… | |
… | |
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 most of this works on all types of file descriptors (for example |
|
|
67 | sockets), using these functions on file descriptors that support |
|
|
68 | nonblocking operation (again, sockets, pipes etc.) is very inefficient or |
|
|
69 | might not work (aio_read fails on sockets/pipes/fifos). Use an event loop |
|
|
70 | for that (such as the L<Event|Event> module): IO::AIO will naturally fit |
|
|
71 | into such an event loop itself. |
|
|
72 | |
47 | Currently, a number of threads are started that execute your read/writes |
73 | 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 |
74 | 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 |
75 | 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 |
76 | 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 |
77 | functions available on many operating systems. However, they are often |
52 | not well-supported (Linux doesn't allow them on normal files currently, |
78 | 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 |
79 | files currently, for example), and they would only support aio_read and |
54 | remaining functionality would have to be implemented using threads anyway. |
80 | aio_write, so the remaining functionality would have to be implemented |
|
|
81 | using threads anyway. |
55 | |
82 | |
56 | Although the module will work with in the presence of other threads, it is |
83 | Although the module will work with in the presence of other (Perl-) |
57 | currently not reentrant, so use appropriate locking yourself, always call |
84 | 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 |
85 | locking yourself, always call C<poll_cb> from within the same thread, or |
59 | C<aio_> functions) recursively. |
86 | never call C<poll_cb> (or other C<aio_> functions) recursively. |
|
|
87 | |
|
|
88 | =head2 EXAMPLE |
|
|
89 | |
|
|
90 | This is a simple example that uses the Event module and loads |
|
|
91 | F</etc/passwd> asynchronously: |
|
|
92 | |
|
|
93 | use Fcntl; |
|
|
94 | use Event; |
|
|
95 | use IO::AIO; |
|
|
96 | |
|
|
97 | # register the IO::AIO callback with Event |
|
|
98 | Event->io (fd => IO::AIO::poll_fileno, |
|
|
99 | poll => 'r', |
|
|
100 | cb => \&IO::AIO::poll_cb); |
|
|
101 | |
|
|
102 | # queue the request to open /etc/passwd |
|
|
103 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
|
|
104 | my $fh = $_[0] |
|
|
105 | or die "error while opening: $!"; |
|
|
106 | |
|
|
107 | # stat'ing filehandles is generally non-blocking |
|
|
108 | my $size = -s $fh; |
|
|
109 | |
|
|
110 | # queue a request to read the file |
|
|
111 | my $contents; |
|
|
112 | aio_read $fh, 0, $size, $contents, 0, sub { |
|
|
113 | $_[0] == $size |
|
|
114 | or die "short read: $!"; |
|
|
115 | |
|
|
116 | close $fh; |
|
|
117 | |
|
|
118 | # file contents now in $contents |
|
|
119 | print $contents; |
|
|
120 | |
|
|
121 | # exit event loop and program |
|
|
122 | Event::unloop; |
|
|
123 | }; |
|
|
124 | }; |
|
|
125 | |
|
|
126 | # possibly queue up other requests, or open GUI windows, |
|
|
127 | # check for sockets etc. etc. |
|
|
128 | |
|
|
129 | # process events as long as there are some: |
|
|
130 | Event::loop; |
|
|
131 | |
|
|
132 | =head1 REQUEST ANATOMY AND LIFETIME |
|
|
133 | |
|
|
134 | Every C<aio_*> function creates a request. which is a C data structure not |
|
|
135 | directly visible to Perl. |
|
|
136 | |
|
|
137 | If called in non-void context, every request function returns a Perl |
|
|
138 | object representing the request. In void context, nothing is returned, |
|
|
139 | which saves a bit of memory. |
|
|
140 | |
|
|
141 | The perl object is a fairly standard ref-to-hash object. The hash contents |
|
|
142 | are not used by IO::AIO so you are free to store anything you like in it. |
|
|
143 | |
|
|
144 | During their existance, aio requests travel through the following states, |
|
|
145 | in order: |
|
|
146 | |
|
|
147 | =over 4 |
|
|
148 | |
|
|
149 | =item ready |
|
|
150 | |
|
|
151 | Immediately after a request is created it is put into the ready state, |
|
|
152 | waiting for a thread to execute it. |
|
|
153 | |
|
|
154 | =item execute |
|
|
155 | |
|
|
156 | A thread has accepted the request for processing and is currently |
|
|
157 | executing it (e.g. blocking in read). |
|
|
158 | |
|
|
159 | =item pending |
|
|
160 | |
|
|
161 | The request has been executed and is waiting for result processing. |
|
|
162 | |
|
|
163 | While request submission and execution is fully asynchronous, result |
|
|
164 | processing is not and relies on the perl interpreter calling C<poll_cb> |
|
|
165 | (or another function with the same effect). |
|
|
166 | |
|
|
167 | =item result |
|
|
168 | |
|
|
169 | The request results are processed synchronously by C<poll_cb>. |
|
|
170 | |
|
|
171 | The C<poll_cb> function will process all outstanding aio requests by |
|
|
172 | calling their callbacks, freeing memory associated with them and managing |
|
|
173 | any groups they are contained in. |
|
|
174 | |
|
|
175 | =item done |
|
|
176 | |
|
|
177 | Request has reached the end of its lifetime and holds no resources anymore |
|
|
178 | (except possibly for the Perl object, but its connection to the actual |
|
|
179 | aio request is severed and calling its methods will either do nothing or |
|
|
180 | result in a runtime error). |
|
|
181 | |
|
|
182 | =back |
60 | |
183 | |
61 | =cut |
184 | =cut |
62 | |
185 | |
63 | package IO::AIO; |
186 | package IO::AIO; |
64 | |
187 | |
65 | no warnings; |
188 | no warnings; |
|
|
189 | use strict 'vars'; |
66 | |
190 | |
67 | use base 'Exporter'; |
191 | use base 'Exporter'; |
68 | |
192 | |
69 | use Fcntl (); |
|
|
70 | |
|
|
71 | BEGIN { |
193 | BEGIN { |
72 | $VERSION = '1.8'; |
194 | our $VERSION = '2.2'; |
73 | |
195 | |
74 | @EXPORT = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat |
196 | 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 |
197 | aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink |
76 | aio_fsync aio_fdatasync aio_readahead aio_rename aio_link aio_move); |
198 | aio_readlink aio_fsync aio_fdatasync aio_readahead aio_rename aio_link |
77 | @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel |
199 | aio_move aio_copy aio_group aio_nop aio_mknod); |
78 | max_outstanding nreqs); |
200 | our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice)); |
|
|
201 | our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush |
|
|
202 | min_parallel max_parallel max_idle |
|
|
203 | nreqs nready npending nthreads |
|
|
204 | max_poll_time max_poll_reqs); |
|
|
205 | |
|
|
206 | @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; |
79 | |
207 | |
80 | require XSLoader; |
