… | |
… | |
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 | # Event |
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 |
|
|
31 | open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!"; |
|
|
32 | my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb }); |
|
|
33 | |
|
|
34 | # Event integration |
21 | Event->io (fd => IO::AIO::poll_fileno, |
35 | Event->io (fd => IO::AIO::poll_fileno, |
22 | poll => 'r', |
36 | poll => 'r', |
23 | cb => \&IO::AIO::poll_cb); |
37 | cb => \&IO::AIO::poll_cb); |
24 | |
38 | |
25 | # Glib/Gtk2 |
39 | # Glib/Gtk2 integration |
26 | add_watch Glib::IO IO::AIO::poll_fileno, |
40 | add_watch Glib::IO IO::AIO::poll_fileno, |
27 | in => sub { IO::AIO::poll_cb, 1 }; |
41 | in => sub { IO::AIO::poll_cb; 1 }; |
28 | |
42 | |
29 | # Tk |
43 | # Tk integration |
30 | Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "", |
44 | Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "", |
31 | readable => \&IO::AIO::poll_cb); |
45 | readable => \&IO::AIO::poll_cb); |
32 | |
46 | |
33 | # Danga::Socket |
47 | # Danga::Socket integration |
34 | Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => |
48 | Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => |
35 | \&IO::AIO::poll_cb); |
49 | \&IO::AIO::poll_cb); |
36 | |
50 | |
37 | |
|
|
38 | =head1 DESCRIPTION |
51 | =head1 DESCRIPTION |
39 | |
52 | |
40 | This module implements asynchronous I/O using whatever means your |
53 | This module implements asynchronous I/O using whatever means your |
41 | operating system supports. |
54 | operating system supports. |
42 | |
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 | |
43 | 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 |
44 | 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 |
45 | 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 |
46 | 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 |
47 | aio functions available on many operating systems. However, they are often |
77 | functions available on many operating systems. However, they are often |
48 | 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 |
49 | 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 |
50 | 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. |
51 | |
82 | |
52 | 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-) |
53 | currently not reentrant, so use appropriate locking yourself. |
84 | threads, it is currently not reentrant in any way, so use appropriate |
|
|
85 | locking yourself, always call C<poll_cb> from within the same thread, or |
|
|
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 |
54 | |
183 | |
55 | =cut |
184 | =cut |
56 | |
185 | |
57 | package IO::AIO; |
186 | package IO::AIO; |
58 | |
187 | |
|
|
188 | no warnings; |
|
|
189 | use strict 'vars'; |
|
|
190 | |
59 | use base 'Exporter'; |
191 | use base 'Exporter'; |
60 | |
192 | |
61 | use Fcntl (); |
|
|
62 | |
|
|
63 | BEGIN { |
193 | BEGIN { |
64 | $VERSION = 0.3; |
194 | our $VERSION = '2.2'; |
65 | |
195 | |
66 | @EXPORT = qw(aio_read aio_write aio_open aio_close aio_stat aio_lstat aio_unlink |
196 | our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat |
67 | aio_fsync aio_fdatasync aio_readahead); |
197 | aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink |
68 | @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs); |
198 | aio_readlink aio_fsync aio_fdatasync aio_readahead aio_rename aio_link |
|
|
199 | aio_move aio_copy aio_group aio_nop aio_mknod); |
|
|
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'; |
69 | |
207 | |
70 | require XSLoader; |
208 | require XSLoader; |
71 | XSLoader::load IO::AIO, $VERSION; |
209 | XSLoader::load ("IO::AIO", $VERSION); |
72 | } |
210 | } |
73 | |
211 | |
74 | =head1 FUNCTIONS |
212 | =head1 FUNCTIONS |
75 | |
213 | |
76 | =head2 AIO FUNCTIONS |
214 | =head2 AIO REQUEST FUNCTIONS |
77 | |
215 | |
78 | All the C<aio_*> calls are more or less thin wrappers around the syscall |
216 | All the C<aio_*> calls are more or less thin wrappers around the syscall |
79 | with the same name (sans C<aio_>). The arguments are similar or identical, |
217 | with the same name (sans C<aio_>). The arguments are similar or identical, |
80 | and they all accept an additional (and optional) C<$callback> argument |
218 | and they all accept an additional (and optional) C<$callback> argument |
81 | 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 |
82 | the syscall return code (e.g. most syscalls return C<-1> on error, unlike |
