… | |
… | |
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 | my $req = aio_unlink "/tmp/file", sub { }; |
|
|
24 | $req->cancel; # cancel request if still in queue |
|
|
25 | |
|
|
26 | my $grp = aio_group sub { print "all stats done\n" }; |
|
|
27 | add $grp aio_stat "..." for ...; |
|
|
28 | |
|
|
29 | # AnyEvent integration |
|
|
30 | open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!"; |
|
|
31 | my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb }); |
|
|
32 | |
|
|
33 | # Event integration |
21 | Event->io (fd => IO::AIO::poll_fileno, |
34 | Event->io (fd => IO::AIO::poll_fileno, |
22 | poll => 'r', |
35 | poll => 'r', |
23 | cb => \&IO::AIO::poll_cb); |
36 | cb => \&IO::AIO::poll_cb); |
24 | |
37 | |
25 | # Glib/Gtk2 |
38 | # Glib/Gtk2 integration |
26 | add_watch Glib::IO IO::AIO::poll_fileno, |
39 | add_watch Glib::IO IO::AIO::poll_fileno, |
27 | in => sub { IO::AIO::poll_cb, 1 }; |
40 | in => sub { IO::AIO::poll_cb; 1 }; |
28 | |
41 | |
29 | # Tk |
42 | # Tk integration |
30 | Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "", |
43 | Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "", |
31 | readable => \&IO::AIO::poll_cb); |
44 | readable => \&IO::AIO::poll_cb); |
32 | |
45 | |
33 | # Danga::Socket |
46 | # Danga::Socket integration |
34 | Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => |
47 | Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => |
35 | \&IO::AIO::poll_cb); |
48 | \&IO::AIO::poll_cb); |
36 | |
|
|
37 | |
49 | |
38 | =head1 DESCRIPTION |
50 | =head1 DESCRIPTION |
39 | |
51 | |
40 | This module implements asynchronous I/O using whatever means your |
52 | This module implements asynchronous I/O using whatever means your |
41 | operating system supports. |
53 | operating system supports. |
… | |
… | |
48 | not well-supported (Linux doesn't allow them on normal files currently, |
60 | not well-supported (Linux doesn't allow them on normal files currently, |
49 | for example), and they would only support aio_read and aio_write, so the |
61 | for example), and they would only support aio_read and aio_write, so the |
50 | remaining functionality would have to be implemented using threads anyway. |
62 | remaining functionality would have to be implemented using threads anyway. |
51 | |
63 | |
52 | Although the module will work with in the presence of other threads, it is |
64 | Although the module will work with in the presence of other threads, it is |
53 | currently not reentrant, so use appropriate locking yourself. |
65 | currently not reentrant, so use appropriate locking yourself, always call |
|
|
66 | C<poll_cb> from within the same thread, or never call C<poll_cb> (or other |
|
|
67 | C<aio_> functions) recursively. |
54 | |
68 | |
55 | =cut |
69 | =cut |
56 | |
70 | |
57 | package IO::AIO; |
71 | package IO::AIO; |
58 | |
72 | |
|
|
73 | no warnings; |
|
|
74 | use strict 'vars'; |
|
|
75 | |
59 | use base 'Exporter'; |
76 | use base 'Exporter'; |
60 | |
77 | |
61 | use Fcntl (); |
|
|
62 | |
|
|
63 | BEGIN { |
78 | BEGIN { |
64 | $VERSION = 0.3; |
79 | our $VERSION = '2.0'; |
65 | |
80 | |
66 | @EXPORT = qw(aio_read aio_write aio_open aio_close aio_stat aio_lstat aio_unlink |
81 | our @EXPORT = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat |
|
|
82 | aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink |
67 | aio_fsync aio_fdatasync aio_readahead); |
83 | aio_fsync aio_fdatasync aio_readahead aio_rename aio_link aio_move |
|
|
84 | aio_group); |
68 | @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs); |
85 | our @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs); |
|
|
86 | |
|
|
87 | @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; |
69 | |
88 | |
70 | require XSLoader; |
