… | |
… | |
5 | =head1 SYNOPSIS |
5 | =head1 SYNOPSIS |
6 | |
6 | |
7 | use IO::AIO; |
7 | use IO::AIO; |
8 | |
8 | |
9 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
9 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
10 | my ($fh) = @_; |
10 | my $fh = shift |
|
|
11 | or die "/etc/passwd: $!"; |
11 | ... |
12 | ... |
12 | }; |
13 | }; |
13 | |
14 | |
14 | aio_unlink "/tmp/file", sub { }; |
15 | aio_unlink "/tmp/file", sub { }; |
15 | |
16 | |
… | |
… | |
18 | }; |
19 | }; |
19 | |
20 | |
20 | # version 2+ has request and group objects |
21 | # version 2+ has request and group objects |
21 | use IO::AIO 2; |
22 | use IO::AIO 2; |
22 | |
23 | |
|
|
24 | aioreq_pri 4; # give next request a very high priority |
23 | my $req = aio_unlink "/tmp/file", sub { }; |
25 | my $req = aio_unlink "/tmp/file", sub { }; |
24 | $req->cancel; # cancel request if still in queue |
26 | $req->cancel; # cancel request if still in queue |
25 | |
27 | |
26 | my $grp = aio_group sub { print "all stats done\n" }; |
28 | my $grp = aio_group sub { print "all stats done\n" }; |
27 | add $grp aio_stat "..." for ...; |
29 | add $grp aio_stat "..." for ...; |
28 | |
30 | |
|
|
31 | # AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...) |
|
|
32 | use AnyEvent::AIO; |
|
|
33 | |
29 | # AnyEvent integration |
34 | # EV integration |
30 | open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!"; |
35 | my $w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; |
31 | my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb }); |
|
|
32 | |
36 | |
33 | # Event integration |
37 | # Event integration |
34 | Event->io (fd => IO::AIO::poll_fileno, |
38 | Event->io (fd => IO::AIO::poll_fileno, |
35 | poll => 'r', |
39 | poll => 'r', |
36 | cb => \&IO::AIO::poll_cb); |
40 | cb => \&IO::AIO::poll_cb); |
… | |
… | |
50 | =head1 DESCRIPTION |
54 | =head1 DESCRIPTION |
51 | |
55 | |
52 | This module implements asynchronous I/O using whatever means your |
56 | This module implements asynchronous I/O using whatever means your |
53 | operating system supports. |
57 | operating system supports. |
54 | |
58 | |
|
|
59 | Asynchronous means that operations that can normally block your program |
|
|
60 | (e.g. reading from disk) will be done asynchronously: the operation |
|
|
61 | will still block, but you can do something else in the meantime. This |
|
|
62 | is extremely useful for programs that need to stay interactive even |
|
|
63 | when doing heavy I/O (GUI programs, high performance network servers |
|
|
64 | etc.), but can also be used to easily do operations in parallel that are |
|
|
65 | normally done sequentially, e.g. stat'ing many files, which is much faster |
|
|
66 | on a RAID volume or over NFS when you do a number of stat operations |
|
|
67 | concurrently. |
|
|
68 | |
|
|
69 | While most of this works on all types of file descriptors (for |
|
|
70 | example sockets), using these functions on file descriptors that |
|
|
71 | support nonblocking operation (again, sockets, pipes etc.) is very |
|
|
72 | inefficient. Use an event loop for that (such as the L<Event|Event> |
|
|
73 | module): IO::AIO will naturally fit into such an event loop itself. |
|
|
74 | |
55 | Currently, a number of threads are started that execute your read/writes |
75 | In this version, a number of threads are started that execute your |
56 | and signal their completion. You don't need thread support in your libc or |
76 | requests and signal their completion. You don't need thread support |
57 | perl, and the threads created by this module will not be visible to the |
77 | in perl, and the threads created by this module will not be visible |
58 | pthreads library. In the future, this module might make use of the native |
78 | to perl. In the future, this module might make use of the native aio |
59 | aio functions available on many operating systems. However, they are often |
79 | functions available on many operating systems. However, they are often |
60 | not well-supported (Linux doesn't allow them on normal files currently, |
80 | not well-supported or restricted (GNU/Linux doesn't allow them on normal |
61 | for example), and they would only support aio_read and aio_write, so the |
81 | files currently, for example), and they would only support aio_read and |
62 | remaining functionality would have to be implemented using threads anyway. |
82 | aio_write, so the remaining functionality would have to be implemented |
|
|
83 | using threads anyway. |
63 | |
84 | |
64 | Although the module will work with in the presence of other threads, it is |
85 | Although the module will work in the presence of other (Perl-) threads, |
65 | currently not reentrant, so use appropriate locking yourself, always call |
86 | it is currently not reentrant in any way, so use appropriate locking |
66 | C<poll_cb> from within the same thread, or never call C<poll_cb> (or other |
87 | yourself, always call C<poll_cb> from within the same thread, or never |
67 | C<aio_> functions) recursively. |
88 | call C<poll_cb> (or other C<aio_> functions) recursively. |
|
|
89 | |
|
|
90 | =head2 EXAMPLE |
|
|
91 | |
|
|
92 | This is a simple example that uses the Event module and loads |
|
|
93 | F</etc/passwd> asynchronously: |
|
|
94 | |
|
|
95 | use Fcntl; |
|
|
96 | use Event; |
|
|
97 | use IO::AIO; |
|
|
98 | |
|
|
99 | # register the IO::AIO callback with Event |
|
|
100 | Event->io (fd => IO::AIO::poll_fileno, |
|
|
101 | poll => 'r', |
|
|
102 | cb => \&IO::AIO::poll_cb); |
|
|
103 | |
|
|
104 | # queue the request to open /etc/passwd |
|
|
105 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
|
|
106 | my $fh = shift |
|
|
107 | or die "error while opening: $!"; |
|
|
108 | |
|
|
109 | # stat'ing filehandles is generally non-blocking |
|
|
110 | my $size = -s $fh; |
|
|
111 | |
|
|
112 | # queue a request to read the file |
|
|
113 | my $contents; |
|
|
114 | aio_read $fh, 0, $size, $contents, 0, sub { |
|
|
115 | $_[0] == $size |
|
|
116 | or die "short read: $!"; |
|
|
117 | |
|
|
118 | close $fh; |
|
|
119 | |
|
|
120 | # file contents now in $contents |
|
|
121 | print $contents; |
|
|
122 | |
|
|
123 | # exit event loop and program |
|
|
124 | Event::unloop; |
|
|
125 | }; |
|
|
126 | }; |
|
|
127 | |
|
|
128 | # possibly queue up other requests, or open GUI windows, |
|
|
129 | # check for sockets etc. etc. |
|
|
130 | |
|
|
131 | # process events as long as there are some: |
|
|
132 | Event::loop; |
|
|
133 | |
|
|
134 | =head1 REQUEST ANATOMY AND LIFETIME |
|
|
135 | |
|
|
136 | Every C<aio_*> function creates a request. which is a C data structure not |
|
|
137 | directly visible to Perl. |
|
|
138 | |
|
|
139 | If called in non-void context, every request function returns a Perl |
|
|
140 | object representing the request. In void context, nothing is returned, |
|
|
141 | which saves a bit of memory. |
|
|
142 | |
|
|
143 | The perl object is a fairly standard ref-to-hash object. The hash contents |
|
|
144 | are not used by IO::AIO so you are free to store anything you like in it. |
|
|
145 | |
|
|
146 | During their existance, aio requests travel through the following states, |
|
|
147 | in order: |
|
|
148 | |
|
|
149 | =over 4 |
|
|
150 | |
|
|
151 | =item ready |
|
|
152 | |
|
|
153 | Immediately after a request is created it is put into the ready state, |
|
|
154 | waiting for a thread to execute it. |
|
|
155 | |
|
|
156 | =item execute |
|
|
157 | |
|
|
158 | A thread has accepted the request for processing and is currently |
|
|
159 | executing it (e.g. blocking in read). |
|
|
160 | |
|
|
161 | =item pending |
|
|
162 | |
|
|
163 | The request has been executed and is waiting for result processing. |
|
|
164 | |
|
|
165 | While request submission and execution is fully asynchronous, result |
|
|
166 | processing is not and relies on the perl interpreter calling C<poll_cb> |
|
|
167 | (or another function with the same effect). |
|
|
168 | |
|
|
169 | =item result |
|
|
170 | |
|
|
171 | The request results are processed synchronously by C<poll_cb>. |
|
|
172 | |
|
|
173 | The C<poll_cb> function will process all outstanding aio requests by |
|
|
174 | calling their callbacks, freeing memory associated with them and managing |
|
|
175 | any groups they are contained in. |
|
|
176 | |
|
|
177 | =item done |
|
|
178 | |
|
|
179 | Request has reached the end of its lifetime and holds no resources anymore |
|
|
180 | (except possibly for the Perl object, but its connection to the actual |
|
|
181 | aio request is severed and calling its methods will either do nothing or |
|
|
182 | result in a runtime error). |
|
|
183 | |
|
|
184 | =back |
68 | |
185 | |
69 | =cut |
186 | =cut |
70 | |
187 | |
71 | package IO::AIO; |
188 | package IO::AIO; |
|
|
189 | |
|
|
190 | use Carp (); |
72 | |
191 | |
73 | no warnings; |
192 | no warnings; |
74 | use strict 'vars'; |
193 | use strict 'vars'; |
75 | |
194 | |
76 | use base 'Exporter'; |
195 | use base 'Exporter'; |
77 | |
196 | |
78 | BEGIN { |
197 | BEGIN { |
79 | our $VERSION = '2.0'; |
198 | our $VERSION = '3.22'; |
80 | |
199 | |
81 | our @EXPORT = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat |
200 | our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close |
82 | aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink |
201 | aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx |
83 | aio_fsync aio_fdatasync aio_readahead aio_rename aio_link aio_move |
202 | aio_scandir aio_symlink aio_readlink aio_sync aio_fsync |
84 | aio_group); |
203 | aio_fdatasync aio_sync_file_range aio_pathsync aio_readahead |
85 | our @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs); |
204 | aio_rename aio_link aio_move aio_copy aio_group |
|
|
205 | aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown |
|
|
206 | aio_chmod aio_utime aio_truncate); |
|
|
207 | |
|
|
208 | our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice)); |
|
|
209 | our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush |
|
|
210 | min_parallel max_parallel max_idle |
|
|
211 | nreqs nready npending nthreads |
|
|
212 | max_poll_time max_poll_reqs); |
|
|
213 | |
|
|
214 | push @AIO_REQ, qw(aio_busy); # not exported |
86 | |
215 | |
87 | @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; |
216 | @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; |
88 | |
217 | |
89 | require XSLoader; |
218 | require XSLoader; |
90 | XSLoader::load ("IO::AIO", $VERSION); |