220 | the syscall return code (e.g. most syscalls return C<-1> on error, unlike |
83 | perl, which usually delivers "false") as it's sole argument when the given |
221 | perl, which usually delivers "false") as it's sole argument when the given |
84 | syscall has been executed asynchronously. |
222 | syscall has been executed asynchronously. |
85 | |
223 | |
86 | All functions that expect a filehandle will also accept a file descriptor. |
224 | All functions expecting a filehandle keep a copy of the filehandle |
|
|
225 | internally until the request has finished. |
87 | |
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 | |
88 | The filenames you pass to these routines I<must> be absolute. The reason |
230 | The pathnames you pass to these routines I<must> be absolute and |
89 | is that at the time the request is being executed, the current working |
231 | encoded as octets. The reason for the former is that at the time the |
90 | directory could have changed. Alternatively, you can make sure that you |
232 | request is being executed, the current working directory could have |
91 | never change the current working directory. |
233 | changed. Alternatively, you can make sure that you never change the |
|
|
234 | current working directory anywhere in the program and then use relative |
|
|
235 | paths. |
|
|
236 | |
|
|
237 | To encode pathnames as octets, either make sure you either: a) always pass |
|
|
238 | in filenames you got from outside (command line, readdir etc.) without |
|
|
239 | tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module and encode |
|
|
240 | your pathnames to the locale (or other) encoding in effect in the user |
|
|
241 | environment, d) use Glib::filename_from_unicode on unicode filenames or e) |
|
|
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. |
92 | |
246 | |
93 | =over 4 |
247 | =over 4 |
94 | |
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. |
|
|
279 | |
95 | =item aio_open $pathname, $flags, $mode, $callback |
280 | =item aio_open $pathname, $flags, $mode, $callback->($fh) |
96 | |
281 | |
97 | 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 |
98 | created filehandle for the file. |
283 | created filehandle for the file. |
99 | |
284 | |
100 | The pathname passed to C<aio_open> must be absolute. See API NOTES, above, |
285 | The pathname passed to C<aio_open> must be absolute. See API NOTES, above, |
101 | for an explanation. |
286 | for an explanation. |
102 | |
287 | |
103 | The C<$mode> argument is a bitmask. See the C<Fcntl> module for a |
288 | The C<$flags> argument is a bitmask. See the C<Fcntl> module for a |
104 | list. They are the same as used in C<sysopen>. |
289 | list. They are the same as used by C<sysopen>. |
|
|
290 | |
|
|
291 | Likewise, C<$mode> specifies the mode of the newly created file, if it |
|
|
292 | didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>, |
|
|
293 | except that it is mandatory (i.e. use C<0> if you don't create new files, |
|
|
294 | and C<0666> or C<0777> if you do). |
105 | |
295 | |
106 | Example: |
296 | Example: |
107 | |
297 | |
108 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
298 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
109 | if ($_[0]) { |
299 | if ($_[0]) { |
… | |
… | |
112 | } else { |
302 | } else { |
113 | die "open failed: $!\n"; |
303 | die "open failed: $!\n"; |
114 | } |
304 | } |
115 | }; |
305 | }; |
116 | |
306 | |
117 | =item aio_close $fh, $callback |
307 | =item aio_close $fh, $callback->($status) |
118 | |
308 | |
119 | Asynchronously close a file and call the callback with the result |
309 | Asynchronously close a file and call the callback with the result |
120 | code. I<WARNING:> although accepted, you should not pass in a perl |
310 | code. I<WARNING:> although accepted, you should not pass in a perl |
121 | filehandle here, as perl will likely close the file descriptor itself when |
311 | filehandle here, as perl will likely close the file descriptor another |
122 | the filehandle is destroyed. Normally, you can safely call perls C<close> |
312 | time when the filehandle is destroyed. Normally, you can safely call perls |
123 | or just let filehandles go out of scope. |
313 | C<close> or just let filehandles go out of scope. |
124 | |
314 | |
|
|
315 | This is supposed to be a bug in the API, so that might change. It's |
|
|
316 | therefore best to avoid this function. |
|
|
317 | |
125 | =item aio_read $fh,$offset,$length, $data,$dataoffset,$callback |
