… | |
… | |
15 | |
15 | |
16 | aio_read $fh, 30000, 1024, $buffer, 0, sub { |
16 | aio_read $fh, 30000, 1024, $buffer, 0, sub { |
17 | $_[0] > 0 or die "read error: $!"; |
17 | $_[0] > 0 or die "read error: $!"; |
18 | }; |
18 | }; |
19 | |
19 | |
20 | # AnyEvent |
20 | # version 2+ has request and group objects |
|
|
21 | use IO::AIO 2; |
|
|
22 | |
|
|
23 | aioreq_pri 4; # give next request a very high priority |
|
|
24 | my $req = aio_unlink "/tmp/file", sub { }; |
|
|
25 | $req->cancel; # cancel request if still in queue |
|
|
26 | |
|
|
27 | my $grp = aio_group sub { print "all stats done\n" }; |
|
|
28 | add $grp aio_stat "..." for ...; |
|
|
29 | |
|
|
30 | # AnyEvent integration |
21 | open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!"; |
31 | open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!"; |
22 | my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb }); |
32 | my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb }); |
23 | |
33 | |
24 | # Event |
34 | # Event integration |
25 | Event->io (fd => IO::AIO::poll_fileno, |
35 | Event->io (fd => IO::AIO::poll_fileno, |
26 | poll => 'r', |
36 | poll => 'r', |
27 | cb => \&IO::AIO::poll_cb); |
37 | cb => \&IO::AIO::poll_cb); |
28 | |
38 | |
29 | # Glib/Gtk2 |
39 | # Glib/Gtk2 integration |
30 | add_watch Glib::IO IO::AIO::poll_fileno, |
40 | add_watch Glib::IO IO::AIO::poll_fileno, |
31 | in => sub { IO::AIO::poll_cb; 1 }; |
41 | in => sub { IO::AIO::poll_cb; 1 }; |
32 | |
42 | |
33 | # Tk |
43 | # Tk integration |
34 | Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "", |
44 | Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "", |
35 | readable => \&IO::AIO::poll_cb); |
45 | readable => \&IO::AIO::poll_cb); |
36 | |
46 | |
37 | # Danga::Socket |
47 | # Danga::Socket integration |
38 | Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => |
48 | Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => |
39 | \&IO::AIO::poll_cb); |
49 | \&IO::AIO::poll_cb); |
40 | |
50 | |
41 | |
|
|
42 | =head1 DESCRIPTION |
51 | =head1 DESCRIPTION |
43 | |
52 | |
44 | This module implements asynchronous I/O using whatever means your |
53 | This module implements asynchronous I/O using whatever means your |
45 | operating system supports. |
54 | operating system supports. |
46 | |
55 | |
|
|
56 | Asynchronous means that operations that can normally block your program |
|
|
57 | (e.g. reading from disk) will be done asynchronously: the operation |
|
|
58 | will still block, but you can do something else in the meantime. This |
|
|
59 | is extremely useful for programs that need to stay interactive even |
|
|
60 | when doing heavy I/O (GUI programs, high performance network servers |
|
|
61 | etc.), but can also be used to easily do operations in parallel that are |
|
|
62 | normally done sequentially, e.g. stat'ing many files, which is much faster |
|
|
63 | on a RAID volume or over NFS when you do a number of stat operations |
|
|
64 | concurrently. |
|
|
65 | |
|
|
66 | While this works on all types of file descriptors (for example sockets), |
|
|
67 | using these functions on file descriptors that support nonblocking |
|
|
68 | operation (again, sockets, pipes etc.) is very inefficient. Use an event |
|
|
69 | loop for that (such as the L<Event|Event> module): IO::AIO will naturally |
|
|
70 | fit into such an event loop itself. |
|
|
71 | |
47 | Currently, a number of threads are started that execute your read/writes |
72 | In this version, a number of threads are started that execute your |
48 | and signal their completion. You don't need thread support in your libc or |
73 | requests and signal their completion. You don't need thread support |
49 | perl, and the threads created by this module will not be visible to the |
74 | in perl, and the threads created by this module will not be visible |
50 | pthreads library. In the future, this module might make use of the native |
75 | to perl. In the future, this module might make use of the native aio |
51 | aio functions available on many operating systems. However, they are often |
76 | functions available on many operating systems. However, they are often |
52 | not well-supported (Linux doesn't allow them on normal files currently, |
77 | not well-supported or restricted (GNU/Linux doesn't allow them on normal |
53 | for example), and they would only support aio_read and aio_write, so the |
78 | files currently, for example), and they would only support aio_read and |
54 | remaining functionality would have to be implemented using threads anyway. |
79 | aio_write, so the remaining functionality would have to be implemented |
|
|
80 | using threads anyway. |
55 | |
81 | |
56 | Although the module will work with in the presence of other threads, it is |
82 | Although the module will work with in the presence of other (Perl-) |
57 | currently not reentrant, so use appropriate locking yourself, always call |
83 | threads, it is currently not reentrant in any way, so use appropriate |
58 | C<poll_cb> from within the same thread, or never call C<poll_cb> (or other |
84 | locking yourself, always call C<poll_cb> from within the same thread, or |
59 | C<aio_> functions) recursively. |
85 | never call C<poll_cb> (or other C<aio_> functions) recursively. |
|
|
86 | |
|
|
87 | =head2 EXAMPLE |
|
|
88 | |
|
|
89 | This is a simple example that uses the Event module and loads |
|
|
90 | F</etc/passwd> asynchronously: |
|
|
91 | |
|
|
92 | use Fcntl; |
|
|
93 | use Event; |
|
|
94 | use IO::AIO; |
|
|
95 | |
|
|
96 | # register the IO::AIO callback with Event |
|
|
97 | Event->io (fd => IO::AIO::poll_fileno, |
|
|
98 | poll => 'r', |
|
|
99 | cb => \&IO::AIO::poll_cb); |
|
|
100 | |
|
|
101 | # queue the request to open /etc/passwd |
|
|
102 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
|
|
103 | my $fh = $_[0] |
|
|
104 | or die "error while opening: $!"; |
|
|
105 | |
|
|
106 | # stat'ing filehandles is generally non-blocking |
|
|
107 | my $size = -s $fh; |
|
|
108 | |
|
|
109 | # queue a request to read the file |
|
|
110 | my $contents; |
|
|
111 | aio_read $fh, 0, $size, $contents, 0, sub { |
|
|
112 | $_[0] == $size |
|
|
113 | or die "short read: $!"; |
|
|
114 | |
|
|
115 | close $fh; |
|
|
116 | |
|
|
117 | # file contents now in $contents |
|
|
118 | print $contents; |
|
|
119 | |
|
|
120 | # exit event loop and program |
|
|
121 | Event::unloop; |
|
|
122 | }; |
|
|
123 | }; |
|
|
124 | |
|
|
125 | # possibly queue up other requests, or open GUI windows, |
|
|
126 | # check for sockets etc. etc. |
|
|
127 | |
|
|
128 | # process events as long as there are some: |
|
|
129 | Event::loop; |
|
|
130 | |
|
|
131 | =head1 REQUEST ANATOMY AND LIFETIME |
|
|
132 | |
|
|
133 | Every C<aio_*> function creates a request. which is a C data structure not |
|
