… | |
… | |
4 | |
4 | |
5 | =head1 SYNOPSIS |
5 | =head1 SYNOPSIS |
6 | |
6 | |
7 | use IO::AIO; |
7 | use IO::AIO; |
8 | |
8 | |
9 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
9 | aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub { |
10 | my $fh = shift |
10 | my $fh = shift |
11 | or die "/etc/passwd: $!"; |
11 | or die "/etc/passwd: $!"; |
12 | ... |
12 | ... |
13 | }; |
13 | }; |
14 | |
14 | |
… | |
… | |
25 | my $req = aio_unlink "/tmp/file", sub { }; |
25 | my $req = aio_unlink "/tmp/file", sub { }; |
26 | $req->cancel; # cancel request if still in queue |
26 | $req->cancel; # cancel request if still in queue |
27 | |
27 | |
28 | my $grp = aio_group sub { print "all stats done\n" }; |
28 | my $grp = aio_group sub { print "all stats done\n" }; |
29 | add $grp aio_stat "..." for ...; |
29 | add $grp aio_stat "..." for ...; |
30 | |
|
|
31 | # AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...) |
|
|
32 | use AnyEvent::AIO; |
|
|
33 | |
|
|
34 | # EV integration |
|
|
35 | my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; |
|
|
36 | |
|
|
37 | # Event integration |
|
|
38 | Event->io (fd => IO::AIO::poll_fileno, |
|
|
39 | poll => 'r', |
|
|
40 | cb => \&IO::AIO::poll_cb); |
|
|
41 | |
|
|
42 | # Glib/Gtk2 integration |
|
|
43 | add_watch Glib::IO IO::AIO::poll_fileno, |
|
|
44 | in => sub { IO::AIO::poll_cb; 1 }; |
|
|
45 | |
|
|
46 | # Tk integration |
|
|
47 | Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "", |
|
|
48 | readable => \&IO::AIO::poll_cb); |
|
|
49 | |
|
|
50 | # Danga::Socket integration |
|
|
51 | Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => |
|
|
52 | \&IO::AIO::poll_cb); |
|
|
53 | |
30 | |
54 | =head1 DESCRIPTION |
31 | =head1 DESCRIPTION |
55 | |
32 | |
56 | This module implements asynchronous I/O using whatever means your |
33 | This module implements asynchronous I/O using whatever means your |
57 | operating system supports. It is implemented as an interface to C<libeio> |
34 | operating system supports. It is implemented as an interface to C<libeio> |
… | |
… | |
99 | |
76 | |
100 | # register the IO::AIO callback with EV |
77 | # register the IO::AIO callback with EV |
101 | my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; |
78 | my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; |
102 | |
79 | |
103 | # queue the request to open /etc/passwd |
80 | # queue the request to open /etc/passwd |
104 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
81 | aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub { |
105 | my $fh = shift |
82 | my $fh = shift |
106 | or die "error while opening: $!"; |
83 | or die "error while opening: $!"; |
107 | |
84 | |
108 | # stat'ing filehandles is generally non-blocking |
85 | # stat'ing filehandles is generally non-blocking |
109 | my $size = -s $fh; |
86 | my $size = -s $fh; |
… | |
… | |
191 | use common::sense; |
168 | use common::sense; |
192 | |
169 | |
193 | use base 'Exporter'; |
170 | use base 'Exporter'; |
194 | |
171 | |
195 | BEGIN { |
172 | BEGIN { |
196 | our $VERSION = '3.5'; |
173 | our $VERSION = '4.13'; |
197 | |
174 | |
198 | our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close |
175 | our @AIO_REQ = qw(aio_sendfile aio_seek aio_read aio_write aio_open aio_close |
199 | aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx |
176 | aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx |
200 | aio_scandir aio_symlink aio_readlink aio_sync aio_fsync |
177 | aio_scandir aio_symlink aio_readlink aio_realpath aio_sync |
201 | aio_fdatasync aio_sync_file_range aio_pathsync aio_readahead |
178 | aio_fsync aio_syncfs aio_fdatasync aio_sync_file_range aio_fallocate |
|
|
179 | aio_pathsync aio_readahead aio_fiemap |
202 | aio_rename aio_link aio_move aio_copy aio_group |
180 | aio_rename aio_link aio_move aio_copy aio_group |
203 | aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown |
181 | aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown |
204 | aio_chmod aio_utime aio_truncate |
182 | aio_chmod aio_utime aio_truncate |
205 | aio_msync aio_mtouch aio_statvfs); |
183 | aio_msync aio_mtouch aio_mlock aio_mlockall |
|
|
184 | aio_statvfs |
|
|
185 | aio_wd); |
206 | |
186 | |
207 | our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice)); |
187 | our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice)); |
208 | our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush |
188 | our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush |
209 | min_parallel max_parallel max_idle |
189 | min_parallel max_parallel max_idle idle_timeout |
210 | nreqs nready npending nthreads |
190 | nreqs nready npending nthreads |
211 | max_poll_time max_poll_reqs |
191 | max_poll_time max_poll_reqs |
212 | sendfile fadvise); |
192 | sendfile fadvise madvise |
|
|
193 | mmap munmap munlock munlockall); |
213 | |
194 | |
214 | push @AIO_REQ, qw(aio_busy); # not exported |
195 | push @AIO_REQ, qw(aio_busy); # not exported |
215 | |
196 | |
216 | @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; |
197 | @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; |
217 | |
198 | |
… | |
… | |
219 | XSLoader::load ("IO::AIO", $VERSION); |
200 | XSLoader::load ("IO::AIO", $VERSION); |
220 | } |
201 | } |
221 | |
202 | |
222 | =head1 FUNCTIONS |
203 | =head1 FUNCTIONS |
223 | |
204 | |
224 | =head2 AIO REQUEST FUNCTIONS |
205 | =head2 QUICK OVERVIEW |
|
|
206 | |
|
|
207 | This section simply lists the prototypes of the most important functions |
|
|
208 | for quick reference. See the following sections for function-by-function |
|
|
209 | documentation. |
|
|
210 | |
|
|
211 | aio_wd $pathname, $callback->($wd) |
|
|
212 | aio_open $pathname, $flags, $mode, $callback->($fh) |
|
|
213 | aio_close $fh, $callback->($status) |
|
|
214 | aio_seek $fh,$offset,$whence, $callback->($offs) |
|
|
215 | aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
|
|
216 | aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
|
|
217 | aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) |
|
|
218 | aio_readahead $fh,$offset,$length, $callback->($retval) |
|
|
219 | aio_stat $fh_or_path, $callback->($status) |
|
|
220 | aio_lstat $fh, $callback->($status) |
|
|
221 | aio_statvfs $fh_or_path, $callback->($statvfs) |
|
|
222 | aio_utime $fh_or_path, $atime, $mtime, $callback->($status) |
|
|
223 | aio_chown $fh_or_path, $uid, $gid, $callback->($status) |
|
|
224 | aio_chmod $fh_or_path, $mode, $callback->($status) |
|
|
225 | aio_truncate $fh_or_path, $offset, $callback->($status) |
|
|
226 | aio_unlink $pathname, $callback->($status) |
|
|
227 | aio_mknod $pathname, $mode, $dev, $callback->($status) |
|
|
228 | aio_link $srcpath, $dstpath, $callback->($status) |
|
|
229 | aio_symlink $srcpath, $dstpath, $callback->($status) |
|
|
230 | aio_readlink $pathname, $callback->($link) |
|
|
231 | aio_realpath $pathname, $callback->($link) |
|
|
232 | aio_rename $srcpath, $dstpath, $callback->($status) |
|
|
233 | aio_mkdir $pathname, $mode, $callback->($status) |
|
|
234 | aio_rmdir $pathname, $callback->($status) |
|
|
235 | aio_readdir $pathname, $callback->($entries) |
|
|
236 | aio_readdirx $pathname, $flags, $callback->($entries, $flags) |
|
|
237 | IO::AIO::READDIR_DENTS IO::AIO::READDIR_DIRS_FIRST |
|
|
238 | IO::AIO::READDIR_STAT_ORDER IO::AIO::READDIR_FOUND_UNKNOWN |
|
|
239 | aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs) |
|
|
240 | aio_load $pathname, $data, $callback->($status) |
|
|
241 | aio_copy $srcpath, $dstpath, $callback->($status) |
|
|
242 | aio_move $srcpath, $dstpath, $callback->($status) |
|
|
243 | aio_rmtree $pathname, $callback->($status) |
|
|
244 | aio_sync $callback->($status) |
|
|
245 | aio_syncfs $fh, $callback->($status) |
|
|
246 | aio_fsync $fh, $callback->($status) |
|
|
247 | aio_fdatasync $fh, $callback->($status) |
|
|
248 | aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status) |
|
|
249 | aio_pathsync $pathname, $callback->($status) |
|
|
250 | aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status) |
|
|
251 | aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status) |
|
|
252 | aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status) |
|
|
253 | aio_mlockall $flags, $callback->($status) |
|
|
254 | aio_group $callback->(...) |
|
|
255 | aio_nop $callback->() |
|
|
256 | |
|
|
257 | $prev_pri = aioreq_pri [$pri] |
|
|
258 | aioreq_nice $pri_adjust |
|
|
259 | |
|
|
260 | IO::AIO::poll_wait |
|
|
261 | IO::AIO::poll_cb |
|
|
262 | IO::AIO::poll |
|
|
263 | IO::AIO::flush |
|
|
264 | IO::AIO::max_poll_reqs $nreqs |
|
|
265 | IO::AIO::max_poll_time $seconds |
|
|
266 | IO::AIO::min_parallel $nthreads |
|
|
267 | IO::AIO::max_parallel $nthreads |
|
|
268 | IO::AIO::max_idle $nthreads |
|
|
269 | IO::AIO::idle_timeout $seconds |
|
|
270 | IO::AIO::max_outstanding $maxreqs |
|
|
271 | IO::AIO::nreqs |
|
|
272 | IO::AIO::nready |
|
|
273 | IO::AIO::npending |
|
|
274 | |
|
|
275 | IO::AIO::sendfile $ofh, $ifh, $offset, $count |
|
|
276 | IO::AIO::fadvise $fh, $offset, $len, $advice |
|
|
277 | IO::AIO::madvise $scalar, $offset, $length, $advice |
|
|
278 | IO::AIO::mprotect $scalar, $offset, $length, $protect |
|
|
279 | IO::AIO::munlock $scalar, $offset = 0, $length = undef |
|
|
280 | IO::AIO::munlockall |
|
|
281 | |
|
|
282 | =head2 API NOTES |
225 | |
283 | |
226 | All the C<aio_*> calls are more or less thin wrappers around the syscall |
284 | All the C<aio_*> calls are more or less thin wrappers around the syscall |
227 | with the same name (sans C<aio_>). The arguments are similar or identical, |
285 | with the same name (sans C<aio_>). The arguments are similar or identical, |