318 | =item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
126 | |
319 | |
127 | =item aio_write $fh,$offset,$length, $data,$dataoffset,$callback |
320 | =item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
128 | |
321 | |
129 | Reads or writes C<length> bytes from the specified C<fh> and C<offset> |
322 | Reads or writes C<length> bytes from the specified C<fh> and C<offset> |
130 | into the scalar given by C<data> and offset C<dataoffset> and calls the |
323 | into the scalar given by C<data> and offset C<dataoffset> and calls the |
131 | callback without the actual number of bytes read (or -1 on error, just |
324 | callback without the actual number of bytes read (or -1 on error, just |
132 | like the syscall). |
325 | like the syscall). |
133 | |
326 | |
|
|
327 | The C<$data> scalar I<MUST NOT> be modified in any way while the request |
|
|
328 | is outstanding. Modifying it can result in segfaults or WW3 (if the |
|
|
329 | necessary/optional hardware is installed). |
|
|
330 | |
134 | Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at |
331 | Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at |
135 | offset C<0> within the scalar: |
332 | offset C<0> within the scalar: |
136 | |
333 | |
137 | aio_read $fh, 7, 15, $buffer, 0, sub { |
334 | aio_read $fh, 7, 15, $buffer, 0, sub { |
138 | $_[0] > 0 or die "read error: $!"; |
335 | $_[0] > 0 or die "read error: $!"; |
139 | print "read $_[0] bytes: <$buffer>\n"; |
336 | print "read $_[0] bytes: <$buffer>\n"; |
140 | }; |
337 | }; |
141 | |
338 | |
|
|
339 | =item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) |
|
|
340 | |
|
|
341 | Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts |
|
|
342 | reading at byte offset C<$in_offset>, and starts writing at the current |
|
|
343 | file offset of C<$out_fh>. Because of that, it is not safe to issue more |
|
|
344 | than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each |
|
|
345 | other. |
|
|
346 | |
|
|
347 | This call tries to make use of a native C<sendfile> syscall to provide |
|
|
348 | zero-copy operation. For this to work, C<$out_fh> should refer to a |
|
|
349 | socket, and C<$in_fh> should refer to mmap'able file. |
|
|
350 | |
|
|
351 | If the native sendfile call fails or is not implemented, it will be |
|
|
352 | emulated, so you can call C<aio_sendfile> on any type of filehandle |
|
|
353 | regardless of the limitations of the operating system. |
|
|
354 | |
|
|
355 | Please note, however, that C<aio_sendfile> can read more bytes from |
|
|
356 | C<$in_fh> than are written, and there is no way to find out how many |
|
|
357 | bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only |
|
|
358 | provides the number of bytes written to C<$out_fh>. Only if the result |
|
|
359 | value equals C<$length> one can assume that C<$length> bytes have been |
|
|
360 | read. |
|
|
361 | |
142 | =item aio_readahead $fh,$offset,$length, $callback |
362 | =item aio_readahead $fh,$offset,$length, $callback->($retval) |
143 | |
363 | |
144 | Asynchronously reads the specified byte range into the page cache, using |
|
|
145 | the C<readahead> syscall. If that syscall doesn't exist (likely if your OS |
|
|
146 | isn't Linux) the status will be C<-1> and C<$!> is set to ENOSYS. |
|
|
147 | |
|
|
148 | readahead() populates the page cache with data from a file so that |
364 | C<aio_readahead> populates the page cache with data from a file so that |
149 | subsequent reads from that file will not block on disk I/O. The C<$offset> |
365 | subsequent reads from that file will not block on disk I/O. The C<$offset> |
150 | argument specifies the starting point from which data is to be read and |
366 | argument specifies the starting point from which data is to be read and |
151 | C<$length> specifies the number of bytes to be read. I/O is performed in |
367 | C<$length> specifies the number of bytes to be read. I/O is performed in |
152 | whole pages, so that offset is effectively rounded down to a page boundary |
368 | whole pages, so that offset is effectively rounded down to a page boundary |
153 | and bytes are read up to the next page boundary greater than or equal to |
369 | and bytes are read up to the next page boundary greater than or equal to |
154 | (off-set+length). aio_readahead() does not read beyond the end of the |
370 | (off-set+length). C<aio_readahead> does not read beyond the end of the |
155 | file. The current file offset of the file is left unchanged. |