|
134 | directly visible to Perl. |
|
|
135 | |
|
|
136 | If called in non-void context, every request function returns a Perl |
|
|
137 | object representing the request. In void context, nothing is returned, |
|
|
138 | which saves a bit of memory. |
|
|
139 | |
|
|
140 | The perl object is a fairly standard ref-to-hash object. The hash contents |
|
|
141 | are not used by IO::AIO so you are free to store anything you like in it. |
|
|
142 | |
|
|
143 | During their existance, aio requests travel through the following states, |
|
|
144 | in order: |
|
|
145 | |
|
|
146 | =over 4 |
|
|
147 | |
|
|
148 | =item ready |
|
|
149 | |
|
|
150 | Immediately after a request is created it is put into the ready state, |
|
|
151 | waiting for a thread to execute it. |
|
|
152 | |
|
|
153 | =item execute |
|
|
154 | |
|
|
155 | A thread has accepted the request for processing and is currently |
|
|
156 | executing it (e.g. blocking in read). |
|
|
157 | |
|
|
158 | =item pending |
|
|
159 | |
|
|
160 | The request has been executed and is waiting for result processing. |
|
|
161 | |
|
|
162 | While request submission and execution is fully asynchronous, result |
|
|
163 | processing is not and relies on the perl interpreter calling C<poll_cb> |
|
|
164 | (or another function with the same effect). |
|
|
165 | |
|
|
166 | =item result |
|
|
167 | |
|
|
168 | The request results are processed synchronously by C<poll_cb>. |
|
|
169 | |
|
|
170 | The C<poll_cb> function will process all outstanding aio requests by |
|
|
171 | calling their callbacks, freeing memory associated with them and managing |
|
|
172 | any groups they are contained in. |
|
|
173 | |
|
|
174 | =item done |
|
|
175 | |
|
|
176 | Request has reached the end of its lifetime and holds no resources anymore |
|
|
177 | (except possibly for the Perl object, but its connection to the actual |
|
|
178 | aio request is severed and calling its methods will either do nothing or |
|
|
179 | result in a runtime error). |
|
|
180 | |
|
|
181 | =back |
60 | |
182 | |
61 | =cut |
183 | =cut |
62 | |
184 | |
63 | package IO::AIO; |
185 | package IO::AIO; |
64 | |
186 | |
65 | no warnings; |
187 | no warnings; |
|
|
188 | use strict 'vars'; |
66 | |
189 | |
67 | use base 'Exporter'; |
190 | use base 'Exporter'; |
68 | |
191 | |
69 | use Fcntl (); |
|
|
70 | |
|
|
71 | BEGIN { |
192 | BEGIN { |
72 | $VERSION = '1.71'; |
193 | our $VERSION = '2.1'; |
73 | |
194 | |
74 | @EXPORT = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat |
195 | our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat |
75 | aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink |
196 | aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink |
76 | aio_fsync aio_fdatasync aio_readahead); |
197 | aio_fsync aio_fdatasync aio_readahead aio_rename aio_link aio_move |
77 | @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel |
198 | aio_copy aio_group aio_nop aio_mknod); |
78 | max_outstanding nreqs); |
199 | our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice)); |
|
|
200 | our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush |
|
|
201 | min_parallel max_parallel max_idle |
|
|
202 | nreqs nready npending nthreads |
|
|
203 | max_poll_time max_poll_reqs); |
|
|
204 | |
|
|
205 | @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; |
79 | |
206 | |
80 | require XSLoader; |
207 | require XSLoader; |
81 | XSLoader::load IO::AIO, $VERSION; |
208 | XSLoader::load ("IO::AIO", $VERSION); |
82 | } |
209 | } |
83 | |
210 | |
84 | =head1 FUNCTIONS |
211 | =head1 FUNCTIONS |
85 | |
212 | |
86 | =head2 AIO FUNCTIONS |
213 | =head2 AIO REQUEST FUNCTIONS |
87 | |
214 | |
88 | All the C<aio_*> calls are more or less thin wrappers around the syscall |
215 | All the C<aio_*> calls are more or less thin wrappers around the syscall |
89 | with the same name (sans C<aio_>). The arguments are similar or identical, |
216 | with the same name (sans C<aio_>). The arguments are similar or identical, |
90 | and they all accept an additional (and optional) C<$callback> argument |
217 | and they all accept an additional (and optional) C<$callback> argument |
91 | which must be a code reference. This code reference will get called with |
218 | which must be a code reference. This code reference will get called with |
… | |
… | |
94 | syscall has been executed asynchronously. |
221 | syscall has been executed asynchronously. |
95 | |
222 | |
96 | All functions expecting a filehandle keep a copy of the filehandle |
223 | All functions expecting a filehandle keep a copy of the filehandle |
97 | internally until the request has finished. |
224 | internally until the request has finished. |
98 | |
225 | |
|
|
226 | All functions return request objects of type L<IO::AIO::REQ> that allow |
|
|
227 | further manipulation of those requests while they are in-flight. |
|
|
228 | |
99 | The pathnames you pass to these routines I<must> be absolute and |
229 | The pathnames you pass to these routines I<must> be absolute and |
100 | encoded in byte form. The reason for the former is that at the time the |
230 | encoded as octets. The reason for the former is that at the time the |
101 | request is being executed, the current working directory could have |
231 | request is being executed, the current working directory could have |
102 | changed. Alternatively, you can make sure that you never change the |
232 | changed. Alternatively, you can make sure that you never change the |
103 | current working directory. |
233 | current working directory anywhere in the program and then use relative |
|
|
234 | paths. |
104 | |
235 | |
105 | To encode pathnames to byte form, either make sure you either: a) |
236 | To encode pathnames as octets, either make sure you either: a) always pass |
106 | always pass in filenames you got from outside (command line, readdir |
237 | in filenames you got from outside (command line, readdir etc.) without |
107 | etc.), b) are ASCII or ISO 8859-1, c) use the Encode module and encode |
238 | tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module and encode |
108 | your pathnames to the locale (or other) encoding in effect in the user |
239 | your pathnames to the locale (or other) encoding in effect in the user |
109 | environment, d) use Glib::filename_from_unicode on unicode filenames or e) |
240 | environment, d) use Glib::filename_from_unicode on unicode filenames or e) |
110 | use something else. |
241 | use something else to ensure your scalar has the correct contents. |
|
|
242 | |
|
|
243 | This works, btw. independent of the internal UTF-8 bit, which IO::AIO |
|
|
244 | handles correctly wether it is set or not. |
111 | |
245 | |
112 | =over 4 |
246 | =over 4 |
|
|
247 | |
|
|
248 | =item $prev_pri = aioreq_pri [$pri] |
|
|
249 | |
|
|