219 | XSLoader::load ("IO::AIO", $VERSION); |
91 | } |
220 | } |
92 | |
221 | |
93 | =head1 FUNCTIONS |
222 | =head1 FUNCTIONS |
94 | |
223 | |
95 | =head2 AIO FUNCTIONS |
224 | =head2 AIO REQUEST FUNCTIONS |
96 | |
225 | |
97 | All the C<aio_*> calls are more or less thin wrappers around the syscall |
226 | All the C<aio_*> calls are more or less thin wrappers around the syscall |
98 | with the same name (sans C<aio_>). The arguments are similar or identical, |
227 | with the same name (sans C<aio_>). The arguments are similar or identical, |
99 | and they all accept an additional (and optional) C<$callback> argument |
228 | and they all accept an additional (and optional) C<$callback> argument |
100 | which must be a code reference. This code reference will get called with |
229 | which must be a code reference. This code reference will get called with |
101 | the syscall return code (e.g. most syscalls return C<-1> on error, unlike |
230 | the syscall return code (e.g. most syscalls return C<-1> on error, unlike |
102 | perl, which usually delivers "false") as it's sole argument when the given |
231 | perl, which usually delivers "false") as its sole argument after the given |
103 | syscall has been executed asynchronously. |
232 | syscall has been executed asynchronously. |
104 | |
233 | |
105 | All functions expecting a filehandle keep a copy of the filehandle |
234 | All functions expecting a filehandle keep a copy of the filehandle |
106 | internally until the request has finished. |
235 | internally until the request has finished. |
107 | |
236 | |
108 | All requests return objects of type L<IO::AIO::REQ> that allow further |
237 | All functions return request objects of type L<IO::AIO::REQ> that allow |
109 | manipulation of those requests while they are in-flight. |
238 | further manipulation of those requests while they are in-flight. |
110 | |
239 | |
111 | The pathnames you pass to these routines I<must> be absolute and |
240 | The pathnames you pass to these routines I<must> be absolute and |
112 | encoded in byte form. The reason for the former is that at the time the |
241 | encoded as octets. The reason for the former is that at the time the |
113 | request is being executed, the current working directory could have |
242 | request is being executed, the current working directory could have |
114 | changed. Alternatively, you can make sure that you never change the |
243 | changed. Alternatively, you can make sure that you never change the |
115 | current working directory. |
244 | current working directory anywhere in the program and then use relative |
|
|
245 | paths. |
116 | |
246 | |
117 | To encode pathnames to byte form, either make sure you either: a) |
247 | To encode pathnames as octets, either make sure you either: a) always pass |
118 | always pass in filenames you got from outside (command line, readdir |
248 | in filenames you got from outside (command line, readdir etc.) without |
119 | etc.), b) are ASCII or ISO 8859-1, c) use the Encode module and encode |
249 | tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module and encode |
120 | your pathnames to the locale (or other) encoding in effect in the user |
250 | your pathnames to the locale (or other) encoding in effect in the user |
121 | environment, d) use Glib::filename_from_unicode on unicode filenames or e) |
251 | environment, d) use Glib::filename_from_unicode on unicode filenames or e) |
122 | use something else. |
252 | use something else to ensure your scalar has the correct contents. |
|
|
253 | |
|
|
254 | This works, btw. independent of the internal UTF-8 bit, which IO::AIO |
|
|
255 | handles correctly whether it is set or not. |
123 | |
256 | |
124 | =over 4 |
257 | =over 4 |
|
|
258 | |
|
|
259 | =item $prev_pri = aioreq_pri [$pri] |
|
|
260 | |
|
|
261 | Returns the priority value that would be used for the next request and, if |
|
|
262 | C<$pri> is given, sets the priority for the next aio request. |
|
|
263 | |
|
|
264 | The default priority is C<0>, the minimum and maximum priorities are C<-4> |
|
|
265 | and C<4>, respectively. Requests with higher priority will be serviced |
|
|
266 | first. |
|
|
267 | |
|
|
268 | The priority will be reset to C<0> after each call to one of the C<aio_*> |
|
|
269 | functions. |
|
|
270 | |
|
|
271 | Example: open a file with low priority, then read something from it with |
|
|
272 | higher priority so the read request is serviced before other low priority |
|
|
273 | open requests (potentially spamming the cache): |
|
|
274 | |
|
|
275 | aioreq_pri -3; |
|
|
276 | aio_open ..., sub { |
|
|
277 | return unless $_[0]; |
|
|
278 | |
|
|
279 | aioreq_pri -2; |
|
|
280 | aio_read $_[0], ..., sub { |
|
|
281 | ... |
|
|
282 | }; |
|
|
283 | }; |
|
|
284 | |
|
|
285 | |
|
|
286 | =item aioreq_nice $pri_adjust |
|
|
287 | |
|
|
288 | Similar to C<aioreq_pri>, but subtracts the given value from the current |
|
|
289 | priority, so the effect is cumulative. |
|
|
290 | |
125 | |
291 | |
126 | =item aio_open $pathname, $flags, $mode, $callback->($fh) |
292 | =item aio_open $pathname, $flags, $mode, $callback->($fh) |
127 | |
293 | |
128 | Asynchronously open or create a file and call the callback with a newly |
294 | Asynchronously open or create a file and call the callback with a newly |
129 | created filehandle for the file. |
295 | created filehandle for the file. |
… | |
… | |
135 | list. They are the same as used by C<sysopen>. |
301 | list. They are the same as used by C<sysopen>. |
136 | |
302 | |
137 | Likewise, C<$mode> specifies the mode of the newly created file, if it |
303 | Likewise, C<$mode> specifies the mode of the newly created file, if it |
138 | didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>, |
304 | didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>, |
139 | except that it is mandatory (i.e. use C<0> if you don't create new files, |
305 | except that it is mandatory (i.e. use C<0> if you don't create new files, |
140 | and C<0666> or C<0777> if you do). |
306 | and C<0666> or C<0777> if you do). Note that the C<$mode> will be modified |
|
|
307 | by the umask in effect then the request is being executed, so better never |
|
|
308 | change the umask. |
141 | |
309 | |
142 | Example: |
310 | Example: |
143 | |
311 | |
144 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
312 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
145 | if ($_[0]) { |
313 | if ($_[0]) { |
… | |
… | |
148 | } else { |
316 | } else { |
149 | die "open failed: $!\n"; |
317 | die "open failed: $!\n"; |
150 | } |
318 | } |
151 | }; |
319 | }; |
152 | |
320 | |
|
|
321 | |
153 | =item aio_close $fh, $callback->($status) |
322 | =item aio_close $fh, $callback->($status) |
154 | |
323 | |
155 | Asynchronously close a file and call the callback with the result |
324 | Asynchronously close a file and call the callback with the result |
156 | code. I<WARNING:> although accepted, you should not pass in a perl |
325 | code. |
157 | filehandle here, as perl will likely close the file descriptor another |
|
|
158 | time when the filehandle is destroyed. Normally, you can safely call perls |
|
|
159 | C<close> or just let filehandles go out of scope. |
|
|
160 | |
326 | |
161 | This is supposed to be a bug in the API, so that might change. It's |
327 | Unfortunately, you can't do this to perl. Perl I<insists> very strongly on |
162 | therefore best to avoid this function. |
328 | closing the file descriptor associated with the filehandle itself. |
|
|
329 | |
|
|
330 | Therefore, C<aio_close> will not close the filehandle - instead it will |
|
|
331 | use dup2 to overwrite the file descriptor with the write-end of a pipe |
|
|
332 | (the pipe fd will be created on demand and will be cached). |
|
|
333 | |
|
|
334 | Or in other words: the file descriptor will be closed, but it will not be |
|
|
335 | free for reuse until the perl filehandle is closed. |
|
|
336 | |
|
|
337 | =cut |
163 | |
338 | |
164 | =item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
339 | =item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
165 | |
340 | |
166 | =item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
341 | =item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
167 | |
342 | |
168 | Reads or writes C<length> bytes from the specified C<fh> and C<offset> |
343 | Reads or writes C<$length> bytes from or to the specified C<$fh> and |
169 | into the scalar given by C<data> and offset C<dataoffset> and calls the |
344 | C<$offset> into the scalar given by C<$data> and offset C<$dataoffset> |
170 | callback without the actual number of bytes read (or -1 on error, just |
345 | and calls the callback without the actual number of bytes read (or -1 on |
171 | like the syscall). |
346 | error, just like the syscall). |
|
|
347 | |
|
|
348 | C<aio_read> will, like C<sysread>, shrink or grow the C<$data> scalar to |
|
|
349 | offset plus the actual number of bytes read. |
|
|
350 | |
|
|
351 | If C<$offset> is undefined, then the current file descriptor offset will |
|
|
352 | be used (and updated), otherwise the file descriptor offset will not be |
|
|
353 | changed by these calls. |
|
|
354 | |
|
|
355 | If C<$length> is undefined in C<aio_write>, use the remaining length of |
|
|
356 | C<$data>. |
|
|
357 | |
|
|
358 | If C<$dataoffset> is less than zero, it will be counted from the end of |
|
|
359 | C<$data>. |
172 | |
360 | |
173 | The C<$data> scalar I<MUST NOT> be modified in any way while the request |
361 | The C<$data> scalar I<MUST NOT> be modified in any way while the request |
174 | is outstanding. Modifying it can result in segfaults or WW3 (if the |
362 | is outstanding. Modifying it can result in segfaults or World War III (if |
175 | necessary/optional hardware is installed). |
363 | the necessary/optional hardware is installed). |
176 | |
364 | |
177 | Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at |
365 | Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at |
178 | offset C<0> within the scalar: |
366 | offset C<0> within the scalar: |
179 | |
367 | |
180 | aio_read $fh, 7, 15, $buffer, 0, sub { |
368 | aio_read $fh, 7, 15, $buffer, 0, sub { |
181 | $_[0] > 0 or die "read error: $!"; |
369 | $_[0] > 0 or die "read error: $!"; |
182 | print "read $_[0] bytes: <$buffer>\n"; |
370 | print "read $_[0] bytes: <$buffer>\n"; |
183 | }; |
371 | }; |
184 | |
372 | |