371 | file. The current file offset of the file is left unchanged. |
156 | |
372 | |
|
|
373 | If that syscall doesn't exist (likely if your OS isn't Linux) it will be |
|
|
374 | emulated by simply reading the data, which would have a similar effect. |
|
|
375 | |
157 | =item aio_stat $fh_or_path, $callback |
376 | =item aio_stat $fh_or_path, $callback->($status) |
158 | |
377 | |
159 | =item aio_lstat $fh, $callback |
378 | =item aio_lstat $fh, $callback->($status) |
160 | |
379 | |
161 | Works like perl's C<stat> or C<lstat> in void context. The callback will |
380 | Works like perl's C<stat> or C<lstat> in void context. The callback will |
162 | be called after the stat and the results will be available using C<stat _> |
381 | be called after the stat and the results will be available using C<stat _> |
163 | or C<-s _> etc... |
382 | or C<-s _> etc... |
164 | |
383 | |
… | |
… | |
174 | aio_stat "/etc/passwd", sub { |
393 | aio_stat "/etc/passwd", sub { |
175 | $_[0] and die "stat failed: $!"; |
394 | $_[0] and die "stat failed: $!"; |
176 | print "size is ", -s _, "\n"; |
395 | print "size is ", -s _, "\n"; |
177 | }; |
396 | }; |
178 | |
397 | |
179 | =item aio_unlink $pathname, $callback |
398 | =item aio_unlink $pathname, $callback->($status) |
180 | |
399 | |
181 | Asynchronously unlink (delete) a file and call the callback with the |
400 | Asynchronously unlink (delete) a file and call the callback with the |
182 | result code. |
401 | result code. |
183 | |
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 | |
|
|
413 | =item aio_link $srcpath, $dstpath, $callback->($status) |
|
|
414 | |
|
|
415 | Asynchronously create a new link to the existing object at C<$srcpath> at |
|
|
416 | the path C<$dstpath> and call the callback with the result code. |
|
|
417 | |
|
|
418 | =item aio_symlink $srcpath, $dstpath, $callback->($status) |
|
|
419 | |
|
|
420 | Asynchronously create a new symbolic link to the existing object at C<$srcpath> at |
|
|
421 | the path C<$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. |
|
|
428 | |
|
|
429 | =item aio_rename $srcpath, $dstpath, $callback->($status) |
|
|
430 | |
|
|
431 | Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as |
|
|
432 | rename(2) and call the callback with the result code. |
|
|
433 | |
|
|
434 | =item aio_rmdir $pathname, $callback->($status) |
|
|
435 | |
|
|
436 | Asynchronously rmdir (delete) a directory and call the callback with the |
|
|
437 | result code. |
|
|
438 | |
|
|
439 | =item aio_readdir $pathname, $callback->($entries) |
|
|
440 | |
|
|
441 | Unlike the POSIX call of the same name, C<aio_readdir> reads an entire |
|
|
442 | directory (i.e. opendir + readdir + closedir). The entries will not be |
|
|
443 | sorted, and will B<NOT> include the C<.> and C<..> entries. |
|
|
444 | |
|
|
445 | The callback a single argument which is either C<undef> or an array-ref |
|
|
446 | with the filenames. |
|
|
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 | |
|
|
550 | =item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) |
|
|
551 | |
|
|
552 | Scans a directory (similar to C<aio_readdir>) but additionally tries to |
|
|
553 | efficiently separate the entries of directory C<$path> into two sets of |
|
|
554 | names, directories you can recurse into (directories), and ones you cannot |
|
|
555 | recurse into (everything else, including symlinks to directories). |
|
|
556 | |
|
|
557 | C<aio_scandir> is a composite request that creates of many sub requests_ |
|
|
558 | C<$maxreq> specifies the maximum number of outstanding aio requests that |
|
|
559 | this function generates. If it is C<< <= 0 >>, then a suitable default |
|
|
560 | will be chosen (currently 4). |
|
|
561 | |
|
|
562 | On error, the callback is called without arguments, otherwise it receives |
|
|
563 | two array-refs with path-relative entry names. |
|
|
564 | |
|
|
565 | Example: |
|
|
566 | |
|
|
567 | aio_scandir $dir, 0, sub { |
|
|
568 | my ($dirs, $nondirs) = @_; |
|
|
569 | print "real directories: @$dirs\n"; |
|
|
570 | print "everything else: @$nondirs\n"; |
|
|
571 | }; |
|
|
572 | |
|
|
573 | Implementation notes. |
|
|
574 | |
|
|
575 | The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can. |
|
|
576 | |
|
|
577 | After reading the directory, the modification time, size etc. of the |
|
|
578 | directory before and after the readdir is checked, and if they match (and |
|
|
579 | isn't the current time), the link count will be used to decide how many |