250 | Returns the priority value that would be used for the next request and, if |
|
|
251 | C<$pri> is given, sets the priority for the next aio request. |
|
|
252 | |
|
|
253 | The default priority is C<0>, the minimum and maximum priorities are C<-4> |
|
|
254 | and C<4>, respectively. Requests with higher priority will be serviced |
|
|
255 | first. |
|
|
256 | |
|
|
257 | The priority will be reset to C<0> after each call to one of the C<aio_*> |
|
|
258 | functions. |
|
|
259 | |
|
|
260 | Example: open a file with low priority, then read something from it with |
|
|
261 | higher priority so the read request is serviced before other low priority |
|
|
262 | open requests (potentially spamming the cache): |
|
|
263 | |
|
|
264 | aioreq_pri -3; |
|
|
265 | aio_open ..., sub { |
|
|
266 | return unless $_[0]; |
|
|
267 | |
|
|
268 | aioreq_pri -2; |
|
|
269 | aio_read $_[0], ..., sub { |
|
|
270 | ... |
|
|
271 | }; |
|
|
272 | }; |
|
|
273 | |
|
|
274 | =item aioreq_nice $pri_adjust |
|
|
275 | |
|
|
276 | Similar to C<aioreq_pri>, but subtracts the given value from the current |
|
|
277 | priority, so the effect is cumulative. |
113 | |
278 | |
114 | =item aio_open $pathname, $flags, $mode, $callback->($fh) |
279 | =item aio_open $pathname, $flags, $mode, $callback->($fh) |
115 | |
280 | |
116 | Asynchronously open or create a file and call the callback with a newly |
281 | Asynchronously open or create a file and call the callback with a newly |
117 | created filehandle for the file. |
282 | created filehandle for the file. |
… | |
… | |
232 | =item aio_unlink $pathname, $callback->($status) |
397 | =item aio_unlink $pathname, $callback->($status) |
233 | |
398 | |
234 | Asynchronously unlink (delete) a file and call the callback with the |
399 | Asynchronously unlink (delete) a file and call the callback with the |
235 | result code. |
400 | result code. |
236 | |
401 | |
|
|
402 | =item aio_mknod $path, $mode, $dev, $callback->($status) |
|
|
403 | |
|
|
404 | [EXPERIMENTAL] |
|
|
405 | |
|
|
406 | Asynchronously create a device node (or fifo). See mknod(2). |
|
|
407 | |
|
|
408 | The only (POSIX-) portable way of calling this function is: |
|
|
409 | |
|
|
410 | aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ... |
|
|
411 | |
|
|
412 | =item aio_link $srcpath, $dstpath, $callback->($status) |
|
|
413 | |
|
|
414 | Asynchronously create a new link to the existing object at C<$srcpath> at |
|
|
415 | the path C<$dstpath> and call the callback with the result code. |
|
|
416 | |
|
|
417 | =item aio_symlink $srcpath, $dstpath, $callback->($status) |
|
|
418 | |
|
|
419 | Asynchronously create a new symbolic link to the existing object at C<$srcpath> at |
|
|
420 | the path C<$dstpath> and call the callback with the result code. |
|
|
421 | |
|
|
422 | =item aio_rename $srcpath, $dstpath, $callback->($status) |
|
|
423 | |
|
|
424 | Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as |
|
|
425 | rename(2) and call the callback with the result code. |
|
|
426 | |
237 | =item aio_rmdir $pathname, $callback->($status) |
427 | =item aio_rmdir $pathname, $callback->($status) |
238 | |
428 | |
239 | Asynchronously rmdir (delete) a directory and call the callback with the |
429 | Asynchronously rmdir (delete) a directory and call the callback with the |
240 | result code. |
430 | result code. |
241 | |
431 | |
242 | =item aio_readdir $pathname $callback->($entries) |
432 | =item aio_readdir $pathname, $callback->($entries) |
243 | |
433 | |
244 | Unlike the POSIX call of the same name, C<aio_readdir> reads an entire |
434 | Unlike the POSIX call of the same name, C<aio_readdir> reads an entire |
245 | directory (i.e. opendir + readdir + closedir). The entries will not be |
435 | directory (i.e. opendir + readdir + closedir). The entries will not be |
246 | sorted, and will B<NOT> include the C<.> and C<..> entries. |
436 | sorted, and will B<NOT> include the C<.> and C<..> entries. |
247 | |
437 | |
248 | The callback a single argument which is either C<undef> or an array-ref |
438 | The callback a single argument which is either C<undef> or an array-ref |
249 | with the filenames. |
439 | with the filenames. |
250 | |
440 | |
|
|
441 | =item aio_copy $srcpath, $dstpath, $callback->($status) |
|
|
442 | |
|
|
443 | Try to copy the I<file> (directories not supported as either source or |
|
|
444 | destination) from C<$srcpath> to C<$dstpath> and call the callback with |
|
|
445 | the C<0> (error) or C<-1> ok. |
|
|
446 | |
|
|
447 | This is a composite request that it creates the destination file with |
|
|
448 | mode 0200 and copies the contents of the source file into it using |
|
|
449 | C<aio_sendfile>, followed by restoring atime, mtime, access mode and |
|
|
450 | uid/gid, in that order. |
|
|
451 | |
|
|
452 | If an error occurs, the partial destination file will be unlinked, if |
|
|
453 | possible, except when setting atime, mtime, access mode and uid/gid, where |
|
|
454 | errors are being ignored. |
|
|
455 | |
|
|
456 | =cut |
|
|
457 | |
|
|
458 | sub aio_copy($$;$) { |
|
|
459 | my ($src, $dst, $cb) = @_; |
|
|
460 | |
|
|
461 | my $pri = aioreq_pri; |
|
|
462 | my $grp = aio_group $cb; |
|
|
463 | |
|
|
464 | aioreq_pri $pri; |
|
|
465 | add $grp aio_open $src, O_RDONLY, 0, sub { |
|
|
466 | if (my $src_fh = $_[0]) { |
|
|
467 | my @stat = stat $src_fh; |
|
|
468 | |
|
|
469 | aioreq_pri $pri; |
|
|
470 | add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub { |
|
|
471 | if (my $dst_fh = $_[0]) { |
|
|
472 | aioreq_pri $pri; |
|
|
473 | add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub { |
|
|
474 | if ($_[0] == $stat[7]) { |
|
|
475 | $grp->result (0); |
|
|
476 | close $src_fh; |
|
|
477 | |
|
|
478 | # those should not normally block. should. should. |
|
|
479 | utime $stat[8], $stat[9], $dst; |
|
|
480 | chmod $stat[2] & 07777, $dst_fh; |
|
|
481 | chown $stat[4], $stat[5], $dst_fh; |
|
|
482 | close $dst_fh; |
|
|
483 | } else { |
|
|
484 | $grp->result (-1); |
|
|
485 | close $src_fh; |
|
|
486 | close $dst_fh; |
|
|
487 | |
|
|
488 | aioreq $pri; |
|
|
489 | add $grp aio_unlink $dst; |
|
|
490 | } |
|
|
491 | }; |
|
|
492 | } else { |
|
|
493 | $grp->result (-1); |
|
|
494 | } |
|
|
495 | }, |
|
|
496 | |
|
|
497 | } else { |
|
|
498 | $grp->result (-1); |
|
|
499 | } |
|
|
500 | }; |
|
|
501 | |
|
|
502 | $grp |
|
|
503 | } |
|
|
504 | |
|
|
505 | =item aio_move $srcpath, $dstpath, $callback->($status) |
|
|
506 | |
|
|
507 | Try to move the I<file> (directories not supported as either source or |
|
|
508 | destination) from C<$srcpath> to C<$dstpath> and call the callback with |
|
|
509 | the C<0> (error) or C<-1> ok. |
|
|
510 | |
|
|
511 | This is a composite request that tries to rename(2) the file first. If |
|
|