208 | require XSLoader; |
81 | XSLoader::load IO::AIO, $VERSION; |
209 | XSLoader::load ("IO::AIO", $VERSION); |
82 | } |
210 | } |
83 | |
211 | |
84 | =head1 FUNCTIONS |
212 | =head1 FUNCTIONS |
85 | |
213 | |
86 | =head2 AIO FUNCTIONS |
214 | =head2 AIO REQUEST FUNCTIONS |
87 | |
215 | |
88 | All the C<aio_*> calls are more or less thin wrappers around the syscall |
216 | All the C<aio_*> calls are more or less thin wrappers around the syscall |
89 | with the same name (sans C<aio_>). The arguments are similar or identical, |
217 | with the same name (sans C<aio_>). The arguments are similar or identical, |
90 | and they all accept an additional (and optional) C<$callback> argument |
218 | 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 |
219 | which must be a code reference. This code reference will get called with |
… | |
… | |
94 | syscall has been executed asynchronously. |
222 | syscall has been executed asynchronously. |
95 | |
223 | |
96 | All functions expecting a filehandle keep a copy of the filehandle |
224 | All functions expecting a filehandle keep a copy of the filehandle |
97 | internally until the request has finished. |
225 | internally until the request has finished. |
98 | |
226 | |
|
|
227 | All functions return request objects of type L<IO::AIO::REQ> that allow |
|
|
228 | further manipulation of those requests while they are in-flight. |
|
|
229 | |
99 | The pathnames you pass to these routines I<must> be absolute and |
230 | 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 |
231 | 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 |
232 | request is being executed, the current working directory could have |
102 | changed. Alternatively, you can make sure that you never change the |
233 | changed. Alternatively, you can make sure that you never change the |
103 | current working directory. |
234 | current working directory anywhere in the program and then use relative |
|
|
235 | paths. |
104 | |
236 | |
105 | To encode pathnames to byte form, either make sure you either: a) |
237 | 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 |
238 | 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 |
239 | 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 |
240 | 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) |
241 | environment, d) use Glib::filename_from_unicode on unicode filenames or e) |
110 | use something else. |
242 | use something else to ensure your scalar has the correct contents. |
|
|
243 | |
|
|
244 | This works, btw. independent of the internal UTF-8 bit, which IO::AIO |
|
|
245 | handles correctly wether it is set or not. |
111 | |
246 | |
112 | =over 4 |
247 | =over 4 |
|
|
248 | |
|
|
249 | =item $prev_pri = aioreq_pri [$pri] |
|
|
250 | |
|
|
251 | Returns the priority value that would be used for the next request and, if |
|
|
252 | C<$pri> is given, sets the priority for the next aio request. |
|
|
253 | |
|
|
254 | The default priority is C<0>, the minimum and maximum priorities are C<-4> |
|
|
255 | and C<4>, respectively. Requests with higher priority will be serviced |
|
|
256 | first. |
|
|
257 | |
|
|
258 | The priority will be reset to C<0> after each call to one of the C<aio_*> |
|
|
259 | functions. |
|
|
260 | |
|
|
261 | Example: open a file with low priority, then read something from it with |
|
|
262 | higher priority so the read request is serviced before other low priority |
|
|
263 | open requests (potentially spamming the cache): |
|
|
264 | |
|
|
265 | aioreq_pri -3; |
|
|
266 | aio_open ..., sub { |
|
|
267 | return unless $_[0]; |
|
|
268 | |
|
|
269 | aioreq_pri -2; |
|
|
270 | aio_read $_[0], ..., sub { |
|
|
271 | ... |
|
|
272 | }; |
|
|
273 | }; |
|
|
274 | |
|
|
275 | =item aioreq_nice $pri_adjust |
|
|
276 | |
|
|
277 | Similar to C<aioreq_pri>, but subtracts the given value from the current |
|
|
278 | priority, so the effect is cumulative. |
113 | |
279 | |
114 | =item aio_open $pathname, $flags, $mode, $callback->($fh) |
280 | =item aio_open $pathname, $flags, $mode, $callback->($fh) |
115 | |
281 | |
116 | Asynchronously open or create a file and call the callback with a newly |
282 | Asynchronously open or create a file and call the callback with a newly |
117 | created filehandle for the file. |
283 | created filehandle for the file. |
… | |
… | |
167 | |
333 | |
168 | aio_read $fh, 7, 15, $buffer, 0, sub { |
334 | aio_read $fh, 7, 15, $buffer, 0, sub { |
169 | $_[0] > 0 or die "read error: $!"; |
335 | $_[0] > 0 or die "read error: $!"; |
170 | print "read $_[0] bytes: <$buffer>\n"; |
336 | print "read $_[0] bytes: <$buffer>\n"; |
171 | }; |
337 | }; |
172 | |
|
|
173 | =item aio_move $srcpath, $dstpath, $callback->($status) |
|
|
174 | |
|
|
175 | [EXPERIMENTAL] |
|
|
176 | |
|
|
177 | Try to move the I<file> (directories not supported as either source or destination) |
|
|
178 | from C<$srcpath> to C<$dstpath> and call the callback with the C<0> (error) or C<-1> ok. |
|
|
179 | |
|
|
180 | This is a composite request that tries to rename(2) the file first. If |
|
|
181 | rename files with C<EXDEV>, it creates the destination file with mode 0200 |
|
|
182 | and copies the contents of the source file into it using C<aio_sendfile>, |
|
|
183 | followed by restoring atime, mtime, access mode and uid/gid, in that |
|
|
184 | order, and unlinking the C<$srcpath>. |
|
|
185 | |
|
|
186 | If an error occurs, the partial destination file will be unlinked, if |
|
|
187 | possible, except when setting atime, mtime, access mode and uid/gid, where |
|
|
188 | errors are being ignored. |
|
|
189 | |
|
|
190 | =cut |
|
|
191 | |
|
|
192 | sub aio_move($$$) { |
|
|
193 | my ($src, $dst, $cb) = @_; |
|
|
194 | |
|
|
195 | aio_rename $src, $dst, sub { |
|
|
196 | if ($_[0] && $! == Errno::EXDEV) { |
|
|
197 | aio_open $src, O_RDONLY, 0, sub { |
|
|
198 | if (my $src_fh = $_[0]) { |
|
|
199 | my @stat = stat $src_fh; |
|
|
200 | |
|
|
201 | aio_open $dst, O_WRONLY, 0200, sub { |
|
|
202 | if (my $dst_fh = $_[0]) { |
|
|
203 | aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub { |
|
|
204 | close $src_fh; |
|
|
205 | |
|
|
206 | if ($_[0] == $stat[7]) { |
|
|
207 | utime $stat[8], $stat[9], $dst; |
|
|
208 | chmod $stat[2] & 07777, $dst_fh; |
|
|
209 | chown $stat[4], $stat[5], $dst_fh; |
|
|
210 | close $dst_fh; |
|
|
211 | |
|
|
212 | aio_unlink $src, sub { |
|
|
213 | $cb->($_[0]); |
|
|
214 | }; |
|
|
215 | } else { |
|
|
216 | my $errno = $!; |
|
|
217 | aio_unlink $dst, sub { |
|
|
218 | $! = $errno; |
|
|
219 | $cb->(-1); |
|
|
220 | }; |
|
|
221 | } |
|
|
222 | }; |
|
|
223 | } else { |
|
|
224 | $cb->(-1); |
|
|
225 | } |
|
|
226 | }, |
|
|
227 | |
|
|
228 | } else { |
|
|
229 | $cb->(-1); |
|