228 | and they all accept an additional (and optional) C<$callback> argument |
286 | and they all accept an additional (and optional) C<$callback> argument |
229 | which must be a code reference. This code reference will get called with |
287 | which must be a code reference. This code reference will be called after |
230 | the syscall return code (e.g. most syscalls return C<-1> on error, unlike |
288 | the syscall has been executed in an asynchronous fashion. The results |
231 | perl, which usually delivers "false") as its sole argument after the given |
289 | of the request will be passed as arguments to the callback (and, if an |
232 | syscall has been executed asynchronously. |
290 | error occured, in C<$!>) - for most requests the syscall return code (e.g. |
|
|
291 | most syscalls return C<-1> on error, unlike perl, which usually delivers |
|
|
292 | "false"). |
|
|
293 | |
|
|
294 | Some requests (such as C<aio_readdir>) pass the actual results and |
|
|
295 | communicate failures by passing C<undef>. |
233 | |
296 | |
234 | All functions expecting a filehandle keep a copy of the filehandle |
297 | All functions expecting a filehandle keep a copy of the filehandle |
235 | internally until the request has finished. |
298 | internally until the request has finished. |
236 | |
299 | |
237 | All functions return request objects of type L<IO::AIO::REQ> that allow |
300 | All functions return request objects of type L<IO::AIO::REQ> that allow |
238 | further manipulation of those requests while they are in-flight. |
301 | further manipulation of those requests while they are in-flight. |
239 | |
302 | |
240 | The pathnames you pass to these routines I<must> be absolute and |
303 | The pathnames you pass to these routines I<should> be absolute. The |
241 | encoded as octets. The reason for the former is that at the time the |
304 | reason for this is that at the time the request is being executed, the |
242 | request is being executed, the current working directory could have |
305 | current working directory could have changed. Alternatively, you can |
243 | changed. Alternatively, you can make sure that you never change the |
306 | make sure that you never change the current working directory anywhere |
244 | current working directory anywhere in the program and then use relative |
307 | in the program and then use relative paths. You can also take advantage |
245 | paths. |
308 | of IO::AIOs working directory abstraction, that lets you specify paths |
|
|
309 | relative to some previously-opened "working directory object" - see the |
|
|
310 | description of the C<IO::AIO::WD> class later in this document. |
246 | |
311 | |
247 | To encode pathnames as octets, either make sure you either: a) always pass |
312 | To encode pathnames as octets, either make sure you either: a) always pass |
248 | in filenames you got from outside (command line, readdir etc.) without |
313 | in filenames you got from outside (command line, readdir etc.) without |
249 | tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module and encode |
314 | tinkering, b) are in your native filesystem encoding, c) use the Encode |
250 | your pathnames to the locale (or other) encoding in effect in the user |
315 | module and encode your pathnames to the locale (or other) encoding in |
251 | environment, d) use Glib::filename_from_unicode on unicode filenames or e) |
316 | effect in the user environment, d) use Glib::filename_from_unicode on |
252 | use something else to ensure your scalar has the correct contents. |
317 | unicode filenames or e) use something else to ensure your scalar has the |
|
|
318 | correct contents. |
253 | |
319 | |
254 | This works, btw. independent of the internal UTF-8 bit, which IO::AIO |
320 | This works, btw. independent of the internal UTF-8 bit, which IO::AIO |
255 | handles correctly whether it is set or not. |
321 | handles correctly whether it is set or not. |
|
|
322 | |
|
|
323 | =head2 AIO REQUEST FUNCTIONS |
256 | |
324 | |
257 | =over 4 |
325 | =over 4 |
258 | |
326 | |
259 | =item $prev_pri = aioreq_pri [$pri] |
327 | =item $prev_pri = aioreq_pri [$pri] |
260 | |
328 | |
… | |
… | |
307 | by the umask in effect then the request is being executed, so better never |
375 | by the umask in effect then the request is being executed, so better never |
308 | change the umask. |
376 | change the umask. |
309 | |
377 | |
310 | Example: |
378 | Example: |
311 | |
379 | |
312 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
380 | aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub { |
313 | if ($_[0]) { |
381 | if ($_[0]) { |
314 | print "open successful, fh is $_[0]\n"; |
382 | print "open successful, fh is $_[0]\n"; |
315 | ... |
383 | ... |
316 | } else { |
384 | } else { |
317 | die "open failed: $!\n"; |
385 | die "open failed: $!\n"; |
318 | } |
386 | } |
319 | }; |
387 | }; |
320 | |
388 | |
|
|
389 | In addition to all the common open modes/flags (C<O_RDONLY>, C<O_WRONLY>, |
|
|
390 | C<O_RDWR>, C<O_CREAT>, C<O_TRUNC>, C<O_EXCL> and C<O_APPEND>), the |
|
|
391 | following POSIX and non-POSIX constants are available (missing ones on |
|
|
392 | your system are, as usual, C<0>): |
|
|
393 | |
|
|
394 | C<O_ASYNC>, C<O_DIRECT>, C<O_NOATIME>, C<O_CLOEXEC>, C<O_NOCTTY>, C<O_NOFOLLOW>, |
|
|
395 | C<O_NONBLOCK>, C<O_EXEC>, C<O_SEARCH>, C<O_DIRECTORY>, C<O_DSYNC>, |
|
|
396 | C<O_RSYNC>, C<O_SYNC> and C<O_TTY_INIT>. |
|
|
397 | |
321 | |
398 | |
322 | =item aio_close $fh, $callback->($status) |
399 | =item aio_close $fh, $callback->($status) |
323 | |
400 | |
324 | Asynchronously close a file and call the callback with the result |
401 | Asynchronously close a file and call the callback with the result |
325 | code. |
402 | code. |
… | |
… | |
333 | |
410 | |
334 | Or in other words: the file descriptor will be closed, but it will not be |
411 | Or in other words: the file descriptor will be closed, but it will not be |
335 | free for reuse until the perl filehandle is closed. |
412 | free for reuse until the perl filehandle is closed. |
336 | |
413 | |
337 | =cut |
414 | =cut |
|
|
415 | |
|
|
416 | =item aio_seek $fh, $offset, $whence, $callback->($offs) |
|
|
417 | |
|
|
418 | Seeks the filehandle to the new C<$offset>, similarly to perl's |
|
|
419 | C<sysseek>. The C<$whence> can use the traditional values (C<0> for |
|
|
420 | C<IO::AIO::SEEK_SET>, C<1> for C<IO::AIO::SEEK_CUR> or C<2> for |
|
|
421 | C<IO::AIO::SEEK_END>). |
|
|
422 | |
|
|
423 | The resulting absolute offset will be passed to the callback, or C<-1> in |
|
|
424 | case of an error. |
|
|
425 | |
|
|
426 | In theory, the C<$whence> constants could be different than the |
|
|
427 | corresponding values from L<Fcntl>, but perl guarantees they are the same, |
|
|
428 | so don't panic. |
338 | |
429 | |
339 | =item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
430 | =item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
340 | |
431 | |
341 | =item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
432 | =item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
342 | |
433 | |
… | |
… | |
375 | |
466 | |
376 | Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts |
467 | Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts |
377 | reading at byte offset C<$in_offset>, and starts writing at the current |
468 | reading at byte offset C<$in_offset>, and starts writing at the current |
378 | file offset of C<$out_fh>. Because of that, it is not safe to issue more |
469 | file offset of C<$out_fh>. Because of that, it is not safe to issue more |
379 | than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each |
470 | than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each |
380 | other. |
471 | other. The same C<$in_fh> works fine though, as this function does not |
|
|
472 | move or use the file offset of C<$in_fh>. |
381 | |
473 | |
|
|
474 | Please note that C<aio_sendfile> can read more bytes from C<$in_fh> than |
|
|
475 | are written, and there is no way to find out how many more bytes have been |
|
|
476 | read from C<aio_sendfile> alone, as C<aio_sendfile> only provides the |
|
|
477 | number of bytes written to C<$out_fh>. Only if the result value equals |
|
|
478 | C<$length> one can assume that C<$length> bytes have been read. |
|
|
479 | |
|
|
480 | Unlike with other C<aio_> functions, it makes a lot of sense to use |
|
|
481 | C<aio_sendfile> on non-blocking sockets, as long as one end (typically |
|
|
482 | the C<$in_fh>) is a file - the file I/O will then be asynchronous, while |
|
|
483 | the socket I/O will be non-blocking. Note, however, that you can run |
|
|
484 | into a trap where C<aio_sendfile> reads some data with readahead, then |
|
|
485 | fails to write all data, and when the socket is ready the next time, the |
|
|
486 | data in the cache is already lost, forcing C<aio_sendfile> to again hit |
|
|
487 | the disk. Explicit C<aio_read> + C<aio_write> let's you better control |
|
|
488 | resource usage. |
|
|
489 | |
382 | This call tries to make use of a native C<sendfile> syscall to provide |
490 | This call tries to make use of a native C<sendfile>-like syscall to |
383 | zero-copy operation. For this to work, C<$out_fh> should refer to a |
491 | provide zero-copy operation. For this to work, C<$out_fh> should refer to |
384 | socket, and C<$in_fh> should refer to mmap'able file. |
492 | a socket, and C<$in_fh> should refer to an mmap'able file. |
385 | |
493 | |
386 | If a native sendfile cannot be found or it fails with C<ENOSYS>, |
494 | If a native sendfile cannot be found or it fails with C<ENOSYS>, |