89 | require XSLoader; |
71 | XSLoader::load IO::AIO, $VERSION; |
90 | XSLoader::load ("IO::AIO", $VERSION); |
72 | } |
91 | } |
73 | |
92 | |
74 | =head1 FUNCTIONS |
93 | =head1 FUNCTIONS |
75 | |
94 | |
76 | =head2 AIO FUNCTIONS |
95 | =head2 AIO FUNCTIONS |
… | |
… | |
81 | which must be a code reference. This code reference will get called with |
100 | 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 |
101 | 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 |
102 | perl, which usually delivers "false") as it's sole argument when the given |
84 | syscall has been executed asynchronously. |
103 | syscall has been executed asynchronously. |
85 | |
104 | |
86 | All functions that expect a filehandle will also accept a file descriptor. |
105 | All functions expecting a filehandle keep a copy of the filehandle |
|
|
106 | internally until the request has finished. |
87 | |
107 | |
|
|
108 | All requests return objects of type L<IO::AIO::REQ> that allow further |
|
|
109 | manipulation of those requests while they are in-flight. |
|
|
110 | |
88 | The filenames you pass to these routines I<must> be absolute. The reason |
111 | 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 |
112 | encoded in byte form. The reason for the former is that at the time the |
90 | directory could have changed. Alternatively, you can make sure that you |
113 | request is being executed, the current working directory could have |
|
|
114 | changed. Alternatively, you can make sure that you never change the |
91 | never change the current working directory. |
115 | current working directory. |
|
|
116 | |
|
|
117 | To encode pathnames to byte form, either make sure you either: a) |
|
|
118 | always pass in filenames you got from outside (command line, readdir |
|
|
119 | etc.), 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 |
|
|
121 | environment, d) use Glib::filename_from_unicode on unicode filenames or e) |
|
|
122 | use something else. |
92 | |
123 | |
93 | =over 4 |
124 | =over 4 |
94 | |
125 | |
95 | =item aio_open $pathname, $flags, $mode, $callback |
126 | =item aio_open $pathname, $flags, $mode, $callback->($fh) |
96 | |
127 | |
97 | Asynchronously open or create a file and call the callback with a newly |
128 | Asynchronously open or create a file and call the callback with a newly |
98 | created filehandle for the file. |
129 | created filehandle for the file. |
99 | |
130 | |
100 | The pathname passed to C<aio_open> must be absolute. See API NOTES, above, |
131 | The pathname passed to C<aio_open> must be absolute. See API NOTES, above, |
101 | for an explanation. |
132 | for an explanation. |
102 | |
133 | |
103 | The C<$mode> argument is a bitmask. See the C<Fcntl> module for a |
134 | The C<$flags> argument is a bitmask. See the C<Fcntl> module for a |
104 | list. They are the same as used in C<sysopen>. |
135 | list. They are the same as used by C<sysopen>. |
|
|
136 | |
|
|
137 | Likewise, C<$mode> specifies the mode of the newly created file, if it |
|
|
138 | didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>, |
|
|
139 | except that it is mandatory (i.e. use C<0> if you don't create new files, |
|
|
140 | and C<0666> or C<0777> if you do). |
105 | |
141 | |
106 | Example: |
142 | Example: |
107 | |
143 | |
108 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
144 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
109 | if ($_[0]) { |
145 | if ($_[0]) { |
… | |
… | |
112 | } else { |
148 | } else { |
113 | die "open failed: $!\n"; |
149 | die "open failed: $!\n"; |
114 | } |
150 | } |
115 | }; |
151 | }; |
116 | |
152 | |
117 | =item aio_close $fh, $callback |
153 | =item aio_close $fh, $callback->($status) |
118 | |
154 | |
119 | Asynchronously close a file and call the callback with the result |