|
230 | } |
|
|
231 | }; |
|
|
232 | } else { |
|
|
233 | $cb->($_[0]); |
|
|
234 | } |
|
|
235 | }; |
|
|
236 | } |
|
|
237 | |
338 | |
238 | =item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) |
339 | =item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) |
239 | |
340 | |
240 | Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts |
341 | Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts |
241 | reading at byte offset C<$in_offset>, and starts writing at the current |
342 | reading at byte offset C<$in_offset>, and starts writing at the current |
… | |
… | |
297 | =item aio_unlink $pathname, $callback->($status) |
398 | =item aio_unlink $pathname, $callback->($status) |
298 | |
399 | |
299 | Asynchronously unlink (delete) a file and call the callback with the |
400 | Asynchronously unlink (delete) a file and call the callback with the |
300 | result code. |
401 | result code. |
301 | |
402 | |
|
|
403 | =item aio_mknod $path, $mode, $dev, $callback->($status) |
|
|
404 | |
|
|
405 | [EXPERIMENTAL] |
|
|
406 | |
|
|
407 | Asynchronously create a device node (or fifo). See mknod(2). |
|
|
408 | |
|
|
409 | The only (POSIX-) portable way of calling this function is: |
|
|
410 | |
|
|
411 | aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ... |
|
|
412 | |
302 | =item aio_link $srcpath, $dstpath, $callback->($status) |
413 | =item aio_link $srcpath, $dstpath, $callback->($status) |
303 | |
414 | |
304 | Asynchronously create a new link to the existing object at C<$srcpath> at |
415 | Asynchronously create a new link to the existing object at C<$srcpath> at |
305 | the path C<$dstpath> and call the callback with the result code. |
416 | the path C<$dstpath> and call the callback with the result code. |
306 | |
417 | |
307 | =item aio_symlink $srcpath, $dstpath, $callback->($status) |
418 | =item aio_symlink $srcpath, $dstpath, $callback->($status) |
308 | |
419 | |
309 | Asynchronously create a new symbolic link to the existing object at C<$srcpath> at |
420 | Asynchronously create a new symbolic link to the existing object at C<$srcpath> at |
310 | the path C<$dstpath> and call the callback with the result code. |
421 | the path C<$dstpath> and call the callback with the result code. |
|
|
422 | |
|
|
423 | =item aio_readlink $path, $callback->($link) |
|
|
424 | |
|
|
425 | Asynchronously read the symlink specified by C<$path> and pass it to |
|
|
426 | the callback. If an error occurs, nothing or undef gets passed to the |
|
|
427 | callback. |
311 | |
428 | |
312 | =item aio_rename $srcpath, $dstpath, $callback->($status) |
429 | =item aio_rename $srcpath, $dstpath, $callback->($status) |
313 | |
430 | |
314 | Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as |
431 | Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as |
315 | rename(2) and call the callback with the result code. |
432 | rename(2) and call the callback with the result code. |
… | |
… | |
326 | sorted, and will B<NOT> include the C<.> and C<..> entries. |
443 | sorted, and will B<NOT> include the C<.> and C<..> entries. |
327 | |
444 | |
328 | The callback a single argument which is either C<undef> or an array-ref |
445 | The callback a single argument which is either C<undef> or an array-ref |
329 | with the filenames. |
446 | with the filenames. |
330 | |
447 | |
|
|
448 | =item aio_copy $srcpath, $dstpath, $callback->($status) |
|
|
449 | |
|
|
450 | Try to copy the I<file> (directories not supported as either source or |
|
|
451 | destination) from C<$srcpath> to C<$dstpath> and call the callback with |
|
|
452 | the C<0> (error) or C<-1> ok. |
|
|
453 | |
|
|
454 | This is a composite request that it creates the destination file with |
|
|
455 | mode 0200 and copies the contents of the source file into it using |
|
|
456 | C<aio_sendfile>, followed by restoring atime, mtime, access mode and |
|
|
457 | uid/gid, in that order. |
|
|
458 | |
|
|
459 | If an error occurs, the partial destination file will be unlinked, if |
|
|
460 | possible, except when setting atime, mtime, access mode and uid/gid, where |
|
|
461 | errors are being ignored. |
|
|
462 | |
|
|
463 | =cut |
|
|
464 | |
|
|
465 | sub aio_copy($$;$) { |
|
|
466 | my ($src, $dst, $cb) = @_; |
|
|
467 | |
|
|
468 | my $pri = aioreq_pri; |
|
|
469 | my $grp = aio_group $cb; |
|
|
470 | |
|
|
471 | aioreq_pri $pri; |
|
|
472 | add $grp aio_open $src, O_RDONLY, 0, sub { |
|
|
473 | if (my $src_fh = $_[0]) { |
|
|
474 | my @stat = stat $src_fh; |
|
|
475 | |
|
|
476 | aioreq_pri $pri; |
|
|
477 | add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub { |
|
|
478 | if (my $dst_fh = $_[0]) { |
|
|
479 | aioreq_pri $pri; |
|
|
480 | add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub { |
|
|
481 | if ($_[0] == $stat[7]) { |
|
|
482 | $grp->result (0); |
|
|
483 | close $src_fh; |
|
|
484 | |
|
|
485 | # those should not normally block. should. should. |
|
|
486 | utime $stat[8], $stat[9], $dst; |
|
|
487 | chmod $stat[2] & 07777, $dst_fh; |
|
|
488 | chown $stat[4], $stat[5], $dst_fh; |
|
|
489 | close $dst_fh; |
|
|
490 | } else { |
|
|
491 | $grp->result (-1); |
|
|
492 | close $src_fh; |
|
|
493 | close $dst_fh; |
|
|
494 | |
|
|
495 | aioreq $pri; |
|
|
496 | add $grp aio_unlink $dst; |
|
|
497 | } |
|
|
498 | }; |
|
|
499 | } else { |
|
|
500 | $grp->result (-1); |
|
|
501 | } |
|
|
502 | }, |
|
|
503 | |
|
|
504 | } else { |
|
|
505 | $grp->result (-1); |
|
|
506 | } |
|
|
507 | }; |
|
|
508 | |
|
|
509 | $grp |
|
|
510 | } |
|
|
511 | |
|
|
512 | =item aio_move $srcpath, $dstpath, $callback->($status) |
|
|
513 | |
|
|
514 | Try to move the I<file> (directories not supported as either source or |
|
|
515 | destination) from C<$srcpath> to C<$dstpath> and call the callback with |
|
|
516 | the C<0> (error) or C<-1> ok. |
|
|
517 | |
|
|
518 | This is a composite request that tries to rename(2) the file first. If |
|
|
519 | rename files with C<EXDEV>, it copies the file with C<aio_copy> and, if |
|
|
520 | that is successful, unlinking the C<$srcpath>. |
|
|
521 | |
|
|
522 | =cut |
|
|
523 | |
|
|
524 | sub aio_move($$;$) { |
|
|
525 | my ($src, $dst, $cb) = @_; |
|
|
526 | |
|
|
527 | my $pri = aioreq_pri; |
|
|
528 | my $grp = aio_group $cb; |
|
|
529 | |
|
|
530 | aioreq_pri $pri; |
|
|
531 | add $grp aio_rename $src, $dst, sub { |
|
|
532 | if ($_[0] && $! == EXDEV) { |
|
|
533 | aioreq_pri $pri; |
|
|
534 | add $grp aio_copy $src, $dst, sub { |
|
|
535 | $grp->result ($_[0]); |
|
|
536 | |
|
|
537 | if (!$_[0]) { |
|
|
538 | aioreq_pri $pri; |
|
|
539 | add $grp aio_unlink $src; |
|
|
540 | } |
|
|
541 | }; |
|
|
542 | } else { |
|
|
543 | $grp->result ($_[0]); |
|
|
544 | } |
|
|
545 | }; |
|
|
546 | |
|
|