387 | C<ENOTSUP>, C<EOPNOTSUPP>, C<EAFNOSUPPORT>, C<EPROTOTYPE> or C<ENOTSOCK>, |
495 | C<EINVAL>, C<ENOTSUP>, C<EOPNOTSUPP>, C<EAFNOSUPPORT>, C<EPROTOTYPE> or |
388 | it will be emulated, so you can call C<aio_sendfile> on any type of |
496 | C<ENOTSOCK>, it will be emulated, so you can call C<aio_sendfile> on any |
389 | filehandle regardless of the limitations of the operating system. |
497 | type of filehandle regardless of the limitations of the operating system. |
390 | |
498 | |
391 | Please note, however, that C<aio_sendfile> can read more bytes from |
499 | As native sendfile syscalls (as practically any non-POSIX interface hacked |
392 | C<$in_fh> than are written, and there is no way to find out how many |
500 | together in a hurry to improve benchmark numbers) tend to be rather buggy |
393 | bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only |
501 | on many systems, this implementation tries to work around some known bugs |
394 | provides the number of bytes written to C<$out_fh>. Only if the result |
502 | in Linux and FreeBSD kernels (probably others, too), but that might fail, |
395 | value equals C<$length> one can assume that C<$length> bytes have been |
503 | so you really really should check the return value of C<aio_sendfile> - |
396 | read. |
504 | fewre bytes than expected might have been transferred. |
397 | |
505 | |
398 | |
506 | |
399 | =item aio_readahead $fh,$offset,$length, $callback->($retval) |
507 | =item aio_readahead $fh,$offset,$length, $callback->($retval) |
400 | |
508 | |
401 | C<aio_readahead> populates the page cache with data from a file so that |
509 | C<aio_readahead> populates the page cache with data from a file so that |
… | |
… | |
424 | |
532 | |
425 | Currently, the stats are always 64-bit-stats, i.e. instead of returning an |
533 | Currently, the stats are always 64-bit-stats, i.e. instead of returning an |
426 | error when stat'ing a large file, the results will be silently truncated |
534 | error when stat'ing a large file, the results will be silently truncated |
427 | unless perl itself is compiled with large file support. |
535 | unless perl itself is compiled with large file support. |
428 | |
536 | |
|
|
537 | To help interpret the mode and dev/rdev stat values, IO::AIO offers the |
|
|
538 | following constants and functions (if not implemented, the constants will |
|
|
539 | be C<0> and the functions will either C<croak> or fall back on traditional |
|
|
540 | behaviour). |
|
|
541 | |
|
|
542 | C<S_IFMT>, C<S_IFIFO>, C<S_IFCHR>, C<S_IFBLK>, C<S_IFLNK>, C<S_IFREG>, |
|
|
543 | C<S_IFDIR>, C<S_IFWHT>, C<S_IFSOCK>, C<IO::AIO::major $dev_t>, |
|
|
544 | C<IO::AIO::minor $dev_t>, C<IO::AIO::makedev $major, $minor>. |
|
|
545 | |
429 | Example: Print the length of F</etc/passwd>: |
546 | Example: Print the length of F</etc/passwd>: |
430 | |
547 | |
431 | aio_stat "/etc/passwd", sub { |
548 | aio_stat "/etc/passwd", sub { |
432 | $_[0] and die "stat failed: $!"; |
549 | $_[0] and die "stat failed: $!"; |
433 | print "size is ", -s _, "\n"; |
550 | print "size is ", -s _, "\n"; |
434 | }; |
551 | }; |
435 | |
552 | |
436 | |
553 | |
437 | =item aio_statvfs $fh_or_path, $callback->($statvfs) |
554 | =item aio_statvfs $fh_or_path, $callback->($statvfs) |
438 | |
555 | |
439 | Works like the POSIX C<statvfs> or C<fstatvfs> syscalls, depending on |
556 | Works like the POSIX C<statvfs> or C<fstatvfs> syscalls, depending on |
440 | whether a file handle or path was passed. |
557 | whether a file handle or path was passed. |
441 | |
558 | |
442 | On success, the callback is passed a hash reference with the following |
559 | On success, the callback is passed a hash reference with the following |
… | |
… | |
524 | |
641 | |
525 | Asynchronously unlink (delete) a file and call the callback with the |
642 | Asynchronously unlink (delete) a file and call the callback with the |
526 | result code. |
643 | result code. |
527 | |
644 | |
528 | |
645 | |
529 | =item aio_mknod $path, $mode, $dev, $callback->($status) |
646 | =item aio_mknod $pathname, $mode, $dev, $callback->($status) |
530 | |
647 | |
531 | [EXPERIMENTAL] |
648 | [EXPERIMENTAL] |
532 | |
649 | |
533 | Asynchronously create a device node (or fifo). See mknod(2). |
650 | Asynchronously create a device node (or fifo). See mknod(2). |
534 | |
651 | |
535 | The only (POSIX-) portable way of calling this function is: |
652 | The only (POSIX-) portable way of calling this function is: |
536 | |
653 | |
537 | aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ... |
654 | aio_mknod $pathname, IO::AIO::S_IFIFO | $mode, 0, sub { ... |
538 | |
655 | |
|
|
656 | See C<aio_stat> for info about some potentially helpful extra constants |
|
|
657 | and functions. |
539 | |
658 | |
540 | =item aio_link $srcpath, $dstpath, $callback->($status) |
659 | =item aio_link $srcpath, $dstpath, $callback->($status) |
541 | |
660 | |
542 | Asynchronously create a new link to the existing object at C<$srcpath> at |
661 | Asynchronously create a new link to the existing object at C<$srcpath> at |
543 | the path C<$dstpath> and call the callback with the result code. |
662 | the path C<$dstpath> and call the callback with the result code. |
… | |
… | |
547 | |
666 | |
548 | Asynchronously create a new symbolic link to the existing object at C<$srcpath> at |
667 | Asynchronously create a new symbolic link to the existing object at C<$srcpath> at |
549 | the path C<$dstpath> and call the callback with the result code. |
668 | the path C<$dstpath> and call the callback with the result code. |
550 | |
669 | |
551 | |
670 | |
552 | =item aio_readlink $path, $callback->($link) |
671 | =item aio_readlink $pathname, $callback->($link) |
553 | |
672 | |
554 | Asynchronously read the symlink specified by C<$path> and pass it to |
673 | Asynchronously read the symlink specified by C<$path> and pass it to |
555 | the callback. If an error occurs, nothing or undef gets passed to the |
674 | the callback. If an error occurs, nothing or undef gets passed to the |
556 | callback. |
675 | callback. |
557 | |
676 | |
558 | |
677 | |
|
|
678 | =item aio_realpath $pathname, $callback->($path) |
|
|
679 | |
|
|
680 | Asynchronously make the path absolute and resolve any symlinks in |
|
|
681 | C<$path>. The resulting path only consists of directories (Same as |
|
|
682 | L<Cwd::realpath>). |
|
|
683 | |
|
|
684 | This request can be used to get the absolute path of the current working |
|
|
685 | directory by passing it a path of F<.> (a single dot). |
|
|
686 | |
|
|
687 | |
559 | =item aio_rename $srcpath, $dstpath, $callback->($status) |
688 | =item aio_rename $srcpath, $dstpath, $callback->($status) |
560 | |
689 | |
561 | Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as |
690 | Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as |
562 | rename(2) and call the callback with the result code. |
691 | rename(2) and call the callback with the result code. |
563 | |
692 | |
… | |
… | |
585 | array-ref with the filenames. |
714 | array-ref with the filenames. |
586 | |
715 | |
587 | |
716 | |
588 | =item aio_readdirx $pathname, $flags, $callback->($entries, $flags) |
717 | =item aio_readdirx $pathname, $flags, $callback->($entries, $flags) |
589 | |
718 | |
590 | Quite similar to C<aio_readdir>, but the C<$flags> argument allows to tune |
719 | Quite similar to C<aio_readdir>, but the C<$flags> argument allows one to |
591 | behaviour and output format. In case of an error, C<$entries> will be |
720 | tune behaviour and output format. In case of an error, C<$entries> will be |
592 | C<undef>. |
721 | C<undef>. |
593 | |
722 | |
594 | The flags are a combination of the following constants, ORed together (the |
723 | The flags are a combination of the following constants, ORed together (the |
595 | flags will also be passed to the callback, possibly modified): |
724 | flags will also be passed to the callback, possibly modified): |
596 | |
725 | |
597 | =over 4 |
726 | =over 4 |
598 | |
727 | |
599 | =item IO::AIO::READDIR_DENTS |
728 | =item IO::AIO::READDIR_DENTS |
600 | |
729 | |
601 | When this flag is off, then the callback gets an arrayref with of names |
730 | When this flag is off, then the callback gets an arrayref consisting of |
602 | only (as with C<aio_readdir>), otherwise it gets an arrayref with |
731 | names only (as with C<aio_readdir>), otherwise it gets an arrayref with |
603 | C<[$name, $type, $inode]> arrayrefs, each describing a single directory |
732 | C<[$name, $type, $inode]> arrayrefs, each describing a single directory |
604 | entry in more detail. |
733 | entry in more detail. |
605 | |
734 | |
606 | C<$name> is the name of the entry. |
735 | C<$name> is the name of the entry. |
607 | |
736 | |
… | |
… | |
620 | systems that do not deliver the inode information. |
749 | systems that do not deliver the inode information. |
621 | |
750 | |
622 | =item IO::AIO::READDIR_DIRS_FIRST |
751 | =item IO::AIO::READDIR_DIRS_FIRST |
623 | |
752 | |
624 | When this flag is set, then the names will be returned in an order where |
753 | When this flag is set, then the names will be returned in an order where |
625 | likely directories come first. This is useful when you need to quickly |
754 | likely directories come first, in optimal stat order. This is useful when |
626 | find directories, or you want to find all directories while avoiding to |
755 | you need to quickly find directories, or you want to find all directories |
627 | stat() each entry. |
756 | while avoiding to stat() each entry. |
628 | |
757 | |
629 | If the system returns type information in readdir, then this is used |
