… | |
… | |
22 | poll => 'r', |
22 | poll => 'r', |
23 | cb => \&IO::AIO::poll_cb); |
23 | cb => \&IO::AIO::poll_cb); |
24 | |
24 | |
25 | # Glib/Gtk2 |
25 | # Glib/Gtk2 |
26 | add_watch Glib::IO IO::AIO::poll_fileno, |
26 | add_watch Glib::IO IO::AIO::poll_fileno, |
27 | sub { IO::AIO::poll_cb, 1 }; |
27 | in => sub { IO::AIO::poll_cb; 1 }; |
28 | |
28 | |
29 | # Tk |
29 | # Tk |
30 | Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "", |
30 | Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "", |
31 | readable => \&IO::AIO::poll_cb); |
31 | readable => \&IO::AIO::poll_cb); |
32 | |
32 | |
… | |
… | |
48 | not well-supported (Linux doesn't allow them on normal files currently, |
48 | not well-supported (Linux doesn't allow them on normal files currently, |
49 | for example), and they would only support aio_read and aio_write, so the |
49 | for example), and they would only support aio_read and aio_write, so the |
50 | remaining functionality would have to be implemented using threads anyway. |
50 | remaining functionality would have to be implemented using threads anyway. |
51 | |
51 | |
52 | Although the module will work with in the presence of other threads, it is |
52 | Although the module will work with in the presence of other threads, it is |
53 | currently not reentrant, so use appropriate locking yourself. |
53 | currently not reentrant, so use appropriate locking yourself, always call |
|
|
54 | C<poll_cb> from within the same thread, or never call C<poll_cb> (or other |
|
|
55 | C<aio_> functions) recursively. |
54 | |
56 | |
55 | =cut |
57 | =cut |
56 | |
58 | |
57 | package IO::AIO; |
59 | package IO::AIO; |
58 | |
60 | |
|
|
61 | no warnings; |
|
|
62 | |
59 | use base 'Exporter'; |
63 | use base 'Exporter'; |
60 | |
64 | |
61 | use Fcntl (); |
65 | use Fcntl (); |
62 | |
66 | |
63 | BEGIN { |
67 | BEGIN { |
64 | $VERSION = 0.3; |
68 | $VERSION = 1.6; |
65 | |
69 | |
66 | @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 |
67 | aio_fsync aio_fdatasync aio_readahead); |
71 | aio_rmdir aio_symlink aio_fsync aio_fdatasync aio_readahead); |
68 | @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); |
69 | |
73 | |
70 | require XSLoader; |
74 | require XSLoader; |
71 | XSLoader::load IO::AIO, $VERSION; |
75 | XSLoader::load IO::AIO, $VERSION; |
72 | } |
76 | } |
… | |
… | |
81 | which must be a code reference. This code reference will get called with |
85 | which must be a code reference. This code reference will get called with |
82 | the syscall return code (e.g. most syscalls return C<-1> on error, unlike |
86 | the syscall return code (e.g. most syscalls return C<-1> on error, unlike |
83 | perl, which usually delivers "false") as it's sole argument when the given |
87 | perl, which usually delivers "false") as it's sole argument when the given |
84 | syscall has been executed asynchronously. |
88 | syscall has been executed asynchronously. |
85 | |
89 | |
86 | All functions that expect a filehandle will also accept a file descriptor. |
90 | All functions expecting a filehandle keep a copy of the filehandle |
|
|
91 | internally until the request has finished. |
87 | |
92 | |
88 | 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 |
89 | is that at the time the request is being executed, the current working |
94 | encoded in byte form. The reason for the former is that at the time the |
90 | directory could have changed. Alternatively, you can make sure that you |
95 | request is being executed, the current working directory could have |
|
|
96 | changed. Alternatively, you can make sure that you never change the |
91 | never change the current working directory. |
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. |
92 | |
105 | |
93 | =over 4 |
106 | =over 4 |
94 | |
107 | |
95 | =item aio_open $pathname, $flags, $mode, $callback |
108 | =item aio_open $pathname, $flags, $mode, $callback |
96 | |
109 | |
… | |
… | |
98 | created filehandle for the file. |
111 | created filehandle for the file. |
99 | |
112 | |
100 | The pathname passed to C<aio_open> must be absolute. See API NOTES, above, |
113 | The pathname passed to C<aio_open> must be absolute. See API NOTES, above, |
101 | for an explanation. |
114 | for an explanation. |
102 | |
115 | |
103 | The C<$mode> argument is a bitmask. See the C<Fcntl> module for a |
116 | The C<$flags> argument is a bitmask. See the C<Fcntl> module for a |
104 | list. They are the same as used in C<sysopen>. |
117 | list. They are the same as used by C<sysopen>. |
|
|
118 | |
|
|
119 | Likewise, C<$mode> specifies the mode of the newly created file, if it |