547 | $grp |
|
|
548 | } |
|
|
549 | |
331 | =item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) |
550 | =item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) |
332 | |
551 | |
333 | Scans a directory (similar to C<aio_readdir>) and tries to separate the |
552 | Scans a directory (similar to C<aio_readdir>) but additionally tries to |
334 | entries of directory C<$path> into two sets of names, ones you can recurse |
553 | efficiently separate the entries of directory C<$path> into two sets of |
335 | into (directories), and ones you cannot recurse into (everything else). |
554 | names, directories you can recurse into (directories), and ones you cannot |
|
|
555 | recurse into (everything else, including symlinks to directories). |
336 | |
556 | |
337 | C<aio_scandir> is a composite request that consists of many |
557 | C<aio_scandir> is a composite request that creates of many sub requests_ |
338 | aio-primitives. C<$maxreq> specifies the maximum number of outstanding |
558 | C<$maxreq> specifies the maximum number of outstanding aio requests that |
339 | aio requests that this function generates. If it is C<< <= 0 >>, then a |
559 | this function generates. If it is C<< <= 0 >>, then a suitable default |
340 | suitable default will be chosen (currently 8). |
560 | will be chosen (currently 4). |
341 | |
561 | |
342 | On error, the callback is called without arguments, otherwise it receives |
562 | On error, the callback is called without arguments, otherwise it receives |
343 | two array-refs with path-relative entry names. |
563 | two array-refs with path-relative entry names. |
344 | |
564 | |
345 | Example: |
565 | Example: |
… | |
… | |
353 | Implementation notes. |
573 | Implementation notes. |
354 | |
574 | |
355 | The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can. |
575 | The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can. |
356 | |
576 | |
357 | After reading the directory, the modification time, size etc. of the |
577 | After reading the directory, the modification time, size etc. of the |
358 | directory before and after the readdir is checked, and if they match, the |
578 | directory before and after the readdir is checked, and if they match (and |
359 | link count will be used to decide how many entries are directories (if |
579 | isn't the current time), the link count will be used to decide how many |
360 | >= 2). Otherwise, no knowledge of the number of subdirectories will be |
580 | entries are directories (if >= 2). Otherwise, no knowledge of the number |
361 | assumed. |
581 | of subdirectories will be assumed. |
362 | |
582 | |
363 | Then entires will be sorted into likely directories (everything without a |
583 | Then entries will be sorted into likely directories (everything without |
364 | non-initial dot) and likely non-directories (everything else). Then every |
584 | a non-initial dot currently) and likely non-directories (everything |
365 | entry + C</.> will be C<stat>'ed, likely directories first. This is often |
585 | else). Then every entry plus an appended C</.> will be C<stat>'ed, |
|
|
586 | likely directories first. If that succeeds, it assumes that the entry |
|
|
587 | is a directory or a symlink to directory (which will be checked |
|
|
588 | seperately). This is often faster than stat'ing the entry itself because |
366 | faster because filesystems might detect the type of the entry without |
589 | filesystems might detect the type of the entry without reading the inode |
367 | reading the inode data (e.g. ext2fs filetype feature). If that succeeds, |
590 | data (e.g. ext2fs filetype feature). |
368 | it assumes that the entry is a directory or a symlink to directory (which |
|
|
369 | will be checked seperately). |
|
|
370 | |
591 | |
371 | If the known number of directories has been reached, the rest of the |
592 | If the known number of directories (link count - 2) has been reached, the |
372 | entries is assumed to be non-directories. |
593 | rest of the entries is assumed to be non-directories. |
|
|
594 | |
|
|
595 | This only works with certainty on POSIX (= UNIX) filesystems, which |
|
|
596 | fortunately are the vast majority of filesystems around. |
|
|
597 | |
|
|
598 | It will also likely work on non-POSIX filesystems with reduced efficiency |
|
|
599 | as those tend to return 0 or 1 as link counts, which disables the |
|
|
600 | directory counting heuristic. |
373 | |
601 | |
374 | =cut |
602 | =cut |
375 | |
603 | |
376 | sub aio_scandir($$$) { |
604 | sub aio_scandir($$$) { |
377 | my ($path, $maxreq, $cb) = @_; |
605 | my ($path, $maxreq, $cb) = @_; |
378 | |
606 | |
|
|
607 | my $pri = aioreq_pri; |
|
|
608 | |
|
|
609 | my $grp = aio_group $cb; |
|
|
610 | |
379 | $maxreq = 8 if $maxreq <= 0; |
611 | $maxreq = 4 if $maxreq <= 0; |
380 | |
612 | |
381 | # stat once |
613 | # stat once |
|
|
614 | aioreq_pri $pri; |
382 | aio_stat $path, sub { |
615 | add $grp aio_stat $path, sub { |
383 | return $cb->() if $_[0]; |
616 | return $grp->result () if $_[0]; |
|
|
617 | my $now = time; |
384 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
618 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
385 | |
619 | |
386 | # read the directory entries |
620 | # read the directory entries |
|
|
621 | aioreq_pri $pri; |
387 | aio_readdir $path, sub { |
622 | add $grp aio_readdir $path, sub { |
388 | my $entries = shift |
623 | my $entries = shift |
389 | or return $cb->(); |
624 | or return $grp->result (); |
390 | |
625 | |
391 | # stat the dir another time |
626 | # stat the dir another time |
|
|
627 | aioreq_pri $pri; |
392 | aio_stat $path, sub { |
628 | add $grp aio_stat $path, sub { |
393 | my $hash2 = join ":", (stat _)[0,1,3,7,9]; |
629 | my $hash2 = join ":", (stat _)[0,1,3,7,9]; |
394 | |
630 | |
395 | my $ndirs; |
631 | my $ndirs; |
396 | |
632 | |
397 | # take the slow route if anything looks fishy |
633 | # take the slow route if anything looks fishy |
398 | if ($hash1 ne $hash2) { |
634 | if ($hash1 ne $hash2 or (stat _)[9] == $now) { |
399 | $ndirs = -1; |
635 | $ndirs = -1; |
400 | } else { |
636 | } else { |
401 | # if nlink == 2, we are finished |
637 | # if nlink == 2, we are finished |
402 | # on non-posix-fs's, we rely on nlink < 2 |
638 | # on non-posix-fs's, we rely on nlink < 2 |
403 | $ndirs = (stat _)[3] - 2 |
639 | $ndirs = (stat _)[3] - 2 |
404 | or return $cb->([], $entries); |
640 | or return $grp->result ([], $entries); |
405 | } |
641 | } |
406 | |
642 | |
407 | # sort into likely dirs and likely nondirs |
643 | # sort into likely dirs and likely nondirs |
408 | # dirs == files without ".", short entries first |
644 | # dirs == files without ".", short entries first |