758 | If the system returns type information in readdir, then this is used |
630 | to find directories directly. Otherwise, likely directories are files |
759 | to find directories directly. Otherwise, likely directories are names |
631 | beginning with ".", or otherwise files with no dots, of which files with |
760 | beginning with ".", or otherwise names with no dots, of which names with |
632 | short names are tried first. |
761 | short names are tried first. |
633 | |
762 | |
634 | =item IO::AIO::READDIR_STAT_ORDER |
763 | =item IO::AIO::READDIR_STAT_ORDER |
635 | |
764 | |
636 | When this flag is set, then the names will be returned in an order |
765 | When this flag is set, then the names will be returned in an order |
… | |
… | |
643 | |
772 | |
644 | =item IO::AIO::READDIR_FOUND_UNKNOWN |
773 | =item IO::AIO::READDIR_FOUND_UNKNOWN |
645 | |
774 | |
646 | This flag should not be set when calling C<aio_readdirx>. Instead, it |
775 | This flag should not be set when calling C<aio_readdirx>. Instead, it |
647 | is being set by C<aio_readdirx>, when any of the C<$type>'s found were |
776 | is being set by C<aio_readdirx>, when any of the C<$type>'s found were |
648 | C<IO::AIO::DT_UNKNOWN>. The absense of this flag therefore indicates that all |
777 | C<IO::AIO::DT_UNKNOWN>. The absence of this flag therefore indicates that all |
649 | C<$type>'s are known, which can be used to speed up some algorithms. |
778 | C<$type>'s are known, which can be used to speed up some algorithms. |
650 | |
779 | |
651 | =back |
780 | =back |
652 | |
781 | |
653 | |
782 | |
654 | =item aio_load $path, $data, $callback->($status) |
783 | =item aio_load $pathname, $data, $callback->($status) |
655 | |
784 | |
656 | This is a composite request that tries to fully load the given file into |
785 | This is a composite request that tries to fully load the given file into |
657 | memory. Status is the same as with aio_read. |
786 | memory. Status is the same as with aio_read. |
658 | |
787 | |
659 | =cut |
788 | =cut |
… | |
… | |
781 | if ($_[0] && $! == EXDEV) { |
910 | if ($_[0] && $! == EXDEV) { |
782 | aioreq_pri $pri; |
911 | aioreq_pri $pri; |
783 | add $grp aio_copy $src, $dst, sub { |
912 | add $grp aio_copy $src, $dst, sub { |
784 | $grp->result ($_[0]); |
913 | $grp->result ($_[0]); |
785 | |
914 | |
786 | if (!$_[0]) { |
915 | unless ($_[0]) { |
787 | aioreq_pri $pri; |
916 | aioreq_pri $pri; |
788 | add $grp aio_unlink $src; |
917 | add $grp aio_unlink $src; |
789 | } |
918 | } |
790 | }; |
919 | }; |
791 | } else { |
920 | } else { |
… | |
… | |
794 | }; |
923 | }; |
795 | |
924 | |
796 | $grp |
925 | $grp |
797 | } |
926 | } |
798 | |
927 | |
799 | =item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) |
928 | =item aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs) |
800 | |
929 | |
801 | Scans a directory (similar to C<aio_readdir>) but additionally tries to |
930 | Scans a directory (similar to C<aio_readdir>) but additionally tries to |
802 | efficiently separate the entries of directory C<$path> into two sets of |
931 | efficiently separate the entries of directory C<$path> into two sets of |
803 | names, directories you can recurse into (directories), and ones you cannot |
932 | names, directories you can recurse into (directories), and ones you cannot |
804 | recurse into (everything else, including symlinks to directories). |
933 | recurse into (everything else, including symlinks to directories). |
… | |
… | |
835 | Then entries will be sorted into likely directories a non-initial dot |
964 | Then entries will be sorted into likely directories a non-initial dot |
836 | currently) and likely non-directories (see C<aio_readdirx>). Then every |
965 | currently) and likely non-directories (see C<aio_readdirx>). Then every |
837 | entry plus an appended C</.> will be C<stat>'ed, likely directories first, |
966 | entry plus an appended C</.> will be C<stat>'ed, likely directories first, |
838 | in order of their inode numbers. If that succeeds, it assumes that the |
967 | in order of their inode numbers. If that succeeds, it assumes that the |
839 | entry is a directory or a symlink to directory (which will be checked |
968 | entry is a directory or a symlink to directory (which will be checked |
840 | seperately). This is often faster than stat'ing the entry itself because |
969 | separately). This is often faster than stat'ing the entry itself because |
841 | filesystems might detect the type of the entry without reading the inode |
970 | filesystems might detect the type of the entry without reading the inode |
842 | data (e.g. ext2fs filetype feature), even on systems that cannot return |
971 | data (e.g. ext2fs filetype feature), even on systems that cannot return |
843 | the filetype information on readdir. |
972 | the filetype information on readdir. |
844 | |
973 | |
845 | If the known number of directories (link count - 2) has been reached, the |
974 | If the known number of directories (link count - 2) has been reached, the |
… | |
… | |
861 | |
990 | |
862 | my $grp = aio_group $cb; |
991 | my $grp = aio_group $cb; |
863 | |
992 | |
864 | $maxreq = 4 if $maxreq <= 0; |
993 | $maxreq = 4 if $maxreq <= 0; |
865 | |
994 | |
866 | # stat once |
995 | # get a wd object |
867 | aioreq_pri $pri; |
996 | aioreq_pri $pri; |
868 | add $grp aio_stat $path, sub { |
997 | add $grp aio_wd $path, sub { |
|
|
998 | $_[0] |
869 | return $grp->result () if $_[0]; |
999 | or return $grp->result (); |
870 | my $now = time; |
|
|
871 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
|
|
872 | |
1000 | |
873 | # read the directory entries |
1001 | my $wd = [shift, "."]; |
|
|
1002 | |
|
|
1003 | # stat once |
874 | aioreq_pri $pri; |
1004 | aioreq_pri $pri; |
875 | add $grp aio_readdirx $path, READDIR_DIRS_FIRST, sub { |
1005 | add $grp aio_stat $wd, sub { |
876 | my $entries = shift |
|
|
877 | or return $grp->result (); |
1006 | return $grp->result () if $_[0]; |
|
|
1007 | my $now = time; |
|
|
1008 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
878 | |
1009 | |
879 | # stat the dir another time |
1010 | # read the directory entries |
880 | aioreq_pri $pri; |
1011 | aioreq_pri $pri; |
|
|
1012 | add $grp aio_readdirx $wd, READDIR_DIRS_FIRST, sub { |
|
|
1013 | my $entries = shift |
|
|
1014 | or return $grp->result (); |
|
|
1015 | |
|
|
1016 | # stat the dir another time |
|
|
1017 | aioreq_pri $pri; |
881 | add $grp aio_stat $path, sub { |
1018 | add $grp aio_stat $wd, sub { |
882 | my $hash2 = join ":", (stat _)[0,1,3,7,9]; |
1019 | my $hash2 = join ":", (stat _)[0,1,3,7,9]; |
883 | |
1020 | |
884 | my $ndirs; |
1021 | my $ndirs; |
885 | |
1022 | |
886 | # take the slow route if anything looks fishy |
1023 | # take the slow route if anything looks fishy |
887 | if ($hash1 ne $hash2 or (stat _)[9] == $now) { |
1024 | if ($hash1 ne $hash2 or (stat _)[9] == $now) { |
888 | $ndirs = -1; |
1025 | $ndirs = -1; |
889 | } else { |
1026 | } else { |
890 | # if nlink == 2, we are finished |
1027 | # if nlink == 2, we are finished |
891 | # for non-posix-fs's, we rely on nlink < 2 |
1028 | # for non-posix-fs's, we rely on nlink < 2 |
892 | $ndirs = (stat _)[3] - 2 |
1029 | $ndirs = (stat _)[3] - 2 |
893 | or return $grp->result ([], $entries); |
1030 | or return $grp->result ([], $entries); |
894 | } |
1031 | } |
895 | |
1032 | |
896 | my (@dirs, @nondirs); |
1033 | my (@dirs, @nondirs); |
897 | |
1034 | |
898 | my $statgrp = add $grp aio_group sub { |
1035 | my $statgrp = add $grp aio_group sub { |
899 | $grp->result (\@dirs, \@nondirs); |
1036 | $grp->result (\@dirs, \@nondirs); |
900 | }; |
1037 | }; |
901 | |
1038 | |
902 | limit $statgrp $maxreq; |
1039 | limit $statgrp $maxreq; |
903 | feed $statgrp sub { |
1040 | feed $statgrp sub { |
904 | return unless @$entries; |
1041 | return unless @$entries; |
905 | my $entry = shift @$entries; |
1042 | my $entry = shift @$entries; |
906 | |
1043 | |
907 | aioreq_pri $pri; |
1044 | aioreq_pri $pri; |
|
|
1045 | $wd->[1] = "$entry/."; |
908 | add $statgrp aio_stat "$path/$entry/.", sub { |
1046 | add $statgrp aio_stat $wd, sub { |
909 | if ($_[0] < 0) { |
1047 | if ($_[0] < 0) { |
910 | push @nondirs, $entry; |
1048 | push @nondirs, $entry; |
911 | } else { |
1049 | } else { |
912 | # need to check for real directory |
1050 | # need to check for real directory |
913 | aioreq_pri $pri; |
1051 | aioreq_pri $pri; |
|
|
1052 | $wd->[1] = $entry; |
914 | add $statgrp aio_lstat "$path/$entry", sub { |
1053 | add $statgrp aio_lstat $wd, sub { |
915 | if (-d _) { |
1054 | if (-d _) { |
916 | push @dirs, $entry; |
1055 | push @dirs, $entry; |
917 | |
1056 | |
918 | unless (--$ndirs) { |
1057 | unless (--$ndirs) { |
919 | push @nondirs, @$entries; |
1058 | push @nondirs, @$entries; |
920 | feed $statgrp; |
1059 | feed $statgrp; |
|
|
1060 | } |
|
|
1061 | } else { |
|
|
1062 | push @nondirs, $entry; |
921 | } |
1063 | } |
922 | } else { |
|
|
923 | push @nondirs, $entry; |
|
|
924 | } |
1064 | } |
925 | } |
1065 | } |
926 | } |
1066 | }; |
927 | }; |
1067 | }; |
928 | }; |
1068 | }; |
929 | }; |
1069 | }; |
930 | }; |
1070 | }; |
931 | }; |
1071 | }; |
932 | |
1072 | |
933 | $grp |
1073 | $grp |
934 | } |
1074 | } |
935 | |
1075 | |
936 | =item aio_rmtree $path, $callback->($status) |
1076 | =item aio_rmtree $pathname, $callback->($status) |
937 | |
1077 | |
938 | Delete a directory tree starting (and including) C<$path>, return the |
1078 | Delete a directory tree starting (and including) C<$path>, return the |
939 | status of the final C<rmdir> only. This is a composite request that |