185 | =item aio_move $srcpath, $dstpath, $callback->($status) |
|
|
186 | |
|
|
187 | [EXPERIMENTAL due to internal aio_group use] |
|
|
188 | |
|
|
189 | Try to move the I<file> (directories not supported as either source or |
|
|
190 | destination) from C<$srcpath> to C<$dstpath> and call the callback with |
|
|
191 | the C<0> (error) or C<-1> ok. |
|
|
192 | |
|
|
193 | This is a composite request that tries to rename(2) the file first. If |
|
|
194 | rename files with C<EXDEV>, it creates the destination file with mode 0200 |
|
|
195 | and copies the contents of the source file into it using C<aio_sendfile>, |
|
|
196 | followed by restoring atime, mtime, access mode and uid/gid, in that |
|
|
197 | order, and unlinking the C<$srcpath>. |
|
|
198 | |
|
|
199 | If an error occurs, the partial destination file will be unlinked, if |
|
|
200 | possible, except when setting atime, mtime, access mode and uid/gid, where |
|
|
201 | errors are being ignored. |
|
|
202 | |
|
|
203 | =cut |
|
|
204 | |
|
|
205 | sub aio_move($$$) { |
|
|
206 | my ($src, $dst, $cb) = @_; |
|
|
207 | |
|
|
208 | my $grp = aio_group $cb; |
|
|
209 | |
|
|
210 | add $grp aio_rename $src, $dst, sub { |
|
|
211 | if ($_[0] && $! == EXDEV) { |
|
|
212 | add $grp aio_open $src, O_RDONLY, 0, sub { |
|
|
213 | if (my $src_fh = $_[0]) { |
|
|
214 | my @stat = stat $src_fh; |
|
|
215 | |
|
|
216 | add $grp aio_open $dst, O_WRONLY, 0200, sub { |
|
|
217 | if (my $dst_fh = $_[0]) { |
|
|
218 | add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub { |
|
|
219 | close $src_fh; |
|
|
220 | |
|
|
221 | if ($_[0] == $stat[7]) { |
|
|
222 | utime $stat[8], $stat[9], $dst; |
|
|
223 | chmod $stat[2] & 07777, $dst_fh; |
|
|
224 | chown $stat[4], $stat[5], $dst_fh; |
|
|
225 | close $dst_fh; |
|
|
226 | |
|
|
227 | add $grp aio_unlink $src, sub { |
|
|
228 | $grp->result ($_[0]); |
|
|
229 | }; |
|
|
230 | } else { |
|
|
231 | my $errno = $!; |
|
|
232 | add $grp aio_unlink $dst, sub { |
|
|
233 | $! = $errno; |
|
|
234 | $grp->result (-1); |
|
|
235 | }; |
|
|
236 | } |
|
|
237 | }; |
|
|
238 | } else { |
|
|
239 | $grp->result (-1); |
|
|
240 | } |
|
|
241 | }, |
|
|
242 | |
|
|
243 | } else { |
|
|
244 | $grp->result (-1); |
|
|
245 | } |
|
|
246 | }; |
|
|
247 | } else { |
|
|
248 | $grp->result ($_[0]); |
|
|
249 | } |
|
|
250 | }; |
|
|
251 | |
|
|
252 | $grp |
|
|
253 | } |
|
|
254 | |
373 | |
255 | =item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) |
374 | =item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) |
256 | |
375 | |
257 | Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts |
376 | Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts |
258 | reading at byte offset C<$in_offset>, and starts writing at the current |
377 | reading at byte offset C<$in_offset>, and starts writing at the current |
… | |
… | |
272 | C<$in_fh> than are written, and there is no way to find out how many |
391 | C<$in_fh> than are written, and there is no way to find out how many |
273 | bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only |
392 | bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only |
274 | provides the number of bytes written to C<$out_fh>. Only if the result |
393 | provides the number of bytes written to C<$out_fh>. Only if the result |
275 | value equals C<$length> one can assume that C<$length> bytes have been |
394 | value equals C<$length> one can assume that C<$length> bytes have been |
276 | read. |
395 | read. |
|
|
396 | |
277 | |
397 | |
278 | =item aio_readahead $fh,$offset,$length, $callback->($retval) |
398 | =item aio_readahead $fh,$offset,$length, $callback->($retval) |
279 | |
399 | |
280 | C<aio_readahead> populates the page cache with data from a file so that |
400 | C<aio_readahead> populates the page cache with data from a file so that |
281 | subsequent reads from that file will not block on disk I/O. The C<$offset> |
401 | subsequent reads from that file will not block on disk I/O. The C<$offset> |
… | |
… | |
287 | file. The current file offset of the file is left unchanged. |
407 | file. The current file offset of the file is left unchanged. |
288 | |
408 | |
289 | If that syscall doesn't exist (likely if your OS isn't Linux) it will be |
409 | If that syscall doesn't exist (likely if your OS isn't Linux) it will be |
290 | emulated by simply reading the data, which would have a similar effect. |
410 | emulated by simply reading the data, which would have a similar effect. |
291 | |
411 | |
|
|
412 | |
292 | =item aio_stat $fh_or_path, $callback->($status) |
413 | =item aio_stat $fh_or_path, $callback->($status) |
293 | |
414 | |
294 | =item aio_lstat $fh, $callback->($status) |
415 | =item aio_lstat $fh, $callback->($status) |
295 | |
416 | |
296 | Works like perl's C<stat> or C<lstat> in void context. The callback will |
417 | Works like perl's C<stat> or C<lstat> in void context. The callback will |
… | |
… | |
309 | aio_stat "/etc/passwd", sub { |
430 | aio_stat "/etc/passwd", sub { |
310 | $_[0] and die "stat failed: $!"; |
431 | $_[0] and die "stat failed: $!"; |
311 | print "size is ", -s _, "\n"; |
432 | print "size is ", -s _, "\n"; |
312 | }; |
433 | }; |
313 | |
434 | |
|
|
435 | |
|
|
436 | =item aio_utime $fh_or_path, $atime, $mtime, $callback->($status) |
|
|
437 | |
|
|
438 | Works like perl's C<utime> function (including the special case of $atime |
|
|
439 | and $mtime being undef). Fractional times are supported if the underlying |
|
|
440 | syscalls support them. |
|
|
441 | |
|
|
442 | When called with a pathname, uses utimes(2) if available, otherwise |
|
|
443 | utime(2). If called on a file descriptor, uses futimes(2) if available, |
|
|
444 | otherwise returns ENOSYS, so this is not portable. |
|
|
445 | |
|
|
446 | Examples: |
|
|
447 | |
|
|
448 | # set atime and mtime to current time (basically touch(1)): |
|
|
449 | aio_utime "path", undef, undef; |
|
|
450 | # set atime to current time and mtime to beginning of the epoch: |
|
|
451 | aio_utime "path", time, undef; # undef==0 |
|
|
452 | |
|
|
453 | |
|
|
454 | =item aio_chown $fh_or_path, $uid, $gid, $callback->($status) |
|
|
455 | |
|
|
456 | Works like perl's C<chown> function, except that C<undef> for either $uid |
|
|
457 | or $gid is being interpreted as "do not change" (but -1 can also be used). |
|
|
458 | |
|
|
459 | Examples: |
|
|
460 | |
|
|
461 | # same as "chown root path" in the shell: |
|
|
462 | aio_chown "path", 0, -1; |
|
|
463 | # same as above: |
|
|
464 | aio_chown "path", 0, undef; |
|
|
465 | |
|
|
466 | |
|
|
467 | =item aio_truncate $fh_or_path, $offset, $callback->($status) |
|
|
468 | |
|
|
469 | Works like truncate(2) or ftruncate(2). |
|
|
470 | |
|
|
471 | |
|
|
472 | =item aio_chmod $fh_or_path, $mode, $callback->($status) |
|
|
473 | |
|
|
474 | Works like perl's C<chmod> function. |
|
|
475 | |
|
|
476 | |
314 | =item aio_unlink $pathname, $callback->($status) |
477 | =item aio_unlink $pathname, $callback->($status) |
315 | |
478 | |
316 | Asynchronously unlink (delete) a file and call the callback with the |
479 | Asynchronously unlink (delete) a file and call the callback with the |
317 | result code. |
480 | result code. |
318 | |
481 | |
|
|
482 | |
|
|
483 | =item aio_mknod $path, $mode, $dev, $callback->($status) |
|
|
484 | |
|
|
485 | [EXPERIMENTAL] |
|
|
486 | |
|
|
487 | Asynchronously create a device node (or fifo). See mknod(2). |
|
|
488 | |
|
|
489 | The only (POSIX-) portable way of calling this function is: |
|
|
490 | |
|
|
491 | aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ... |
|
|
492 | |
|
|
493 | |
319 | =item aio_link $srcpath, $dstpath, $callback->($status) |
494 | =item aio_link $srcpath, $dstpath, $callback->($status) |
320 | |
495 | |
321 | Asynchronously create a new link to the existing object at C<$srcpath> at |
496 | Asynchronously create a new link to the existing object at C<$srcpath> at |
322 | the path C<$dstpath> and call the callback with the result code. |
497 | the path C<$dstpath> and call the callback with the result code. |
323 | |
498 | |
|
|
499 | |
324 | =item aio_symlink $srcpath, $dstpath, $callback->($status) |
500 | =item aio_symlink $srcpath, $dstpath, $callback->($status) |
325 | |
501 | |
326 | Asynchronously create a new symbolic link to the existing object at C<$srcpath> at |
502 | Asynchronously create a new symbolic link to the existing object at C<$srcpath> at |
327 | the path C<$dstpath> and call the callback with the result code. |
503 | the path C<$dstpath> and call the callback with the result code. |
328 | |
504 | |
|
|
505 | |
|
|
506 | =item aio_readlink $path, $callback->($link) |
|
|
507 | |
|
|
508 | Asynchronously read the symlink specified by C<$path> and pass it to |
|
|
509 | the callback. If an error occurs, nothing or undef gets passed to the |
|
|
510 | callback. |
|
|
511 | |
|
|
512 | |
329 | =item aio_rename $srcpath, $dstpath, $callback->($status) |
513 | =item aio_rename $srcpath, $dstpath, $callback->($status) |
330 | |
514 | |
331 | Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as |
515 | Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as |
332 | rename(2) and call the callback with the result code. |
516 | rename(2) and call the callback with the result code. |
333 | |
517 | |
|
|
518 | |
|
|
519 | =item aio_mkdir $pathname, $mode, $callback->($status) |
|
|
520 | |
|
|
521 | Asynchronously mkdir (create) a directory and call the callback with |
|
|
522 | the result code. C<$mode> will be modified by the umask at the time the |
|
|
523 | request is executed, so do not change your umask. |
|
|
524 | |
|
|
525 | |
334 | =item aio_rmdir $pathname, $callback->($status) |
526 | =item aio_rmdir $pathname, $callback->($status) |
335 | |
527 | |
336 | Asynchronously rmdir (delete) a directory and call the callback with the |
528 | Asynchronously rmdir (delete) a directory and call the callback with the |
337 | result code. |
529 | result code. |
|
|
530 | |
338 | |
531 | |
339 | =item aio_readdir $pathname, $callback->($entries) |
532 | =item aio_readdir $pathname, $callback->($entries) |
340 | |
533 | |
341 | Unlike the POSIX call of the same name, C<aio_readdir> reads an entire |
534 | Unlike the POSIX call of the same name, C<aio_readdir> reads an entire |
342 | directory (i.e. opendir + readdir + closedir). The entries will not be |
535 | directory (i.e. opendir + readdir + closedir). The entries will not be |