409 | $entries = [map $_->[0], |
645 | $entries = [map $_->[0], |
… | |
… | |
411 | map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length], |
647 | map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length], |
412 | @$entries]; |
648 | @$entries]; |
413 | |
649 | |
414 | my (@dirs, @nondirs); |
650 | my (@dirs, @nondirs); |
415 | |
651 | |
416 | my ($statcb, $schedcb); |
652 | my $statgrp = add $grp aio_group sub { |
417 | my $nreq = 0; |
653 | $grp->result (\@dirs, \@nondirs); |
|
|
654 | }; |
418 | |
655 | |
419 | $schedcb = sub { |
656 | limit $statgrp $maxreq; |
420 | if (@$entries) { |
657 | feed $statgrp sub { |
421 | if ($nreq < $maxreq) { |
658 | return unless @$entries; |
422 | my $ent = pop @$entries; |
659 | my $entry = pop @$entries; |
|
|
660 | |
|
|
661 | aioreq_pri $pri; |
|
|
662 | add $statgrp aio_stat "$path/$entry/.", sub { |
|
|
663 | if ($_[0] < 0) { |
|
|
664 | push @nondirs, $entry; |
|
|
665 | } else { |
|
|
666 | # need to check for real directory |
|
|
667 | aioreq_pri $pri; |
|
|
668 | add $statgrp aio_lstat "$path/$entry", sub { |
|
|
669 | if (-d _) { |
|
|
670 | push @dirs, $entry; |
|
|
671 | |
|
|
672 | unless (--$ndirs) { |
|
|
673 | push @nondirs, @$entries; |
|
|
674 | feed $statgrp; |
|
|
675 | } |
|
|
676 | } else { |
|
|
677 | push @nondirs, $entry; |
|
|
678 | } |
423 | $nreq++; |
679 | } |
424 | aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) }; |
|
|
425 | } |
680 | } |
426 | } elsif (!$nreq) { |
|
|
427 | # finished |
|
|
428 | undef $statcb; |
|
|
429 | undef $schedcb; |
|
|
430 | $cb->(\@dirs, \@nondirs) if $cb; |
|
|
431 | undef $cb; |
|
|
432 | } |
681 | }; |
433 | }; |
682 | }; |
434 | $statcb = sub { |
|
|
435 | my ($status, $entry) = @_; |
|
|
436 | |
|
|
437 | if ($status < 0) { |
|
|
438 | $nreq--; |
|
|
439 | push @nondirs, $entry; |
|
|
440 | &$schedcb; |
|
|
441 | } else { |
|
|
442 | # need to check for real directory |
|
|
443 | aio_lstat "$path/$entry", sub { |
|
|
444 | $nreq--; |
|
|
445 | |
|
|
446 | if (-d _) { |
|
|
447 | push @dirs, $entry; |
|
|
448 | |
|
|
449 | if (!--$ndirs) { |
|
|
450 | push @nondirs, @$entries; |
|
|
451 | $entries = []; |
|
|
452 | } |
|
|
453 | } else { |
|
|
454 | push @nondirs, $entry; |
|
|
455 | } |
|
|
456 | |
|
|
457 | &$schedcb; |
|
|
458 | } |
|
|
459 | } |
|
|
460 | }; |
|
|
461 | |
|
|
462 | &$schedcb while @$entries && $nreq < $maxreq; |
|
|
463 | }; |
683 | }; |
464 | }; |
684 | }; |
465 | }; |
685 | }; |
|
|
686 | |
|
|
687 | $grp |
466 | } |
688 | } |
467 | |
689 | |
468 | =item aio_fsync $fh, $callback->($status) |
690 | =item aio_fsync $fh, $callback->($status) |
469 | |
691 | |
470 | Asynchronously call fsync on the given filehandle and call the callback |
692 | Asynchronously call fsync on the given filehandle and call the callback |
… | |
… | |
476 | callback with the fdatasync result code. |
698 | callback with the fdatasync result code. |
477 | |
699 | |
478 | If this call isn't available because your OS lacks it or it couldn't be |
700 | If this call isn't available because your OS lacks it or it couldn't be |
479 | detected, it will be emulated by calling C<fsync> instead. |
701 | detected, it will be emulated by calling C<fsync> instead. |
480 | |
702 | |
|
|
703 | =item aio_group $callback->(...) |
|
|
704 | |
|
|
705 | This is a very special aio request: Instead of doing something, it is a |
|
|
706 | container for other aio requests, which is useful if you want to bundle |
|
|
707 | many requests into a single, composite, request with a definite callback |
|
|
708 | and the ability to cancel the whole request with its subrequests. |
|
|
709 | |
|
|
710 | Returns an object of class L<IO::AIO::GRP>. See its documentation below |
|
|
711 | for more info. |
|
|
712 | |
|
|
713 | Example: |
|
|
714 | |
|
|
715 | my $grp = aio_group sub { |
|
|
716 | print "all stats done\n"; |
|
|
717 | }; |
|
|
718 | |
|
|
719 | add $grp |
|
|
720 | (aio_stat ...), |
|
|
721 | (aio_stat ...), |
|
|
722 | ...; |
|
|
723 | |
|
|
724 | =item aio_nop $callback->() |
|
|
725 | |
|
|
726 | This is a special request - it does nothing in itself and is only used for |
|
|
727 | side effects, such as when you want to add a dummy request to a group so |
|
|
728 | that finishing the requests in the group depends on executing the given |
|
|
729 | code. |
|
|
730 | |
|
|
731 | While this request does nothing, it still goes through the execution |
|
|
732 | phase and still requires a worker thread. Thus, the callback will not |
|
|
733 | be executed immediately but only after other requests in the queue have |
|
|
734 | entered their execution phase. This can be used to measure request |
|
|
735 | latency. |
|
|
736 | |
|
|
737 | =item IO::AIO::aio_busy $fractional_seconds, $callback->() *NOT EXPORTED* |
|
|
738 | |
|
|
739 | Mainly used for debugging and benchmarking, this aio request puts one of |
|
|
740 | the request workers to sleep for the given time. |
|
|
741 | |
|
|
742 | While it is theoretically handy to have simple I/O scheduling requests |
|
|
743 | like sleep and file handle readable/writable, the overhead this creates is |
|
|
744 | immense (it blocks a thread for a long time) so do not use this function |
|
|
745 | except to put your application under artificial I/O pressure. |
|
|
746 | |
481 | =back |
747 | =back |
482 | |
748 | |
|
|
749 | =head2 IO::AIO::REQ CLASS |
|
|
750 | |
|
|
751 | All non-aggregate C<aio_*> functions return an object of this class when |
|
|
752 | called in non-void context. |
|
|
753 | |
|
|
754 | =over 4 |
|
|
755 | |
|
|
756 | =item cancel $req |
|
|
757 | |
|
|
758 | Cancels the request, if possible. Has the effect of skipping execution |
|
|
759 | when entering the B<execute> state and skipping calling the callback when |
|
|
760 | entering the the B<result> state, but will leave the request otherwise |
|
|
761 | untouched. That means that requests that currently execute will not be |
|
|
762 | stopped and resources held by the request will not be freed prematurely. |
|
|
763 | |
|
|
764 | =item cb $req $callback->(...) |
|
|
765 | |
|
|
766 | Replace (or simply set) the callback registered to the request. |
|
|
767 | |
|
|
768 | =back |
|
|
769 | |
|
|
770 | =head2 IO::AIO::GRP CLASS |
|
|
771 | |
|
|
772 | This class is a subclass of L<IO::AIO::REQ>, so all its methods apply to |
|
|
773 | objects of this class, too. |
|
|
774 | |
|
|
775 | A IO::AIO::GRP object is a special request that can contain multiple other |
|
|
776 | aio requests. |
|
|
777 | |
|
|
778 | You create one by calling the C<aio_group> constructing function with a |
|
|
779 | callback that will be called when all contained requests have entered the |
|
|
780 | C<done> state: |
|
|
781 | |