1079 | status of the final C<rmdir> only. This is a composite request that |
940 | uses C<aio_scandir> to recurse into and rmdir directories, and unlink |
1080 | uses C<aio_scandir> to recurse into and rmdir directories, and unlink |
941 | everything else. |
1081 | everything else. |
… | |
… | |
983 | callback with the fdatasync result code. |
1123 | callback with the fdatasync result code. |
984 | |
1124 | |
985 | If this call isn't available because your OS lacks it or it couldn't be |
1125 | If this call isn't available because your OS lacks it or it couldn't be |
986 | detected, it will be emulated by calling C<fsync> instead. |
1126 | detected, it will be emulated by calling C<fsync> instead. |
987 | |
1127 | |
|
|
1128 | =item aio_syncfs $fh, $callback->($status) |
|
|
1129 | |
|
|
1130 | Asynchronously call the syncfs syscall to sync the filesystem associated |
|
|
1131 | to the given filehandle and call the callback with the syncfs result |
|
|
1132 | code. If syncfs is not available, calls sync(), but returns C<-1> and sets |
|
|
1133 | errno to C<ENOSYS> nevertheless. |
|
|
1134 | |
988 | =item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status) |
1135 | =item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status) |
989 | |
1136 | |
990 | Sync the data portion of the file specified by C<$offset> and C<$length> |
1137 | Sync the data portion of the file specified by C<$offset> and C<$length> |
991 | to disk (but NOT the metadata), by calling the Linux-specific |
1138 | to disk (but NOT the metadata), by calling the Linux-specific |
992 | sync_file_range call. If sync_file_range is not available or it returns |
1139 | sync_file_range call. If sync_file_range is not available or it returns |
… | |
… | |
995 | C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>, |
1142 | C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>, |
996 | C<IO::AIO::SYNC_FILE_RANGE_WRITE> and |
1143 | C<IO::AIO::SYNC_FILE_RANGE_WRITE> and |
997 | C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range |
1144 | C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range |
998 | manpage for details. |
1145 | manpage for details. |
999 | |
1146 | |
1000 | =item aio_pathsync $path, $callback->($status) |
1147 | =item aio_pathsync $pathname, $callback->($status) |
1001 | |
1148 | |
1002 | This request tries to open, fsync and close the given path. This is a |
1149 | This request tries to open, fsync and close the given path. This is a |
1003 | composite request intended to sync directories after directory operations |
1150 | composite request intended to sync directories after directory operations |
1004 | (E.g. rename). This might not work on all operating systems or have any |
1151 | (E.g. rename). This might not work on all operating systems or have any |
1005 | specific effect, but usually it makes sure that directory changes get |
1152 | specific effect, but usually it makes sure that directory changes get |
… | |
… | |
1039 | } |
1186 | } |
1040 | |
1187 | |
1041 | =item aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status) |
1188 | =item aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status) |
1042 | |
1189 | |
1043 | This is a rather advanced IO::AIO call, which only works on mmap(2)ed |
1190 | This is a rather advanced IO::AIO call, which only works on mmap(2)ed |
1044 | scalars (see the L<Sys::Mmap> or L<Mmap> modules for details on this, note |
1191 | scalars (see the C<IO::AIO::mmap> function, although it also works on data |
|
|
1192 | scalars managed by the L<Sys::Mmap> or L<Mmap> modules, note that the |
1045 | that the scalar must only be modified in-place while an aio operation is |
1193 | scalar must only be modified in-place while an aio operation is pending on |
1046 | pending on it). |
1194 | it). |
1047 | |
1195 | |
1048 | It calls the C<msync> function of your OS, if available, with the memory |
1196 | It calls the C<msync> function of your OS, if available, with the memory |
1049 | area starting at C<$offset> in the string and ending C<$length> bytes |
1197 | area starting at C<$offset> in the string and ending C<$length> bytes |
1050 | later. If C<$length> is negative, counts from the end, and if C<$length> |
1198 | later. If C<$length> is negative, counts from the end, and if C<$length> |
1051 | is C<undef>, then it goes till the end of the string. The flags can be |
1199 | is C<undef>, then it goes till the end of the string. The flags can be |
… | |
… | |
1062 | as for C<aio_msync>, above, except for flags, which must be either |
1210 | as for C<aio_msync>, above, except for flags, which must be either |
1063 | C<0> (which reads all pages and ensures they are instantiated) or |
1211 | C<0> (which reads all pages and ensures they are instantiated) or |
1064 | C<IO::AIO::MT_MODIFY>, which modifies the memory page s(by reading and |
1212 | C<IO::AIO::MT_MODIFY>, which modifies the memory page s(by reading and |
1065 | writing an octet from it, which dirties the page). |
1213 | writing an octet from it, which dirties the page). |
1066 | |
1214 | |
|
|
1215 | =item aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status) |
|
|
1216 | |
|
|
1217 | This is a rather advanced IO::AIO call, which works best on mmap(2)ed |
|
|
1218 | scalars. |
|
|
1219 | |
|
|
1220 | It reads in all the pages of the underlying storage into memory (if any) |
|
|
1221 | and locks them, so they are not getting swapped/paged out or removed. |
|
|
1222 | |
|
|
1223 | If C<$length> is undefined, then the scalar will be locked till the end. |
|
|
1224 | |
|
|
1225 | On systems that do not implement C<mlock>, this function returns C<-1> |
|
|
1226 | and sets errno to C<ENOSYS>. |
|
|
1227 | |
|
|
1228 | Note that the corresponding C<munlock> is synchronous and is |
|
|
1229 | documented under L<MISCELLANEOUS FUNCTIONS>. |
|
|
1230 | |
|
|
1231 | Example: open a file, mmap and mlock it - both will be undone when |
|
|
1232 | C<$data> gets destroyed. |
|
|
1233 | |
|
|
1234 | open my $fh, "<", $path or die "$path: $!"; |
|
|
1235 | my $data; |
|
|
1236 | IO::AIO::mmap $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh; |
|
|
1237 | aio_mlock $data; # mlock in background |
|
|
1238 | |
|
|
1239 | =item aio_mlockall $flags, $callback->($status) |
|
|
1240 | |
|
|
1241 | Calls the C<mlockall> function with the given C<$flags> (a combination of |
|
|
1242 | C<IO::AIO::MCL_CURRENT> and C<IO::AIO::MCL_FUTURE>). |
|
|
1243 | |
|
|
1244 | On systems that do not implement C<mlockall>, this function returns C<-1> |
|
|
1245 | and sets errno to C<ENOSYS>. |
|
|
1246 | |
|
|
1247 | Note that the corresponding C<munlockall> is synchronous and is |
|
|
1248 | documented under L<MISCELLANEOUS FUNCTIONS>. |
|
|
1249 | |
|
|
1250 | Example: asynchronously lock all current and future pages into memory. |
|
|
1251 | |
|
|
1252 | aio_mlockall IO::AIO::MCL_FUTURE; |
|
|
1253 | |
|
|
1254 | =item aio_fiemap $fh, $start, $length, $flags, $count, $cb->(\@extents) |
|
|
1255 | |
|
|
1256 | Queries the extents of the given file (by calling the Linux FIEMAP ioctl, |
|
|
1257 | see L<http://cvs.schmorp.de/IO-AIO/doc/fiemap.txt> for details). If the |
|
|
1258 | C<ioctl> is not available on your OS, then this rquiest will fail with |
|
|
1259 | C<ENOSYS>. |
|
|
1260 | |
|
|
1261 | C<$start> is the starting offset to query extents for, C<$length> is the |
|
|
1262 | size of the range to query - if it is C<undef>, then the whole file will |
|
|
1263 | be queried. |
|
|
1264 | |
|
|
1265 | C<$flags> is a combination of flags (C<IO::AIO::FIEMAP_FLAG_SYNC> or |
|
|
1266 | C<IO::AIO::FIEMAP_FLAG_XATTR> - C<IO::AIO::FIEMAP_FLAGS_COMPAT> is also |
|
|
1267 | exported), and is normally C<0> or C<IO::AIO::FIEMAP_FLAG_SYNC> to query |
|
|
1268 | the data portion. |
|
|
1269 | |
|
|
1270 | C<$count> is the maximum number of extent records to return. If it is |
|
|
1271 | C<undef>, then IO::AIO queries all extents of the file. As a very special |
|
|
1272 | case, if it is C<0>, then the callback receives the number of extents |
|
|
1273 | instead of the extents themselves. |
|
|
1274 | |
|
|
1275 | If an error occurs, the callback receives no arguments. The special |
|
|
1276 | C<errno> value C<IO::AIO::EBADR> is available to test for flag errors. |
|
|
1277 | |
|
|
1278 | Otherwise, the callback receives an array reference with extent |
|
|
1279 | structures. Each extent structure is an array reference itself, with the |
|
|
1280 | following members: |
|
|
1281 | |
|
|
1282 | [$logical, $physical, $length, $flags] |
|
|
1283 | |
|
|
1284 | Flags is any combination of the following flag values (typically either C<0> |
|
|
1285 | or C<IO::AIO::FIEMAP_EXTENT_LAST>): |
|
|
1286 | |
|
|
1287 | C<IO::AIO::FIEMAP_EXTENT_LAST>, C<IO::AIO::FIEMAP_EXTENT_UNKNOWN>, |
|
|
1288 | C<IO::AIO::FIEMAP_EXTENT_DELALLOC>, C<IO::AIO::FIEMAP_EXTENT_ENCODED>, |
|
|
1289 | C<IO::AIO::FIEMAP_EXTENT_DATA_ENCRYPTED>, C<IO::AIO::FIEMAP_EXTENT_NOT_ALIGNED>, |
|
|
1290 | C<IO::AIO::FIEMAP_EXTENT_DATA_INLINE>, C<IO::AIO::FIEMAP_EXTENT_DATA_TAIL>, |
|
|
1291 | C<IO::AIO::FIEMAP_EXTENT_UNWRITTEN>, C<IO::AIO::FIEMAP_EXTENT_MERGED> or |
|
|
1292 | C<IO::AIO::FIEMAP_EXTENT_SHARED>. |
|
|
1293 | |
1067 | =item aio_group $callback->(...) |
1294 | =item aio_group $callback->(...) |
1068 | |
1295 | |
1069 | This is a very special aio request: Instead of doing something, it is a |
1296 | This is a very special aio request: Instead of doing something, it is a |
1070 | container for other aio requests, which is useful if you want to bundle |
1297 | container for other aio requests, which is useful if you want to bundle |