512 | rename files with C<EXDEV>, it copies the file with C<aio_copy> and, if |
|
|
513 | that is successful, unlinking the C<$srcpath>. |
|
|
514 | |
|
|
515 | =cut |
|
|
516 | |
|
|
517 | sub aio_move($$;$) { |
|
|
518 | my ($src, $dst, $cb) = @_; |
|
|
519 | |
|
|
520 | my $pri = aioreq_pri; |
|
|
521 | my $grp = aio_group $cb; |
|
|
522 | |
|
|
523 | aioreq_pri $pri; |
|
|
524 | add $grp aio_rename $src, $dst, sub { |
|
|
525 | if ($_[0] && $! == EXDEV) { |
|
|
526 | aioreq_pri $pri; |
|
|
527 | add $grp aio_copy $src, $dst, sub { |
|
|
528 | $grp->result ($_[0]); |
|
|
529 | |
|
|
530 | if (!$_[0]) { |
|
|
531 | aioreq_pri $pri; |
|
|
532 | add $grp aio_unlink $src; |
|
|
533 | } |
|
|
534 | }; |
|
|
535 | } else { |
|
|
536 | $grp->result ($_[0]); |
|
|
537 | } |
|
|
538 | }; |
|
|
539 | |
|
|
540 | $grp |
|
|
541 | } |
|
|
542 | |
251 | =item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) |
543 | =item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) |
252 | |
544 | |
253 | Scans a directory (similar to C<aio_readdir>) and tries to separate the |
545 | Scans a directory (similar to C<aio_readdir>) but additionally tries to |
254 | entries of directory C<$path> into two sets of names, ones you can recurse |
546 | efficiently separate the entries of directory C<$path> into two sets of |
255 | into (directories), and ones you cannot recurse into (everything else). |
547 | names, directories you can recurse into (directories), and ones you cannot |
|
|
548 | recurse into (everything else, including symlinks to directories). |
256 | |
549 | |
257 | C<aio_scandir> is a composite request that consists of many |
550 | C<aio_scandir> is a composite request that creates of many sub requests_ |
258 | aio-primitives. C<$maxreq> specifies the maximum number of outstanding |
551 | C<$maxreq> specifies the maximum number of outstanding aio requests that |
259 | aio requests that this function generates. If it is C<< <= 0 >>, then a |
552 | this function generates. If it is C<< <= 0 >>, then a suitable default |
260 | suitable default will be chosen (currently 8). |
553 | will be chosen (currently 4). |
261 | |
554 | |
262 | On error, the callback is called without arguments, otherwise it receives |
555 | On error, the callback is called without arguments, otherwise it receives |
263 | two array-refs with path-relative entry names. |
556 | two array-refs with path-relative entry names. |
264 | |
557 | |
265 | Example: |
558 | Example: |
… | |
… | |
273 | Implementation notes. |
566 | Implementation notes. |
274 | |
567 | |
275 | The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can. |
568 | The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can. |
276 | |
569 | |
277 | After reading the directory, the modification time, size etc. of the |
570 | After reading the directory, the modification time, size etc. of the |
278 | directory before and after the readdir is checked, and if they match, the |
571 | directory before and after the readdir is checked, and if they match (and |
279 | link count will be used to decide how many entries are directories (if |
572 | isn't the current time), the link count will be used to decide how many |
280 | >= 2). Otherwise, no knowledge of the number of subdirectories will be |
573 | entries are directories (if >= 2). Otherwise, no knowledge of the number |
281 | assumed. |
574 | of subdirectories will be assumed. |
282 | |
575 | |
283 | Then entires will be sorted into likely directories (everything without a |
576 | Then entries will be sorted into likely directories (everything without |
284 | non-initial dot) and likely non-directories (everything else). Then every |
577 | a non-initial dot currently) and likely non-directories (everything |
285 | entry + C</.> will be C<stat>'ed, likely directories first. This is often |
578 | else). Then every entry plus an appended C</.> will be C<stat>'ed, |
|
|
579 | likely directories first. If that succeeds, it assumes that the entry |
|
|
580 | is a directory or a symlink to directory (which will be checked |
|
|
581 | seperately). This is often faster than stat'ing the entry itself because |
286 | faster because filesystems might detect the type of the entry without |
582 | filesystems might detect the type of the entry without reading the inode |
287 | reading the inode data (e.g. ext2s filetype feature). If that succeeds, |
583 | data (e.g. ext2fs filetype feature). |
288 | it assumes that the entry is a directory or a symlink to directory (which |
|
|
289 | will be checked seperately). |
|
|
290 | |
584 | |
291 | If the known number of directories has been reached, the rest of the |
585 | If the known number of directories (link count - 2) has been reached, the |
292 | entries is assumed to be non-directories. |
586 | rest of the entries is assumed to be non-directories. |
|
|
587 | |
|
|
588 | This only works with certainty on POSIX (= UNIX) filesystems, which |
|
|
589 | fortunately are the vast majority of filesystems around. |
|
|
590 | |
|
|
591 | It will also likely work on non-POSIX filesystems with reduced efficiency |
|
|
592 | as those tend to return 0 or 1 as link counts, which disables the |
|
|
593 | directory counting heuristic. |
293 | |
594 | |
294 | =cut |
595 | =cut |
295 | |
596 | |
296 | sub aio_scandir($$$) { |
597 | sub aio_scandir($$$) { |
297 | my ($path, $maxreq, $cb) = @_; |
598 | my ($path, $maxreq, $cb) = @_; |
298 | |
599 | |
|
|
600 | my $pri = aioreq_pri; |
|
|
601 | |
|
|
602 | my $grp = aio_group $cb; |
|
|
603 | |
299 | $maxreq = 8 if $maxreq <= 0; |
604 | $maxreq = 4 if $maxreq <= 0; |
300 | |
605 | |
301 | # stat once |
606 | # stat once |
|
|
607 | aioreq_pri $pri; |
302 | aio_stat $path, sub { |
608 | add $grp aio_stat $path, sub { |
303 | $cb->() if $_[0]; |
609 | return $grp->result () if $_[0]; |
|
|
610 | my $now = time; |
304 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
611 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
305 | |
612 | |
306 | # read the directory entries |
613 | # read the directory entries |
|
|
614 | aioreq_pri $pri; |
307 | aio_readdir $path, sub { |
615 | add $grp aio_readdir $path, sub { |
308 | my $entries = shift |
616 | my $entries = shift |
309 | or return $cb->(); |
617 | or return $grp->result (); |
310 | |
618 | |
311 | # stat the dir another time |
619 | # stat the dir another time |
|
|
620 | aioreq_pri $pri; |
312 | aio_stat $path, sub { |
621 | add $grp aio_stat $path, sub { |
313 | my $hash2 = join ":", (stat _)[0,1,3,7,9]; |
622 | my $hash2 = join ":", (stat _)[0,1,3,7,9]; |
314 | |
623 | |
315 | my $ndirs; |
624 | my $ndirs; |
316 | |
625 | |
317 | # take the slow route if anything looks fishy |
626 | # take the slow route if anything looks fishy |
318 | if ($hash1 ne $hash2) { |
