ViewVC Help
View File | Revision Log | Show Annotations | Download File
/cvs/IO-AIO/AIO.pm
(Generate patch)

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.11 by root, Mon Jul 11 00:51:32 2005 UTC vs.
Revision 1.39 by root, Sun Aug 28 11:05:50 2005 UTC

… …
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 \&IO::AIO::poll_cb; 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
… …
48not well-supported (Linux doesn't allow them on normal files currently, 48not well-supported (Linux doesn't allow them on normal files currently,
49for example), and they would only support aio_read and aio_write, so the 49for example), and they would only support aio_read and aio_write, so the
50remaining functionality would have to be implemented using threads anyway. 50remaining functionality would have to be implemented using threads anyway.
51 51
52Although the module will work with in the presence of other threads, it is 52Although the module will work with in the presence of other threads, it is
53currently not reentrant, so use appropriate locking yourself. 53currently not reentrant, so use appropriate locking yourself, always call
54C<poll_cb> from within the same thread, or never call C<poll_cb> (or other
55C<aio_> functions) recursively.
54 56
55=cut 57=cut
56 58
57package IO::AIO; 59package IO::AIO;
58 60
61no warnings;
62
59use base 'Exporter'; 63use base 'Exporter';
60 64
61use Fcntl (); 65use Fcntl ();
62 66
63BEGIN { 67BEGIN {
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_sendfile aio_read aio_write aio_open aio_close aio_stat
71 aio_lstat aio_unlink aio_rmdir aio_readdir aio_symlink
67 aio_fsync aio_fdatasync aio_readahead); 72 aio_fsync aio_fdatasync aio_readahead);
68 @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);
69 75
70 require XSLoader; 76 require XSLoader;
71 XSLoader::load IO::AIO, $VERSION; 77 XSLoader::load IO::AIO, $VERSION;
72} 78}
73 79
… …
75 81
76=head2 AIO FUNCTIONS 82=head2 AIO FUNCTIONS
77 83
78All the C<aio_*> calls are more or less thin wrappers around the syscall 84All the C<aio_*> calls are more or less thin wrappers around the syscall
79with the same name (sans C<aio_>). The arguments are similar or identical, 85with the same name (sans C<aio_>). The arguments are similar or identical,
80and they all accept an additional C<$callback> argument which must be 86and they all accept an additional (and optional) C<$callback> argument
81a code reference. This code reference will get called with the syscall 87which must be a code reference. This code reference will get called with
82return code (e.g. most syscalls return C<-1> on error, unlike perl, which 88the syscall return code (e.g. most syscalls return C<-1> on error, unlike
83usually delivers "false") as it's sole argument when the given syscall has 89perl, which usually delivers "false") as it's sole argument when the given
84been executed asynchronously. 90syscall has been executed asynchronously.
85 91
86All functions that expect a filehandle will also accept a file descriptor. 92All functions expecting a filehandle keep a copy of the filehandle
93internally until the request has finished.
87 94
88The filenames you pass to these routines I<must> be absolute. The reason 95The pathnames you pass to these routines I<must> be absolute and
89is that at the time the request is being executed, the current working 96encoded in byte form. The reason for the former is that at the time the
90directory could have changed. Alternatively, you can make sure that you 97request is being executed, the current working directory could have
98changed. Alternatively, you can make sure that you never change the
91never change the current working directory. 99current working directory.
100
101To encode pathnames to byte form, either make sure you either: a)
102always pass in filenames you got from outside (command line, readdir
103etc.), b) are ASCII or ISO 8859-1, c) use the Encode module and encode
104your pathnames to the locale (or other) encoding in effect in the user
105environment, d) use Glib::filename_from_unicode on unicode filenames or e)
106use something else.
92 107
93=over 4 108=over 4
94 109
95=item aio_open $pathname, $flags, $mode, $callback 110=item aio_open $pathname, $flags, $mode, $callback
96 111
… …
98created filehandle for the file. 113created filehandle for the file.
99 114
100The pathname passed to C<aio_open> must be absolute. See API NOTES, above, 115The pathname passed to C<aio_open> must be absolute. See API NOTES, above,
101for an explanation. 116for an explanation.
102 117
103The C<$mode> argument is a bitmask. See the C<Fcntl> module for a 118The C<$flags> argument is a bitmask. See the C<Fcntl> module for a
104list. They are the same as used in C<sysopen>. 119list. They are the same as used by C<sysopen>.
120
121Likewise, C<$mode> specifies the mode of the newly created file, if it
122didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,
123except that it is mandatory (i.e. use C<0> if you don't create new files,
124and C<0666> or C<0777> if you do).