1071 | many requests into a single, composite, request with a definite callback |
1298 | many requests into a single, composite, request with a definite callback |
… | |
… | |
1107 | like sleep and file handle readable/writable, the overhead this creates is |
1334 | like sleep and file handle readable/writable, the overhead this creates is |
1108 | immense (it blocks a thread for a long time) so do not use this function |
1335 | immense (it blocks a thread for a long time) so do not use this function |
1109 | except to put your application under artificial I/O pressure. |
1336 | except to put your application under artificial I/O pressure. |
1110 | |
1337 | |
1111 | =back |
1338 | =back |
|
|
1339 | |
|
|
1340 | |
|
|
1341 | =head2 IO::AIO::WD - multiple working directories |
|
|
1342 | |
|
|
1343 | Your process only has one current working directory, which is used by all |
|
|
1344 | threads. This makes it hard to use relative paths (some other component |
|
|
1345 | could call C<chdir> at any time, and it is hard to control when the path |
|
|
1346 | will be used by IO::AIO). |
|
|
1347 | |
|
|
1348 | One solution for this is to always use absolute paths. This usually works, |
|
|
1349 | but can be quite slow (the kernel has to walk the whole path on every |
|
|
1350 | access), and can also be a hassle to implement. |
|
|
1351 | |
|
|
1352 | Newer POSIX systems have a number of functions (openat, fdopendir, |
|
|
1353 | futimensat and so on) that make it possible to specify working directories |
|
|
1354 | per operation. |
|
|
1355 | |
|
|
1356 | For portability, and because the clowns who "designed", or shall I write, |
|
|
1357 | perpetrated this new interface were obviously half-drunk, this abstraction |
|
|
1358 | cannot be perfect, though. |
|
|
1359 | |
|
|
1360 | IO::AIO allows you to convert directory paths into a so-called IO::AIO::WD |
|
|
1361 | object. This object stores the canonicalised, absolute version of the |
|
|
1362 | path, and on systems that allow it, also a directory file descriptor. |
|
|
1363 | |
|
|
1364 | Everywhere where a pathname is accepted by IO::AIO (e.g. in C<aio_stat> |
|
|
1365 | or C<aio_unlink>), one can specify an array reference with an IO::AIO::WD |
|
|
1366 | object and a pathname instead (or the IO::AIO::WD object alone, which |
|
|
1367 | gets interpreted as C<[$wd, "."]>). If the pathname is absolute, the |
|
|
1368 | IO::AIO::WD object is ignored, otherwise the pathname is resolved relative |
|
|
1369 | to that IO::AIO::WD object. |
|
|
1370 | |
|
|
1371 | For example, to get a wd object for F</etc> and then stat F<passwd> |
|
|
1372 | inside, you would write: |
|
|
1373 | |
|
|
1374 | aio_wd "/etc", sub { |
|
|
1375 | my $etcdir = shift; |
|
|
1376 | |
|
|
1377 | # although $etcdir can be undef on error, there is generally no reason |
|
|
1378 | # to check for errors here, as aio_stat will fail with ENOENT |
|
|
1379 | # when $etcdir is undef. |
|
|
1380 | |
|
|
1381 | aio_stat [$etcdir, "passwd"], sub { |
|
|
1382 | # yay |
|
|
1383 | }; |
|
|
1384 | }; |
|
|
1385 | |
|
|
1386 | That C<aio_wd> is a request and not a normal function shows that creating |
|
|
1387 | an IO::AIO::WD object is itself a potentially blocking operation, which is |
|
|
1388 | why it is done asynchronously. |
|
|
1389 | |
|
|
1390 | To stat the directory obtained with C<aio_wd> above, one could write |
|
|
1391 | either of the following three request calls: |
|
|
1392 | |
|
|
1393 | aio_lstat "/etc" , sub { ... # pathname as normal string |
|
|
1394 | aio_lstat [$wd, "."], sub { ... # "." relative to $wd (i.e. $wd itself) |
|
|
1395 | aio_lstat $wd , sub { ... # shorthand for the previous |
|
|
1396 | |
|
|
1397 | As with normal pathnames, IO::AIO keeps a copy of the working directory |
|
|
1398 | object and the pathname string, so you could write the following without |
|
|
1399 | causing any issues due to C<$path> getting reused: |
|
|
1400 | |
|
|
1401 | my $path = [$wd, undef]; |
|
|
1402 | |
|
|
1403 | for my $name (qw(abc def ghi)) { |
|
|
1404 | $path->[1] = $name; |
|
|
1405 | aio_stat $path, sub { |
|
|
1406 | # ... |
|
|
1407 | }; |
|
|
1408 | } |
|
|
1409 | |
|
|
1410 | There are some caveats: when directories get renamed (or deleted), the |
|
|
1411 | pathname string doesn't change, so will point to the new directory (or |
|
|
1412 | nowhere at all), while the directory fd, if available on the system, |
|
|
1413 | will still point to the original directory. Most functions accepting a |
|
|
1414 | pathname will use the directory fd on newer systems, and the string on |
|
|
1415 | older systems. Some functions (such as realpath) will always rely on the |
|
|
1416 | string form of the pathname. |
|
|
1417 | |
|
|
1418 | So this fucntionality is mainly useful to get some protection against |
|
|
1419 | C<chdir>, to easily get an absolute path out of a relative path for future |
|
|
1420 | reference, and to speed up doing many operations in the same directory |
|
|
1421 | (e.g. when stat'ing all files in a directory). |
|
|
1422 | |
|
|
1423 | The following functions implement this working directory abstraction: |
|
|
1424 | |
|
|
1425 | =over 4 |
|
|
1426 | |
|
|
1427 | =item aio_wd $pathname, $callback->($wd) |
|
|
1428 | |
|
|
1429 | Asynchonously canonicalise the given pathname and convert it to an |
|
|
1430 | IO::AIO::WD object representing it. If possible and supported on the |
|
|
1431 | system, also open a directory fd to speed up pathname resolution relative |
|
|
1432 | to this working directory. |
|
|
1433 | |
|
|
1434 | If something goes wrong, then C<undef> is passwd to the callback instead |
|
|
1435 | of a working directory object and C<$!> is set appropriately. Since |
|
|
1436 | passing C<undef> as working directory component of a pathname fails the |
|
|
1437 | request with C<ENOENT>, there is often no need for error checking in the |
|
|
1438 | C<aio_wd> callback, as future requests using the value will fail in the |
|
|
1439 | expected way. |
|
|
1440 | |
|
|
1441 | If this call isn't available because your OS lacks it or it couldn't be |
|
|
1442 | detected, it will be emulated by calling C<fsync> instead. |
|
|
1443 | |
|
|
1444 | =item IO::AIO::CWD |
|
|
1445 | |
|
|
1446 | This is a compiletime constant (object) that represents the process |
|
|
1447 | current working directory. |
|
|
1448 | |
|
|
1449 | Specifying this object as working directory object for a pathname is as |
|
|
1450 | if the pathname would be specified directly, without a directory object, |
|
|
1451 | e.g., these calls are functionally identical: |
|
|
1452 | |
|
|
1453 | aio_stat "somefile", sub { ... }; |
|
|
1454 | aio_stat [IO::AIO::CWD, "somefile"], sub { ... }; |
|
|
1455 | |
|
|
1456 | =back |
|
|
1457 | |
1112 | |
1458 | |
1113 | =head2 IO::AIO::REQ CLASS |
1459 | =head2 IO::AIO::REQ CLASS |
1114 | |
1460 | |
1115 | All non-aggregate C<aio_*> functions return an object of this class when |
1461 | All non-aggregate C<aio_*> functions return an object of this class when |
1116 | called in non-void context. |
1462 | called in non-void context. |
… | |
… | |
1234 | |
1580 | |
1235 | Sets a feeder/generator on this group: every group can have an attached |
1581 | Sets a feeder/generator on this group: every group can have an attached |
1236 | generator that generates requests if idle. The idea behind this is that, |
1582 | generator that generates requests if idle. The idea behind this is that, |
1237 | although you could just queue as many requests as you want in a group, |
1583 | although you could just queue as many requests as you want in a group, |
1238 | this might starve other requests for a potentially long time. For example, |
1584 | this might starve other requests for a potentially long time. For example, |
1239 | C<aio_scandir> might generate hundreds of thousands C<aio_stat> requests, |
1585 | C<aio_scandir> might generate hundreds of thousands of C<aio_stat> |
1240 | delaying any later requests for a long time. |
1586 | requests, delaying any later requests for a long time. |
1241 | |
1587 | |
1242 | To avoid this, and allow incremental generation of requests, you can |
1588 | To avoid this, and allow incremental generation of requests, you can |
1243 | instead a group and set a feeder on it that generates those requests. The |
1589 | instead a group and set a feeder on it that generates those requests. The |
1244 | feed callback will be called whenever there are few enough (see C<limit>, |
1590 | feed callback will be called whenever there are few enough (see C<limit>, |
1245 | below) requests active in the group itself and is expected to queue more |
1591 | below) requests active in the group itself and is expected to queue more |
… | |
… | |
1294 | |
1640 | |
1295 | See C<poll_cb> for an example. |
1641 | See C<poll_cb> for an example. |
1296 | |
1642 | |
1297 | =item IO::AIO::poll_cb |
1643 | =item IO::AIO::poll_cb |
1298 | |
1644 | |
1299 | Process some outstanding events on the result pipe. You have to call this |
1645 | Process some outstanding events on the result pipe. You have to call |
1300 | regularly. Returns C<0> if all events could be processed, or C<-1> if it |
1646 | this regularly. Returns C<0> if all events could be processed (or there |
1301 | returned earlier for whatever reason. Returns immediately when no events |
1647 | were no events to process), or C<-1> if it returned earlier for whatever |
1302 | are outstanding. The amount of events processed depends on the settings of |
1648 | reason. Returns immediately when no events are outstanding. The amount of |