|
|
580 | entries are directories (if >= 2). Otherwise, no knowledge of the number |
|
|
581 | of subdirectories will be assumed. |
|
|
582 | |
|
|
583 | Then entries will be sorted into likely directories (everything without |
|
|
584 | a non-initial dot currently) and likely non-directories (everything |
|
|
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 |
|
|
589 | filesystems might detect the type of the entry without reading the inode |
|
|
590 | data (e.g. ext2fs filetype feature). |
|
|
591 | |
|
|
592 | If the known number of directories (link count - 2) has been reached, the |
|
|
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. |
|
|
601 | |
|
|
602 | =cut |
|
|
603 | |
|
|
604 | sub aio_scandir($$$) { |
|
|
605 | my ($path, $maxreq, $cb) = @_; |
|
|
606 | |
|
|
607 | my $pri = aioreq_pri; |
|
|
608 | |
|
|
609 | my $grp = aio_group $cb; |
|
|
610 | |
|
|
611 | $maxreq = 4 if $maxreq <= 0; |
|
|
612 | |
|
|
613 | # stat once |
|
|
614 | aioreq_pri $pri; |
|
|
615 | add $grp aio_stat $path, sub { |
|
|
616 | return $grp->result () if $_[0]; |
|
|
617 | my $now = time; |
|
|
618 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
|
|
619 | |
|
|
620 | # read the directory entries |
|
|
621 | aioreq_pri $pri; |
|
|
622 | add $grp aio_readdir $path, sub { |
|
|
623 | my $entries = shift |
|
|
624 | or return $grp->result (); |
|
|
625 | |
|
|
626 | # stat the dir another time |
|
|
627 | aioreq_pri $pri; |
|
|
628 | add $grp aio_stat $path, sub { |
|
|
629 | my $hash2 = join ":", (stat _)[0,1,3,7,9]; |
|
|
630 | |
|
|
631 | my $ndirs; |
|
|
632 | |
|
|
633 | # take the slow route if anything looks fishy |
|
|
634 | if ($hash1 ne $hash2 or (stat _)[9] == $now) { |
|
|
635 | $ndirs = -1; |
|
|
636 | } else { |
|
|
637 | # if nlink == 2, we are finished |
|
|
638 | # on non-posix-fs's, we rely on nlink < 2 |
|
|
639 | $ndirs = (stat _)[3] - 2 |
|
|
640 | or return $grp->result ([], $entries); |
|
|
641 | } |
|
|
642 | |
|
|
643 | # sort into likely dirs and likely nondirs |
|
|
644 | # dirs == files without ".", short entries first |
|
|
645 | $entries = [map $_->[0], |
|
|
646 | sort { $b->[1] cmp $a->[1] } |
|
|
647 | map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length], |
|
|
648 | @$entries]; |
|
|
649 | |
|
|
650 | my (@dirs, @nondirs); |
|
|
651 | |
|
|
652 | my $statgrp = add $grp aio_group sub { |
|
|
653 | $grp->result (\@dirs, \@nondirs); |
|
|
654 | }; |
|
|
655 | |
|
|
656 | limit $statgrp $maxreq; |
|
|
657 | feed $statgrp sub { |
|
|
658 | return unless @$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 | } |
|
|
679 | } |
|
|
680 | } |
|
|
681 | }; |
|
|
682 | }; |
|
|
683 | }; |
|
|
684 | }; |
|
|
685 | }; |
|
|
686 | |
|
|
687 | $grp |
|
|
688 | } |
|
|
689 | |
184 | =item aio_fsync $fh, $callback |
690 | =item aio_fsync $fh, $callback->($status) |
185 | |
691 | |
186 | Asynchronously call fsync on the given filehandle and call the callback |
692 | Asynchronously call fsync on the given filehandle and call the callback |
187 | with the fsync result code. |
693 | with the fsync result code. |
188 | |
694 | |
189 | =item aio_fdatasync $fh, $callback |
695 | =item aio_fdatasync $fh, $callback->($status) |
190 | |
696 | |
191 | Asynchronously call fdatasync on the given filehandle and call the |
697 | Asynchronously call fdatasync on the given filehandle and call the |
192 | callback with the fdatasync result code. |
698 | callback with the fdatasync result code. |
193 | |
699 | |
|
|
700 | If this call isn't available because your OS lacks it or it couldn't be |
|
|
701 | detected, it will be emulated by calling C<fsync> instead. |
|
|
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 | |
194 | =back |
747 | =back |
195 | |
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 | |
196 | =head2 SUPPORT FUNCTIONS |
909 | =head2 SUPPORT FUNCTIONS |
197 | |
910 | |
|
|
911 | =head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION |
|
|
912 | |
198 | =over 4 |
913 | =over 4 |
199 | |
914 | |
200 | =item $fileno = IO::AIO::poll_fileno |
915 | =item $fileno = IO::AIO::poll_fileno |
201 | |
916 | |
202 | Return the I<request result pipe filehandle>. This filehandle must be |
917 | Return the I<request result pipe file descriptor>. This filehandle must be |
203 | polled for reading by some mechanism outside this module (e.g. Event |
918 | polled for reading by some mechanism outside this module (e.g. Event or |
204 | or select, see below). If the pipe becomes readable you have to call |