105 125
106Example: 126Example:
107 127
108 aio_open "/etc/passwd", O_RDONLY, 0, sub { 128 aio_open "/etc/passwd", O_RDONLY, 0, sub {
109 if ($_[0]) { 129 if ($_[0]) {
… …
116 136
117=item aio_close $fh, $callback 137=item aio_close $fh, $callback
118 138
119Asynchronously close a file and call the callback with the result 139Asynchronously close a file and call the callback with the result
120code. I<WARNING:> although accepted, you should not pass in a perl 140code. I<WARNING:> although accepted, you should not pass in a perl
121filehandle here, as perl will likely close the file descriptor itself when 141filehandle here, as perl will likely close the file descriptor another
122the filehandle is destroyed. Normally, you can safely call perls C<close> 142time when the filehandle is destroyed. Normally, you can safely call perls
123or just let filehandles go out of scope. 143C<close> or just let filehandles go out of scope.
144
145This is supposed to be a bug in the API, so that might change. It's
146therefore best to avoid this function.
124 147
125=item aio_read $fh,$offset,$length, $data,$dataoffset,$callback 148=item aio_read $fh,$offset,$length, $data,$dataoffset,$callback
126 149
127=item aio_write $fh,$offset,$length, $data,$dataoffset,$callback 150=item aio_write $fh,$offset,$length, $data,$dataoffset,$callback
128 151
129Reads or writes C<length> bytes from the specified C<fh> and C<offset> 152Reads or writes C<length> bytes from the specified C<fh> and C<offset>
130into the scalar given by C<data> and offset C<dataoffset> and calls the 153into the scalar given by C<data> and offset C<dataoffset> and calls the
131callback without the actual number of bytes read (or -1 on error, just 154callback without the actual number of bytes read (or -1 on error, just
132like the syscall). 155like the syscall).
133 156
157The C<$data> scalar I<MUST NOT> be modified in any way while the request
158is outstanding. Modifying it can result in segfaults or WW3 (if the
159necessary/optional hardware is installed).
160
134Example: Read 15 bytes at offset 7 into scalar C<$buffer>, strating at 161Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at
135offset C<0> within the scalar: 162offset C<0> within the scalar:
136 163
137 aio_read $fh, 7, 15, $buffer, 0, sub { 164 aio_read $fh, 7, 15, $buffer, 0, sub {
138 $_[0] > 0 or die "read error: $!"; 165 $_[0] > 0 or die "read error: $!";
139 print "read $_[0] bytes: <$buffer>\n"; 166 print "read $_[0] bytes: <$buffer>\n";
140 }; 167 };
141 168
169=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback
170
171Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
172reading at byte offset C<$in_offset>, and starts writing at the current
173file offset of C<$out_fh>. Because of that, it is not safe to issue more
174than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each
175other.
176
177This call tries to make use of a native C<sendfile> syscall to provide
178zero-copy operation. For this to work, C<$out_fh> should refer to a
179socket, and C<$in_fh> should refer to mmap'able file.
180
181If the native sendfile call fails or is not implemented, it will be
182emulated, so you can call C<aio_sendfile> on any type of filehandle
183regardless of the limitations of the operating system.
184
185Please note, however, that C<aio_sendfile> can read more bytes from
186C<$in_fh> than are written, and there is no way to find out how many
187bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only
188provides the number of bytes written to C<$out_fh>. Only if the result
189value equals C<$length> one can assume that C<$length> bytes have been
190read.
191
142=item aio_readahead $fh,$offset,$length, $callback 192=item aio_readahead $fh,$offset,$length, $callback
143 193
144Asynchronously reads the specified byte range into the page cache, using
145the C<readahead> syscall. If that syscall doesn't exist the status will be
146C<-1> and C<$!> is set to ENOSYS.
147
148readahead() populates the page cache with data from a file so that 194C<aio_readahead> populates the page cache with data from a file so that
149subsequent reads from that file will not block on disk I/O. The C<$offset> 195subsequent reads from that file will not block on disk I/O. The C<$offset>
150argument specifies the starting point from which data is to be read and 196argument specifies the starting point from which data is to be read and
151C<$length> specifies the number of bytes to be read. I/O is performed in 197C<$length> specifies the number of bytes to be read. I/O is performed in
152whole pages, so that offset is effectively rounded down to a page boundary 198whole pages, so that offset is effectively rounded down to a page boundary
153and bytes are read up to the next page boundary greater than or equal to 199and 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 200(off-set+length). C<aio_readahead> does not read beyond the end of the
155file. The current file offset of the file is left unchanged. 201file. The current file offset of the file is left unchanged.