1303 | C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>. |
1649 | events processed depends on the settings of C<IO::AIO::max_poll_req> and |
|
|
1650 | C<IO::AIO::max_poll_time>. |
1304 | |
1651 | |
1305 | If not all requests were processed for whatever reason, the filehandle |
1652 | If not all requests were processed for whatever reason, the filehandle |
1306 | will still be ready when C<poll_cb> returns, so normally you don't have to |
1653 | will still be ready when C<poll_cb> returns, so normally you don't have to |
1307 | do anything special to have it called later. |
1654 | do anything special to have it called later. |
1308 | |
1655 | |
|
|
1656 | Apart from calling C<IO::AIO::poll_cb> when the event filehandle becomes |
|
|
1657 | ready, it can be beneficial to call this function from loops which submit |
|
|
1658 | a lot of requests, to make sure the results get processed when they become |
|
|
1659 | available and not just when the loop is finished and the event loop takes |
|
|
1660 | over again. This function returns very fast when there are no outstanding |
|
|
1661 | requests. |
|
|
1662 | |
1309 | Example: Install an Event watcher that automatically calls |
1663 | Example: Install an Event watcher that automatically calls |
1310 | IO::AIO::poll_cb with high priority (more examples can be found in the |
1664 | IO::AIO::poll_cb with high priority (more examples can be found in the |
1311 | SYNOPSIS section, at the top of this document): |
1665 | SYNOPSIS section, at the top of this document): |
1312 | |
1666 | |
1313 | Event->io (fd => IO::AIO::poll_fileno, |
1667 | Event->io (fd => IO::AIO::poll_fileno, |
1314 | poll => 'r', async => 1, |
1668 | poll => 'r', async => 1, |
1315 | cb => \&IO::AIO::poll_cb); |
1669 | cb => \&IO::AIO::poll_cb); |
|
|
1670 | |
|
|
1671 | =item IO::AIO::poll_wait |
|
|
1672 | |
|
|
1673 | If there are any outstanding requests and none of them in the result |
|
|
1674 | phase, wait till the result filehandle becomes ready for reading (simply |
|
|
1675 | does a C<select> on the filehandle. This is useful if you want to |
|
|
1676 | synchronously wait for some requests to finish). |
|
|
1677 | |
|
|
1678 | See C<nreqs> for an example. |
|
|
1679 | |
|
|
1680 | =item IO::AIO::poll |
|
|
1681 | |
|
|
1682 | Waits until some requests have been handled. |
|
|
1683 | |
|
|
1684 | Returns the number of requests processed, but is otherwise strictly |
|
|
1685 | equivalent to: |
|
|
1686 | |
|
|
1687 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
1688 | |
|
|
1689 | =item IO::AIO::flush |
|
|
1690 | |
|
|
1691 | Wait till all outstanding AIO requests have been handled. |
|
|
1692 | |
|
|
1693 | Strictly equivalent to: |
|
|
1694 | |
|
|
1695 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
1696 | while IO::AIO::nreqs; |
1316 | |
1697 | |
1317 | =item IO::AIO::max_poll_reqs $nreqs |
1698 | =item IO::AIO::max_poll_reqs $nreqs |
1318 | |
1699 | |
1319 | =item IO::AIO::max_poll_time $seconds |
1700 | =item IO::AIO::max_poll_time $seconds |
1320 | |
1701 | |
… | |
… | |
1345 | # use a low priority so other tasks have priority |
1726 | # use a low priority so other tasks have priority |
1346 | Event->io (fd => IO::AIO::poll_fileno, |
1727 | Event->io (fd => IO::AIO::poll_fileno, |
1347 | poll => 'r', nice => 1, |
1728 | poll => 'r', nice => 1, |
1348 | cb => &IO::AIO::poll_cb); |
1729 | cb => &IO::AIO::poll_cb); |
1349 | |
1730 | |
1350 | =item IO::AIO::poll_wait |
|
|
1351 | |
|
|
1352 | If there are any outstanding requests and none of them in the result |
|
|
1353 | phase, wait till the result filehandle becomes ready for reading (simply |
|
|
1354 | does a C<select> on the filehandle. This is useful if you want to |
|
|
1355 | synchronously wait for some requests to finish). |
|
|
1356 | |
|
|
1357 | See C<nreqs> for an example. |
|
|
1358 | |
|
|
1359 | =item IO::AIO::poll |
|
|
1360 | |
|
|
1361 | Waits until some requests have been handled. |
|
|
1362 | |
|
|
1363 | Returns the number of requests processed, but is otherwise strictly |
|
|
1364 | equivalent to: |
|
|
1365 | |
|
|
1366 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
1367 | |
|
|
1368 | =item IO::AIO::flush |
|
|
1369 | |
|
|
1370 | Wait till all outstanding AIO requests have been handled. |
|
|
1371 | |
|
|
1372 | Strictly equivalent to: |
|
|
1373 | |
|
|
1374 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
1375 | while IO::AIO::nreqs; |
|
|
1376 | |
|
|
1377 | =back |
1731 | =back |
1378 | |
1732 | |
1379 | =head3 CONTROLLING THE NUMBER OF THREADS |
1733 | =head3 CONTROLLING THE NUMBER OF THREADS |
1380 | |
1734 | |
1381 | =over |
1735 | =over |
… | |
… | |
1414 | |
1768 | |
1415 | Under normal circumstances you don't need to call this function. |
1769 | Under normal circumstances you don't need to call this function. |
1416 | |
1770 | |
1417 | =item IO::AIO::max_idle $nthreads |
1771 | =item IO::AIO::max_idle $nthreads |
1418 | |
1772 | |
1419 | Limit the number of threads (default: 4) that are allowed to idle (i.e., |
1773 | Limit the number of threads (default: 4) that are allowed to idle |
1420 | threads that did not get a request to process within 10 seconds). That |
1774 | (i.e., threads that did not get a request to process within the idle |
1421 | means if a thread becomes idle while C<$nthreads> other threads are also |
1775 | timeout (default: 10 seconds). That means if a thread becomes idle while |
1422 | idle, it will free its resources and exit. |
1776 | C<$nthreads> other threads are also idle, it will free its resources and |
|
|
1777 | exit. |
1423 | |
1778 | |
1424 | This is useful when you allow a large number of threads (e.g. 100 or 1000) |
1779 | This is useful when you allow a large number of threads (e.g. 100 or 1000) |
1425 | to allow for extremely high load situations, but want to free resources |
1780 | to allow for extremely high load situations, but want to free resources |
1426 | under normal circumstances (1000 threads can easily consume 30MB of RAM). |
1781 | under normal circumstances (1000 threads can easily consume 30MB of RAM). |
1427 | |
1782 | |
1428 | The default is probably ok in most situations, especially if thread |
1783 | The default is probably ok in most situations, especially if thread |
1429 | creation is fast. If thread creation is very slow on your system you might |
1784 | creation is fast. If thread creation is very slow on your system you might |
1430 | want to use larger values. |
1785 | want to use larger values. |
1431 | |
1786 | |
|
|
1787 | =item IO::AIO::idle_timeout $seconds |
|
|
1788 | |
|
|
1789 | Sets the minimum idle timeout (default 10) after which worker threads are |
|
|
1790 | allowed to exit. SEe C<IO::AIO::max_idle>. |
|
|
1791 | |
1432 | =item IO::AIO::max_outstanding $maxreqs |
1792 | =item IO::AIO::max_outstanding $maxreqs |
|
|
1793 | |
|
|
1794 | Sets the maximum number of outstanding requests to C<$nreqs>. If |
|
|
1795 | you do queue up more than this number of requests, the next call to |
|
|
1796 | C<IO::AIO::poll_cb> (and other functions calling C<poll_cb>, such as |
|
|
1797 | C<IO::AIO::flush> or C<IO::AIO::poll>) will block until the limit is no |
|
|
1798 | longer exceeded. |
|
|
1799 | |
|
|
1800 | In other words, this setting does not enforce a queue limit, but can be |
|
|
1801 | used to make poll functions block if the limit is exceeded. |
1433 | |
1802 | |
1434 | This is a very bad function to use in interactive programs because it |
1803 | This is a very bad function to use in interactive programs because it |
1435 | blocks, and a bad way to reduce concurrency because it is inexact: Better |
1804 | blocks, and a bad way to reduce concurrency because it is inexact: Better |
1436 | use an C<aio_group> together with a feed callback. |
1805 | use an C<aio_group> together with a feed callback. |
1437 | |
1806 | |
1438 | Sets the maximum number of outstanding requests to C<$nreqs>. If you |
1807 | It's main use is in scripts without an event loop - when you want to stat |
1439 | do queue up more than this number of requests, the next call to the |
1808 | a lot of files, you can write somehting like this: |
1440 | C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>) |
|
|
1441 | function will block until the limit is no longer exceeded. |
|
|
1442 | |
1809 | |
1443 | The default value is very large, so there is no practical limit on the |
1810 | IO::AIO::max_outstanding 32; |
1444 | number of outstanding requests. |
|
|
1445 | |
1811 | |
1446 | You can still queue as many requests as you want. Therefore, |
1812 | for my $path (...) { |
1447 | C<max_outstanding> is mainly useful in simple scripts (with low values) or |
1813 | aio_stat $path , ...; |
1448 | as a stop gap to shield against fatal memory overflow (with large values). |
1814 | IO::AIO::poll_cb; |
|
|
1815 | } |
|
|
1816 | |
|
|
1817 | IO::AIO::flush; |
|
|
1818 | |
|
|
1819 | The call to C<poll_cb> inside the loop will normally return instantly, but |
|
|
1820 | as soon as more thna C<32> reqeusts are in-flight, it will block until |
|
|
1821 | some requests have been handled. This keeps the loop from pushing a large |
|
|
1822 | number of C<aio_stat> requests onto the queue. |
|
|
1823 | |
|
|
1824 | The default value for C<max_outstanding> is very large, so there is no |
|
|
1825 | practical limit on the number of outstanding requests. |
1449 | |
1826 | |
1450 | =back |
1827 | =back |
1451 | |
1828 | |
1452 | =head3 STATISTICAL INFORMATION |
1829 | =head3 STATISTICAL INFORMATION |
1453 | |
1830 | |
… | |
… | |
1491 | |
1868 | |
1492 | Returns the number of bytes copied, or C<-1> on error. |