155 | Asynchronously close a file and call the callback with the result |
120 | code. I<WARNING:> although accepted, you should not pass in a perl |
156 | 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 |
157 | filehandle here, as perl will likely close the file descriptor another |
122 | the filehandle is destroyed. Normally, you can safely call perls C<close> |
158 | time when the filehandle is destroyed. Normally, you can safely call perls |
123 | or just let filehandles go out of scope. |
159 | C<close> or just let filehandles go out of scope. |
124 | |
160 | |
|
|
161 | This is supposed to be a bug in the API, so that might change. It's |
|
|
162 | therefore best to avoid this function. |
|
|
163 | |
125 | =item aio_read $fh,$offset,$length, $data,$dataoffset,$callback |
164 | =item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
126 | |
165 | |
127 | =item aio_write $fh,$offset,$length, $data,$dataoffset,$callback |
166 | =item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
128 | |
167 | |
129 | Reads or writes C<length> bytes from the specified C<fh> and C<offset> |
168 | 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 |
169 | 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 |
170 | callback without the actual number of bytes read (or -1 on error, just |
132 | like the syscall). |
171 | like the syscall). |
133 | |
172 | |
|
|
173 | The C<$data> scalar I<MUST NOT> be modified in any way while the request |
|
|
174 | is outstanding. Modifying it can result in segfaults or WW3 (if the |
|
|
175 | necessary/optional hardware is installed). |
|
|
176 | |
134 | Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at |
177 | Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at |
135 | offset C<0> within the scalar: |
178 | offset C<0> within the scalar: |
136 | |
179 | |
137 | aio_read $fh, 7, 15, $buffer, 0, sub { |
180 | aio_read $fh, 7, 15, $buffer, 0, sub { |
138 | $_[0] > 0 or die "read error: $!"; |
181 | $_[0] > 0 or die "read error: $!"; |
139 | print "read $_[0] bytes: <$buffer>\n"; |
182 | print "read $_[0] bytes: <$buffer>\n"; |
140 | }; |
183 | }; |
141 | |
184 | |
|
|
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 | |
|
|
255 | =item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) |
|
|
256 | |
|
|
257 | 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 |
|
|
259 | file offset of C<$out_fh>. Because of that, it is not safe to issue more |
|
|
260 | than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each |
|
|
261 | other. |
|
|
262 | |
|
|
263 | This call tries to make use of a native C<sendfile> syscall to provide |
|
|
264 | zero-copy operation. For this to work, C<$out_fh> should refer to a |
|
|
265 | socket, and C<$in_fh> should refer to mmap'able file. |
|
|
266 | |
|
|
267 | If the native sendfile call fails or is not implemented, it will be |
|
|
268 | emulated, so you can call C<aio_sendfile> on any type of filehandle |
|
|
269 | regardless of the limitations of the operating system. |
|
|
270 | |
|
|
271 | Please note, however, that C<aio_sendfile> can read more bytes from |
|
|
272 | 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 |
|
|
274 | 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 |
|
|
276 | read. |
|
|
277 | |
142 | =item aio_readahead $fh,$offset,$length, $callback |
278 | =item aio_readahead $fh,$offset,$length, $callback->($retval) |
143 | |
279 | |
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 |
280 | 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> |
281 | 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 |
282 | 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 |
283 | 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 |