|
|
120 | didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>, |
|
|
121 | except that it is mandatory (i.e. use C<0> if you don't create new files, |
|
|
122 | and C<0666> or C<0777> if you do). |
105 | |
123 | |
106 | Example: |
124 | Example: |
107 | |
125 | |
108 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
126 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
109 | if ($_[0]) { |
127 | if ($_[0]) { |
… | |
… | |
116 | |
134 | |
117 | =item aio_close $fh, $callback |
135 | =item aio_close $fh, $callback |
118 | |
136 | |
119 | Asynchronously close a file and call the callback with the result |
137 | Asynchronously close a file and call the callback with the result |
120 | code. I<WARNING:> although accepted, you should not pass in a perl |
138 | code. I<WARNING:> although accepted, you should not pass in a perl |
121 | filehandle here, as perl will likely close the file descriptor itself when |
139 | filehandle here, as perl will likely close the file descriptor another |
122 | the filehandle is destroyed. Normally, you can safely call perls C<close> |
140 | time when the filehandle is destroyed. Normally, you can safely call perls |
123 | or just let filehandles go out of scope. |
141 | C<close> or just let filehandles go out of scope. |
|
|
142 | |
|
|
143 | This is supposed to be a bug in the API, so that might change. It's |
|
|
144 | therefore best to avoid this function. |
124 | |
145 | |
125 | =item aio_read $fh,$offset,$length, $data,$dataoffset,$callback |
146 | =item aio_read $fh,$offset,$length, $data,$dataoffset,$callback |
126 | |
147 | |
127 | =item aio_write $fh,$offset,$length, $data,$dataoffset,$callback |
148 | =item aio_write $fh,$offset,$length, $data,$dataoffset,$callback |
128 | |
149 | |
129 | Reads or writes C<length> bytes from the specified C<fh> and C<offset> |
150 | Reads or writes C<length> bytes from the specified C<fh> and C<offset> |
130 | into the scalar given by C<data> and offset C<dataoffset> and calls the |
151 | into the scalar given by C<data> and offset C<dataoffset> and calls the |
131 | callback without the actual number of bytes read (or -1 on error, just |
152 | callback without the actual number of bytes read (or -1 on error, just |
132 | like the syscall). |
153 | like the syscall). |
133 | |
154 | |
|
|
155 | The C<$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 | |
134 | Example: Read 15 bytes at offset 7 into scalar C<$buffer>, strating at |
159 | Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at |
135 | offset C<0> within the scalar: |
160 | offset C<0> within the scalar: |
136 | |
161 | |
137 | aio_read $fh, 7, 15, $buffer, 0, sub { |
162 | aio_read $fh, 7, 15, $buffer, 0, sub { |
138 | $_[0] > 0 or die "read error: $!"; |
163 | $_[0] > 0 or die "read error: $!"; |
139 | print "read $_[0] bytes: <$buffer>\n"; |
164 | print "read $_[0] bytes: <$buffer>\n"; |
140 | }; |
165 | }; |
141 | |
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. |
|
|
189 | |
142 | =item aio_readahead $fh,$offset,$length, $callback |
190 | =item aio_readahead $fh,$offset,$length, $callback |
143 | |
191 | |
144 | Asynchronously reads the specified byte range into the page cache, using |
|
|
145 | the C<readahead> syscall. If that syscall doesn't exist the status will be |
|
|
146 | C<-1> and C<$!> is set to ENOSYS. |
|
|
147 | |
|
|
148 | 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 |
149 | 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> |
150 | argument specifies the starting point from which data is to be read and |
194 | argument specifies the starting point from which data is to be read and |
151 | C<$length> specifies the number of bytes to be read. I/O is performed in |
195 | C<$length> specifies the number of bytes to be read. I/O is performed in |
152 | whole pages, so that offset is effectively rounded down to a page boundary |
196 | whole pages, so that offset is effectively rounded down to a page boundary |
153 | and bytes are read up to the next page boundary greater than or equal to |
197 | and bytes are read up to the next page boundary greater than or equal to |
154 | (off-set+length). aio_readahead() does not read beyond the end of the |
198 | (off-set+length). C<aio_readahead> does not read beyond the end of the |
155 | file. The current file offset of the file is left unchanged. |
199 | file. The current file offset of the file is left unchanged. |
|
|
200 | |
|
|
201 | If that syscall doesn't exist (likely if your OS isn't Linux) it will be |
|
|
