… | |
… | |
56 | |
56 | |
57 | =cut |
57 | =cut |
58 | |
58 | |
59 | package IO::AIO; |
59 | package IO::AIO; |
60 | |
60 | |
|
|
61 | no warnings; |
|
|
62 | |
61 | use base 'Exporter'; |
63 | use base 'Exporter'; |
62 | |
64 | |
63 | use Fcntl (); |
65 | use Fcntl (); |
64 | |
66 | |
65 | BEGIN { |
67 | BEGIN { |
66 | $VERSION = 0.9; |
68 | $VERSION = 1.6; |
67 | |
69 | |
68 | @EXPORT = qw(aio_read aio_write aio_open aio_close aio_stat aio_lstat aio_unlink |
70 | @EXPORT = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat |
|
|
71 | aio_lstat aio_unlink aio_rmdir aio_readdir aio_symlink |
69 | aio_fsync aio_fdatasync aio_readahead); |
72 | aio_fsync aio_fdatasync aio_readahead); |
70 | @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs); |
73 | @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel |
|
|
74 | max_outstanding nreqs); |
71 | |
75 | |
72 | require XSLoader; |
76 | require XSLoader; |
73 | XSLoader::load IO::AIO, $VERSION; |
77 | XSLoader::load IO::AIO, $VERSION; |
74 | } |
78 | } |
75 | |
79 | |
… | |
… | |
83 | which must be a code reference. This code reference will get called with |
87 | which must be a code reference. This code reference will get called with |
84 | the syscall return code (e.g. most syscalls return C<-1> on error, unlike |
88 | the syscall return code (e.g. most syscalls return C<-1> on error, unlike |
85 | perl, which usually delivers "false") as it's sole argument when the given |
89 | perl, which usually delivers "false") as it's sole argument when the given |
86 | syscall has been executed asynchronously. |
90 | syscall has been executed asynchronously. |
87 | |
91 | |
88 | All functions that expect a filehandle will also accept a file descriptor. |
92 | All functions expecting a filehandle keep a copy of the filehandle |
|
|
93 | internally until the request has finished. |
89 | |
94 | |
90 | The filenames you pass to these routines I<must> be absolute. The reason |
95 | The pathnames you pass to these routines I<must> be absolute and |
91 | for this is that at the time the request is being executed, the current |
96 | encoded in byte form. The reason for the former is that at the time the |
92 | working directory could have changed. Alternatively, you can make sure |
97 | request is being executed, the current working directory could have |
93 | that you never change the current working directory. |
98 | changed. Alternatively, you can make sure that you never change the |
|
|
99 | current working directory. |
|
|
100 | |
|
|
101 | To encode pathnames to byte form, either make sure you either: a) |
|
|
102 | always pass in filenames you got from outside (command line, readdir |
|
|
103 | etc.), b) are ASCII or ISO 8859-1, c) use the Encode module and encode |
|
|
104 | your pathnames to the locale (or other) encoding in effect in the user |
|
|
105 | environment, d) use Glib::filename_from_unicode on unicode filenames or e) |
|
|
106 | use something else. |
94 | |
107 | |
95 | =over 4 |
108 | =over 4 |
96 | |
109 | |
97 | =item aio_open $pathname, $flags, $mode, $callback |
110 | =item aio_open $pathname, $flags, $mode, $callback |
98 | |
111 | |
… | |
… | |
139 | Reads or writes C<length> bytes from the specified C<fh> and C<offset> |
152 | Reads or writes C<length> bytes from the specified C<fh> and C<offset> |
140 | into the scalar given by C<data> and offset C<dataoffset> and calls the |
153 | into the scalar given by C<data> and offset C<dataoffset> and calls the |
141 | callback without the actual number of bytes read (or -1 on error, just |
154 | callback without the actual number of bytes read (or -1 on error, just |
142 | like the syscall). |
155 | like the syscall). |
143 | |
156 | |
|
|
157 | The C<$data> scalar I<MUST NOT> be modified in any way while the request |
|
|
158 | is outstanding. Modifying it can result in segfaults or WW3 (if the |
|
|
159 | necessary/optional hardware is installed). |
|
|
160 | |
144 | Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at |
