… | |
… | |
63 | use base 'Exporter'; |
63 | use base 'Exporter'; |
64 | |
64 | |
65 | use Fcntl (); |
65 | use Fcntl (); |
66 | |
66 | |
67 | BEGIN { |
67 | BEGIN { |
68 | $VERSION = 1.1; |
68 | $VERSION = 1.6; |
69 | |
69 | |
70 | @EXPORT = qw(aio_read aio_write aio_open aio_close aio_stat aio_lstat aio_unlink |
70 | @EXPORT = qw(aio_read aio_write aio_open aio_close aio_stat aio_lstat aio_unlink |
71 | aio_rmdir aio_symlink aio_fsync aio_fdatasync aio_readahead); |
71 | aio_rmdir aio_symlink aio_fsync aio_fdatasync aio_readahead); |
72 | @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs); |
72 | @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs); |
73 | |
73 | |
… | |
… | |
88 | syscall has been executed asynchronously. |
88 | syscall has been executed asynchronously. |
89 | |
89 | |
90 | All functions expecting a filehandle keep a copy of the filehandle |
90 | All functions expecting a filehandle keep a copy of the filehandle |
91 | internally until the request has finished. |
91 | internally until the request has finished. |
92 | |
92 | |
93 | The filenames you pass to these routines I<must> be absolute. The reason |
93 | The pathnames you pass to these routines I<must> be absolute and |
94 | for this is that at the time the request is being executed, the current |
94 | encoded in byte form. The reason for the former is that at the time the |
95 | working directory could have changed. Alternatively, you can make sure |
95 | request is being executed, the current working directory could have |
96 | that you never change the current working directory. |
96 | changed. Alternatively, you can make sure that you never change the |
|
|
97 | current working directory. |
|
|
98 | |
|
|
99 | To encode pathnames to byte form, either make sure you either: a) |
|
|
100 | always pass in filenames you got from outside (command line, readdir |
|
|
101 | etc.), b) are ASCII or ISO 8859-1, c) use the Encode module and encode |
|
|
102 | your pathnames to the locale (or other) encoding in effect in the user |
|
|
103 | environment, d) use Glib::filename_from_unicode on unicode filenames or e) |
|
|
104 | use something else. |
97 | |
105 | |
98 | =over 4 |
106 | =over 4 |
99 | |
107 | |
100 | =item aio_open $pathname, $flags, $mode, $callback |
108 | =item aio_open $pathname, $flags, $mode, $callback |
101 | |
109 | |
… | |
… | |
142 | Reads or writes C<length> bytes from the specified C<fh> and C<offset> |
150 | Reads or writes C<length> bytes from the specified C<fh> and C<offset> |
143 | into the scalar given by C<data> and offset C<dataoffset> and calls the |
151 | into the scalar given by C<data> and offset C<dataoffset> and calls the |
144 | callback without the actual number of bytes read (or -1 on error, just |
152 | callback without the actual number of bytes read (or -1 on error, just |
145 | like the syscall). |
153 | like the syscall). |
146 | |
154 | |
|
|
155 | The C<$data> scalar I<MUST NOT> be modified in any way while the request |
|
|
156 | is outstanding. Modifying it can result in segfaults or WW3 (if the |
|
|
157 | necessary/optional hardware is installed). |
|
|
158 | |
147 | Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at |
159 | Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at |
148 | offset C<0> within the scalar: |
160 | offset C<0> within the scalar: |
149 | |
161 | |
150 | aio_read $fh, 7, 15, $buffer, 0, sub { |
162 | aio_read $fh, 7, 15, $buffer, 0, sub { |
151 | $_[0] > 0 or die "read error: $!"; |
163 | $_[0] > 0 or die "read error: $!"; |
152 | print "read $_[0] bytes: <$buffer>\n"; |
164 | print "read $_[0] bytes: <$buffer>\n"; |
153 | }; |
165 | }; |
|
|
166 | |
|
|
167 | =item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback |
|
|
168 | |
|
|
169 | Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts |
|
|
170 | reading at byte offset C<$in_offset>, and starts writing at the current |
|
|
171 | file offset of C<$out_fh>. Because of that, it is not safe to issue more |
|
|
172 | than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each |
|
|
173 | other. |
|
|
174 | |
|
|
175 | This call tries to make use of a native C<sendfile> syscall to provide |
|
|
176 | zero-copy operation. For this to work, C<$out_fh> should refer to a |
|
|
177 | socket, and C<$in_fh> should refer to mmap'able file. |
|
|
178 | |
|
|
179 | If the native sendfile call fails or is not implemented, it will be |
|
|
180 | emulated, so you can call C<aio_sendfile> on any type of filehandle |
|
|
181 | regardless of the limitations of the operating system. |
|
|
182 | |
|
|
183 | Please note, however, that C<aio_sendfile> can read more bytes from |
|
|
184 | C<$in_fh> than are written, and there is no way to find out how many |
|
|
185 | bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only |
|
|
186 | provides the number of bytes written to C<$out_fh>. Only if the result |
|
|
187 | value equals C<$length> one can assume that C<$length> bytes have been |
|
|
188 | read. |
154 | |
189 | |
155 | =item aio_readahead $fh,$offset,$length, $callback |
190 | =item aio_readahead $fh,$offset,$length, $callback |
156 | |
191 | |
157 | C<aio_readahead> populates the page cache with data from a file so that |
192 | C<aio_readahead> populates the page cache with data from a file so that |