202 | emulated by simply reading the data, which would have a similar effect. |
156 | |
203 | |
157 | =item aio_stat $fh_or_path, $callback |
204 | =item aio_stat $fh_or_path, $callback |
158 | |
205 | |
159 | =item aio_lstat $fh, $callback |
206 | =item aio_lstat $fh, $callback |
160 | |
207 | |
… | |
… | |
179 | =item aio_unlink $pathname, $callback |
226 | =item aio_unlink $pathname, $callback |
180 | |
227 | |
181 | Asynchronously unlink (delete) a file and call the callback with the |
228 | Asynchronously unlink (delete) a file and call the callback with the |
182 | result code. |
229 | result code. |
183 | |
230 | |
|
|
231 | =item aio_rmdir $pathname, $callback |
|
|
232 | |
|
|
233 | Asynchronously rmdir (delete) a directory and call the callback with the |
|
|
234 | result code. |
|
|
235 | |
184 | =item aio_fsync $fh, $callback |
236 | =item aio_fsync $fh, $callback |
185 | |
237 | |
186 | Asynchronously call fsync on the given filehandle and call the callback |
238 | Asynchronously call fsync on the given filehandle and call the callback |
187 | with the fsync result code. |
239 | with the fsync result code. |
188 | |
240 | |
189 | =item aio_fdatasync $fh, $callback |
241 | =item aio_fdatasync $fh, $callback |
190 | |
242 | |
191 | Asynchronously call fdatasync on the given filehandle and call the |
243 | Asynchronously call fdatasync on the given filehandle and call the |
192 | callback with the fdatasync result code. |
244 | callback with the fdatasync result code. |
193 | |
245 | |
|
|
246 | If this call isn't available because your OS lacks it or it couldn't be |
|
|
247 | detected, it will be emulated by calling C<fsync> instead. |
|
|
248 | |
194 | =back |
249 | =back |
195 | |
250 | |
196 | =head2 SUPPORT FUNCTIONS |
251 | =head2 SUPPORT FUNCTIONS |
197 | |
252 | |
198 | =over 4 |
253 | =over 4 |
199 | |
254 | |
200 | =item $fileno = IO::AIO::poll_fileno |
255 | =item $fileno = IO::AIO::poll_fileno |
201 | |
256 | |
202 | Return the I<request result pipe filehandle>. This filehandle must be |
257 | Return the I<request result pipe file descriptor>. This filehandle must be |
203 | polled for reading by some mechanism outside this module (e.g. Event |
258 | polled for reading by some mechanism outside this module (e.g. Event or |
204 | or select, see below). If the pipe becomes readable you have to call |
259 | select, see below or the SYNOPSIS). If the pipe becomes readable you have |
205 | C<poll_cb> to check the results. |
260 | to call C<poll_cb> to check the results. |
206 | |
261 | |
207 | See C<poll_cb> for an example. |
262 | See C<poll_cb> for an example. |
208 | |
263 | |
209 | =item IO::AIO::poll_cb |
264 | =item IO::AIO::poll_cb |
210 | |
265 | |
211 | Process all outstanding events on the result pipe. You have to call this |
266 | Process all outstanding events on the result pipe. You have to call this |
212 | regularly. Returns the number of events processed. Returns immediately |
267 | regularly. Returns the number of events processed. Returns immediately |
213 | when no events are outstanding. |
268 | when no events are outstanding. |
214 | |
269 | |
215 | You can use Event to multiplex, e.g.: |
270 | Example: Install an Event watcher that automatically calls |
|
|
271 | IO::AIO::poll_cb with high priority: |
216 | |
272 | |
217 | Event->io (fd => IO::AIO::poll_fileno, |
273 | Event->io (fd => IO::AIO::poll_fileno, |
218 | poll => 'r', async => 1, |
274 | poll => 'r', async => 1, |
219 | cb => \&IO::AIO::poll_cb); |
275 | cb => \&IO::AIO::poll_cb); |
220 | |
276 | |
221 | =item IO::AIO::poll_wait |
277 | =item IO::AIO::poll_wait |
222 | |
278 | |
223 | Wait till the result filehandle becomes ready for reading (simply does a |
279 | Wait till the result filehandle becomes ready for reading (simply does a |
224 | select on the filehandle. This is useful if you want to synchronously wait |
280 | C<select> on the filehandle. This is useful if you want to synchronously wait |
225 | for some requests to finish). |
281 | for some requests to finish). |
226 | |
282 | |
227 | See C<nreqs> for an example. |
283 | See C<nreqs> for an example. |
228 | |
284 | |
229 | =item IO::AIO::nreqs |
285 | =item IO::AIO::nreqs |
230 | |
286 | |
231 | Returns the number of requests currently outstanding. |
287 | Returns the number of requests currently outstanding (i.e. for which their |
|
|
288 | callback has not been invoked yet). |
232 | |
289 | |
233 | Example: wait till there are no outstanding requests anymore: |
290 | Example: wait till there are no outstanding requests anymore: |
234 | |
291 | |
235 | IO::AIO::poll_wait, IO::AIO::poll_cb |