|
|
782 | my $grp = aio_group sub { |
|
|
783 | print "all requests are done\n"; |
|
|
784 | }; |
|
|
785 | |
|
|
786 | You add requests by calling the C<add> method with one or more |
|
|
787 | C<IO::AIO::REQ> objects: |
|
|
788 | |
|
|
789 | $grp->add (aio_unlink "..."); |
|
|
790 | |
|
|
791 | add $grp aio_stat "...", sub { |
|
|
792 | $_[0] or return $grp->result ("error"); |
|
|
793 | |
|
|
794 | # add another request dynamically, if first succeeded |
|
|
795 | add $grp aio_open "...", sub { |
|
|
796 | $grp->result ("ok"); |
|
|
797 | }; |
|
|
798 | }; |
|
|
799 | |
|
|
800 | This makes it very easy to create composite requests (see the source of |
|
|
801 | C<aio_move> for an application) that work and feel like simple requests. |
|
|
802 | |
|
|
803 | =over 4 |
|
|
804 | |
|
|
805 | =item * The IO::AIO::GRP objects will be cleaned up during calls to |
|
|
806 | C<IO::AIO::poll_cb>, just like any other request. |
|
|
807 | |
|
|
808 | =item * They can be canceled like any other request. Canceling will cancel not |
|
|
809 | only the request itself, but also all requests it contains. |
|
|
810 | |
|
|
811 | =item * They can also can also be added to other IO::AIO::GRP objects. |
|
|
812 | |
|
|
813 | =item * You must not add requests to a group from within the group callback (or |
|
|
814 | any later time). |
|
|
815 | |
|
|
816 | =back |
|
|
817 | |
|
|
818 | Their lifetime, simplified, looks like this: when they are empty, they |
|
|
819 | will finish very quickly. If they contain only requests that are in the |
|
|
820 | C<done> state, they will also finish. Otherwise they will continue to |
|
|
821 | exist. |
|
|
822 | |
|
|
823 | That means after creating a group you have some time to add requests. And |
|
|
824 | in the callbacks of those requests, you can add further requests to the |
|
|
825 | group. And only when all those requests have finished will the the group |
|
|
826 | itself finish. |
|
|
827 | |
|
|
828 | =over 4 |
|
|
829 | |
|
|
830 | =item add $grp ... |
|
|
831 | |
|
|
832 | =item $grp->add (...) |
|
|
833 | |
|
|
834 | Add one or more requests to the group. Any type of L<IO::AIO::REQ> can |
|
|
835 | be added, including other groups, as long as you do not create circular |
|
|
836 | dependencies. |
|
|
837 | |
|
|
838 | Returns all its arguments. |
|
|
839 | |
|
|
840 | =item $grp->cancel_subs |
|
|
841 | |
|
|
842 | Cancel all subrequests and clears any feeder, but not the group request |
|
|
843 | itself. Useful when you queued a lot of events but got a result early. |
|
|
844 | |
|
|
845 | =item $grp->result (...) |
|
|
846 | |
|
|
847 | Set the result value(s) that will be passed to the group callback when all |
|
|
848 | subrequests have finished and set thre groups errno to the current value |
|
|
849 | of errno (just like calling C<errno> without an error number). By default, |
|
|
850 | no argument will be passed and errno is zero. |
|
|
851 | |
|
|
852 | =item $grp->errno ([$errno]) |
|
|
853 | |
|
|
854 | Sets the group errno value to C<$errno>, or the current value of errno |
|
|
855 | when the argument is missing. |
|
|
856 | |
|
|
857 | Every aio request has an associated errno value that is restored when |
|
|
858 | the callback is invoked. This method lets you change this value from its |
|
|
859 | default (0). |
|
|
860 | |
|
|
861 | Calling C<result> will also set errno, so make sure you either set C<$!> |
|
|
862 | before the call to C<result>, or call c<errno> after it. |
|
|
863 | |
|
|
864 | =item feed $grp $callback->($grp) |
|
|
865 | |
|
|
866 | Sets a feeder/generator on this group: every group can have an attached |
|
|
867 | generator that generates requests if idle. The idea behind this is that, |
|
|
868 | although you could just queue as many requests as you want in a group, |
|
|
869 | this might starve other requests for a potentially long time. For |
|
|
870 | example, C<aio_scandir> might generate hundreds of thousands C<aio_stat> |
|
|
871 | requests, delaying any later requests for a long time. |
|
|
872 | |
|
|
873 | To avoid this, and allow incremental generation of requests, you can |
|
|
874 | instead a group and set a feeder on it that generates those requests. The |
|
|
875 | feed callback will be called whenever there are few enough (see C<limit>, |
|
|
876 | below) requests active in the group itself and is expected to queue more |
|
|
877 | requests. |
|
|
878 | |
|
|
879 | The feed callback can queue as many requests as it likes (i.e. C<add> does |
|
|
880 | not impose any limits). |
|
|
881 | |
|
|
882 | If the feed does not queue more requests when called, it will be |
|
|
883 | automatically removed from the group. |
|
|
884 | |
|
|
885 | If the feed limit is C<0>, it will be set to C<2> automatically. |
|
|
886 | |
|
|
887 | Example: |
|
|
888 | |
|
|
889 | # stat all files in @files, but only ever use four aio requests concurrently: |
|
|
890 | |
|
|
891 | my $grp = aio_group sub { print "finished\n" }; |
|
|
892 | limit $grp 4; |
|
|
893 | feed $grp sub { |
|
|
894 | my $file = pop @files |
|
|
895 | or return; |
|
|
896 | |
|
|
897 | add $grp aio_stat $file, sub { ... }; |
|
|
898 | }; |
|
|
899 | |
|
|
900 | =item limit $grp $num |
|
|
901 | |
|
|
902 | Sets the feeder limit for the group: The feeder will be called whenever |
|
|
903 | the group contains less than this many requests. |
|
|
904 | |
|
|
905 | Setting the limit to C<0> will pause the feeding process. |
|
|
906 | |
|
|
907 | =back |
|
|
908 | |
483 | =head2 SUPPORT FUNCTIONS |
909 | =head2 SUPPORT FUNCTIONS |
|
|
910 | |
|
|
911 | =head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION |
484 | |
912 | |
485 | =over 4 |
913 | =over 4 |
486 | |
914 | |
487 | =item $fileno = IO::AIO::poll_fileno |
915 | =item $fileno = IO::AIO::poll_fileno |
488 | |
916 | |
… | |
… | |
493 | |
921 | |
494 | See C<poll_cb> for an example. |
922 | See C<poll_cb> for an example. |
495 | |
923 | |
496 | =item IO::AIO::poll_cb |
924 | =item IO::AIO::poll_cb |
497 | |
925 | |
498 | Process all outstanding events on the result pipe. You have to call this |
926 | Process some outstanding events on the result pipe. You have to call this |
499 | regularly. Returns the number of events processed. Returns immediately |
927 | regularly. Returns the number of events processed. Returns immediately |
500 | when no events are outstanding. |
928 | when no events are outstanding. The amount of events processed depends on |
|
|
929 | the settings of C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>. |
|
|
930 | |
|
|
931 | If not all requests were processed for whatever reason, the filehandle |
|
|
932 | will still be ready when C<poll_cb> returns. |
501 | |
933 | |