202
203If that syscall doesn't exist (likely if your OS isn't Linux) it will be
204emulated by simply reading the data, which would have a similar effect.
156 205
157=item aio_stat $fh_or_path, $callback 206=item aio_stat $fh_or_path, $callback
158 207
159=item aio_lstat $fh, $callback 208=item aio_lstat $fh, $callback
160 209
… …
179=item aio_unlink $pathname, $callback 228=item aio_unlink $pathname, $callback
180 229
181Asynchronously unlink (delete) a file and call the callback with the 230Asynchronously unlink (delete) a file and call the callback with the
182result code. 231result code.
183 232
233=item aio_rmdir $pathname, $callback
234
235Asynchronously rmdir (delete) a directory and call the callback with the
236result code.
237
238=item aio_readdir $pathname $callback
239
240Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
241directory (i.e. opendir + readdir + closedir). The entries will not be
242sorted, and will B<NOT> include the C<.> and C<..> entries.
243
244The callback a single argument which is either C<undef> or an array-ref
245with the filenames.
246
184=item aio_fsync $fh, $callback 247=item aio_fsync $fh, $callback
185 248
186Asynchronously call fsync on the given filehandle and call the callback 249Asynchronously call fsync on the given filehandle and call the callback
187with the fsync result code. 250with the fsync result code.
188 251
189=item aio_fdatasync $fh, $callback 252=item aio_fdatasync $fh, $callback
190 253
191Asynchronously call fdatasync on the given filehandle and call the 254Asynchronously call fdatasync on the given filehandle and call the
192callback with the fdatasync result code. 255callback with the fdatasync result code.
193 256
257If this call isn't available because your OS lacks it or it couldn't be
258detected, it will be emulated by calling C<fsync> instead.
259
194=back 260=back
195 261
196=head2 SUPPORT FUNCTIONS 262=head2 SUPPORT FUNCTIONS
197 263
198=over 4 264=over 4
199 265
200=item $fileno = IO::AIO::poll_fileno 266=item $fileno = IO::AIO::poll_fileno
201 267
202Return the I<request result pipe filehandle>. This filehandle must be 268Return the I<request result pipe file descriptor>. This filehandle must be
203polled for reading by some mechanism outside this module (e.g. Event 269polled for reading by some mechanism outside this module (e.g. Event or
204or select, see below). If the pipe becomes readable you have to call 270select, see below or the SYNOPSIS). If the pipe becomes readable you have
205C<poll_cb> to check the results. 271to call C<poll_cb> to check the results.
206 272
207See C<poll_cb> for an example. 273See C<poll_cb> for an example.
208 274
209=item IO::AIO::poll_cb 275=item IO::AIO::poll_cb
210 276
211Process all outstanding events on the result pipe. You have to call this 277Process all outstanding events on the result pipe. You have to call this
212regularly. Returns the number of events processed. Returns immediately 278regularly. Returns the number of events processed. Returns immediately
213when no events are outstanding. 279when no events are outstanding.
214 280
215You can use Event to multiplex, e.g.: 281Example: Install an Event watcher that automatically calls
282IO::AIO::poll_cb with high priority:
216 283
217 Event->io (fd => IO::AIO::poll_fileno, 284 Event->io (fd => IO::AIO::poll_fileno,
218 poll => 'r', async => 1, 285 poll => 'r', async => 1,
219 cb => \&IO::AIO::poll_cb); 286 cb => \&IO::AIO::poll_cb);
220 287
221=item IO::AIO::poll_wait 288=item IO::AIO::poll_wait
222 289
223Wait till the result filehandle becomes ready for reading (simply does a 290Wait till the result filehandle becomes ready for reading (simply does a
224select on the filehandle. This is useful if you want to synchronously wait 291C<select> on the filehandle. This is useful if you want to synchronously wait
225for some requests to finish). 292for some requests to finish).
226 293
227See C<nreqs> for an example. 294See C<nreqs> for an example.
228 295
229=item IO::AIO::nreqs 296=item IO::AIO::nreqs
230 297
231Returns the number of requests currently outstanding. 298Returns the number of requests currently outstanding (i.e. for which their
299callback has not been invoked yet).
232 300
233Example: wait till there are no outstanding requests anymore: 301Example: wait till there are no outstanding requests anymore:
234 302
235 IO::AIO::poll_wait, IO::AIO::poll_cb 303 IO::AIO::poll_wait, IO::AIO::poll_cb
236 while IO::AIO::nreqs; 304 while IO::AIO::nreqs;
237 305
306=item IO::AIO::flush
307
308Wait till all outstanding AIO requests have been handled.