158 | subsequent reads from that file will not block on disk I/O. The C<$offset> |
193 | subsequent reads from that file will not block on disk I/O. The C<$offset> |
… | |
… | |
275 | IO::AIO::poll_wait, IO::AIO::poll_cb |
310 | IO::AIO::poll_wait, IO::AIO::poll_cb |
276 | if IO::AIO::nreqs; |
311 | if IO::AIO::nreqs; |
277 | |
312 | |
278 | =item IO::AIO::min_parallel $nthreads |
313 | =item IO::AIO::min_parallel $nthreads |
279 | |
314 | |
280 | Set the minimum number of AIO threads to C<$nthreads>. The default is |
315 | Set the minimum number of AIO threads to C<$nthreads>. The current default |
281 | C<1>, which means a single asynchronous operation can be done at one time |
316 | is C<4>, which means four asynchronous operations can be done at one time |
282 | (the number of outstanding operations, however, is unlimited). |
317 | (the number of outstanding operations, however, is unlimited). |
|
|
318 | |
|
|
319 | IO::AIO starts threads only on demand, when an AIO request is queued and |
|
|
320 | no free thread exists. |
283 | |
321 | |
284 | It is recommended to keep the number of threads low, as some Linux |
322 | It is recommended to keep the number of threads low, as some Linux |
285 | kernel versions will scale negatively with the number of threads (higher |
323 | kernel versions will scale negatively with the number of threads (higher |
286 | parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32 |
324 | parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32 |
287 | threads should be fine. |
325 | threads should be fine. |
288 | |
326 | |
289 | Under normal circumstances you don't need to call this function, as this |
327 | Under most circumstances you don't need to call this function, as the |
290 | module automatically starts some threads (the exact number might change, |
328 | module selects a default that is suitable for low to moderate load. |
291 | and is currently 4). |
|
|
292 | |
329 | |
293 | =item IO::AIO::max_parallel $nthreads |
330 | =item IO::AIO::max_parallel $nthreads |
294 | |
331 | |
295 | Sets the maximum number of AIO threads to C<$nthreads>. If more than |
332 | Sets the maximum number of AIO threads to C<$nthreads>. If more than the |
296 | the specified number of threads are currently running, kill them. This |
333 | specified number of threads are currently running, this function kills |
297 | function blocks until the limit is reached. |
334 | them. This function blocks until the limit is reached. |
|
|
335 | |
|
|
336 | While C<$nthreads> are zero, aio requests get queued but not executed |
|
|
337 | until the number of threads has been increased again. |
298 | |
338 | |
299 | This module automatically runs C<max_parallel 0> at program end, to ensure |
339 | This module automatically runs C<max_parallel 0> at program end, to ensure |
300 | that all threads are killed and that there are no outstanding requests. |
340 | that all threads are killed and that there are no outstanding requests. |
301 | |
341 | |
302 | Under normal circumstances you don't need to call this function. |
342 | Under normal circumstances you don't need to call this function. |
… | |
… | |
306 | Sets the maximum number of outstanding requests to C<$nreqs>. If you |
346 | Sets the maximum number of outstanding requests to C<$nreqs>. If you |
307 | try to queue up more than this number of requests, the caller will block until |
347 | try to queue up more than this number of requests, the caller will block until |
308 | some requests have been handled. |
348 | some requests have been handled. |
309 | |
349 | |
310 | The default is very large, so normally there is no practical limit. If you |
350 | The default is very large, so normally there is no practical limit. If you |
311 | queue up many requests in a loop it it often improves speed if you set |
351 | queue up many requests in a loop it often improves speed if you set |
312 | this to a relatively low number, such as C<100>. |
352 | this to a relatively low number, such as C<100>. |
313 | |
353 | |
314 | Under normal circumstances you don't need to call this function. |
354 | Under normal circumstances you don't need to call this function. |
315 | |
355 | |
316 | =back |
356 | =back |
… | |
… | |
341 | |
381 | |
342 | 1; |
382 | 1; |
343 | |
383 | |
344 | =head2 FORK BEHAVIOUR |
384 | =head2 FORK BEHAVIOUR |
345 | |
385 | |
346 | IO::AIO handles all outstanding AIO requests before the fork, destroys all |
386 | Before the fork, IO::AIO enters a quiescent state where no requests |
347 | AIO threads, and recreates them in both the parent and the child after the |
387 | can be added in other threads and no results will be processed. After |
348 | fork. |
388 | the fork the parent simply leaves the quiescent state and continues |
349 | |
389 | request/result processing, while the child clears the request/result |
|
|
390 | queue (so the requests started before the fork will only be handled in |
|
|
391 | the parent). Threats will be started on demand until the limit ste in the |
|
|
392 | parent process has been reached again. |
350 | |
393 | |
351 | =head1 SEE ALSO |
394 | =head1 SEE ALSO |
352 | |
395 | |
353 | L<Coro>, L<Linux::AIO>. |
396 | L<Coro>, L<Linux::AIO>. |
354 | |
397 | |