919 | select, see below or the SYNOPSIS). If the pipe becomes readable you have |
205 | C<poll_cb> to check the results. |
920 | to call C<poll_cb> to check the results. |
206 | |
921 | |
207 | See C<poll_cb> for an example. |
922 | See C<poll_cb> for an example. |
208 | |
923 | |
209 | =item IO::AIO::poll_cb |
924 | =item IO::AIO::poll_cb |
210 | |
925 | |
211 | 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 |
212 | regularly. Returns the number of events processed. Returns immediately |
927 | regularly. Returns the number of events processed. Returns immediately |
213 | 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>. |
214 | |
930 | |
215 | You can use Event to multiplex, e.g.: |
931 | If not all requests were processed for whatever reason, the filehandle |
|
|
932 | will still be ready when C<poll_cb> returns. |
|
|
933 | |
|
|
934 | Example: Install an Event watcher that automatically calls |
|
|
935 | IO::AIO::poll_cb with high priority: |
216 | |
936 | |
217 | Event->io (fd => IO::AIO::poll_fileno, |
937 | Event->io (fd => IO::AIO::poll_fileno, |
218 | poll => 'r', async => 1, |
938 | poll => 'r', async => 1, |
219 | cb => \&IO::AIO::poll_cb); |
939 | cb => \&IO::AIO::poll_cb); |
220 | |
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 | |
221 | =item IO::AIO::poll_wait |
974 | =item IO::AIO::poll_wait |
222 | |
975 | |
|
|
976 | If there are any outstanding requests and none of them in the result |
223 | Wait till the result filehandle becomes ready for reading (simply does a |
977 | phase, wait till the result filehandle becomes ready for reading (simply |
224 | select on the filehandle. This is useful if you want to synchronously wait |
978 | does a C<select> on the filehandle. This is useful if you want to |
225 | for some requests to finish). |
979 | synchronously wait for some requests to finish). |
226 | |
980 | |
227 | See C<nreqs> for an example. |
981 | See C<nreqs> for an example. |
228 | |
982 | |
|
|
983 | =item IO::AIO::poll |
|
|
984 | |
|
|
985 | Waits until some requests have been handled. |
|
|
986 | |
|
|
987 | Returns the number of requests processed, but is otherwise strictly |
|
|
988 | equivalent to: |
|
|
989 | |
|
|
990 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
991 | |
229 | =item IO::AIO::nreqs |
992 | =item IO::AIO::flush |
230 | |
993 | |
231 | Returns the number of requests currently outstanding. |
994 | Wait till all outstanding AIO requests have been handled. |
232 | |
995 | |
233 | Example: wait till there are no outstanding requests anymore: |
996 | Strictly equivalent to: |
234 | |
997 | |
235 | IO::AIO::poll_wait, IO::AIO::poll_cb |
998 | IO::AIO::poll_wait, IO::AIO::poll_cb |
236 | while IO::AIO::nreqs; |
999 | while IO::AIO::nreqs; |
237 | |
1000 | |
|
|
1001 | =head3 CONTROLLING THE NUMBER OF THREADS |
|
|
1002 | |
|
|
1003 | =item IO::AIO::min_parallel $nthreads |
|
|
1004 | |
|
|
1005 | Set the minimum number of AIO threads to C<$nthreads>. The current |
|
|
1006 | default is C<8>, which means eight asynchronous operations can execute |
|
|
1007 | concurrently at any one time (the number of outstanding requests, |
|
|
1008 | however, is unlimited). |
|
|
1009 | |
|
|
1010 | IO::AIO starts threads only on demand, when an AIO request is queued and |
|
|
1011 | no free thread exists. Please note that queueing up a hundred requests can |
|
|
1012 | create demand for a hundred threads, even if it turns out that everything |
|
|
1013 | is in the cache and could have been processed faster by a single thread. |
|
|
1014 | |
|
|
1015 | It is recommended to keep the number of threads relatively low, as some |
|
|
1016 | Linux kernel versions will scale negatively with the number of threads |
|
|
1017 | (higher parallelity => MUCH higher latency). With current Linux 2.6 |
|
|
1018 | versions, 4-32 threads should be fine. |
|
|
1019 | |
|
|
1020 | Under most circumstances you don't need to call this function, as the |
|
|
1021 | module selects a default that is suitable for low to moderate load. |
|
|
1022 | |
|
|
1023 | =item IO::AIO::max_parallel $nthreads |
|
|
1024 | |
|
|
1025 | Sets the maximum number of AIO threads to C<$nthreads>. If more than the |
|
|
1026 | specified number of threads are currently running, this function kills |
|
|
1027 | them. This function blocks until the limit is reached. |
|
|
1028 | |
|
|
1029 | While C<$nthreads> are zero, aio requests get queued but not executed |
|
|