502 | Example: Install an Event watcher that automatically calls |
934 | Example: Install an Event watcher that automatically calls |
503 | IO::AIO::poll_cb with high priority: |
935 | IO::AIO::poll_cb with high priority: |
504 | |
936 | |
505 | Event->io (fd => IO::AIO::poll_fileno, |
937 | Event->io (fd => IO::AIO::poll_fileno, |
506 | poll => 'r', async => 1, |
938 | poll => 'r', async => 1, |
507 | cb => \&IO::AIO::poll_cb); |
939 | cb => \&IO::AIO::poll_cb); |
508 | |
940 | |
|
|
941 | =item IO::AIO::max_poll_reqs $nreqs |
|
|
942 | |
|
|
943 | =item IO::AIO::max_poll_time $seconds |
|
|
944 | |
|
|
945 | These set the maximum number of requests (default C<0>, meaning infinity) |
|
|
946 | that are being processed by C<IO::AIO::poll_cb> in one call, respectively |
|
|
947 | the maximum amount of time (default C<0>, meaning infinity) spent in |
|
|
948 | C<IO::AIO::poll_cb> to process requests (more correctly the mininum amount |
|
|
949 | of time C<poll_cb> is allowed to use). |
|
|
950 | |
|
|
951 | Setting C<max_poll_time> to a non-zero value creates an overhead of one |
|
|
952 | syscall per request processed, which is not normally a problem unless your |
|
|
953 | callbacks are really really fast or your OS is really really slow (I am |
|
|
954 | not mentioning Solaris here). Using C<max_poll_reqs> incurs no overhead. |
|
|
955 | |
|
|
956 | Setting these is useful if you want to ensure some level of |
|
|
957 | interactiveness when perl is not fast enough to process all requests in |
|
|
958 | time. |
|
|
959 | |
|
|
960 | For interactive programs, values such as C<0.01> to C<0.1> should be fine. |
|
|
961 | |
|
|
962 | Example: Install an Event watcher that automatically calls |
|
|
963 | IO::AIO::poll_cb with low priority, to ensure that other parts of the |
|
|
964 | program get the CPU sometimes even under high AIO load. |
|
|
965 | |
|
|
966 | # try not to spend much more than 0.1s in poll_cb |
|
|
967 | IO::AIO::max_poll_time 0.1; |
|
|
968 | |
|
|
969 | # use a low priority so other tasks have priority |
|
|
970 | Event->io (fd => IO::AIO::poll_fileno, |
|
|
971 | poll => 'r', nice => 1, |
|
|
972 | cb => &IO::AIO::poll_cb); |
|
|
973 | |
509 | =item IO::AIO::poll_wait |
974 | =item IO::AIO::poll_wait |
510 | |
975 | |
511 | Wait till the result filehandle becomes ready for reading (simply does a |
976 | Wait till the result filehandle becomes ready for reading (simply does a |
512 | C<select> on the filehandle. This is useful if you want to synchronously wait |
977 | C<select> on the filehandle. This is useful if you want to synchronously |
513 | for some requests to finish). |
978 | wait for some requests to finish). |
514 | |
979 | |
515 | See C<nreqs> for an example. |
980 | See C<nreqs> for an example. |
516 | |
981 | |
|
|
982 | =item IO::AIO::poll |
|
|
983 | |
|
|
984 | Waits until some requests have been handled. |
|
|
985 | |
|
|
986 | Strictly equivalent to: |
|
|
987 | |
|
|
988 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
989 | if IO::AIO::nreqs; |
|
|
990 | |
517 | =item IO::AIO::nreqs |
991 | =item IO::AIO::flush |
518 | |
992 | |
519 | Returns the number of requests currently outstanding (i.e. for which their |
993 | Wait till all outstanding AIO requests have been handled. |
520 | callback has not been invoked yet). |
|
|
521 | |
994 | |
522 | Example: wait till there are no outstanding requests anymore: |
995 | Strictly equivalent to: |
523 | |
996 | |
524 | IO::AIO::poll_wait, IO::AIO::poll_cb |
997 | IO::AIO::poll_wait, IO::AIO::poll_cb |
525 | while IO::AIO::nreqs; |
998 | while IO::AIO::nreqs; |
526 | |
999 | |
527 | =item IO::AIO::flush |
1000 | =head3 CONTROLLING THE NUMBER OF THREADS |
528 | |
|
|
529 | Wait till all outstanding AIO requests have been handled. |
|
|
530 | |
|
|
531 | Strictly equivalent to: |
|
|
532 | |
|
|
533 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
534 | while IO::AIO::nreqs; |
|
|
535 | |
|
|
536 | =item IO::AIO::poll |
|
|
537 | |
|
|
538 | Waits until some requests have been handled. |
|
|
539 | |
|
|
540 | Strictly equivalent to: |
|
|
541 | |
|
|
542 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
543 | if IO::AIO::nreqs; |
|
|
544 | |
1001 | |
545 | =item IO::AIO::min_parallel $nthreads |
1002 | =item IO::AIO::min_parallel $nthreads |
546 | |
1003 | |
547 | Set the minimum number of AIO threads to C<$nthreads>. The current default |
1004 | Set the minimum number of AIO threads to C<$nthreads>. The current |
548 | is C<4>, which means four asynchronous operations can be done at one time |
1005 | default is C<8>, which means eight asynchronous operations can execute |
549 | (the number of outstanding operations, however, is unlimited). |
1006 | concurrently at any one time (the number of outstanding requests, |
|
|
1007 | however, is unlimited). |
550 | |
1008 | |
551 | IO::AIO starts threads only on demand, when an AIO request is queued and |
1009 | IO::AIO starts threads only on demand, when an AIO request is queued and |
552 | no free thread exists. |
1010 | no free thread exists. Please note that queueing up a hundred requests can |
|
|
1011 | create demand for a hundred threads, even if it turns out that everything |
|
|
1012 | is in the cache and could have been processed faster by a single thread. |
553 | |
1013 | |
554 | It is recommended to keep the number of threads low, as some Linux |
1014 | It is recommended to keep the number of threads relatively low, as some |
555 | kernel versions will scale negatively with the number of threads (higher |
1015 | Linux kernel versions will scale negatively with the number of threads |
556 | parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32 |
1016 | (higher parallelity => MUCH higher latency). With current Linux 2.6 |
557 | threads should be fine. |
1017 | versions, 4-32 threads should be fine. |
558 | |
1018 | |
559 | Under most circumstances you don't need to call this function, as the |
1019 | Under most circumstances you don't need to call this function, as the |
560 | module selects a default that is suitable for low to moderate load. |
1020 | module selects a default that is suitable for low to moderate load. |
561 | |
1021 | |
562 | =item IO::AIO::max_parallel $nthreads |
1022 | =item IO::AIO::max_parallel $nthreads |
… | |
… | |
571 | This module automatically runs C<max_parallel 0> at program end, to ensure |
1031 | This module automatically runs C<max_parallel 0> at program end, to ensure |
572 | that all threads are killed and that there are no outstanding requests. |
1032 | that all threads are killed and that there are no outstanding requests. |
573 | |
1033 | |
574 | Under normal circumstances you don't need to call this function. |