161 | Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at |
145 | offset C<0> within the scalar: |
162 | offset C<0> within the scalar: |
146 | |
163 | |
147 | aio_read $fh, 7, 15, $buffer, 0, sub { |
164 | aio_read $fh, 7, 15, $buffer, 0, sub { |
148 | $_[0] > 0 or die "read error: $!"; |
165 | $_[0] > 0 or die "read error: $!"; |
149 | print "read $_[0] bytes: <$buffer>\n"; |
166 | print "read $_[0] bytes: <$buffer>\n"; |
150 | }; |
167 | }; |
151 | |
168 | |
|
|
169 | =item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback |
|
|
170 | |
|
|
171 | Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts |
|
|
172 | reading at byte offset C<$in_offset>, and starts writing at the current |
|
|
173 | file offset of C<$out_fh>. Because of that, it is not safe to issue more |
|
|
174 | than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each |
|
|
175 | other. |
|
|
176 | |
|
|
177 | This call tries to make use of a native C<sendfile> syscall to provide |
|
|
178 | zero-copy operation. For this to work, C<$out_fh> should refer to a |
|
|
179 | socket, and C<$in_fh> should refer to mmap'able file. |
|
|
180 | |
|
|
181 | If the native sendfile call fails or is not implemented, it will be |
|
|
182 | emulated, so you can call C<aio_sendfile> on any type of filehandle |
|
|
183 | regardless of the limitations of the operating system. |
|
|
184 | |
|
|
185 | Please note, however, that C<aio_sendfile> can read more bytes from |
|
|
186 | C<$in_fh> than are written, and there is no way to find out how many |
|
|
187 | bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only |
|
|
188 | provides the number of bytes written to C<$out_fh>. Only if the result |
|
|
189 | value equals C<$length> one can assume that C<$length> bytes have been |
|
|
190 | read. |
|
|
191 | |
152 | =item aio_readahead $fh,$offset,$length, $callback |
192 | =item aio_readahead $fh,$offset,$length, $callback |
153 | |
|
|
154 | Asynchronously reads the specified byte range into the page cache, using |
|
|
155 | the C<readahead> syscall. If that syscall doesn't exist (likely if your OS |
|
|
156 | isn't Linux) the status will be C<-1> and C<$!> is set to C<ENOSYS>. |
|
|
157 | |
193 | |
158 | C<aio_readahead> populates the page cache with data from a file so that |
194 | C<aio_readahead> populates the page cache with data from a file so that |
159 | subsequent reads from that file will not block on disk I/O. The C<$offset> |
195 | subsequent reads from that file will not block on disk I/O. The C<$offset> |
160 | argument specifies the starting point from which data is to be read and |
196 | argument specifies the starting point from which data is to be read and |
161 | C<$length> specifies the number of bytes to be read. I/O is performed in |
197 | C<$length> specifies the number of bytes to be read. I/O is performed in |
162 | whole pages, so that offset is effectively rounded down to a page boundary |
198 | whole pages, so that offset is effectively rounded down to a page boundary |
163 | and bytes are read up to the next page boundary greater than or equal to |
199 | and bytes are read up to the next page boundary greater than or equal to |
164 | (off-set+length). C<aio_readahead> does not read beyond the end of the |
200 | (off-set+length). C<aio_readahead> does not read beyond the end of the |
165 | file. The current file offset of the file is left unchanged. |
201 | file. The current file offset of the file is left unchanged. |
166 | |
202 | |
|
|
203 | If that syscall doesn't exist (likely if your OS isn't Linux) it will be |
|
|
204 | emulated by simply reading the data, which would have a similar effect. |
|
|
205 | |
167 | =item aio_stat $fh_or_path, $callback |
206 | =item aio_stat $fh_or_path, $callback |
168 | |
207 | |
169 | =item aio_lstat $fh, $callback |
208 | =item aio_lstat $fh, $callback |
170 | |
209 | |
171 | Works like perl's C<stat> or C<lstat> in void context. The callback will |