284 | 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 |
285 | 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 |
286 | (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. |
287 | file. The current file offset of the file is left unchanged. |
156 | |
288 | |
|
|
289 | 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. |
|
|
291 | |
157 | =item aio_stat $fh_or_path, $callback |
292 | =item aio_stat $fh_or_path, $callback->($status) |
158 | |
293 | |
159 | =item aio_lstat $fh, $callback |
294 | =item aio_lstat $fh, $callback->($status) |
160 | |
295 | |
161 | Works like perl's C<stat> or C<lstat> in void context. The callback will |
296 | 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 _> |
297 | be called after the stat and the results will be available using C<stat _> |
163 | or C<-s _> etc... |
298 | or C<-s _> etc... |
164 | |
299 | |
… | |
… | |
174 | aio_stat "/etc/passwd", sub { |
309 | aio_stat "/etc/passwd", sub { |
175 | $_[0] and die "stat failed: $!"; |
310 | $_[0] and die "stat failed: $!"; |
176 | print "size is ", -s _, "\n"; |
311 | print "size is ", -s _, "\n"; |
177 | }; |
312 | }; |
178 | |
313 | |
179 | =item aio_unlink $pathname, $callback |
314 | =item aio_unlink $pathname, $callback->($status) |
180 | |
315 | |
181 | Asynchronously unlink (delete) a file and call the callback with the |
316 | Asynchronously unlink (delete) a file and call the callback with the |
182 | result code. |
317 | result code. |
183 | |
318 | |
|
|
319 | =item aio_link $srcpath, $dstpath, $callback->($status) |
|
|
320 | |
|
|
321 | 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. |
|
|
323 | |
|
|
324 | =item aio_symlink $srcpath, $dstpath, $callback->($status) |
|
|
325 | |
|
|
326 | 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. |
|
|
328 | |
|
|
329 | =item aio_rename $srcpath, $dstpath, $callback->($status) |
|
|
330 | |
|
|
331 | Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as |
|
|
332 | rename(2) and call the callback with the result code. |
|
|
333 | |
|
|
334 | =item aio_rmdir $pathname, $callback->($status) |
|
|
335 | |
|
|
336 | Asynchronously rmdir (delete) a directory and call the callback with the |
|
|
337 | result code. |
|
|
338 | |
|
|
339 | =item aio_readdir $pathname, $callback->($entries) |
|
|
340 | |
|
|
341 | 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 |
|
|
343 | sorted, and will B<NOT> include the C<.> and C<..> entries. |
|
|
344 | |
|
|
345 | The callback a single argument which is either C<undef> or an array-ref |
|
|
346 | with the filenames. |
|
|
347 | |
|
|
348 | =item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) |
|
|
349 | |
|
|
350 | [EXPERIMENTAL due to internal aio_group use] |
|
|
351 | |
|
|
352 | 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 |
|
|
354 | you can recurse into (directories or links to them), and ones you cannot |
|
|
355 | recurse into (everything else). |
|
|
356 | |
|
|
357 | C<aio_scandir> is a composite request that creates of many sub requests_ |
|
|
358 | C<$maxreq> specifies the maximum number of outstanding aio requests that |
|
|
359 | this function generates. If it is C<< <= 0 >>, then a suitable default |
|
|
360 | will be chosen (currently 6). |
|
|
361 | |
|
|
362 | On error, the callback is called without arguments, otherwise it receives |
|
|
363 | two array-refs with path-relative entry names. |
|
|
364 | |
|
|
365 | Example: |
|
|
366 | |
|
|
367 | aio_scandir $dir, 0, sub { |
|
|
368 | my ($dirs, $nondirs) = @_; |
|
|
369 | print "real directories: @$dirs\n"; |
|
|
370 | print "everything else: @$nondirs\n"; |
|
|
371 | }; |
|
|
372 | |
|
|
373 | Implementation notes. |
|
|
374 | |
|
|
375 | The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can. |