1034 | Under normal circumstances you don't need to call this function. |
575 | |
1035 | |
|
|
1036 | =item IO::AIO::max_idle $nthreads |
|
|
1037 | |
|
|
1038 | Limit the number of threads (default: 4) that are allowed to idle (i.e., |
|
|
1039 | threads that did not get a request to process within 10 seconds). That |
|
|
1040 | means if a thread becomes idle while C<$nthreads> other threads are also |
|
|
1041 | idle, it will free its resources and exit. |
|
|
1042 | |
|
|
1043 | This is useful when you allow a large number of threads (e.g. 100 or 1000) |
|
|
1044 | to allow for extremely high load situations, but want to free resources |
|
|
1045 | under normal circumstances (1000 threads can easily consume 30MB of RAM). |
|
|
1046 | |
|
|
1047 | The default is probably ok in most situations, especially if thread |
|
|
1048 | creation is fast. If thread creation is very slow on your system you might |
|
|
1049 | want to use larger values. |
|
|
1050 | |
576 | =item $oldnreqs = IO::AIO::max_outstanding $nreqs |
1051 | =item $oldmaxreqs = IO::AIO::max_outstanding $maxreqs |
|
|
1052 | |
|
|
1053 | This is a very bad function to use in interactive programs because it |
|
|
1054 | blocks, and a bad way to reduce concurrency because it is inexact: Better |
|
|
1055 | use an C<aio_group> together with a feed callback. |
577 | |
1056 | |
578 | Sets the maximum number of outstanding requests to C<$nreqs>. If you |
1057 | Sets the maximum number of outstanding requests to C<$nreqs>. If you |
579 | try to queue up more than this number of requests, the caller will block until |
1058 | to queue up more than this number of requests, the next call to the |
580 | some requests have been handled. |
1059 | C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>) |
|
|
1060 | function will block until the limit is no longer exceeded. |
581 | |
1061 | |
582 | The default is very large, so normally there is no practical limit. If you |
1062 | The default value is very large, so there is no practical limit on the |
583 | queue up many requests in a loop it often improves speed if you set |
1063 | number of outstanding requests. |
584 | this to a relatively low number, such as C<100>. |
|
|
585 | |
1064 | |
586 | Under normal circumstances you don't need to call this function. |
1065 | You can still queue as many requests as you want. Therefore, |
|
|
1066 | C<max_oustsanding> is mainly useful in simple scripts (with low values) or |
|
|
1067 | as a stop gap to shield against fatal memory overflow (with large values). |
|
|
1068 | |
|
|
1069 | =head3 STATISTICAL INFORMATION |
|
|
1070 | |
|
|
1071 | =item IO::AIO::nreqs |
|
|
1072 | |
|
|
1073 | Returns the number of requests currently in the ready, execute or pending |
|
|
1074 | states (i.e. for which their callback has not been invoked yet). |
|
|
1075 | |
|
|
1076 | Example: wait till there are no outstanding requests anymore: |
|
|
1077 | |
|
|
1078 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
1079 | while IO::AIO::nreqs; |
|
|
1080 | |
|
|
1081 | =item IO::AIO::nready |
|
|
1082 | |
|
|
1083 | Returns the number of requests currently in the ready state (not yet |
|
|
1084 | executed). |
|
|
1085 | |
|
|
1086 | =item IO::AIO::npending |
|
|
1087 | |
|
|
1088 | Returns the number of requests currently in the pending state (executed, |
|
|
1089 | but not yet processed by poll_cb). |
587 | |
1090 | |
588 | =back |
1091 | =back |
589 | |
1092 | |
590 | =cut |
1093 | =cut |
591 | |
1094 | |
… | |
… | |
603 | or return undef; |
1106 | or return undef; |
604 | |
1107 | |
605 | *$sym |
1108 | *$sym |
606 | } |
1109 | } |
607 | |
1110 | |
608 | min_parallel 4; |
1111 | min_parallel 8; |
609 | |
1112 | |
610 | END { |
1113 | END { |
611 | max_parallel 0; |
1114 | min_parallel 1; |
612 | } |
1115 | flush; |
|
|
1116 | }; |
613 | |
1117 | |
614 | 1; |
1118 | 1; |
615 | |
1119 | |
616 | =head2 FORK BEHAVIOUR |
1120 | =head2 FORK BEHAVIOUR |
|
|
1121 | |
|
|
1122 | This module should do "the right thing" when the process using it forks: |
617 | |
1123 | |
618 | Before the fork, IO::AIO enters a quiescent state where no requests |
1124 | Before the fork, IO::AIO enters a quiescent state where no requests |
619 | can be added in other threads and no results will be processed. After |
1125 | can be added in other threads and no results will be processed. After |
620 | the fork the parent simply leaves the quiescent state and continues |
1126 | the fork the parent simply leaves the quiescent state and continues |
621 | request/result processing, while the child clears the request/result |
1127 | request/result processing, while the child frees the request/result queue |
622 | queue (so the requests started before the fork will only be handled in |
1128 | (so that the requests started before the fork will only be handled in the |
623 | the parent). Threats will be started on demand until the limit ste in the |
1129 | parent). Threads will be started on demand until the limit set in the |
624 | parent process has been reached again. |
1130 | parent process has been reached again. |
625 | |
1131 | |
|
|
1132 | In short: the parent will, after a short pause, continue as if fork had |
|
|
1133 | not been called, while the child will act as if IO::AIO has not been used |
|
|
1134 | yet. |
|
|
1135 | |
|
|
1136 | =head2 MEMORY USAGE |
|
|
1137 | |
|
|
1138 | Per-request usage: |
|
|
1139 | |
|
|
1140 | Each aio request uses - depending on your architecture - around 100-200 |
|
|
1141 | bytes of memory. In addition, stat requests need a stat buffer (possibly |
|
|
1142 | a few hundred bytes), readdir requires a result buffer and so on. Perl |
|
|
1143 | scalars and other data passed into aio requests will also be locked and |
|
|
1144 | will consume memory till the request has entered the done state. |
|
|
1145 | |
|
|
1146 | This is now awfully much, so queuing lots of requests is not usually a |
|
|
1147 | problem. |
|
|
1148 | |
|
|
1149 | Per-thread usage: |
|
|
1150 | |
|
|
1151 | In the execution phase, some aio requests require more memory for |
|
|
1152 | temporary buffers, and each thread requires a stack and other data |
|
|
1153 | structures (usually around 16k-128k, depending on the OS). |
|
|
1154 | |
|
|
1155 | =head1 KNOWN BUGS |
|
|
1156 | |
|
|
1157 | Known bugs will be fixed in the next release. |
|
|
1158 | |
626 | =head1 SEE ALSO |
1159 | =head1 SEE ALSO |
627 | |
1160 | |
628 | L<Coro>, L<Linux::AIO>. |
1161 | L<Coro::AIO>. |
629 | |
1162 | |
630 | =head1 AUTHOR |
1163 | =head1 AUTHOR |
631 | |
1164 | |
632 | Marc Lehmann <schmorp@schmorp.de> |
1165 | Marc Lehmann <schmorp@schmorp.de> |
633 | http://home.schmorp.de/ |
1166 | http://home.schmorp.de/ |