210 | Works like perl's C<stat> or C<lstat> in void context. The callback will |
… | |
… | |
189 | =item aio_unlink $pathname, $callback |
228 | =item aio_unlink $pathname, $callback |
190 | |
229 | |
191 | Asynchronously unlink (delete) a file and call the callback with the |
230 | Asynchronously unlink (delete) a file and call the callback with the |
192 | result code. |
231 | result code. |
193 | |
232 | |
|
|
233 | =item aio_rmdir $pathname, $callback |
|
|
234 | |
|
|
235 | Asynchronously rmdir (delete) a directory and call the callback with the |
|
|
236 | result code. |
|
|
237 | |
|
|
238 | =item aio_readdir $pathname $callback |
|
|
239 | |
|
|
240 | Unlike the POSIX call of the same name, C<aio_readdir> reads an entire |
|
|
241 | directory (i.e. opendir + readdir + closedir). The entries will not be |
|
|
242 | sorted, and will B<NOT> include the C<.> and C<..> entries. |
|
|
243 | |
|
|
244 | The callback a single argument which is either C<undef> or an array-ref |
|
|
245 | with the filenames. |
|
|
246 | |
194 | =item aio_fsync $fh, $callback |
247 | =item aio_fsync $fh, $callback |
195 | |
248 | |
196 | Asynchronously call fsync on the given filehandle and call the callback |
249 | Asynchronously call fsync on the given filehandle and call the callback |
197 | with the fsync result code. |
250 | with the fsync result code. |
198 | |
251 | |
199 | =item aio_fdatasync $fh, $callback |
252 | =item aio_fdatasync $fh, $callback |
200 | |
253 | |
201 | Asynchronously call fdatasync on the given filehandle and call the |
254 | Asynchronously call fdatasync on the given filehandle and call the |
202 | callback with the fdatasync result code. Might set C<$!> to C<ENOSYS> if |
255 | callback with the fdatasync result code. |
203 | C<fdatasync> is not available. |
256 | |
|
|
257 | If this call isn't available because your OS lacks it or it couldn't be |
|
|
258 | detected, it will be emulated by calling C<fsync> instead. |
204 | |
259 | |
205 | =back |
260 | =back |
206 | |
261 | |
207 | =head2 SUPPORT FUNCTIONS |
262 | =head2 SUPPORT FUNCTIONS |
208 | |
263 | |
… | |
… | |
266 | IO::AIO::poll_wait, IO::AIO::poll_cb |
321 | IO::AIO::poll_wait, IO::AIO::poll_cb |
267 | if IO::AIO::nreqs; |
322 | if IO::AIO::nreqs; |
268 | |
323 | |
269 | =item IO::AIO::min_parallel $nthreads |
324 | =item IO::AIO::min_parallel $nthreads |
270 | |
325 | |
271 | Set the minimum number of AIO threads to C<$nthreads>. The default is |
326 | Set the minimum number of AIO threads to C<$nthreads>. The current default |
272 | C<1>, which means a single asynchronous operation can be done at one time |
327 | is C<4>, which means four asynchronous operations can be done at one time |
273 | (the number of outstanding operations, however, is unlimited). |
328 | (the number of outstanding operations, however, is unlimited). |
|
|
329 | |
|
|
330 | IO::AIO starts threads only on demand, when an AIO request is queued and |
|
|
331 | no free thread exists. |
274 | |
332 | |
275 | It is recommended to keep the number of threads low, as some Linux |
333 | It is recommended to keep the number of threads low, as some Linux |
276 | kernel versions will scale negatively with the number of threads (higher |
334 | kernel versions will scale negatively with the number of threads (higher |
277 | parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32 |
335 | parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32 |
278 | threads should be fine. |
336 | threads should be fine. |
279 | |
337 | |
280 | Under normal circumstances you don't need to call this function, as this |
338 | Under most circumstances you don't need to call this function, as the |
281 | module automatically starts some threads (the exact number might change, |
339 | module selects a default that is suitable for low to moderate load. |
282 | and is currently 4). |
|
|
283 | |
340 | |
284 | =item IO::AIO::max_parallel $nthreads |
341 | =item IO::AIO::max_parallel $nthreads |
285 | |