343 | sorted, and will B<NOT> include the C<.> and C<..> entries. |
536 | sorted, and will B<NOT> include the C<.> and C<..> entries. |
344 | |
537 | |
345 | The callback a single argument which is either C<undef> or an array-ref |
538 | The callback is passed a single argument which is either C<undef> or an |
346 | with the filenames. |
539 | array-ref with the filenames. |
|
|
540 | |
|
|
541 | |
|
|
542 | =item aio_readdirx $pathname, $flags, $callback->($entries, $flags) |
|
|
543 | |
|
|
544 | Quite similar to C<aio_readdir>, but the C<$flags> argument allows to tune |
|
|
545 | behaviour and output format. In case of an error, C<$entries> will be |
|
|
546 | C<undef>. |
|
|
547 | |
|
|
548 | The flags are a combination of the following constants, ORed together (the |
|
|
549 | flags will also be passed to the callback, possibly modified): |
|
|
550 | |
|
|
551 | =over 4 |
|
|
552 | |
|
|
553 | =item IO::AIO::READDIR_DENTS |
|
|
554 | |
|
|
555 | When this flag is off, then the callback gets an arrayref with of names |
|
|
556 | only (as with C<aio_readdir>), otherwise it gets an arrayref with |
|
|
557 | C<[$name, $type, $inode]> arrayrefs, each describing a single directory |
|
|
558 | entry in more detail. |
|
|
559 | |
|
|
560 | C<$name> is the name of the entry. |
|
|
561 | |
|
|
562 | C<$type> is one of the C<IO::AIO::DT_xxx> constants: |
|
|
563 | |
|
|
564 | C<IO::AIO::DT_UNKNOWN>, C<IO::AIO::DT_FIFO>, C<IO::AIO::DT_CHR>, C<IO::AIO::DT_DIR>, |
|
|
565 | C<IO::AIO::DT_BLK>, C<IO::AIO::DT_REG>, C<IO::AIO::DT_LNK>, C<IO::AIO::DT_SOCK>, |
|
|
566 | C<IO::AIO::DT_WHT>. |
|
|
567 | |
|
|
568 | C<IO::AIO::DT_UNKNOWN> means just that: readdir does not know. If you need to |
|
|
569 | know, you have to run stat yourself. Also, for speed reasons, the C<$type> |
|
|
570 | scalars are read-only: you can not modify them. |
|
|
571 | |
|
|
572 | C<$inode> is the inode number (which might not be exact on systems with 64 |
|
|
573 | bit inode numbers and 32 bit perls). On systems that do not deliver the |
|
|
574 | inode information, this will always be zero. |
|
|
575 | |
|
|
576 | =item IO::AIO::READDIR_DIRS_FIRST |
|
|
577 | |
|
|
578 | When this flag is set, then the names will be returned in an order where |
|
|
579 | likely directories come first. This is useful when you need to quickly |
|
|
580 | find directories, or you want to find all directories while avoiding to |
|
|
581 | stat() each entry. |
|
|
582 | |
|
|
583 | If the system returns type information in readdir, then this is used |
|
|
584 | to find directories directly. Otherwise, likely directories are files |
|
|
585 | beginning with ".", or otherwise files with no dots, of which files with |
|
|
586 | short names are tried first. |
|
|
587 | |
|
|
588 | =item IO::AIO::READDIR_STAT_ORDER |
|
|
589 | |
|
|
590 | When this flag is set, then the names will be returned in an order |
|
|
591 | suitable for stat()'ing each one. That is, when you plan to stat() |
|
|
592 | all files in the given directory, then the returned order will likely |
|
|
593 | be fastest. |
|
|
594 | |
|
|
595 | If both this flag and C<IO::AIO::READDIR_DIRS_FIRST> are specified, then |
|
|
596 | the likely dirs come first, resulting in a less optimal stat order. |
|
|
597 | |
|
|
598 | =item IO::AIO::READDIR_FOUND_UNKNOWN |
|
|
599 | |
|
|
600 | This flag should not be set when calling C<aio_readdirx>. Instead, it |
|
|
601 | is being set by C<aio_readdirx>, when any of the C<$type>'s found were |
|
|
602 | C<IO::AIO::DT_UNKNOWN>. The absense of this flag therefore indicates that all |
|
|
603 | C<$type>'s are known, which can be used to speed up some algorithms. |
|
|
604 | |
|
|
605 | =back |
|
|
606 | |
|
|
607 | |
|
|
608 | =item aio_load $path, $data, $callback->($status) |
|
|
609 | |
|
|
610 | This is a composite request that tries to fully load the given file into |
|
|
611 | memory. Status is the same as with aio_read. |
|
|
612 | |
|
|
613 | =cut |
|
|
614 | |
|
|
615 | sub aio_load($$;$) { |
|
|
616 | my ($path, undef, $cb) = @_; |
|
|
617 | my $data = \$_[1]; |
|
|
618 | |
|
|
619 | my $pri = aioreq_pri; |
|
|
620 | my $grp = aio_group $cb; |
|
|
621 | |
|
|
622 | aioreq_pri $pri; |
|
|
623 | add $grp aio_open $path, O_RDONLY, 0, sub { |
|
|
624 | my $fh = shift |
|
|
625 | or return $grp->result (-1); |
|
|
626 | |
|
|
627 | aioreq_pri $pri; |
|
|
628 | add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub { |
|
|
629 | $grp->result ($_[0]); |
|
|
630 | }; |
|
|
631 | }; |
|
|
632 | |
|
|
633 | $grp |
|
|
634 | } |
|
|
635 | |
|
|
636 | =item aio_copy $srcpath, $dstpath, $callback->($status) |
|
|
637 | |
|
|
638 | Try to copy the I<file> (directories not supported as either source or |
|
|
639 | destination) from C<$srcpath> to C<$dstpath> and call the callback with |
|
|
640 | the C<0> (error) or C<-1> ok. |
|
|
641 | |
|
|
642 | This is a composite request that creates the destination file with |
|
|
643 | mode 0200 and copies the contents of the source file into it using |
|
|
644 | C<aio_sendfile>, followed by restoring atime, mtime, access mode and |
|
|
645 | uid/gid, in that order. |
|
|
646 | |
|
|
647 | If an error occurs, the partial destination file will be unlinked, if |
|
|
648 | possible, except when setting atime, mtime, access mode and uid/gid, where |
|
|
649 | errors are being ignored. |
|
|
650 | |
|
|
651 | =cut |
|
|
652 | |
|
|
653 | sub aio_copy($$;$) { |
|
|
654 | my ($src, $dst, $cb) = @_; |
|
|
655 | |
|
|
656 | my $pri = aioreq_pri; |
|
|
657 | my $grp = aio_group $cb; |
|
|
658 | |
|
|
659 | aioreq_pri $pri; |
|
|
660 | add $grp aio_open $src, O_RDONLY, 0, sub { |
|
|
661 | if (my $src_fh = $_[0]) { |
|
|
662 | my @stat = stat $src_fh; # hmm, might bock over nfs? |
|
|
663 | |
|
|
664 | aioreq_pri $pri; |
|
|
665 | add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub { |
|
|
666 | if (my $dst_fh = $_[0]) { |
|
|
667 | aioreq_pri $pri; |
|
|
668 | add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub { |
|
|
669 | if ($_[0] == $stat[7]) { |
|
|
670 | $grp->result (0); |
|
|
671 | close $src_fh; |
|
|
672 | |
|
|
673 | my $ch = sub { |
|
|
674 | aioreq_pri $pri; |
|
|
675 | add $grp aio_chmod $dst_fh, $stat[2] & 07777, sub { |
|
|
676 | aioreq_pri $pri; |
|
|
677 | add $grp aio_chown $dst_fh, $stat[4], $stat[5], sub { |
|
|
678 | aioreq_pri $pri; |
|
|
679 | add $grp aio_close $dst_fh; |
|
|
680 | } |
|
|
681 | }; |
|
|
682 | }; |
|
|
683 | |
|
|
684 | aioreq_pri $pri; |
|
|
685 | add $grp aio_utime $dst_fh, $stat[8], $stat[9], sub { |
|
|
686 | if ($_[0] < 0 && $! == ENOSYS) { |
|
|
687 | aioreq_pri $pri; |
|
|
688 | add $grp aio_utime $dst, $stat[8], $stat[9], $ch; |
|
|
689 | } else { |
|
|
690 | $ch->(); |
|
|
691 | } |
|
|
692 | }; |
|
|
693 | } else { |
|
|
694 | $grp->result (-1); |
|
|
695 | close $src_fh; |
|
|
696 | close $dst_fh; |
|
|
697 | |
|
|
698 | aioreq $pri; |
|
|
699 | add $grp aio_unlink $dst; |
|
|
700 | } |
|
|
701 | }; |
|
|
702 | } else { |
|
|
703 | $grp->result (-1); |
|
|
704 | } |
|
|
705 | }, |
|
|
706 | |
|
|
707 | } else { |
|
|
708 | $grp->result (-1); |
|
|
709 | } |
|
|
710 | }; |
|
|
711 | |
|
|
712 | $grp |
|
|
713 | } |
|
|
714 | |
|
|
715 | =item aio_move $srcpath, $dstpath, $callback->($status) |
|
|
716 | |
|
|
717 | Try to move the I<file> (directories not supported as either source or |
|
|
718 | destination) from C<$srcpath> to C<$dstpath> and call the callback with |
|
|
719 | the C<0> (error) or C<-1> ok. |
|
|
720 | |
|
|
721 | This is a composite request that tries to rename(2) the file first; if |
|
|
722 | rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if |
|
|
723 | that is successful, unlinks the C<$srcpath>. |
|
|
724 | |
|
|
725 | =cut |
|
|
726 | |
|
|
727 | sub aio_move($$;$) { |
|
|
728 | my ($src, $dst, $cb) = @_; |
|
|
729 | |
|
|
730 | my $pri = aioreq_pri; |
|
|
731 | my $grp = aio_group $cb; |
|
|
732 | |
|
|
733 | aioreq_pri $pri; |
|
|
734 | add $grp aio_rename $src, $dst, sub { |
|
|
735 | if ($_[0] && $! == EXDEV) { |
|
|
736 | aioreq_pri $pri; |
|
|
737 | add $grp aio_copy $src, $dst, sub { |
|
|
738 | $grp->result ($_[0]); |
|
|
739 | |
|
|
740 | if (!$_[0]) { |
|
|
741 | aioreq_pri $pri; |
|
|
742 | add $grp aio_unlink $src; |
|
|
743 | } |
|
|
744 | }; |
|
|
745 | } else { |
|
|
746 | $grp->result ($_[0]); |
|
|
747 | } |
|
|
748 | }; |
|
|
749 | |
|
|
750 | $grp |
|
|
751 | } |
347 | |
752 | |
348 | =item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) |
753 | =item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) |
349 | |
754 | |
350 | [EXPERIMENTAL due to internal aio_group use] |
|
|
351 | |
|
|
352 | Scans a directory (similar to C<aio_readdir>) but additionally tries to |
755 | Scans a directory (similar to C<aio_readdir>) but additionally tries to |
353 | separate the entries of directory C<$path> into two sets of names, ones |
756 | efficiently separate the entries of directory C<$path> into two sets of |
354 | you can recurse into (directories or links to them), and ones you cannot |
757 | names, directories you can recurse into (directories), and ones you cannot |
355 | recurse into (everything else). |
758 | recurse into (everything else, including symlinks to directories). |
356 | |
759 | |
357 | C<aio_scandir> is a composite request that consists of many sub |
760 | C<aio_scandir> is a composite request that creates of many sub requests_ |
358 | requests. C<$maxreq> specifies the maximum number of outstanding aio |
761 | C<$maxreq> specifies the maximum number of outstanding aio requests that |
359 | requests that this function generates. If it is C<< <= 0 >>, then a |
762 | this function generates. If it is C<< <= 0 >>, then a suitable default |
360 | suitable default will be chosen (currently 8). |
763 | will be chosen (currently 4). |
361 | |
764 | |
362 | On error, the callback is called without arguments, otherwise it receives |
765 | On error, the callback is called without arguments, otherwise it receives |
363 | two array-refs with path-relative entry names. |
766 | two array-refs with path-relative entry names. |
364 | |
767 | |
365 | Example: |
768 | Example: |
… | |
… | |
372 | |
775 | |
373 | Implementation notes. |
776 | Implementation notes. |
374 | |
777 | |
375 | The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can. |
778 | The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can. |
376 | |
779 | |
|
|
780 | If readdir returns file type information, then this is used directly to |