309
310Strictly equivalent to:
311
312 IO::AIO::poll_wait, IO::AIO::poll_cb
313 while IO::AIO::nreqs;
314
315=item IO::AIO::poll
316
317Waits until some requests have been handled.
318
319Strictly equivalent to:
320
321 IO::AIO::poll_wait, IO::AIO::poll_cb
322 if IO::AIO::nreqs;
323
238=item IO::AIO::min_parallel $nthreads 324=item IO::AIO::min_parallel $nthreads
239 325
240Set the minimum number of AIO threads to C<$nthreads>. The default is 326Set the minimum number of AIO threads to C<$nthreads>. The current default
241C<1>, which means a single asynchronous operation can be done at one time 327is C<4>, which means four asynchronous operations can be done at one time
242(the number of outstanding operations, however, is unlimited). 328(the number of outstanding operations, however, is unlimited).
329
330IO::AIO starts threads only on demand, when an AIO request is queued and
331no free thread exists.
243 332
244It is recommended to keep the number of threads low, as some Linux 333It is recommended to keep the number of threads low, as some Linux
245kernel versions will scale negatively with the number of threads (higher 334kernel versions will scale negatively with the number of threads (higher
246parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32 335parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32
247threads should be fine. 336threads should be fine.
248 337
249Under normal circumstances you don't need to call this function, as this 338Under most circumstances you don't need to call this function, as the
250module automatically starts some threads (the exact number might change, 339module selects a default that is suitable for low to moderate load.
251and is currently 4).
252 340
253=item IO::AIO::max_parallel $nthreads 341=item IO::AIO::max_parallel $nthreads
254 342
255Sets the maximum number of AIO threads to C<$nthreads>. If more than 343Sets the maximum number of AIO threads to C<$nthreads>. If more than the
256the specified number of threads are currently running, kill them. This 344specified number of threads are currently running, this function kills
257function blocks until the limit is reached. 345them. This function blocks until the limit is reached.
346
347While C<$nthreads> are zero, aio requests get queued but not executed
348until the number of threads has been increased again.
258 349
259This module automatically runs C<max_parallel 0> at program end, to ensure 350This module automatically runs C<max_parallel 0> at program end, to ensure
260that all threads are killed and that there are no outstanding requests. 351that all threads are killed and that there are no outstanding requests.
261 352
262Under normal circumstances you don't need to call this function. 353Under normal circumstances you don't need to call this function.
… …
266Sets the maximum number of outstanding requests to C<$nreqs>. If you 357Sets the maximum number of outstanding requests to C<$nreqs>. If you
267try to queue up more than this number of requests, the caller will block until 358try to queue up more than this number of requests, the caller will block until
268some requests have been handled. 359some requests have been handled.
269 360
270The default is very large, so normally there is no practical limit. If you 361The default is very large, so normally there is no practical limit. If you
271queue up many requests in a loop it it often improves speed if you set 362queue up many requests in a loop it often improves speed if you set
272this to a relatively low number, such as C<100>. 363this to a relatively low number, such as C<100>.
273 364
274Under normal circumstances you don't need to call this function. 365Under normal circumstances you don't need to call this function.
275 366
276=back 367=back
… …
279 370
280# support function to convert a fd into a perl filehandle 371# support function to convert a fd into a perl filehandle
281sub _fd2fh { 372sub _fd2fh {
282 return undef if $_[0] < 0; 373 return undef if $_[0] < 0;
283 374
284 # try to be perl5.6-compatible 375 # try to generate nice filehandles
285 local *AIO_FH; 376 my $sym = "IO::AIO::fd#$_[0]";
286 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
287 or return undef; 382 or return undef;
288 383
289 *AIO_FH 384 *$sym
290} 385}
291 386
292min_parallel 4; 387min_parallel 4;
293 388
294END { 389END {
295 max_parallel 0; 390 max_parallel 0;
296} 391}
297 392
2981; 3931;
299 394
395=head2 FORK BEHAVIOUR
396
397Before the fork, IO::AIO enters a quiescent state where no requests
398can be added in other threads and no results will be processed. After
399the fork the parent simply leaves the quiescent state and continues
400request/result processing, while the child clears the request/result
401queue (so the requests started before the fork will only be handled in
402the parent). Threats will be started on demand until the limit ste in the
403parent process has been reached again.
404
300=head1 SEE ALSO 405=head1 SEE ALSO
301 406
302L<Coro>, L<Linux::AIO>. 407L<Coro>, L<Linux::AIO>.
303 408
304=head1 AUTHOR 409=head1 AUTHOR

Diff Legend

– Removed lines
+ Added lines
< Changed lines
> Changed lines