|
|
376 | |
|
|
377 | After reading the directory, the modification time, size etc. of the |
|
|
378 | directory before and after the readdir is checked, and if they match (and |
|
|
379 | isn't the current time), the link count will be used to decide how many |
|
|
380 | entries are directories (if >= 2). Otherwise, no knowledge of the number |
|
|
381 | of subdirectories will be assumed. |
|
|
382 | |
|
|
383 | Then entries will be sorted into likely directories (everything without |
|
|
384 | a non-initial dot currently) and likely non-directories (everything |
|
|
385 | else). Then every entry plus an appended C</.> will be C<stat>'ed, |
|
|
386 | likely directories first. If that succeeds, it assumes that the entry |
|
|
387 | 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 |
|
|
389 | filesystems might detect the type of the entry without reading the inode |
|
|
390 | data (e.g. ext2fs filetype feature). |
|
|
391 | |
|
|
392 | If the known number of directories (link count - 2) has been reached, the |
|
|
393 | rest of the entries is assumed to be non-directories. |
|
|
394 | |
|
|
395 | This only works with certainty on POSIX (= UNIX) filesystems, which |
|
|
396 | fortunately are the vast majority of filesystems around. |
|
|
397 | |
|
|
398 | It will also likely work on non-POSIX filesystems with reduced efficiency |
|
|
399 | as those tend to return 0 or 1 as link counts, which disables the |
|
|
400 | directory counting heuristic. |
|
|
401 | |
|
|
402 | =cut |
|
|
403 | |
|
|
404 | sub aio_scandir($$$) { |
|
|
405 | my ($path, $maxreq, $cb) = @_; |
|
|
406 | |
|
|
407 | my $grp = aio_group $cb; |
|
|
408 | |
|
|
409 | $maxreq = 6 if $maxreq <= 0; |
|
|
410 | |
|
|
411 | # stat once |
|
|
412 | add $grp aio_stat $path, sub { |
|
|
413 | return $grp->result () if $_[0]; |
|
|
414 | my $now = time; |
|
|
415 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
|
|
416 | |
|
|
417 | # read the directory entries |
|
|
418 | add $grp aio_readdir $path, sub { |
|
|
419 | my $entries = shift |
|
|
420 | or return $grp->result (); |
|
|
421 | |
|
|
422 | # stat the dir another time |
|
|
423 | add $grp aio_stat $path, sub { |
|
|
424 | my $hash2 = join ":", (stat _)[0,1,3,7,9]; |
|
|
425 | |
|
|
426 | my $ndirs; |
|
|
427 | |
|
|
428 | # take the slow route if anything looks fishy |
|
|
429 | if ($hash1 ne $hash2 or (stat _)[9] == $now) { |
|
|
430 | $ndirs = -1; |
|
|
431 | } else { |
|
|
432 | # if nlink == 2, we are finished |
|
|
433 | # on non-posix-fs's, we rely on nlink < 2 |
|
|
434 | $ndirs = (stat _)[3] - 2 |
|
|
435 | or return $grp->result ([], $entries); |
|
|
436 | } |
|
|
437 | |
|
|
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 | @$entries]; |
|
|
444 | |
|
|
445 | my (@dirs, @nondirs); |
|
|
446 | |
|
|
447 | my ($statcb, $schedcb); |
|
|
448 | my $nreq = 0; |
|
|
449 | |
|
|
450 | my $statgrp = add $grp aio_group; |
|
|
451 | |
|
|
452 | $schedcb = sub { |
|
|
453 | if (@$entries) { |
|
|
454 | if ($nreq < $maxreq) { |
|
|
455 | my $ent = pop @$entries; |
|
|
456 | $nreq++; |
|
|
457 | add $statgrp aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) }; |
|
|
458 | } |
|
|
459 | } elsif (!$nreq) { |
|
|
460 | # finished |
|
|
461 | $statgrp->cancel; |
|
|
462 | undef $statcb; |
|
|
463 | undef $schedcb; |
|
|
464 | $grp->result (\@dirs, \@nondirs); |
|
|
465 | } |
|
|
466 | }; |
|
|
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 | }; |
|
|
497 | }; |
|
|
498 | }; |
|
|
499 | |
|
|
500 | $grp |
|
|
501 | } |
|
|
502 | |
184 | =item aio_fsync $fh, $callback |
503 | =item aio_fsync $fh, $callback->($status) |
185 | |
504 | |
186 | Asynchronously call fsync on the given filehandle and call the callback |