|
|
781 | find directories. |
|
|
782 | |
377 | After reading the directory, the modification time, size etc. of the |
783 | Otherwise, after reading the directory, the modification time, size etc. |
378 | directory before and after the readdir is checked, and if they match (and |
784 | of the directory before and after the readdir is checked, and if they |
379 | isn't the current time), the link count will be used to decide how many |
785 | match (and isn't the current time), the link count will be used to decide |
380 | entries are directories (if >= 2). Otherwise, no knowledge of the number |
786 | how many entries are directories (if >= 2). Otherwise, no knowledge of the |
381 | of subdirectories will be assumed. |
787 | number of subdirectories will be assumed. |
382 | |
788 | |
383 | Then entries will be sorted into likely directories (everything without |
789 | Then entries will be sorted into likely directories a non-initial dot |
384 | a non-initial dot currently) and likely non-directories (everything |
790 | currently) and likely non-directories (see C<aio_readdirx>). Then every |
385 | else). Then every entry plus an appended C</.> will be C<stat>'ed, |
791 | entry plus an appended C</.> will be C<stat>'ed, likely directories first, |
386 | likely directories first. If that succeeds, it assumes that the entry |
792 | in order of their inode numbers. If that succeeds, it assumes that the |
387 | is a directory or a symlink to directory (which will be checked |
793 | entry is a directory or a symlink to directory (which will be checked |
388 | seperately). This is often faster than stat'ing the entry itself because |
794 | seperately). This is often faster than stat'ing the entry itself because |
389 | filesystems might detect the type of the entry without reading the inode |
795 | filesystems might detect the type of the entry without reading the inode |
390 | data (e.g. ext2fs filetype feature). |
796 | data (e.g. ext2fs filetype feature), even on systems that cannot return |
|
|
797 | the filetype information on readdir. |
391 | |
798 | |
392 | If the known number of directories (link count - 2) has been reached, the |
799 | If the known number of directories (link count - 2) has been reached, the |
393 | rest of the entries is assumed to be non-directories. |
800 | rest of the entries is assumed to be non-directories. |
394 | |
801 | |
395 | This only works with certainty on POSIX (= UNIX) filesystems, which |
802 | This only works with certainty on POSIX (= UNIX) filesystems, which |
… | |
… | |
399 | as those tend to return 0 or 1 as link counts, which disables the |
806 | as those tend to return 0 or 1 as link counts, which disables the |
400 | directory counting heuristic. |
807 | directory counting heuristic. |
401 | |
808 | |
402 | =cut |
809 | =cut |
403 | |
810 | |
404 | sub aio_scandir($$$) { |
811 | sub aio_scandir($$;$) { |
405 | my ($path, $maxreq, $cb) = @_; |
812 | my ($path, $maxreq, $cb) = @_; |
406 | |
813 | |
|
|
814 | my $pri = aioreq_pri; |
|
|
815 | |
407 | my $grp = aio_group $cb; |
816 | my $grp = aio_group $cb; |
408 | |
817 | |
409 | $maxreq = 8 if $maxreq <= 0; |
818 | $maxreq = 4 if $maxreq <= 0; |
410 | |
819 | |
411 | # stat once |
820 | # stat once |
|
|
821 | aioreq_pri $pri; |
412 | add $grp aio_stat $path, sub { |
822 | add $grp aio_stat $path, sub { |
413 | return $grp->result () if $_[0]; |
823 | return $grp->result () if $_[0]; |
414 | my $now = time; |
824 | my $now = time; |
415 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
825 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
416 | |
826 | |
417 | # read the directory entries |
827 | # read the directory entries |
|
|
828 | aioreq_pri $pri; |
418 | add $grp aio_readdir $path, sub { |
829 | add $grp aio_readdirx $path, READDIR_DIRS_FIRST, sub { |
419 | my $entries = shift |
830 | my $entries = shift |
420 | or return $grp->result (); |
831 | or return $grp->result (); |
421 | |
832 | |
422 | # stat the dir another time |
833 | # stat the dir another time |
|
|
834 | aioreq_pri $pri; |
423 | add $grp aio_stat $path, sub { |
835 | add $grp aio_stat $path, sub { |
424 | my $hash2 = join ":", (stat _)[0,1,3,7,9]; |
836 | my $hash2 = join ":", (stat _)[0,1,3,7,9]; |
425 | |
837 | |
426 | my $ndirs; |
838 | my $ndirs; |
427 | |
839 | |
428 | # take the slow route if anything looks fishy |
840 | # take the slow route if anything looks fishy |
429 | if ($hash1 ne $hash2 or (stat _)[9] == $now) { |
841 | if ($hash1 ne $hash2 or (stat _)[9] == $now) { |
430 | $ndirs = -1; |
842 | $ndirs = -1; |
431 | } else { |
843 | } else { |
432 | # if nlink == 2, we are finished |
844 | # if nlink == 2, we are finished |
433 | # on non-posix-fs's, we rely on nlink < 2 |
845 | # for non-posix-fs's, we rely on nlink < 2 |
434 | $ndirs = (stat _)[3] - 2 |
846 | $ndirs = (stat _)[3] - 2 |
435 | or return $grp->result ([], $entries); |
847 | or return $grp->result ([], $entries); |
436 | } |
848 | } |
437 | |
849 | |
438 | # sort into likely dirs and likely nondirs |
|
|
439 | # dirs == files without ".", short entries first |
|
|
440 | $entries = [map $_->[0], |
|
|
441 | sort { $b->[1] cmp $a->[1] } |
|
|
442 | map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length], |
|
|
443 | @$entries]; |
|
|
444 | |
|
|
445 | my (@dirs, @nondirs); |
850 | my (@dirs, @nondirs); |
446 | |
851 | |
447 | my ($statcb, $schedcb); |
|
|
448 | my $nreq = 0; |
|
|
449 | |
|
|
450 | my $statgrp = add $grp aio_group; |
852 | my $statgrp = add $grp aio_group sub { |
|
|
853 | $grp->result (\@dirs, \@nondirs); |
|
|
854 | }; |
451 | |
855 | |
452 | $schedcb = sub { |
856 | limit $statgrp $maxreq; |
453 | if (@$entries) { |
857 | feed $statgrp sub { |
454 | if ($nreq < $maxreq) { |
858 | return unless @$entries; |
455 | my $ent = pop @$entries; |
859 | my $entry = shift @$entries; |
|
|
860 | |
|
|
861 | aioreq_pri $pri; |
|
|
862 | add $statgrp aio_stat "$path/$entry/.", sub { |
|
|
863 | if ($_[0] < 0) { |
|
|
864 | push @nondirs, $entry; |
|
|
865 | } else { |
|
|
866 | # need to check for real directory |
|
|
867 | aioreq_pri $pri; |
|
|
868 | add $statgrp aio_lstat "$path/$entry", sub { |
|
|
869 | if (-d _) { |
|
|
870 | push @dirs, $entry; |
|
|
871 | |
|
|
872 | unless (--$ndirs) { |
|
|
873 | push @nondirs, @$entries; |
|
|
874 | feed $statgrp; |
|
|
875 | } |
|
|
876 | } else { |
|
|
877 | push @nondirs, $entry; |
|
|
878 | } |
456 | $nreq++; |
879 | } |
457 | add $statgrp aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) }; |
|
|
458 | } |
880 | } |
459 | } elsif (!$nreq) { |
|
|
460 | # finished |
|
|
461 | $statgrp->cancel; |
|
|
462 | undef $statcb; |
|
|
463 | undef $schedcb; |
|
|
464 | $grp->result (\@dirs, \@nondirs); |
|
|
465 | } |
881 | }; |
466 | }; |
882 | }; |
467 | $statcb = sub { |
|
|
468 | my ($status, $entry) = @_; |
|
|
469 | |
|
|
470 | if ($status < 0) { |
|
|
471 | $nreq--; |
|
|
472 | push @nondirs, $entry; |
|
|
473 | &$schedcb; |
|
|
474 | } else { |
|
|
475 | # need to check for real directory |
|
|
476 | add $grp aio_lstat "$path/$entry", sub { |
|
|
477 | $nreq--; |
|
|
478 | |
|
|
479 | if (-d _) { |
|
|
480 | push @dirs, $entry; |
|
|
481 | |
|
|
482 | if (!--$ndirs) { |
|
|
483 | push @nondirs, @$entries; |
|
|
484 | $entries = []; |
|
|
485 | } |
|
|
486 | } else { |
|
|
487 | push @nondirs, $entry; |
|
|
488 | } |
|
|
489 | |
|
|
490 | &$schedcb; |
|
|
491 | } |
|
|
492 | } |
|
|
493 | }; |
|
|
494 | |
|
|
495 | &$schedcb while @$entries && $nreq < $maxreq; |
|
|
496 | }; |
883 | }; |
497 | }; |
884 | }; |
498 | }; |
885 | }; |
499 | |
886 | |
500 | $grp |
887 | $grp |
501 | } |
888 | } |
502 | |
889 | |
|
|
890 | =item aio_rmtree $path, $callback->($status) |
|
|
891 | |
|
|
892 | Delete a directory tree starting (and including) C<$path>, return the |
|
|
893 | status of the final C<rmdir> only. This is a composite request that |
|
|
894 | uses C<aio_scandir> to recurse into and rmdir directories, and unlink |
|
|
895 | everything else. |
|
|
896 | |
|
|
897 | =cut |
|
|
898 | |
|
|
899 | sub aio_rmtree; |
|
|
900 | sub aio_rmtree($;$) { |
|
|
901 | my ($path, $cb) = @_; |
|
|
902 | |
|
|
903 | my $pri = aioreq_pri; |
|
|
904 | my $grp = aio_group $cb; |
|
|
905 | |
|
|
906 | aioreq_pri $pri; |
|
|
907 | add $grp aio_scandir $path, 0, sub { |
|
|
908 | my ($dirs, $nondirs) = @_; |
|
|
909 | |
|
|
910 | my $dirgrp = aio_group sub { |
|
|
911 | add $grp aio_rmdir $path, sub { |
|
|
912 | $grp->result ($_[0]); |
|
|
913 | }; |
|
|
914 | }; |
|
|
915 | |
|
|
916 | (aioreq_pri $pri), add $dirgrp aio_rmtree "$path/$_" for @$dirs; |
|
|
917 | (aioreq_pri $pri), add $dirgrp aio_unlink "$path/$_" for @$nondirs; |
|
|
918 | |
|
|
919 | add $grp $dirgrp; |
|
|
920 | }; |
|
|
921 | |
|
|
922 | $grp |
|
|
923 | } |
|
|
924 | |
|
|
925 | =item aio_sync $callback->($status) |
|
|
926 | |
|
|
927 | Asynchronously call sync and call the callback when finished. |
|
|
928 | |
503 | =item aio_fsync $fh, $callback->($status) |
929 | =item aio_fsync $fh, $callback->($status) |
504 | |
930 | |
505 | Asynchronously call fsync on the given filehandle and call the callback |
931 | Asynchronously call fsync on the given filehandle and call the callback |
506 | with the fsync result code. |
932 | with the fsync result code. |
507 | |
933 | |
… | |
… | |
511 | callback with the fdatasync result code. |
937 | callback with the fdatasync result code. |
512 | |
938 | |
513 | If this call isn't available because your OS lacks it or it couldn't be |
939 | If this call isn't available because your OS lacks it or it couldn't be |
514 | detected, it will be emulated by calling C<fsync> instead. |
940 | detected, it will be emulated by calling C<fsync> instead. |
515 | |
941 | |
|
|
942 | =item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status) |
|
|
943 | |
|
|
944 | Sync the data portion of the file specified by C<$offset> and C<$length> |
|
|
945 | to disk (but NOT the metadata), by calling the Linux-specific |
|
|
946 | sync_file_range call. If sync_file_range is not available or it returns |
|
|
947 | ENOSYS, then fdatasync or fsync is being substituted. |
|
|
948 | |
|
|
949 | C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>, |
|
|
950 | C<IO::AIO::SYNC_FILE_RANGE_WRITE> and |
|
|
951 | C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range |
|
|
952 | manpage for details. |
|
|
953 | |
|
|