342 | |
286 | Sets the maximum number of AIO threads to C<$nthreads>. If more than |
343 | Sets the maximum number of AIO threads to C<$nthreads>. If more than the |
287 | the specified number of threads are currently running, kill them. This |
344 | specified number of threads are currently running, this function kills |
288 | function blocks until the limit is reached. |
345 | them. This function blocks until the limit is reached. |
|
|
346 | |
|
|
347 | While C<$nthreads> are zero, aio requests get queued but not executed |
|
|
348 | until the number of threads has been increased again. |
289 | |
349 | |
290 | This module automatically runs C<max_parallel 0> at program end, to ensure |
350 | This module automatically runs C<max_parallel 0> at program end, to ensure |
291 | that all threads are killed and that there are no outstanding requests. |
351 | that all threads are killed and that there are no outstanding requests. |
292 | |
352 | |
293 | Under normal circumstances you don't need to call this function. |
353 | Under normal circumstances you don't need to call this function. |
… | |
… | |
297 | Sets the maximum number of outstanding requests to C<$nreqs>. If you |
357 | Sets the maximum number of outstanding requests to C<$nreqs>. If you |
298 | try to queue up more than this number of requests, the caller will block until |
358 | try to queue up more than this number of requests, the caller will block until |
299 | some requests have been handled. |
359 | some requests have been handled. |
300 | |
360 | |
301 | The default is very large, so normally there is no practical limit. If you |
361 | The default is very large, so normally there is no practical limit. If you |
302 | queue up many requests in a loop it it often improves speed if you set |
362 | queue up many requests in a loop it often improves speed if you set |
303 | this to a relatively low number, such as C<100>. |
363 | this to a relatively low number, such as C<100>. |
304 | |
364 | |
305 | Under normal circumstances you don't need to call this function. |
365 | Under normal circumstances you don't need to call this function. |
306 | |
366 | |
307 | =back |
367 | =back |
… | |
… | |
310 | |
370 | |
311 | # support function to convert a fd into a perl filehandle |
371 | # support function to convert a fd into a perl filehandle |
312 | sub _fd2fh { |
372 | sub _fd2fh { |
313 | return undef if $_[0] < 0; |
373 | return undef if $_[0] < 0; |
314 | |
374 | |
315 | # try to be perl5.6-compatible |
375 | # try to generate nice filehandles |
316 | local *AIO_FH; |
376 | my $sym = "IO::AIO::fd#$_[0]"; |
317 | open AIO_FH, "+<&=$_[0]" |
377 | local *$sym; |
|
|
378 | |
|
|
379 | open *$sym, "+<&=$_[0]" # usually works under any unix |
|
|
380 | or open *$sym, "<&=$_[0]" # cygwin needs this |
|
|
381 | or open *$sym, ">&=$_[0]" # or this |
318 | or return undef; |
382 | or return undef; |
319 | |
383 | |
320 | *AIO_FH |
384 | *$sym |
321 | } |
385 | } |
322 | |
386 | |
323 | min_parallel 4; |
387 | min_parallel 4; |
324 | |
388 | |
325 | END { |
389 | END { |
326 | max_parallel 0; |
390 | max_parallel 0; |
327 | } |
391 | } |
328 | |
392 | |
329 | 1; |
393 | 1; |
330 | |
394 | |
|
|
395 | =head2 FORK BEHAVIOUR |
|
|
396 | |
|
|
397 | Before the fork, IO::AIO enters a quiescent state where no requests |
|
|
398 | can be added in other threads and no results will be processed. After |
|
|
399 | the fork the parent simply leaves the quiescent state and continues |
|
|
400 | request/result processing, while the child clears the request/result |
|
|
401 | queue (so the requests started before the fork will only be handled in |
|
|
402 | the parent). Threats will be started on demand until the limit ste in the |
|
|
403 | parent process has been reached again. |
|
|
404 | |
331 | =head1 SEE ALSO |
405 | =head1 SEE ALSO |
332 | |
406 | |
333 | L<Coro>, L<Linux::AIO>. |
407 | L<Coro>, L<Linux::AIO>. |
334 | |
408 | |
335 | =head1 AUTHOR |
409 | =head1 AUTHOR |