627 | if ($hash1 ne $hash2 or (stat _)[9] == $now) { |
319 | $ndirs = -1; |
628 | $ndirs = -1; |
320 | } else { |
629 | } else { |
321 | # if nlink == 2, we are finished |
630 | # if nlink == 2, we are finished |
322 | # on non-posix-fs's, we rely on nlink < 2 |
631 | # on non-posix-fs's, we rely on nlink < 2 |
323 | $ndirs = (stat _)[3] - 2 |
632 | $ndirs = (stat _)[3] - 2 |
324 | or return $cb->([], $entries); |
633 | or return $grp->result ([], $entries); |
325 | } |
634 | } |
326 | |
635 | |
327 | # sort into likely dirs and likely nondirs |
636 | # sort into likely dirs and likely nondirs |
328 | # dirs == files without ".", short entries first |
637 | # dirs == files without ".", short entries first |
329 | $entries = [map $_->[0], |
638 | $entries = [map $_->[0], |
… | |
… | |
331 | map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length], |
640 | map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length], |
332 | @$entries]; |
641 | @$entries]; |
333 | |
642 | |
334 | my (@dirs, @nondirs); |
643 | my (@dirs, @nondirs); |
335 | |
644 | |
336 | my ($statcb, $schedcb); |
645 | my $statgrp = add $grp aio_group sub { |
337 | my $nreq = 0; |
646 | $grp->result (\@dirs, \@nondirs); |
|
|
647 | }; |
338 | |
648 | |
339 | $schedcb = sub { |
649 | limit $statgrp $maxreq; |
340 | if (@$entries) { |
650 | feed $statgrp sub { |
341 | if ($nreq < $maxreq) { |
651 | return unless @$entries; |
342 | my $ent = pop @$entries; |
652 | my $entry = pop @$entries; |
|
|
653 | |
|
|
654 | aioreq_pri $pri; |
|
|
655 | add $statgrp aio_stat "$path/$entry/.", sub { |
|
|
656 | if ($_[0] < 0) { |
|
|
657 | push @nondirs, $entry; |
|
|
658 | } else { |
|
|
659 | # need to check for real directory |
|
|
660 | aioreq_pri $pri; |
|
|
661 | add $statgrp aio_lstat "$path/$entry", sub { |
|
|
662 | if (-d _) { |
|
|
663 | push @dirs, $entry; |
|
|
664 | |
|
|
665 | unless (--$ndirs) { |
|
|
666 | push @nondirs, @$entries; |
|
|
667 | feed $statgrp; |
|
|
668 | } |
|
|
669 | } else { |
|
|
670 | push @nondirs, $entry; |
|
|
671 | } |
343 | $nreq++; |
672 | } |
344 | aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) }; |
|
|
345 | } |
673 | } |
346 | } elsif (!$nreq) { |
|
|
347 | # finished |
|
|
348 | undef $statcb; |
|
|
349 | undef $schedcb; |
|
|
350 | $cb->(\@dirs, \@nondirs) if $cb; |
|
|
351 | undef $cb; |
|
|
352 | } |
674 | }; |
353 | }; |
675 | }; |
354 | $statcb = sub { |
|
|
355 | my ($status, $entry) = @_; |
|
|
356 | |
|
|
357 | if ($status < 0) { |
|
|
358 | $nreq--; |
|
|
359 | push @nondirs, $entry; |
|
|
360 | &$schedcb; |
|
|
361 | } else { |
|
|
362 | # need to check for real directory |
|
|
363 | aio_lstat "$path/$entry", sub { |
|
|
364 | $nreq--; |
|
|
365 | |
|
|
366 | if (-d _) { |
|
|
367 | push @dirs, $entry; |
|
|
368 | |
|
|
369 | if (!--$ndirs) { |
|
|
370 | push @nondirs, @$entries; |
|
|
371 | $entries = []; |
|
|
372 | } |
|
|
373 | } else { |
|
|
374 | push @nondirs, $entry; |
|
|
375 | } |
|
|
376 | |
|
|
377 | &$schedcb; |
|
|
378 | } |
|
|
379 | } |
|
|
380 | }; |
|
|
381 | |
|
|
382 | &$schedcb while @$entries && $nreq < $maxreq; |
|
|
383 | }; |
676 | }; |
384 | }; |
677 | }; |
385 | }; |
678 | }; |
|
|
679 | |
|
|
680 | $grp |
386 | } |
681 | } |
387 | |
682 | |
388 | =item aio_fsync $fh, $callback->($status) |
683 | =item aio_fsync $fh, $callback->($status) |
389 | |
684 | |
390 | Asynchronously call fsync on the given filehandle and call the callback |
685 | Asynchronously call fsync on the given filehandle and call the callback |
… | |
… | |
396 | callback with the fdatasync result code. |
691 | callback with the fdatasync result code. |
397 | |
692 | |
398 | If this call isn't available because your OS lacks it or it couldn't be |
693 | If this call isn't available because your OS lacks it or it couldn't be |
399 | detected, it will be emulated by calling C<fsync> instead. |
694 | detected, it will be emulated by calling C<fsync> instead. |
400 | |
695 | |
|
|
696 | =item aio_group $callback->(...) |
|
|
697 | |
|
|
698 | This is a very special aio request: Instead of doing something, it is a |
|
|
699 | container for other aio requests, which is useful if you want to bundle |
|
|
700 | many requests into a single, composite, request with a definite callback |
|
|
701 | and the ability to cancel the whole request with its subrequests. |
|
|
702 | |
|
|
703 | Returns an object of class L<IO::AIO::GRP>. See its documentation below |
|
|
704 | for more info. |
|
|
705 | |
|
|
706 | Example: |
|
|
707 | |
|
|
708 | my $grp = aio_group sub { |
|
|
709 | print "all stats done\n"; |
|
|
710 | }; |
|
|
711 | |
|
|
712 | add $grp |
|
|
713 | (aio_stat ...), |
|
|
714 | (aio_stat ...), |
|
|
715 | ...; |
|
|
716 | |
|
|
717 | =item aio_nop $callback->() |
|
|
718 | |
|
|
719 | This is a special request - it does nothing in itself and is only used for |
|
|
720 | side effects, such as when you want to add a dummy request to a group so |
|
|
721 | that finishing the requests in the group depends on executing the given |
|
|
722 | code. |
|
|
723 | |
|
|
724 | While this request does nothing, it still goes through the execution |
|
|
725 | phase and still requires a worker thread. Thus, the callback will not |
|
|
726 | be executed immediately but only after other requests in the queue have |
|
|
727 | entered their execution phase. This can be used to measure request |
|
|
728 | latency. |
|
|
729 | |
|
|
730 | =item IO::AIO::aio_busy $fractional_seconds, $callback->() *NOT EXPORTED* |
|
|
731 | |
|
|
732 | Mainly used for debugging and benchmarking, this aio request puts one of |
|
|
733 | the request workers to sleep for the given time. |
|
|
734 | |
|
|
735 | While it is theoretically handy to have simple I/O scheduling requests |
|
|
736 | like sleep and file handle readable/writable, the overhead this creates is |
|
|
737 | immense (it blocks a thread for a long time) so do not use this function |
|
|
738 | except to put your application under artificial I/O pressure. |
|
|
739 | |
401 | =back |
740 | =back |
402 | |
741 | |
|
|
742 | =head2 IO::AIO::REQ CLASS |
|
|
743 | |
|
|
744 | All non-aggregate C<aio_*> functions return an object of this class when |
|
|
745 | called in non-void context. |
|
|
746 | |
|
|
747 | =over 4 |
|
|
748 | |
|
|
749 | =item cancel $req |
|
|
750 | |
|
|
751 | Cancels the request, if possible. Has the effect of skipping execution |
|
|
752 | when entering the B<execute> state and skipping calling the callback when |
|
|
753 | entering the the B<result> state, but will leave the request otherwise |
|
|
754 | untouched. That means that requests that currently execute will not be |
|
|
755 | stopped and resources held by the request will not be freed prematurely. |
|
|
756 | |
|
|
757 | =item cb $req $callback->(...) |
|
|
758 | |
|
|