954 | =item aio_pathsync $path, $callback->($status) |
|
|
955 | |
|
|
956 | This request tries to open, fsync and close the given path. This is a |
|
|
957 | composite request intended to sync directories after directory operations |
|
|
958 | (E.g. rename). This might not work on all operating systems or have any |
|
|
959 | specific effect, but usually it makes sure that directory changes get |
|
|
960 | written to disc. It works for anything that can be opened for read-only, |
|
|
961 | not just directories. |
|
|
962 | |
|
|
963 | Passes C<0> when everything went ok, and C<-1> on error. |
|
|
964 | |
|
|
965 | =cut |
|
|
966 | |
|
|
967 | sub aio_pathsync($;$) { |
|
|
968 | my ($path, $cb) = @_; |
|
|
969 | |
|
|
970 | my $pri = aioreq_pri; |
|
|
971 | my $grp = aio_group $cb; |
|
|
972 | |
|
|
973 | aioreq_pri $pri; |
|
|
974 | add $grp aio_open $path, O_RDONLY, 0, sub { |
|
|
975 | my ($fh) = @_; |
|
|
976 | if ($fh) { |
|
|
977 | aioreq_pri $pri; |
|
|
978 | add $grp aio_fsync $fh, sub { |
|
|
979 | $grp->result ($_[0]); |
|
|
980 | |
|
|
981 | aioreq_pri $pri; |
|
|
982 | add $grp aio_close $fh; |
|
|
983 | }; |
|
|
984 | } else { |
|
|
985 | $grp->result (-1); |
|
|
986 | } |
|
|
987 | }; |
|
|
988 | |
|
|
989 | $grp |
|
|
990 | } |
|
|
991 | |
516 | =item aio_group $callback->(...) |
992 | =item aio_group $callback->(...) |
517 | |
|
|
518 | [EXPERIMENTAL] |
|
|
519 | |
993 | |
520 | This is a very special aio request: Instead of doing something, it is a |
994 | This is a very special aio request: Instead of doing something, it is a |
521 | container for other aio requests, which is useful if you want to bundle |
995 | container for other aio requests, which is useful if you want to bundle |
522 | many requests into a single, composite, request. |
996 | many requests into a single, composite, request with a definite callback |
|
|
997 | and the ability to cancel the whole request with its subrequests. |
523 | |
998 | |
524 | Returns an object of class L<IO::AIO::GRP>. See its documentation below |
999 | Returns an object of class L<IO::AIO::GRP>. See its documentation below |
525 | for more info. |
1000 | for more info. |
526 | |
1001 | |
527 | Example: |
1002 | Example: |
… | |
… | |
533 | add $grp |
1008 | add $grp |
534 | (aio_stat ...), |
1009 | (aio_stat ...), |
535 | (aio_stat ...), |
1010 | (aio_stat ...), |
536 | ...; |
1011 | ...; |
537 | |
1012 | |
|
|
1013 | =item aio_nop $callback->() |
|
|
1014 | |
|
|
1015 | This is a special request - it does nothing in itself and is only used for |
|
|
1016 | side effects, such as when you want to add a dummy request to a group so |
|
|
1017 | that finishing the requests in the group depends on executing the given |
|
|
1018 | code. |
|
|
1019 | |
|
|
1020 | While this request does nothing, it still goes through the execution |
|
|
1021 | phase and still requires a worker thread. Thus, the callback will not |
|
|
1022 | be executed immediately but only after other requests in the queue have |
|
|
1023 | entered their execution phase. This can be used to measure request |
|
|
1024 | latency. |
|
|
1025 | |
538 | =item IO::AIO::aio_sleep $fractional_seconds, $callback->() *NOT EXPORTED* |
1026 | =item IO::AIO::aio_busy $fractional_seconds, $callback->() *NOT EXPORTED* |
539 | |
1027 | |
540 | Mainly used for debugging and benchmarking, this aio request puts one of |
1028 | Mainly used for debugging and benchmarking, this aio request puts one of |
541 | the request workers to sleep for the given time. |
1029 | the request workers to sleep for the given time. |
542 | |
1030 | |
543 | While it is theoretically handy to have simple I/O scheduling requests |
1031 | While it is theoretically handy to have simple I/O scheduling requests |
544 | like sleep and file handle readable/writable, the overhead this creates |
1032 | like sleep and file handle readable/writable, the overhead this creates is |
545 | is immense, so do not use this function except to put your application |
1033 | immense (it blocks a thread for a long time) so do not use this function |
546 | under artificial I/O pressure. |
1034 | except to put your application under artificial I/O pressure. |
547 | |
1035 | |
548 | =back |
1036 | =back |
549 | |
1037 | |
550 | =head2 IO::AIO::REQ CLASS |
1038 | =head2 IO::AIO::REQ CLASS |
551 | |
1039 | |
552 | All non-aggregate C<aio_*> functions return an object of this class when |
1040 | All non-aggregate C<aio_*> functions return an object of this class when |
553 | called in non-void context. |
1041 | called in non-void context. |
554 | |
1042 | |
555 | A request always moves through the following five states in its lifetime, |
|
|
556 | in order: B<ready> (request has been created, but has not been executed |
|
|
557 | yet), B<execute> (request is currently being executed), B<pending> |
|
|
558 | (request has been executed but callback has not been called yet), |
|
|
559 | B<result> (results are being processed synchronously, includes calling the |
|
|
560 | callback) and B<done> (request has reached the end of its lifetime and |
|
|
561 | holds no resources anymore). |
|
|
562 | |
|
|
563 | =over 4 |
1043 | =over 4 |
564 | |
1044 | |
565 | =item $req->cancel |
1045 | =item cancel $req |
566 | |
1046 | |
567 | Cancels the request, if possible. Has the effect of skipping execution |
1047 | Cancels the request, if possible. Has the effect of skipping execution |
568 | when entering the B<execute> state and skipping calling the callback when |
1048 | when entering the B<execute> state and skipping calling the callback when |
569 | entering the the B<result> state, but will leave the request otherwise |
1049 | entering the the B<result> state, but will leave the request otherwise |
570 | untouched. That means that requests that currently execute will not be |
1050 | untouched (with the exception of readdir). That means that requests that |
571 | stopped and resources held by the request will not be freed prematurely. |
1051 | currently execute will not be stopped and resources held by the request |
|
|
1052 | will not be freed prematurely. |
|
|
1053 | |
|
|
1054 | =item cb $req $callback->(...) |
|
|
1055 | |
|
|
1056 | Replace (or simply set) the callback registered to the request. |
572 | |
1057 | |
573 | =back |
1058 | =back |
574 | |
1059 | |
575 | =head2 IO::AIO::GRP CLASS |
1060 | =head2 IO::AIO::GRP CLASS |
576 | |
1061 | |
… | |
… | |
603 | }; |
1088 | }; |
604 | |
1089 | |
605 | This makes it very easy to create composite requests (see the source of |
1090 | This makes it very easy to create composite requests (see the source of |
606 | C<aio_move> for an application) that work and feel like simple requests. |
1091 | C<aio_move> for an application) that work and feel like simple requests. |
607 | |
1092 | |
|
|
1093 | =over 4 |
|
|
1094 | |
608 | The IO::AIO::GRP objects will be cleaned up during calls to |
1095 | =item * The IO::AIO::GRP objects will be cleaned up during calls to |
609 | C<IO::AIO::poll_cb>, just like any other request. |
1096 | C<IO::AIO::poll_cb>, just like any other request. |
610 | |
1097 | |
611 | They can be canceled like any other request. Canceling will cancel not |
1098 | =item * They can be canceled like any other request. Canceling will cancel not |
612 | only the request itself, but also all requests it contains. |
1099 | only the request itself, but also all requests it contains. |
613 | |
1100 | |
614 | They can also can also be added to other IO::AIO::GRP objects. |
1101 | =item * They can also can also be added to other IO::AIO::GRP objects. |
615 | |
1102 | |
616 | You must not add requests to a group from within the group callback (or |
1103 | =item * You must not add requests to a group from within the group callback (or |
617 | any later time). |
1104 | any later time). |
|
|
1105 | |
|
|
1106 | =back |
618 | |
1107 | |
619 | Their lifetime, simplified, looks like this: when they are empty, they |
1108 | Their lifetime, simplified, looks like this: when they are empty, they |
620 | will finish very quickly. If they contain only requests that are in the |
1109 | will finish very quickly. If they contain only requests that are in the |
621 | C<done> state, they will also finish. Otherwise they will continue to |
1110 | C<done> state, they will also finish. Otherwise they will continue to |
622 | exist. |
1111 | exist. |
623 | |
1112 | |
624 | That means after creating a group you have some time to add requests. And |
1113 | That means after creating a group you have some time to add requests |
625 | in the callbacks of those requests, you can add further requests to the |
1114 | (precisely before the callback has been invoked, which is only done within |
626 | group. And only when all those requests have finished will the the group |
1115 | the C<poll_cb>). And in the callbacks of those requests, you can add |
627 | itself finish. |
1116 | further requests to the group. And only when all those requests have |
|
|
1117 | finished will the the group itself finish. |
628 | |
1118 | |
629 | =over 4 |
1119 | =over 4 |
630 | |
1120 | |
|
|
1121 | =item add $grp ... |
|
|
1122 | |
631 | =item $grp->add (...) |
1123 | =item $grp->add (...) |
632 | |
|
|
633 | =item add $grp ... |
|
|
634 | |
1124 | |
635 | Add one or more requests to the group. Any type of L<IO::AIO::REQ> can |
1125 | Add one or more requests to the group. Any type of L<IO::AIO::REQ> can |
636 | be added, including other groups, as long as you do not create circular |
1126 | be added, including other groups, as long as you do not create circular |
637 | dependencies. |
1127 | dependencies. |
638 | |
1128 | |
639 | Returns all its arguments. |
1129 | Returns all its arguments. |
640 | |
1130 | |
|
|
1131 | =item $grp->cancel_subs |
|
|
1132 | |
|
|
1133 | Cancel all subrequests and clears any feeder, but not the group request |
|
|
1134 | itself. Useful when you queued a lot of events but got a result early. |
|
|
1135 | |
641 | =item $grp->result (...) |
1136 | =item $grp->result (...) |
642 | |
1137 | |
643 | Set the result value(s) that will be passed to the group callback when all |
1138 | Set the result value(s) that will be passed to the group callback when all |
644 | subrequests have finished. By default, no argument will be passed. |
1139 | subrequests have finished and set the groups errno to the current value |
|
|
1140 | of errno (just like calling C<errno> without an error number). By default, |