1030 | until the number of threads has been increased again. |
|
|
1031 | |
|
|
1032 | This module automatically runs C<max_parallel 0> at program end, to ensure |
|
|
1033 | that all threads are killed and that there are no outstanding requests. |
|
|
1034 | |
|
|
1035 | Under normal circumstances you don't need to call this function. |
|
|
1036 | |
|
|
1037 | =item IO::AIO::max_idle $nthreads |
|
|
1038 | |
|
|
1039 | Limit the number of threads (default: 4) that are allowed to idle (i.e., |
|
|
1040 | threads that did not get a request to process within 10 seconds). That |
|
|
1041 | means if a thread becomes idle while C<$nthreads> other threads are also |
|
|
1042 | idle, it will free its resources and exit. |
|
|
1043 | |
|
|
1044 | This is useful when you allow a large number of threads (e.g. 100 or 1000) |
|
|
1045 | to allow for extremely high load situations, but want to free resources |
|
|
1046 | under normal circumstances (1000 threads can easily consume 30MB of RAM). |
|
|
1047 | |
|
|
1048 | The default is probably ok in most situations, especially if thread |
|
|
1049 | creation is fast. If thread creation is very slow on your system you might |
|
|
1050 | want to use larger values. |
|
|
1051 | |
|
|
1052 | =item $oldmaxreqs = IO::AIO::max_outstanding $maxreqs |
|
|
1053 | |
|
|
1054 | This is a very bad function to use in interactive programs because it |
|
|
1055 | blocks, and a bad way to reduce concurrency because it is inexact: Better |
|
|
1056 | use an C<aio_group> together with a feed callback. |
|
|
1057 | |
|
|
1058 | Sets the maximum number of outstanding requests to C<$nreqs>. If you |
|
|
1059 | to queue up more than this number of requests, the next call to the |
|
|
1060 | C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>) |
|
|
1061 | function will block until the limit is no longer exceeded. |
|
|
1062 | |
|
|
1063 | The default value is very large, so there is no practical limit on the |
|
|
1064 | number of outstanding requests. |
|
|
1065 | |
|
|
1066 | You can still queue as many requests as you want. Therefore, |
|
|
1067 | C<max_oustsanding> is mainly useful in simple scripts (with low values) or |
|
|
1068 | as a stop gap to shield against fatal memory overflow (with large values). |
|
|
1069 | |
|
|
1070 | =head3 STATISTICAL INFORMATION |
|
|
1071 | |
238 | =item IO::AIO::flush |
1072 | =item IO::AIO::nreqs |
239 | |
1073 | |
240 | Wait till all outstanding AIO requests have been handled. |
1074 | Returns the number of requests currently in the ready, execute or pending |
|
|
1075 | states (i.e. for which their callback has not been invoked yet). |
241 | |
1076 | |
242 | Strictly equivalent to: |
1077 | Example: wait till there are no outstanding requests anymore: |
243 | |
1078 | |
244 | IO::AIO::poll_wait, IO::AIO::poll_cb |
1079 | IO::AIO::poll_wait, IO::AIO::poll_cb |
245 | while IO::AIO::nreqs; |
1080 | while IO::AIO::nreqs; |
246 | |
1081 | |
|
|
1082 | =item IO::AIO::nready |
|
|
1083 | |
|
|
1084 | Returns the number of requests currently in the ready state (not yet |
|
|
1085 | executed). |
|
|
1086 | |
247 | =item IO::AIO::poll |
1087 | =item IO::AIO::npending |
248 | |
1088 | |
249 | Waits until some requests have been handled. |
1089 | Returns the number of requests currently in the pending state (executed, |
250 | |
1090 | but not yet processed by poll_cb). |
251 | Strictly equivalent to: |
|
|
252 | |
|
|
253 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
254 | if IO::AIO::nreqs; |
|
|
255 | |
|
|
256 | =item IO::AIO::min_parallel $nthreads |
|
|
257 | |
|
|
258 | Set the minimum number of AIO threads to C<$nthreads>. The default is |
|
|
259 | C<1>, which means a single asynchronous operation can be done at one time |
|
|
260 | (the number of outstanding operations, however, is unlimited). |
|
|
261 | |
|
|
262 | It is recommended to keep the number of threads low, as some Linux |
|
|
263 | kernel versions will scale negatively with the number of threads (higher |
|
|
264 | parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32 |
|
|
265 | threads should be fine. |
|
|
266 | |
|
|
267 | Under normal circumstances you don't need to call this function, as this |
|
|
268 | module automatically starts some threads (the exact number might change, |
|
|
269 | and is currently 4). |
|
|
270 | |
|
|
271 | =item IO::AIO::max_parallel $nthreads |
|
|
272 | |
|
|
273 | Sets the maximum number of AIO threads to C<$nthreads>. If more than |
|
|