759 | Replace (or simply set) the callback registered to the request. |
|
|
760 | |
|
|
761 | =back |
|
|
762 | |
|
|
763 | =head2 IO::AIO::GRP CLASS |
|
|
764 | |
|
|
765 | This class is a subclass of L<IO::AIO::REQ>, so all its methods apply to |
|
|
766 | objects of this class, too. |
|
|
767 | |
|
|
768 | A IO::AIO::GRP object is a special request that can contain multiple other |
|
|
769 | aio requests. |
|
|
770 | |
|
|
771 | You create one by calling the C<aio_group> constructing function with a |
|
|
772 | callback that will be called when all contained requests have entered the |
|
|
773 | C<done> state: |
|
|
774 | |
|
|
775 | my $grp = aio_group sub { |
|
|
776 | print "all requests are done\n"; |
|
|
777 | }; |
|
|
778 | |
|
|
779 | You add requests by calling the C<add> method with one or more |
|
|
780 | C<IO::AIO::REQ> objects: |
|
|
781 | |
|
|
782 | $grp->add (aio_unlink "..."); |
|
|
783 | |
|
|
784 | add $grp aio_stat "...", sub { |
|
|
785 | $_[0] or return $grp->result ("error"); |
|
|
786 | |
|
|
787 | # add another request dynamically, if first succeeded |
|
|
788 | add $grp aio_open "...", sub { |
|
|
789 | $grp->result ("ok"); |
|
|
790 | }; |
|
|
791 | }; |
|
|
792 | |
|
|
793 | This makes it very easy to create composite requests (see the source of |
|
|
794 | C<aio_move> for an application) that work and feel like simple requests. |
|
|
795 | |
|
|
796 | =over 4 |
|
|
797 | |
|
|
798 | =item * The IO::AIO::GRP objects will be cleaned up during calls to |
|
|
799 | C<IO::AIO::poll_cb>, just like any other request. |
|
|
800 | |
|
|
801 | =item * They can be canceled like any other request. Canceling will cancel not |
|
|
802 | only the request itself, but also all requests it contains. |
|
|
803 | |
|
|
804 | =item * They can also can also be added to other IO::AIO::GRP objects. |
|
|
805 | |
|
|
806 | =item * You must not add requests to a group from within the group callback (or |
|
|
807 | any later time). |
|
|
808 | |
|
|
809 | =back |
|
|
810 | |
|
|
811 | Their lifetime, simplified, looks like this: when they are empty, they |
|
|
812 | will finish very quickly. If they contain only requests that are in the |
|
|
813 | C<done> state, they will also finish. Otherwise they will continue to |
|
|
814 | exist. |
|
|
815 | |
|
|
816 | That means after creating a group you have some time to add requests. And |
|
|
817 | in the callbacks of those requests, you can add further requests to the |
|
|
818 | group. And only when all those requests have finished will the the group |
|
|
819 | itself finish. |
|
|
820 | |
|
|
821 | =over 4 |
|
|
822 | |
|
|
823 | =item add $grp ... |
|
|
824 | |
|
|
825 | =item $grp->add (...) |
|
|
826 | |
|
|
827 | Add one or more requests to the group. Any type of L<IO::AIO::REQ> can |
|
|
828 | be added, including other groups, as long as you do not create circular |
|
|
829 | dependencies. |
|
|
830 | |
|
|
831 | Returns all its arguments. |
|
|
832 | |
|
|
833 | =item $grp->cancel_subs |
|
|
834 | |
|
|
835 | Cancel all subrequests and clears any feeder, but not the group request |
|
|
836 | itself. Useful when you queued a lot of events but got a result early. |
|
|
837 | |
|
|
838 | =item $grp->result (...) |
|
|
839 | |
|
|
840 | Set the result value(s) that will be passed to the group callback when all |
|
|
841 | subrequests have finished and set thre groups errno to the current value |
|
|
842 | of errno (just like calling C<errno> without an error number). By default, |
|
|
843 | no argument will be passed and errno is zero. |
|
|
844 | |
|
|
845 | =item $grp->errno ([$errno]) |
|
|
846 | |
|
|
847 | Sets the group errno value to C<$errno>, or the current value of errno |
|
|
848 | when the argument is missing. |
|
|
849 | |
|
|
850 | Every aio request has an associated errno value that is restored when |
|
|
851 | the callback is invoked. This method lets you change this value from its |
|
|
852 | default (0). |
|
|
853 | |
|
|
854 | Calling C<result> will also set errno, so make sure you either set C<$!> |
|
|
855 | before the call to C<result>, or call c<errno> after it. |
|
|
856 | |
|
|
857 | =item feed $grp $callback->($grp) |
|
|
858 | |
|
|
859 | Sets a feeder/generator on this group: every group can have an attached |
|
|
860 | generator that generates requests if idle. The idea behind this is that, |
|
|
861 | although you could just queue as many requests as you want in a group, |
|
|
862 | this might starve other requests for a potentially long time. For |
|
|
863 | example, C<aio_scandir> might generate hundreds of thousands C<aio_stat> |
|
|
864 | requests, delaying any later requests for a long time. |
|
|
865 | |
|
|
866 | To avoid this, and allow incremental generation of requests, you can |
|
|
867 | instead a group and set a feeder on it that generates those requests. The |
|
|
868 | feed callback will be called whenever there are few enough (see C<limit>, |
|
|
869 | below) requests active in the group itself and is expected to queue more |
|
|
870 | requests. |
|
|
871 | |
|
|
872 | The feed callback can queue as many requests as it likes (i.e. C<add> does |
|
|
873 | not impose any limits). |
|
|
874 | |
|
|
875 | If the feed does not queue more requests when called, it will be |
|
|
876 | automatically removed from the group. |
|
|
877 | |
|
|
878 | If the feed limit is C<0>, it will be set to C<2> automatically. |
|
|
879 | |
|
|
880 | Example: |
|
|
881 | |
|
|
882 | # stat all files in @files, but only ever use four aio requests concurrently: |
|
|
883 | |
|
|
884 | my $grp = aio_group sub { print "finished\n" }; |
|
|
885 | limit $grp 4; |
|
|
886 | feed $grp sub { |
|
|
887 | my $file = pop @files |
|
|
888 | or return; |
|
|
889 | |
|
|
890 | add $grp aio_stat $file, sub { ... }; |
|
|
891 | }; |
|
|
892 | |
|
|
893 | =item limit $grp $num |
|
|
894 | |
|
|
895 | Sets the feeder limit for the group: The feeder will be called whenever |
|
|
896 | the group contains less than this many requests. |
|
|
897 | |
|
|
898 | Setting the limit to C<0> will pause the feeding process. |
|
|
899 | |
|
|
900 | =back |
|
|
901 | |
403 | =head2 SUPPORT FUNCTIONS |
902 | =head2 SUPPORT FUNCTIONS |
|
|
903 | |
|
|
904 | =head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION |
404 | |
905 | |
405 | =over 4 |
906 | =over 4 |
406 | |
907 | |
407 | =item $fileno = IO::AIO::poll_fileno |
908 | =item $fileno = IO::AIO::poll_fileno |
408 | |
909 | |
… | |
… | |
413 | |
914 | |
414 | See C<poll_cb> for an example. |
915 | See C<poll_cb> for an example. |
415 | |
916 | |
416 | =item IO::AIO::poll_cb |
917 | =item IO::AIO::poll_cb |
417 | |
918 | |
418 | Process all outstanding events on the result pipe. You have to call this |
919 | Process some outstanding events on the result pipe. You have to call this |