505 | Asynchronously call fsync on the given filehandle and call the callback |
187 | with the fsync result code. |
506 | with the fsync result code. |
188 | |
507 | |
189 | =item aio_fdatasync $fh, $callback |
508 | =item aio_fdatasync $fh, $callback->($status) |
190 | |
509 | |
191 | Asynchronously call fdatasync on the given filehandle and call the |
510 | Asynchronously call fdatasync on the given filehandle and call the |
192 | callback with the fdatasync result code. |
511 | callback with the fdatasync result code. |
193 | |
512 | |
|
|
513 | 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. |
|
|
515 | |
|
|
516 | =item aio_group $callback->(...) |
|
|
517 | |
|
|
518 | [EXPERIMENTAL] |
|
|
519 | |
|
|
520 | 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 |
|
|
522 | many requests into a single, composite, request. |
|
|
523 | |
|
|
524 | Returns an object of class L<IO::AIO::GRP>. See its documentation below |
|
|
525 | for more info. |
|
|
526 | |
|
|
527 | Example: |
|
|
528 | |
|
|
529 | my $grp = aio_group sub { |
|
|
530 | print "all stats done\n"; |
|
|
531 | }; |
|
|
532 | |
|
|
533 | add $grp |
|
|
534 | (aio_stat ...), |
|
|
535 | (aio_stat ...), |
|
|
536 | ...; |
|
|
537 | |
|
|
538 | =item IO::AIO::aio_sleep $fractional_seconds, $callback->() *NOT EXPORTED* |
|
|
539 | |
|
|
540 | Mainly used for debugging and benchmarking, this aio request puts one of |
|
|
541 | the request workers to sleep for the given time. |
|
|
542 | |
|
|
543 | While it is theoretically handy to have simple I/O scheduling requests |
|
|
544 | like sleep and file handle readable/writable, the overhead this creates |
|
|
545 | is immense, so do not use this function except to put your application |
|
|
546 | under artificial I/O pressure. |
|
|
547 | |
194 | =back |
548 | =back |
195 | |
549 | |
|
|
550 | =head2 IO::AIO::REQ CLASS |
|
|
551 | |
|
|
552 | All non-aggregate C<aio_*> functions return an object of this class when |
|
|
553 | called in non-void context. |
|
|
554 | |
|
|
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 |
|
|
564 | |
|
|
565 | =item $req->cancel |
|
|
566 | |
|
|
567 | Cancels the request, if possible. Has the effect of skipping execution |
|
|
568 | 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 |
|
|
570 | untouched. That means that requests that currently execute will not be |
|
|
571 | stopped and resources held by the request will not be freed prematurely. |
|
|
572 | |
|
|
573 | =back |
|
|
574 | |
|
|
575 | =head2 IO::AIO::GRP CLASS |
|
|
576 | |
|
|
577 | This class is a subclass of L<IO::AIO::REQ>, so all its methods apply to |
|
|
578 | objects of this class, too. |
|
|
579 | |
|
|
580 | A IO::AIO::GRP object is a special request that can contain multiple other |
|
|
581 | aio requests. |
|
|
582 | |
|
|
583 | You create one by calling the C<aio_group> constructing function with a |
|
|
584 | callback that will be called when all contained requests have entered the |
|
|
585 | C<done> state: |
|
|
586 | |
|
|
587 | my $grp = aio_group sub { |
|
|
588 | print "all requests are done\n"; |
|
|
589 | }; |
|
|
590 | |
|
|
591 | You add requests by calling the C<add> method with one or more |
|
|
592 | C<IO::AIO::REQ> objects: |
|
|
593 | |
|
|
594 | $grp->add (aio_unlink "..."); |
|
|
595 | |
|
|
596 | add $grp aio_stat "...", sub { |
|
|
597 | $_[0] or return $grp->result ("error"); |
|
|
598 | |
|
|
599 | # add another request dynamically, if first succeeded |
|
|
600 | add $grp aio_open "...", sub { |
|
|
601 | $grp->result ("ok"); |
|
|
602 | }; |
|
|
603 | }; |
|
|
604 | |
|
|
605 | 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. |
|
|
607 | |
|
|
608 | =over 4 |
|
|
609 | |
|
|
610 | =item * The IO::AIO::GRP objects will be cleaned up during calls to |