292 | IO::AIO::poll_wait, IO::AIO::poll_cb |
236 | while IO::AIO::nreqs; |
293 | while IO::AIO::nreqs; |
… | |
… | |
253 | IO::AIO::poll_wait, IO::AIO::poll_cb |
310 | IO::AIO::poll_wait, IO::AIO::poll_cb |
254 | if IO::AIO::nreqs; |
311 | if IO::AIO::nreqs; |
255 | |
312 | |
256 | =item IO::AIO::min_parallel $nthreads |
313 | =item IO::AIO::min_parallel $nthreads |
257 | |
314 | |
258 | Set the minimum number of AIO threads to C<$nthreads>. The default is |
315 | Set the minimum number of AIO threads to C<$nthreads>. The current default |
259 | 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 |
260 | (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. |
261 | |
321 | |
262 | 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 |
263 | kernel versions will scale negatively with the number of threads (higher |
323 | kernel versions will scale negatively with the number of threads (higher |
264 | 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 |
265 | threads should be fine. |
325 | threads should be fine. |
266 | |
326 | |
267 | 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 |
268 | module automatically starts some threads (the exact number might change, |
328 | module selects a default that is suitable for low to moderate load. |
269 | and is currently 4). |
|
|
270 | |
329 | |
271 | =item IO::AIO::max_parallel $nthreads |
330 | =item IO::AIO::max_parallel $nthreads |
272 | |
331 | |
273 | Sets the maximum number of AIO threads to C<$nthreads>. If more than |
332 | Sets the maximum number of AIO threads to C<$nthreads>. If more than the |
274 | the specified number of threads are currently running, kill them. This |
333 | specified number of threads are currently running, this function kills |
275 | function blocks until the limit is reached. |
334 | them. This function blocks until the limit is reached. |
|
|
335 | |
|
|
336 | While C<$nthreads> are zero, aio requests get queued but not executed |
|
|
337 | until the number of threads has been increased again. |
276 | |
338 | |
277 | 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 |
278 | 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. |
279 | |
341 | |
280 | Under normal circumstances you don't need to call this function. |
342 | Under normal circumstances you don't need to call this function. |
… | |
… | |
284 | 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 |
285 | 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 |
286 | some requests have been handled. |
348 | some requests have been handled. |
287 | |
349 | |
288 | 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 |
289 | 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 |
290 | this to a relatively low number, such as C<100>. |
352 | this to a relatively low number, such as C<100>. |
291 | |
353 | |
292 | Under normal circumstances you don't need to call this function. |
354 | Under normal circumstances you don't need to call this function. |
293 | |
355 | |
294 | =back |
356 | =back |
… | |
… | |
297 | |
359 | |
298 | # support function to convert a fd into a perl filehandle |
360 | # support function to convert a fd into a perl filehandle |
299 | sub _fd2fh { |
361 | sub _fd2fh { |
300 | return undef if $_[0] < 0; |
362 | return undef if $_[0] < 0; |
301 | |
363 | |
302 | # try to be perl5.6-compatible |
364 | # try to generate nice filehandles |
303 | local *AIO_FH; |
365 | my $sym = "IO::AIO::fd#$_[0]"; |
304 | open AIO_FH, "+<&=$_[0]" |
366 | local *$sym; |
|
|
367 | |
|
|
368 | open *$sym, "+<&=$_[0]" # usually works under any unix |
|
|
369 | or open *$sym, "<&=$_[0]" # cygwin needs this |
|
|
370 | or open *$sym, ">&=$_[0]" # or this |
305 | or return undef; |
371 | or return undef; |
306 | |
372 | |
307 | *AIO_FH |
373 | *$sym |
308 | } |
374 | } |
309 | |
375 | |
310 | min_parallel 4; |
376 | min_parallel 4; |
311 | |
377 | |
312 | END { |
378 | END { |
313 | max_parallel 0; |
379 | max_parallel 0; |
314 | } |
380 | } |
315 | |
381 | |
316 | 1; |
382 | 1; |
317 | |
383 | |
|
|
384 | =head2 FORK BEHAVIOUR |
|
|
385 | |
|
|
386 | Before the fork, IO::AIO enters a quiescent state where no requests |
|
|
387 | can be added in other threads and no results will be processed. After |
|
|
388 | the fork the parent simply leaves the quiescent state and continues |
|
|
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. |
|
|
393 | |
318 | =head1 SEE ALSO |
394 | =head1 SEE ALSO |
319 | |
395 | |
320 | L<Coro>, L<Linux::AIO>. |
396 | L<Coro>, L<Linux::AIO>. |
321 | |
397 | |
322 | =head1 AUTHOR |
398 | =head1 AUTHOR |