419 | regularly. Returns the number of events processed. Returns immediately |
920 | regularly. Returns the number of events processed. Returns immediately |
420 | when no events are outstanding. |
921 | when no events are outstanding. The amount of events processed depends on |
|
|
922 | the settings of C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>. |
|
|
923 | |
|
|
924 | If not all requests were processed for whatever reason, the filehandle |
|
|
925 | will still be ready when C<poll_cb> returns. |
421 | |
926 | |
422 | Example: Install an Event watcher that automatically calls |
927 | Example: Install an Event watcher that automatically calls |
423 | IO::AIO::poll_cb with high priority: |
928 | IO::AIO::poll_cb with high priority: |
424 | |
929 | |
425 | Event->io (fd => IO::AIO::poll_fileno, |
930 | Event->io (fd => IO::AIO::poll_fileno, |
426 | poll => 'r', async => 1, |
931 | poll => 'r', async => 1, |
427 | cb => \&IO::AIO::poll_cb); |
932 | cb => \&IO::AIO::poll_cb); |
428 | |
933 | |
|
|
934 | =item IO::AIO::max_poll_reqs $nreqs |
|
|
935 | |
|
|
936 | =item IO::AIO::max_poll_time $seconds |
|
|
937 | |
|
|
938 | These set the maximum number of requests (default C<0>, meaning infinity) |
|
|
939 | that are being processed by C<IO::AIO::poll_cb> in one call, respectively |
|
|
940 | the maximum amount of time (default C<0>, meaning infinity) spent in |
|
|
941 | C<IO::AIO::poll_cb> to process requests (more correctly the mininum amount |
|
|
942 | of time C<poll_cb> is allowed to use). |
|
|
943 | |
|
|
944 | Setting these is useful if you want to ensure some level of |
|
|
945 | interactiveness when perl is not fast enough to process all requests in |
|
|
946 | time. |
|
|
947 | |
|
|
948 | For interactive programs, values such as C<0.01> to C<0.1> should be fine. |
|
|
949 | |
|
|
950 | Example: Install an Event watcher that automatically calls |
|
|
951 | IO::AIO::poll_some with low priority, to ensure that other parts of the |
|
|
952 | program get the CPU sometimes even under high AIO load. |
|
|
953 | |
|
|
954 | # try not to spend much more than 0.1s in poll_cb |
|
|
955 | IO::AIO::max_poll_time 0.1; |
|
|
956 | |
|
|
957 | # use a low priority so other tasks have priority |
|
|
958 | Event->io (fd => IO::AIO::poll_fileno, |
|
|
959 | poll => 'r', nice => 1, |
|
|
960 | cb => &IO::AIO::poll_cb); |
|
|
961 | |
429 | =item IO::AIO::poll_wait |
962 | =item IO::AIO::poll_wait |
430 | |
963 | |
431 | Wait till the result filehandle becomes ready for reading (simply does a |
964 | Wait till the result filehandle becomes ready for reading (simply does a |
432 | C<select> on the filehandle. This is useful if you want to synchronously wait |
965 | C<select> on the filehandle. This is useful if you want to synchronously |
433 | for some requests to finish). |
966 | wait for some requests to finish). |
434 | |
967 | |
435 | See C<nreqs> for an example. |
968 | See C<nreqs> for an example. |
436 | |
969 | |
|
|
970 | =item IO::AIO::poll |
|
|
971 | |
|
|
972 | Waits until some requests have been handled. |
|
|
973 | |
|
|
974 | Strictly equivalent to: |
|
|
975 | |
|
|
976 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
977 | if IO::AIO::nreqs; |
|
|
978 | |
437 | =item IO::AIO::nreqs |
979 | =item IO::AIO::flush |
438 | |
980 | |
439 | Returns the number of requests currently outstanding (i.e. for which their |
981 | Wait till all outstanding AIO requests have been handled. |
440 | callback has not been invoked yet). |
|
|
441 | |
982 | |
442 | Example: wait till there are no outstanding requests anymore: |
983 | Strictly equivalent to: |
443 | |
984 | |
444 | IO::AIO::poll_wait, IO::AIO::poll_cb |
985 | IO::AIO::poll_wait, IO::AIO::poll_cb |
445 | while IO::AIO::nreqs; |
986 | while IO::AIO::nreqs; |
446 | |
987 | |
447 | =item IO::AIO::flush |
988 | =head3 CONTROLLING THE NUMBER OF THREADS |
448 | |
|
|
449 | Wait till all outstanding AIO requests have been handled. |
|
|
450 | |
|
|
451 | Strictly equivalent to: |
|
|
452 | |
|
|
453 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
454 | while IO::AIO::nreqs; |
|
|
455 | |
|
|
456 | =item IO::AIO::poll |
|
|
457 | |
|
|
458 | Waits until some requests have been handled. |
|
|
459 | |
|
|
460 | Strictly equivalent to: |
|
|
461 | |
|
|
462 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
463 | if IO::AIO::nreqs; |
|
|
464 | |
989 | |
465 | =item IO::AIO::min_parallel $nthreads |
990 | =item IO::AIO::min_parallel $nthreads |
466 | |
991 | |
467 | Set the minimum number of AIO threads to C<$nthreads>. The current default |
992 | Set the minimum number of AIO threads to C<$nthreads>. The current |
468 | is C<4>, which means four asynchronous operations can be done at one time |
993 | default is C<8>, which means eight asynchronous operations can execute |
469 | (the number of outstanding operations, however, is unlimited). |
994 | concurrently at any one time (the number of outstanding requests, |
|
|
995 | however, is unlimited). |
470 | |
996 | |
471 | IO::AIO starts threads only on demand, when an AIO request is queued and |
997 | IO::AIO starts threads only on demand, when an AIO request is queued and |
472 | no free thread exists. |
998 | no free thread exists. Please note that queueing up a hundred requests can |
|
|
999 | create demand for a hundred threads, even if it turns out that everything |
|
|
1000 | is in the cache and could have been processed faster by a single thread. |
473 | |
1001 | |
474 | It is recommended to keep the number of threads low, as some Linux |
1002 | It is recommended to keep the number of threads relatively low, as some |
475 | kernel versions will scale negatively with the number of threads (higher |
1003 | Linux kernel versions will scale negatively with the number of threads |
476 | parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32 |
1004 | (higher parallelity => MUCH higher latency). With current Linux 2.6 |
477 | threads should be fine. |
1005 | versions, 4-32 threads should be fine. |
478 | |
1006 | |
479 | Under most circumstances you don't need to call this function, as the |
1007 | Under most circumstances you don't need to call this function, as the |
480 | module selects a default that is suitable for low to moderate load. |
1008 | module selects a default that is suitable for low to moderate load. |
481 | |
1009 | |
482 | =item IO::AIO::max_parallel $nthreads |
1010 | =item IO::AIO::max_parallel $nthreads |
… | |
… | |
491 | This module automatically runs C<max_parallel 0> at program end, to ensure |
1019 | This module automatically runs C<max_parallel 0> at program end, to ensure |
492 | that all threads are killed and that there are no outstanding requests. |
1020 | that all threads are killed and that there are no outstanding requests. |