|
|
1141 | no argument will be passed and errno is zero. |
645 | |
1142 | |
646 | =item $grp->set_feeder ($callback->($grp)) |
1143 | =item $grp->errno ([$errno]) |
647 | |
1144 | |
648 | [VERY EXPERIMENTAL] |
1145 | Sets the group errno value to C<$errno>, or the current value of errno |
|
|
1146 | when the argument is missing. |
|
|
1147 | |
|
|
1148 | Every aio request has an associated errno value that is restored when |
|
|
1149 | the callback is invoked. This method lets you change this value from its |
|
|
1150 | default (0). |
|
|
1151 | |
|
|
1152 | Calling C<result> will also set errno, so make sure you either set C<$!> |
|
|
1153 | before the call to C<result>, or call c<errno> after it. |
|
|
1154 | |
|
|
1155 | =item feed $grp $callback->($grp) |
649 | |
1156 | |
650 | Sets a feeder/generator on this group: every group can have an attached |
1157 | Sets a feeder/generator on this group: every group can have an attached |
651 | generator that generates requests if idle. The idea behind this is that, |
1158 | generator that generates requests if idle. The idea behind this is that, |
652 | although you could just queue as many requests as you want in a group, |
1159 | although you could just queue as many requests as you want in a group, |
653 | this might starve other requests for a potentially long time. For |
1160 | this might starve other requests for a potentially long time. For example, |
654 | example, C<aio_scandir> might generate hundreds of thousands C<aio_stat> |
1161 | C<aio_scandir> might generate hundreds of thousands C<aio_stat> requests, |
655 | requests, delaying any later requests for a long time. |
1162 | delaying any later requests for a long time. |
656 | |
1163 | |
657 | To avoid this, and allow incremental generation of requests, you can |
1164 | To avoid this, and allow incremental generation of requests, you can |
658 | instead a group and set a feeder on it that generates those requests. The |
1165 | instead a group and set a feeder on it that generates those requests. The |
659 | feeder will be called whenever there are few enough (see C<feeder_limit>, |
1166 | feed callback will be called whenever there are few enough (see C<limit>, |
660 | below) requests active in the group itself and is expected to queue more |
1167 | below) requests active in the group itself and is expected to queue more |
661 | requests. |
1168 | requests. |
662 | |
1169 | |
663 | The feeder can queue as many requests as it likes (i.e. C<add> does not |
1170 | The feed callback can queue as many requests as it likes (i.e. C<add> does |
664 | impose any limits). |
1171 | not impose any limits). |
665 | |
1172 | |
666 | If the feeder does not queue more requests when called, it will be |
1173 | If the feed does not queue more requests when called, it will be |
667 | automatically removed from the group. |
1174 | automatically removed from the group. |
668 | |
1175 | |
669 | If the feeder limit is C<0>, it will be set to C<2> automatically. |
1176 | If the feed limit is C<0> when this method is called, it will be set to |
|
|
1177 | C<2> automatically. |
670 | |
1178 | |
671 | Example: |
1179 | Example: |
672 | |
1180 | |
673 | # stat all files in @files, but only ever use four aio requests concurrently: |
1181 | # stat all files in @files, but only ever use four aio requests concurrently: |
674 | |
1182 | |
675 | my $grp = aio_group sub { print "finished\n" }; |
1183 | my $grp = aio_group sub { print "finished\n" }; |
676 | $grp->feeder_limit (4); |
1184 | limit $grp 4; |
677 | $grp->set_feeder (sub { |
1185 | feed $grp sub { |
678 | my $file = pop @files |
1186 | my $file = pop @files |
679 | or return; |
1187 | or return; |
680 | |
1188 | |
681 | add $grp aio_stat $file, sub { ... }; |
1189 | add $grp aio_stat $file, sub { ... }; |
682 | }); |
1190 | }; |
683 | |
1191 | |
684 | =item $grp->feeder_limit ($num) |
1192 | =item limit $grp $num |
685 | |
1193 | |
686 | Sets the feeder limit for the group: The feeder will be called whenever |
1194 | Sets the feeder limit for the group: The feeder will be called whenever |
687 | the group contains less than this many requests. |
1195 | the group contains less than this many requests. |
688 | |
1196 | |
689 | Setting the limit to C<0> will pause the feeding process. |
1197 | Setting the limit to C<0> will pause the feeding process. |
690 | |
1198 | |
|
|
1199 | The default value for the limit is C<0>, but note that setting a feeder |
|
|
1200 | automatically bumps it up to C<2>. |
|
|
1201 | |
691 | =back |
1202 | =back |
692 | |
1203 | |
693 | =head2 SUPPORT FUNCTIONS |
1204 | =head2 SUPPORT FUNCTIONS |
|
|
1205 | |
|
|
1206 | =head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION |
694 | |
1207 | |
695 | =over 4 |
1208 | =over 4 |
696 | |
1209 | |
697 | =item $fileno = IO::AIO::poll_fileno |
1210 | =item $fileno = IO::AIO::poll_fileno |
698 | |
1211 | |
… | |
… | |
703 | |
1216 | |
704 | See C<poll_cb> for an example. |
1217 | See C<poll_cb> for an example. |
705 | |
1218 | |
706 | =item IO::AIO::poll_cb |
1219 | =item IO::AIO::poll_cb |
707 | |
1220 | |
708 | Process all outstanding events on the result pipe. You have to call this |
1221 | Process some outstanding events on the result pipe. You have to call this |
709 | regularly. Returns the number of events processed. Returns immediately |
1222 | regularly. Returns C<0> if all events could be processed, or C<-1> if it |
710 | when no events are outstanding. |
1223 | returned earlier for whatever reason. Returns immediately when no events |
|
|
1224 | are outstanding. The amount of events processed depends on the settings of |
|
|
1225 | C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>. |
|
|
1226 | |
|
|
1227 | If not all requests were processed for whatever reason, the filehandle |
|
|
1228 | will still be ready when C<poll_cb> returns, so normally you don't have to |
|
|
1229 | do anything special to have it called later. |
711 | |
1230 | |
712 | Example: Install an Event watcher that automatically calls |
1231 | Example: Install an Event watcher that automatically calls |
713 | IO::AIO::poll_cb with high priority: |
1232 | IO::AIO::poll_cb with high priority: |
714 | |
1233 | |
715 | Event->io (fd => IO::AIO::poll_fileno, |
1234 | Event->io (fd => IO::AIO::poll_fileno, |
716 | poll => 'r', async => 1, |
1235 | poll => 'r', async => 1, |
717 | cb => \&IO::AIO::poll_cb); |
1236 | cb => \&IO::AIO::poll_cb); |
718 | |
1237 | |
|
|
1238 | =item IO::AIO::max_poll_reqs $nreqs |
|
|
1239 | |
|
|
1240 | =item IO::AIO::max_poll_time $seconds |
|
|
1241 | |
|
|
1242 | These set the maximum number of requests (default C<0>, meaning infinity) |
|
|
1243 | that are being processed by C<IO::AIO::poll_cb> in one call, respectively |
|
|
1244 | the maximum amount of time (default C<0>, meaning infinity) spent in |
|
|
1245 | C<IO::AIO::poll_cb> to process requests (more correctly the mininum amount |
|
|
1246 | of time C<poll_cb> is allowed to use). |
|
|
1247 | |
|
|
1248 | Setting C<max_poll_time> to a non-zero value creates an overhead of one |
|
|
1249 | syscall per request processed, which is not normally a problem unless your |
|
|
1250 | callbacks are really really fast or your OS is really really slow (I am |
|
|
1251 | not mentioning Solaris here). Using C<max_poll_reqs> incurs no overhead. |
|
|
1252 | |
|
|
1253 | Setting these is useful if you want to ensure some level of |
|
|
1254 | interactiveness when perl is not fast enough to process all requests in |
|
|
1255 | time. |
|
|
1256 | |
|
|
1257 | For interactive programs, values such as C<0.01> to C<0.1> should be fine. |
|
|
1258 | |
|
|
1259 | Example: Install an Event watcher that automatically calls |
|
|
1260 | IO::AIO::poll_cb with low priority, to ensure that other parts of the |
|
|
1261 | program get the CPU sometimes even under high AIO load. |
|
|
1262 | |
|
|
1263 | # try not to spend much more than 0.1s in poll_cb |
|
|
1264 | IO::AIO::max_poll_time 0.1; |
|
|
1265 | |
|
|
1266 | # use a low priority so other tasks have priority |
|
|
1267 | Event->io (fd => IO::AIO::poll_fileno, |
|
|
1268 | poll => 'r', nice => 1, |
|
|
1269 | cb => &IO::AIO::poll_cb); |
|
|
1270 | |
719 | =item IO::AIO::poll_wait |
1271 | =item IO::AIO::poll_wait |
720 | |
1272 | |
|
|
1273 | If there are any outstanding requests and none of them in the result |
721 | Wait till the result filehandle becomes ready for reading (simply does a |
1274 | phase, wait till the result filehandle becomes ready for reading (simply |
722 | C<select> on the filehandle. This is useful if you want to synchronously wait |
1275 | does a C<select> on the filehandle. This is useful if you want to |
723 | for some requests to finish). |
1276 | synchronously wait for some requests to finish). |
724 | |
1277 | |
725 | See C<nreqs> for an example. |
1278 | See C<nreqs> for an example. |
726 | |
1279 | |
|
|
1280 | =item IO::AIO::poll |
|
|
1281 | |
|
|
1282 | Waits until some requests have been handled. |
|
|
1283 | |
|
|
1284 | Returns the number of requests processed, but is otherwise strictly |
|
|
1285 | equivalent to: |
|
|
1286 | |
|
|
1287 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
1288 | |
727 | =item IO::AIO::nreqs |
1289 | =item IO::AIO::flush |
728 | |
1290 | |
729 | Returns the number of requests currently outstanding (i.e. for which their |
1291 | Wait till all outstanding AIO requests have been handled. |
730 | callback has not been invoked yet). |
|
|
731 | |
1292 | |
732 | Example: wait till there are no outstanding requests anymore: |
1293 | Strictly equivalent to: |
733 | |
1294 | |
734 | IO::AIO::poll_wait, IO::AIO::poll_cb |
1295 | IO::AIO::poll_wait, IO::AIO::poll_cb |
735 | while IO::AIO::nreqs; |
1296 | while IO::AIO::nreqs; |
736 | |
1297 | |
737 | =item IO::AIO::flush |
1298 | =back |
738 | |
1299 | |
739 | Wait till all outstanding AIO requests have been handled. |
1300 | =head3 CONTROLLING THE NUMBER OF THREADS |
740 | |
1301 | |
741 | Strictly equivalent to: |
1302 | =over |
742 | |
|
|
743 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
744 | while IO::AIO::nreqs; |
|
|
745 | |
|
|
746 | =item IO::AIO::poll |
|
|
747 | |
|
|
748 | Waits until some requests have been handled. |
|
|
749 | |
|
|
750 | Strictly equivalent to: |
|
|
751 | |
|
|
752 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
753 | if IO::AIO::nreqs; |
|
|
754 | |
1303 | |