1869 | Returns the number of bytes copied, or C<-1> on error. |
1493 | |
1870 | |
1494 | =item IO::AIO::fadvise $fh, $offset, $len, $advice |
1871 | =item IO::AIO::fadvise $fh, $offset, $len, $advice |
1495 | |
1872 | |
1496 | Simply calls the C<posix_fadvise> function (see it's |
1873 | Simply calls the C<posix_fadvise> function (see its |
1497 | manpage for details). The following advice constants are |
1874 | manpage for details). The following advice constants are |
1498 | avaiable: C<IO::AIO::FADV_NORMAL>, C<IO::AIO::FADV_SEQUENTIAL>, |
1875 | available: C<IO::AIO::FADV_NORMAL>, C<IO::AIO::FADV_SEQUENTIAL>, |
1499 | C<IO::AIO::FADV_RANDOM>, C<IO::AIO::FADV_NOREUSE>, |
1876 | C<IO::AIO::FADV_RANDOM>, C<IO::AIO::FADV_NOREUSE>, |
1500 | C<IO::AIO::FADV_WILLNEED>, C<IO::AIO::FADV_DONTNEED>. |
1877 | C<IO::AIO::FADV_WILLNEED>, C<IO::AIO::FADV_DONTNEED>. |
1501 | |
1878 | |
1502 | On systems that do not implement C<posix_fadvise>, this function returns |
1879 | On systems that do not implement C<posix_fadvise>, this function returns |
1503 | ENOSYS, otherwise the return value of C<posix_fadvise>. |
1880 | ENOSYS, otherwise the return value of C<posix_fadvise>. |
1504 | |
1881 | |
|
|
1882 | =item IO::AIO::madvise $scalar, $offset, $len, $advice |
|
|
1883 | |
|
|
1884 | Simply calls the C<posix_madvise> function (see its |
|
|
1885 | manpage for details). The following advice constants are |
|
|
1886 | available: C<IO::AIO::MADV_NORMAL>, C<IO::AIO::MADV_SEQUENTIAL>, |
|
|
1887 | C<IO::AIO::MADV_RANDOM>, C<IO::AIO::MADV_WILLNEED>, C<IO::AIO::MADV_DONTNEED>. |
|
|
1888 | |
|
|
1889 | On systems that do not implement C<posix_madvise>, this function returns |
|
|
1890 | ENOSYS, otherwise the return value of C<posix_madvise>. |
|
|
1891 | |
|
|
1892 | =item IO::AIO::mprotect $scalar, $offset, $len, $protect |
|
|
1893 | |
|
|
1894 | Simply calls the C<mprotect> function on the preferably AIO::mmap'ed |
|
|
1895 | $scalar (see its manpage for details). The following protect |
|
|
1896 | constants are available: C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_READ>, |
|
|
1897 | C<IO::AIO::PROT_WRITE>, C<IO::AIO::PROT_EXEC>. |
|
|
1898 | |
|
|
1899 | On systems that do not implement C<mprotect>, this function returns |
|
|
1900 | ENOSYS, otherwise the return value of C<mprotect>. |
|
|
1901 | |
|
|
1902 | =item IO::AIO::mmap $scalar, $length, $prot, $flags, $fh[, $offset] |
|
|
1903 | |
|
|
1904 | Memory-maps a file (or anonymous memory range) and attaches it to the |
|
|
1905 | given C<$scalar>, which will act like a string scalar. |
|
|
1906 | |
|
|
1907 | The only operations allowed on the scalar are C<substr>/C<vec> that don't |
|
|
1908 | change the string length, and most read-only operations such as copying it |
|
|
1909 | or searching it with regexes and so on. |
|
|
1910 | |
|
|
1911 | Anything else is unsafe and will, at best, result in memory leaks. |
|
|
1912 | |
|
|
1913 | The memory map associated with the C<$scalar> is automatically removed |
|
|
1914 | when the C<$scalar> is destroyed, or when the C<IO::AIO::mmap> or |
|
|
1915 | C<IO::AIO::munmap> functions are called. |
|
|
1916 | |
|
|
1917 | This calls the C<mmap>(2) function internally. See your system's manual |
|
|
1918 | page for details on the C<$length>, C<$prot> and C<$flags> parameters. |
|
|
1919 | |
|
|
1920 | The C<$length> must be larger than zero and smaller than the actual |
|
|
1921 | filesize. |
|
|
1922 | |
|
|
1923 | C<$prot> is a combination of C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_EXEC>, |
|
|
1924 | C<IO::AIO::PROT_READ> and/or C<IO::AIO::PROT_WRITE>, |
|
|
1925 | |
|
|
1926 | C<$flags> can be a combination of C<IO::AIO::MAP_SHARED> or |
|
|
1927 | C<IO::AIO::MAP_PRIVATE>, or a number of system-specific flags (when |
|
|
1928 | not available, the are defined as 0): C<IO::AIO::MAP_ANONYMOUS> |
|
|
1929 | (which is set to C<MAP_ANON> if your system only provides this |
|
|
1930 | constant), C<IO::AIO::MAP_HUGETLB>, C<IO::AIO::MAP_LOCKED>, |
|
|
1931 | C<IO::AIO::MAP_NORESERVE>, C<IO::AIO::MAP_POPULATE> or |
|
|
1932 | C<IO::AIO::MAP_NONBLOCK> |
|
|
1933 | |
|
|
1934 | If C<$fh> is C<undef>, then a file descriptor of C<-1> is passed. |
|
|
1935 | |
|
|
1936 | C<$offset> is the offset from the start of the file - it generally must be |
|
|
1937 | a multiple of C<IO::AIO::PAGESIZE> and defaults to C<0>. |
|
|
1938 | |
|
|
1939 | Example: |
|
|
1940 | |
|
|
1941 | use Digest::MD5; |
|
|
1942 | use IO::AIO; |
|
|
1943 | |
|
|
1944 | open my $fh, "<verybigfile" |
|
|
1945 | or die "$!"; |
|
|
1946 | |
|
|
1947 | IO::AIO::mmap my $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh |
|
|
1948 | or die "verybigfile: $!"; |
|
|
1949 | |
|
|
1950 | my $fast_md5 = md5 $data; |
|
|
1951 | |
|
|
1952 | =item IO::AIO::munmap $scalar |
|
|
1953 | |
|
|
1954 | Removes a previous mmap and undefines the C<$scalar>. |
|
|
1955 | |
|
|
1956 | =item IO::AIO::munlock $scalar, $offset = 0, $length = undef |
|
|
1957 | |
|
|
1958 | Calls the C<munlock> function, undoing the effects of a previous |
|
|
1959 | C<aio_mlock> call (see its description for details). |
|
|
1960 | |
|
|
1961 | =item IO::AIO::munlockall |
|
|
1962 | |
|
|
1963 | Calls the C<munlockall> function. |
|
|
1964 | |
|
|
1965 | On systems that do not implement C<munlockall>, this function returns |
|
|
1966 | ENOSYS, otherwise the return value of C<munlockall>. |
|
|
1967 | |
1505 | =back |
1968 | =back |
1506 | |
1969 | |
1507 | =cut |
1970 | =cut |
1508 | |
1971 | |
1509 | min_parallel 8; |
1972 | min_parallel 8; |
1510 | |
1973 | |
1511 | END { flush } |
1974 | END { flush } |
1512 | |
1975 | |
1513 | 1; |
1976 | 1; |
1514 | |
1977 | |
|
|
1978 | =head1 EVENT LOOP INTEGRATION |
|
|
1979 | |
|
|
1980 | It is recommended to use L<AnyEvent::AIO> to integrate IO::AIO |
|
|
1981 | automatically into many event loops: |
|
|
1982 | |
|
|
1983 | # AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...) |
|
|
1984 | use AnyEvent::AIO; |
|
|
1985 | |
|
|
1986 | You can also integrate IO::AIO manually into many event loops, here are |
|
|
1987 | some examples of how to do this: |
|
|
1988 | |
|
|
1989 | # EV integration |
|
|
1990 | my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; |
|
|
1991 | |
|
|
1992 | # Event integration |
|
|
1993 | Event->io (fd => IO::AIO::poll_fileno, |
|
|
1994 | poll => 'r', |
|
|
1995 | cb => \&IO::AIO::poll_cb); |
|
|
1996 | |
|
|
1997 | # Glib/Gtk2 integration |
|
|
1998 | add_watch Glib::IO IO::AIO::poll_fileno, |
|
|
1999 | in => sub { IO::AIO::poll_cb; 1 }; |
|
|
2000 | |
|
|
2001 | # Tk integration |
|
|
2002 | Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "", |
|
|
2003 | readable => \&IO::AIO::poll_cb); |
|
|
2004 | |
|
|
2005 | # Danga::Socket integration |
|
|
2006 | Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => |
|
|
2007 | \&IO::AIO::poll_cb); |
|
|
2008 | |
1515 | =head2 FORK BEHAVIOUR |
2009 | =head2 FORK BEHAVIOUR |
1516 | |
2010 | |
1517 | This module should do "the right thing" when the process using it forks: |
2011 | Usage of pthreads in a program changes the semantics of fork |
|
|
2012 | considerably. Specifically, only async-safe functions can be called after |
|
|
2013 | fork. Perl doesn't know about this, so in general, you cannot call fork |
|
|
2014 | with defined behaviour in perl if pthreads are involved. IO::AIO uses |
|
|
2015 | pthreads, so this applies, but many other extensions and (for inexplicable |
|
|
2016 | reasons) perl itself often is linked against pthreads, so this limitation |
|
|
2017 | applies to quite a lot of perls. |
1518 | |
2018 | |
1519 | Before the fork, IO::AIO enters a quiescent state where no requests |
2019 | This module no longer tries to fight your OS, or POSIX. That means IO::AIO |
1520 | can be added in other threads and no results will be processed. After |
2020 | only works in the process that loaded it. Forking is fully supported, but |
1521 | the fork the parent simply leaves the quiescent state and continues |
2021 | using IO::AIO in the child is not. |
1522 | request/result processing, while the child frees the request/result queue |
|
|
1523 | (so that the requests started before the fork will only be handled in the |
|
|
1524 | parent). Threads will be started on demand until the limit set in the |
|
|
1525 | parent process has been reached again. |
|
|
1526 | |
2022 | |
1527 | In short: the parent will, after a short pause, continue as if fork had |
2023 | You might get around by not I<using> IO::AIO before (or after) |
1528 | not been called, while the child will act as if IO::AIO has not been used |
2024 | forking. You could also try to call the L<IO::AIO::reinit> function in the |
1529 | yet. |
2025 | child: |
|
|
2026 | |
|
|
2027 | =over 4 |
|
|
2028 | |
|
|
2029 | =item IO::AIO::reinit |
|
|
2030 | |
|
|
2031 | Abandons all current requests and I/O threads and simply reinitialises all |
|
|
2032 | data structures. This is not an operation supported by any standards, but |
|
|
2033 | happens to work on GNU/Linux and some newer BSD systems. |
|
|
2034 | |
|
|
2035 | The only reasonable use for this function is to call it after forking, if |
|
|
2036 | C<IO::AIO> was used in the parent. Calling it while IO::AIO is active in |
|
|
2037 | the process will result in undefined behaviour. Calling it at any time |
|
|
2038 | will also result in any undefined (by POSIX) behaviour. |
|
|
2039 | |
|
|
2040 | =back |
1530 | |
2041 | |
1531 | =head2 MEMORY USAGE |
2042 | =head2 MEMORY USAGE |
1532 | |
2043 | |
1533 | Per-request usage: |
2044 | Per-request usage: |
1534 | |
2045 | |