493 | |
1021 | |
494 | Under normal circumstances you don't need to call this function. |
1022 | Under normal circumstances you don't need to call this function. |
495 | |
1023 | |
|
|
1024 | =item IO::AIO::max_idle $nthreads |
|
|
1025 | |
|
|
1026 | Limit the number of threads (default: 4) that are allowed to idle (i.e., |
|
|
1027 | threads that did not get a request to process within 10 seconds). That |
|
|
1028 | means if a thread becomes idle while C<$nthreads> other threads are also |
|
|
1029 | idle, it will free its resources and exit. |
|
|
1030 | |
|
|
1031 | This is useful when you allow a large number of threads (e.g. 100 or 1000) |
|
|
1032 | to allow for extremely high load situations, but want to free resources |
|
|
1033 | under normal circumstances (1000 threads can easily consume 30MB of RAM). |
|
|
1034 | |
|
|
1035 | The default is probably ok in most situations, especially if thread |
|
|
1036 | creation is fast. If thread creation is very slow on your system you might |
|
|
1037 | want to use larger values. |
|
|
1038 | |
496 | =item $oldnreqs = IO::AIO::max_outstanding $nreqs |
1039 | =item $oldmaxreqs = IO::AIO::max_outstanding $maxreqs |
|
|
1040 | |
|
|
1041 | This is a very bad function to use in interactive programs because it |
|
|
1042 | blocks, and a bad way to reduce concurrency because it is inexact: Better |
|
|
1043 | use an C<aio_group> together with a feed callback. |
497 | |
1044 | |
498 | Sets the maximum number of outstanding requests to C<$nreqs>. If you |
1045 | Sets the maximum number of outstanding requests to C<$nreqs>. If you |
499 | try to queue up more than this number of requests, the caller will block until |
1046 | to queue up more than this number of requests, the next call to the |
500 | some requests have been handled. |
1047 | C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>) |
|
|
1048 | function will block until the limit is no longer exceeded. |
501 | |
1049 | |
502 | The default is very large, so normally there is no practical limit. If you |
1050 | The default value is very large, so there is no practical limit on the |
503 | queue up many requests in a loop it often improves speed if you set |
1051 | number of outstanding requests. |
504 | this to a relatively low number, such as C<100>. |
|
|
505 | |
1052 | |
506 | Under normal circumstances you don't need to call this function. |
1053 | You can still queue as many requests as you want. Therefore, |
|
|
1054 | C<max_oustsanding> is mainly useful in simple scripts (with low values) or |
|
|
1055 | as a stop gap to shield against fatal memory overflow (with large values). |
|
|
1056 | |
|
|
1057 | =head3 STATISTICAL INFORMATION |
|
|
1058 | |
|
|
1059 | =item IO::AIO::nreqs |
|
|
1060 | |
|
|
1061 | Returns the number of requests currently in the ready, execute or pending |
|
|
1062 | states (i.e. for which their callback has not been invoked yet). |
|
|
1063 | |
|
|
1064 | Example: wait till there are no outstanding requests anymore: |
|
|
1065 | |
|
|
1066 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
1067 | while IO::AIO::nreqs; |
|
|
1068 | |
|
|
1069 | =item IO::AIO::nready |
|
|
1070 | |
|
|
1071 | Returns the number of requests currently in the ready state (not yet |
|
|
1072 | executed). |
|
|
1073 | |
|
|
1074 | =item IO::AIO::npending |
|
|
1075 | |
|
|
1076 | Returns the number of requests currently in the pending state (executed, |
|
|
1077 | but not yet processed by poll_cb). |
507 | |
1078 | |
508 | =back |
1079 | =back |
509 | |
1080 | |
510 | =cut |
1081 | =cut |
511 | |
1082 | |
… | |
… | |
523 | or return undef; |
1094 | or return undef; |
524 | |
1095 | |
525 | *$sym |
1096 | *$sym |
526 | } |
1097 | } |
527 | |
1098 | |
528 | min_parallel 4; |
1099 | min_parallel 8; |
529 | |
1100 | |
530 | END { |
1101 | END { |
531 | max_parallel 0; |
1102 | min_parallel 1; |
532 | } |
1103 | flush; |
|
|
1104 | }; |
533 | |
1105 | |
534 | 1; |
1106 | 1; |
535 | |
1107 | |
536 | =head2 FORK BEHAVIOUR |
1108 | =head2 FORK BEHAVIOUR |
|
|
1109 | |
|
|
1110 | This module should do "the right thing" when the process using it forks: |
537 | |
1111 | |
538 | Before the fork, IO::AIO enters a quiescent state where no requests |
1112 | Before the fork, IO::AIO enters a quiescent state where no requests |
539 | can be added in other threads and no results will be processed. After |
1113 | can be added in other threads and no results will be processed. After |
540 | the fork the parent simply leaves the quiescent state and continues |
1114 | the fork the parent simply leaves the quiescent state and continues |
541 | request/result processing, while the child clears the request/result |
1115 | request/result processing, while the child frees the request/result queue |
542 | queue (so the requests started before the fork will only be handled in |
1116 | (so that the requests started before the fork will only be handled in the |
543 | the parent). Threats will be started on demand until the limit ste in the |
1117 | parent). Threads will be started on demand until the limit set in the |
544 | parent process has been reached again. |
1118 | parent process has been reached again. |
545 | |
1119 | |
|
|
1120 | In short: the parent will, after a short pause, continue as if fork had |
|
|
1121 | not been called, while the child will act as if IO::AIO has not been used |
|
|
1122 | yet. |
|
|
1123 | |
|
|
1124 | =head2 MEMORY USAGE |
|
|
1125 | |
|
|
1126 | Per-request usage: |
|
|
1127 | |
|
|
1128 | Each aio request uses - depending on your architecture - around 100-200 |
|
|
1129 | bytes of memory. In addition, stat requests need a stat buffer (possibly |
|
|
1130 | a few hundred bytes), readdir requires a result buffer and so on. Perl |
|
|
1131 | scalars and other data passed into aio requests will also be locked and |
|
|
1132 | will consume memory till the request has entered the done state. |
|
|
1133 | |
|
|
1134 | This is now awfully much, so queuing lots of requests is not usually a |
|
|
1135 | problem. |
|
|
1136 | |
|
|
1137 | Per-thread usage: |
|
|
1138 | |
|
|
1139 | In the execution phase, some aio requests require more memory for |
|
|
1140 | temporary buffers, and each thread requires a stack and other data |
|
|
1141 | structures (usually around 16k-128k, depending on the OS). |
|
|
1142 | |
|
|
1143 | =head1 KNOWN BUGS |
|
|
1144 | |
|
|
1145 | Known bugs will be fixed in the next release. |
|
|
1146 | |
546 | =head1 SEE ALSO |
1147 | =head1 SEE ALSO |
547 | |
1148 | |
548 | L<Coro>, L<Linux::AIO>. |
1149 | L<Coro::AIO>. |
549 | |
1150 | |
550 | =head1 AUTHOR |
1151 | =head1 AUTHOR |
551 | |
1152 | |
552 | Marc Lehmann <schmorp@schmorp.de> |
1153 | Marc Lehmann <schmorp@schmorp.de> |
553 | http://home.schmorp.de/ |
1154 | http://home.schmorp.de/ |