntl> module for a |
149 |
|
|
list. They are the same as used in C<sysopen>. |
150 |
|
|
|
151 |
|
|
Example: |
152 |
|
|
|
153 |
|
|
aio_open "/etc/passwd", O_RDONLY, 0, sub { |
154 |
root |
1.2 |
if ($_[0]) { |
155 |
|
|
print "open successful, fh is $_[0]\n"; |
156 |
root |
1.1 |
... |
157 |
|
|
} else { |
158 |
|
|
die "open failed: $!\n"; |
159 |
|
|
} |
160 |
|
|
}; |
161 |
|
|
|
162 |
|
|
=item aio_close $fh, $callback |
163 |
|
|
|
164 |
root |
1.2 |
Asynchronously close a file and call the callback with the result |
165 |
|
|
code. I<WARNING:> although accepted, you should not pass in a perl |
166 |
|
|
filehandle here, as perl will likely close the file descriptor itself when |
167 |
|
|
the filehandle is destroyed. Normally, you can safely call perls C<close> |
168 |
|
|
or just let filehandles go out of scope. |
169 |
root |
1.1 |
|
170 |
|
|
=item aio_read $fh,$offset,$length, $data,$dataoffset,$callback |
171 |
|
|
|
172 |
|
|
=item aio_write $fh,$offset,$length, $data,$dataoffset,$callback |
173 |
|
|
|
174 |
|
|
Reads or writes C<length> bytes from the specified C<fh> and C<offset> |
175 |
|
|
into the scalar given by C<data> and offset C<dataoffset> and calls the |
176 |
|
|
callback without the actual number of bytes read (or -1 on error, just |
177 |
|
|
like the syscall). |
178 |
|
|
|
179 |
|
|
Example: Read 15 bytes at offset 7 into scalar C<$buffer>, strating at |
180 |
|
|
offset C<0> within the scalar: |
181 |
|
|
|
182 |
|
|
aio_read $fh, 7, 15, $buffer, 0, sub { |
183 |
|
|
$_[0] >= 0 or die "read error: $!"; |
184 |
|
|
print "read <$buffer>\n"; |
185 |
|
|
}; |
186 |
|
|
|
187 |
|
|
=item aio_readahead $fh,$offset,$length, $callback |
188 |
|
|
|
189 |
|
|
Asynchronously reads the specified byte range into the page cache, using |
190 |
|
|
the C<readahead> syscall. If that syscall doesn't exist the status will be |
191 |
|
|
C<-1> and C<$!> is set to ENOSYS. |
192 |
|
|
|
193 |
|
|
readahead() populates the page cache with data from a file so that |
194 |
|
|
subsequent reads from that file will not block on disk I/O. The C<$offset> |
195 |
|
|
argument specifies the starting point from which data is to be read and |
196 |
|
|
C<$length> specifies the number of bytes to be read. I/O is performed in |
197 |
|
|
whole pages, so that offset is effectively rounded down to a page boundary |
198 |
|
|
and bytes are read up to the next page boundary greater than or equal to |
199 |
|
|
(off-set+length). aio_readahead() does not read beyond the end of the |
200 |
|
|
file. The current file offset of the file is left unchanged. |
201 |
|
|
|
202 |
|
|
=item aio_stat $fh_or_path, $callback |
203 |
|
|
|
204 |
|
|
=item aio_lstat $fh, $callback |
205 |
|
|
|
206 |
|
|
Works like perl's C<stat> or C<lstat> in void context. The callback will |
207 |
|
|
be called after the stat and the results will be available using C<stat _> |
208 |
|
|
or C<-s _> etc... |
209 |
|
|
|
210 |
|
|
The pathname passed to C<aio_stat> must be absolute. See API NOTES, above, |
211 |
|
|
for an explanation. |
212 |
|
|
|
213 |
|
|
Currently, the stats are always 64-bit-stats, i.e. instead of returning an |
214 |
|
|
error when stat'ing a large file, the results will be silently truncated |
215 |
|
|
unless perl itself is compiled with large file support. |
216 |
|
|
|
217 |
|
|
Example: Print the length of F</etc/passwd>: |
218 |
|
|
|
219 |
|
|
aio_stat "/etc/passwd", sub { |
220 |
|
|
$_[0] and die "stat failed: $!"; |
221 |
|
|
print "size is ", -s _, "\n"; |
222 |
|
|
}; |
223 |
|
|
|
224 |
|
|
=item aio_unlink $pathname, $callback |
225 |
|
|
|
226 |
|
|
Asynchronously unlink (delete) a file and call the callback with the |
227 |
|
|
result code. |
228 |
|
|
|
229 |
|
|
=item aio_fsync $fh, $callback |
230 |
|
|
|
231 |
|
|
Asynchronously call fsync on the given filehandle and call the callback |
232 |
|
|
with the fsync result code. |
233 |
|
|
|
234 |
|
|
=item aio_fdatasync $fh, $callback |
235 |
|
|
|
236 |
|
|
Asynchronously call fdatasync on the given filehandle and call the |
237 |
|
|
callback with the fdatasync result code. |
238 |
|
|
|
239 |
|
|
=cut |
240 |
|
|
|
241 |
root |
1.2 |
# support function to convert a fd into a perl filehandle |
242 |
|
|
sub _fd2fh { |
243 |
|
|
return undef if $_[0] < 0; |
244 |
|
|
|
245 |
|
|
# try to be perl5.6-compatible |
246 |
|
|
local *AIO_FH; |
247 |
|
|
open AIO_FH, "+<&=$_[0]" |
248 |
|
|
or return undef; |
249 |
|
|
|
250 |
|
|
*AIO_FH |
251 |
|
|
} |
252 |
|
|
|
253 |
root |
1.1 |
min_parallel 4; |
254 |
|
|
|
255 |
|
|
END { |
256 |
|
|
max_parallel 0; |
257 |
|
|
} |
258 |
|
|
|
259 |
|
|
1; |
260 |
|
|
|
261 |
|
|
=back |
262 |
|
|
|
263 |
|
|
=head1 BUGS |
264 |
|
|
|
265 |
root |
1.2 |
- could be optimized to use more semaphores instead of filehandles. |
266 |
root |
1.1 |
|
267 |
|
|
=head1 SEE ALSO |
268 |
|
|
|
269 |
|
|
L<Coro>, L<Linux::AIO>. |
270 |
|
|
|
271 |
|
|
=head1 AUTHOR |
272 |
|
|
|
273 |
|
|
Marc Lehmann <schmorp@schmorp.de> |
274 |
|
|
http://home.schmorp.de/ |
275 |
|
|
|
276 |
|
|
=cut |
277 |
|
|
|