274 | the specified number of threads are currently running, kill them. This |
|
|
275 | function blocks until the limit is reached. |
|
|
276 | |
|
|
277 | This module automatically runs C<max_parallel 0> at program end, to ensure |
|
|
278 | that all threads are killed and that there are no outstanding requests. |
|
|
279 | |
|
|
280 | Under normal circumstances you don't need to call this function. |
|
|
281 | |
|
|
282 | =item $oldnreqs = IO::AIO::max_outstanding $nreqs |
|
|
283 | |
|
|
284 | Sets the maximum number of outstanding requests to C<$nreqs>. If you |
|
|
285 | try to queue up more than this number of requests, the caller will block until |
|
|
286 | some requests have been handled. |
|
|
287 | |
|
|
288 | The default is very large, so normally there is no practical limit. If you |
|
|
289 | queue up many requests in a loop it it often improves speed if you set |
|
|
290 | this to a relatively low number, such as C<100>. |
|
|
291 | |
|
|
292 | Under normal circumstances you don't need to call this function. |
|
|
293 | |
1091 | |
294 | =back |
1092 | =back |
295 | |
1093 | |
296 | =cut |
1094 | =cut |
297 | |
1095 | |
298 | # support function to convert a fd into a perl filehandle |
1096 | # support function to convert a fd into a perl filehandle |
299 | sub _fd2fh { |
1097 | sub _fd2fh { |
300 | return undef if $_[0] < 0; |
1098 | return undef if $_[0] < 0; |
301 | |
1099 | |
302 | # try to be perl5.6-compatible |
1100 | # try to generate nice filehandles |
303 | local *AIO_FH; |
1101 | my $sym = "IO::AIO::fd#$_[0]"; |
304 | open AIO_FH, "+<&=$_[0]" |
1102 | local *$sym; |
|
|
1103 | |
|
|
1104 | open *$sym, "+<&=$_[0]" # usually works under any unix |
|
|
1105 | or open *$sym, "<&=$_[0]" # cygwin needs this |
|
|
1106 | or open *$sym, ">&=$_[0]" # or this |
305 | or return undef; |
1107 | or return undef; |
306 | |
1108 | |
307 | *AIO_FH |
1109 | *$sym |
308 | } |
1110 | } |
309 | |
1111 | |
310 | min_parallel 4; |
1112 | min_parallel 8; |
311 | |
1113 | |
312 | END { |
1114 | END { |
313 | max_parallel 0; |
1115 | min_parallel 1; |
314 | } |
1116 | flush; |
|
|
1117 | }; |
315 | |
1118 | |
316 | 1; |
1119 | 1; |
317 | |
1120 | |
|
|
1121 | =head2 FORK BEHAVIOUR |
|
|
1122 | |
|
|
1123 | This module should do "the right thing" when the process using it forks: |
|
|
1124 | |
|
|
1125 | Before the fork, IO::AIO enters a quiescent state where no requests |
|
|
1126 | can be added in other threads and no results will be processed. After |
|
|
1127 | the fork the parent simply leaves the quiescent state and continues |
|
|
1128 | request/result processing, while the child frees the request/result queue |
|
|
1129 | (so that the requests started before the fork will only be handled in the |
|
|
1130 | parent). Threads will be started on demand until the limit set in the |
|
|
1131 | parent process has been reached again. |
|
|
1132 | |
|
|
1133 | In short: the parent will, after a short pause, continue as if fork had |
|
|
1134 | not been called, while the child will act as if IO::AIO has not been used |
|
|
1135 | yet. |
|
|
1136 | |
|
|
1137 | =head2 MEMORY USAGE |
|
|
1138 | |
|
|
1139 | Per-request usage: |
|
|
1140 | |
|
|
1141 | Each aio request uses - depending on your architecture - around 100-200 |
|
|
1142 | bytes of memory. In addition, stat requests need a stat buffer (possibly |
|
|
1143 | a few hundred bytes), readdir requires a result buffer and so on. Perl |
|
|
1144 | scalars and other data passed into aio requests will also be locked and |
|
|
1145 | will consume memory till the request has entered the done state. |
|
|
1146 | |
|
|
1147 | This is now awfully much, so queuing lots of requests is not usually a |
|
|
1148 | problem. |
|
|
1149 | |
|
|
1150 | Per-thread usage: |
|
|
1151 | |
|
|
1152 | In the execution phase, some aio requests require more memory for |
|
|
1153 | temporary buffers, and each thread requires a stack and other data |
|
|
1154 | structures (usually around 16k-128k, depending on the OS). |
|
|
1155 | |
|
|
1156 | =head1 KNOWN BUGS |
|
|
1157 | |
|
|
1158 | Known bugs will be fixed in the next release. |
|
|
1159 | |
318 | =head1 SEE ALSO |
1160 | =head1 SEE ALSO |
319 | |
1161 | |
320 | L<Coro>, L<Linux::AIO>. |
1162 | L<Coro::AIO>. |
321 | |
1163 | |
322 | =head1 AUTHOR |
1164 | =head1 AUTHOR |
323 | |
1165 | |
324 | Marc Lehmann <schmorp@schmorp.de> |
1166 | Marc Lehmann <schmorp@schmorp.de> |
325 | http://home.schmorp.de/ |
1167 | http://home.schmorp.de/ |