755 | =item IO::AIO::min_parallel $nthreads |
1304 | =item IO::AIO::min_parallel $nthreads |
756 | |
1305 | |
757 | Set the minimum number of AIO threads to C<$nthreads>. The current default |
1306 | Set the minimum number of AIO threads to C<$nthreads>. The current |
758 | is C<4>, which means four asynchronous operations can be done at one time |
1307 | default is C<8>, which means eight asynchronous operations can execute |
759 | (the number of outstanding operations, however, is unlimited). |
1308 | concurrently at any one time (the number of outstanding requests, |
|
|
1309 | however, is unlimited). |
760 | |
1310 | |
761 | IO::AIO starts threads only on demand, when an AIO request is queued and |
1311 | IO::AIO starts threads only on demand, when an AIO request is queued and |
762 | no free thread exists. |
1312 | no free thread exists. Please note that queueing up a hundred requests can |
|
|
1313 | create demand for a hundred threads, even if it turns out that everything |
|
|
1314 | is in the cache and could have been processed faster by a single thread. |
763 | |
1315 | |
764 | It is recommended to keep the number of threads low, as some Linux |
1316 | It is recommended to keep the number of threads relatively low, as some |
765 | kernel versions will scale negatively with the number of threads (higher |
1317 | Linux kernel versions will scale negatively with the number of threads |
766 | parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32 |
1318 | (higher parallelity => MUCH higher latency). With current Linux 2.6 |
767 | threads should be fine. |
1319 | versions, 4-32 threads should be fine. |
768 | |
1320 | |
769 | Under most circumstances you don't need to call this function, as the |
1321 | Under most circumstances you don't need to call this function, as the |
770 | module selects a default that is suitable for low to moderate load. |
1322 | module selects a default that is suitable for low to moderate load. |
771 | |
1323 | |
772 | =item IO::AIO::max_parallel $nthreads |
1324 | =item IO::AIO::max_parallel $nthreads |
… | |
… | |
781 | This module automatically runs C<max_parallel 0> at program end, to ensure |
1333 | This module automatically runs C<max_parallel 0> at program end, to ensure |
782 | that all threads are killed and that there are no outstanding requests. |
1334 | that all threads are killed and that there are no outstanding requests. |
783 | |
1335 | |
784 | Under normal circumstances you don't need to call this function. |
1336 | Under normal circumstances you don't need to call this function. |
785 | |
1337 | |
|
|
1338 | =item IO::AIO::max_idle $nthreads |
|
|
1339 | |
|
|
1340 | Limit the number of threads (default: 4) that are allowed to idle (i.e., |
|
|
1341 | threads that did not get a request to process within 10 seconds). That |
|
|
1342 | means if a thread becomes idle while C<$nthreads> other threads are also |
|
|
1343 | idle, it will free its resources and exit. |
|
|
1344 | |
|
|
1345 | This is useful when you allow a large number of threads (e.g. 100 or 1000) |
|
|
1346 | to allow for extremely high load situations, but want to free resources |
|
|
1347 | under normal circumstances (1000 threads can easily consume 30MB of RAM). |
|
|
1348 | |
|
|
1349 | The default is probably ok in most situations, especially if thread |
|
|
1350 | creation is fast. If thread creation is very slow on your system you might |
|
|
1351 | want to use larger values. |
|
|
1352 | |
786 | =item $oldnreqs = IO::AIO::max_outstanding $nreqs |
1353 | =item IO::AIO::max_outstanding $maxreqs |
|
|
1354 | |
|
|
1355 | This is a very bad function to use in interactive programs because it |
|
|
1356 | blocks, and a bad way to reduce concurrency because it is inexact: Better |
|
|
1357 | use an C<aio_group> together with a feed callback. |
787 | |
1358 | |
788 | Sets the maximum number of outstanding requests to C<$nreqs>. If you |
1359 | Sets the maximum number of outstanding requests to C<$nreqs>. If you |
789 | try to queue up more than this number of requests, the caller will block until |
1360 | do queue up more than this number of requests, the next call to the |
790 | some requests have been handled. |
1361 | C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>) |
|
|
1362 | function will block until the limit is no longer exceeded. |
791 | |
1363 | |
792 | The default is very large, so normally there is no practical limit. If you |
1364 | The default value is very large, so there is no practical limit on the |
793 | queue up many requests in a loop it often improves speed if you set |
1365 | number of outstanding requests. |
794 | this to a relatively low number, such as C<100>. |
|
|
795 | |
1366 | |
796 | Under normal circumstances you don't need to call this function. |
1367 | You can still queue as many requests as you want. Therefore, |
|
|
1368 | C<max_outstanding> is mainly useful in simple scripts (with low values) or |
|
|
1369 | as a stop gap to shield against fatal memory overflow (with large values). |
797 | |
1370 | |
798 | =back |
1371 | =back |
799 | |
1372 | |
|
|
1373 | =head3 STATISTICAL INFORMATION |
|
|
1374 | |
|
|
1375 | =over |
|
|
1376 | |
|
|
1377 | =item IO::AIO::nreqs |
|
|
1378 | |
|
|
1379 | Returns the number of requests currently in the ready, execute or pending |
|
|
1380 | states (i.e. for which their callback has not been invoked yet). |
|
|
1381 | |
|
|
1382 | Example: wait till there are no outstanding requests anymore: |
|
|
1383 | |
|
|
1384 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
1385 | while IO::AIO::nreqs; |
|
|
1386 | |
|
|
1387 | =item IO::AIO::nready |
|
|
1388 | |
|
|
1389 | Returns the number of requests currently in the ready state (not yet |
|
|
1390 | executed). |
|
|
1391 | |
|
|
1392 | =item IO::AIO::npending |
|
|
1393 | |
|
|
1394 | Returns the number of requests currently in the pending state (executed, |
|
|
1395 | but not yet processed by poll_cb). |
|
|
1396 | |
|
|
1397 | =back |
|
|
1398 | |
800 | =cut |
1399 | =cut |
801 | |
1400 | |
802 | # support function to convert a fd into a perl filehandle |
|
|
803 | sub _fd2fh { |
|
|
804 | return undef if $_[0] < 0; |
|
|
805 | |
|
|
806 | # try to generate nice filehandles |
|
|
807 | my $sym = "IO::AIO::fd#$_[0]"; |
|
|
808 | local *$sym; |
|
|
809 | |
|
|
810 | open *$sym, "+<&=$_[0]" # usually works under any unix |
|
|
811 | or open *$sym, "<&=$_[0]" # cygwin needs this |
|
|
812 | or open *$sym, ">&=$_[0]" # or this |
|
|
813 | or return undef; |
|
|
814 | |
|
|
815 | *$sym |
|
|
816 | } |
|
|
817 | |
|
|
818 | min_parallel 4; |
1401 | min_parallel 8; |
819 | |
1402 | |
820 | END { |
1403 | END { flush } |
821 | max_parallel 0; |
|
|
822 | } |
|
|
823 | |
1404 | |
824 | 1; |
1405 | 1; |
825 | |
1406 | |
826 | =head2 FORK BEHAVIOUR |
1407 | =head2 FORK BEHAVIOUR |
827 | |
1408 | |
828 | This module should do "the right thing" when the process using it forks: |
1409 | This module should do "the right thing" when the process using it forks: |
829 | |
1410 | |
830 | Before the fork, IO::AIO enters a quiescent state where no requests |
1411 | Before the fork, IO::AIO enters a quiescent state where no requests |
831 | can be added in other threads and no results will be processed. After |
1412 | can be added in other threads and no results will be processed. After |
832 | the fork the parent simply leaves the quiescent state and continues |
1413 | the fork the parent simply leaves the quiescent state and continues |
833 | request/result processing, while the child clears the request/result |
1414 | request/result processing, while the child frees the request/result queue |
834 | queue (so the requests started before the fork will only be handled in |
1415 | (so that the requests started before the fork will only be handled in the |
835 | the parent). Threads will be started on demand until the limit ste in the |
1416 | parent). Threads will be started on demand until the limit set in the |
836 | parent process has been reached again. |
1417 | parent process has been reached again. |
837 | |
1418 | |
838 | In short: the parent will, after a short pause, continue as if fork had |
1419 | In short: the parent will, after a short pause, continue as if fork had |
839 | not been called, while the child will act as if IO::AIO has not been used |
1420 | not been called, while the child will act as if IO::AIO has not been used |
840 | yet. |
1421 | yet. |
841 | |
1422 | |
842 | =head2 MEMORY USAGE |
1423 | =head2 MEMORY USAGE |
843 | |
1424 | |
|
|
1425 | Per-request usage: |
|
|
1426 | |
844 | Each aio request uses - depending on your architecture - around 128 bytes |
1427 | Each aio request uses - depending on your architecture - around 100-200 |
845 | of memory. In addition, stat requests need a stat buffer (possibly a few |
1428 | bytes of memory. In addition, stat requests need a stat buffer (possibly |
846 | hundred bytes). Perl scalars and other data passed into aio requests will |
1429 | a few hundred bytes), readdir requires a result buffer and so on. Perl |
847 | also be locked. |
1430 | scalars and other data passed into aio requests will also be locked and |
|
|
1431 | will consume memory till the request has entered the done state. |
848 | |
1432 | |
849 | This is now awfully much, so queuing lots of requests is not usually a |
1433 | This is not awfully much, so queuing lots of requests is not usually a |
850 | problem. |
1434 | problem. |
851 | |
1435 | |
852 | Each thread needs a stack area which is usually around 16k, sometimes much |
1436 | Per-thread usage: |
853 | larger, depending on the OS. |
1437 | |
|
|
1438 | In the execution phase, some aio requests require more memory for |
|
|
1439 | temporary buffers, and each thread requires a stack and other data |
|
|
1440 | structures (usually around 16k-128k, depending on the OS). |
|
|
1441 | |
|
|
1442 | =head1 KNOWN BUGS |
|
|
1443 | |
|
|
1444 | Known bugs will be fixed in the next release. |
854 | |
1445 | |
855 | =head1 SEE ALSO |
1446 | =head1 SEE ALSO |
856 | |
1447 | |
857 | L<Coro>, L<Linux::AIO> (obsolete). |
1448 | L<AnyEvent::AIO> for easy integration into event loops, L<Coro::AIO> for a |
|
|
1449 | more natural syntax. |
858 | |
1450 | |
859 | =head1 AUTHOR |
1451 | =head1 AUTHOR |
860 | |
1452 | |
861 | Marc Lehmann <schmorp@schmorp.de> |
1453 | Marc Lehmann <schmorp@schmorp.de> |
862 | http://home.schmorp.de/ |
1454 | http://home.schmorp.de/ |