|
|
611 | C<IO::AIO::poll_cb>, just like any other request. |
|
|
612 | |
|
|
613 | =item * They can be canceled like any other request. Canceling will cancel not |
|
|
614 | only the request itself, but also all requests it contains. |
|
|
615 | |
|
|
616 | =item * They can also can also be added to other IO::AIO::GRP objects. |
|
|
617 | |
|
|
618 | =item * You must not add requests to a group from within the group callback (or |
|
|
619 | any later time). |
|
|
620 | |
|
|
621 | =item * This does not harmonise well with C<max_outstanding>, so best do |
|
|
622 | not combine C<aio_group> with it. Groups and feeders are recommended for |
|
|
623 | this kind of concurrency-limiting. |
|
|
624 | |
|
|
625 | =back |
|
|
626 | |
|
|
627 | Their lifetime, simplified, looks like this: when they are empty, they |
|
|
628 | will finish very quickly. If they contain only requests that are in the |
|
|
629 | C<done> state, they will also finish. Otherwise they will continue to |
|
|
630 | exist. |
|
|
631 | |
|
|
632 | That means after creating a group you have some time to add requests. And |
|
|
633 | in the callbacks of those requests, you can add further requests to the |
|
|
634 | group. And only when all those requests have finished will the the group |
|
|
635 | itself finish. |
|
|
636 | |
|
|
637 | =over 4 |
|
|
638 | |
|
|
639 | =item $grp->add (...) |
|
|
640 | |
|
|
641 | =item add $grp ... |
|
|
642 | |
|
|
643 | Add one or more requests to the group. Any type of L<IO::AIO::REQ> can |
|
|
644 | be added, including other groups, as long as you do not create circular |
|
|
645 | dependencies. |
|
|
646 | |
|
|
647 | Returns all its arguments. |
|
|
648 | |
|
|
649 | =item $grp->result (...) |
|
|
650 | |
|
|
651 | Set the result value(s) that will be passed to the group callback when all |
|
|
652 | subrequests have finished. By default, no argument will be passed. |
|
|
653 | |
|
|
654 | =item $grp->set_feeder ($callback->($grp)) |
|
|
655 | |
|
|
656 | [VERY EXPERIMENTAL] |
|
|
657 | |
|
|
658 | Sets a feeder/generator on this group: every group can have an attached |
|
|
659 | generator that generates requests if idle. The idea behind this is that, |
|
|
660 | although you could just queue as many requests as you want in a group, |
|
|
661 | this might starve other requests for a potentially long time. For |
|
|
662 | example, C<aio_scandir> might generate hundreds of thousands C<aio_stat> |
|
|
663 | requests, delaying any later requests for a long time. |
|
|
664 | |
|
|
665 | To avoid this, and allow incremental generation of requests, you can |
|
|
666 | instead a group and set a feeder on it that generates those requests. The |
|
|
667 | feeder will be called whenever there are few enough (see C<feeder_limit>, |
|
|
668 | below) requests active in the group itself and is expected to queue more |
|
|
669 | requests. |
|
|
670 | |
|
|
671 | The feeder can queue as many requests as it likes (i.e. C<add> does not |
|
|
672 | impose any limits). |
|
|
673 | |
|
|
674 | If the feeder does not queue more requests when called, it will be |
|
|
675 | automatically removed from the group. |
|
|
676 | |
|
|
677 | If the feeder limit is C<0>, it will be set to C<2> automatically. |
|
|
678 | |
|
|
679 | Example: |
|
|
680 | |
|
|
681 | # stat all files in @files, but only ever use four aio requests concurrently: |
|
|
682 | |
|
|
683 | my $grp = aio_group sub { print "finished\n" }; |
|
|
684 | $grp->feeder_limit (4); |
|
|
685 | $grp->set_feeder (sub { |
|
|
686 | my $file = pop @files |
|
|
687 | or return; |
|
|
688 | |
|
|
689 | add $grp aio_stat $file, sub { ... }; |
|
|
690 | }); |
|
|
691 | |
|
|
692 | =item $grp->feeder_limit ($num) |
|
|
693 | |
|
|
694 | Sets the feeder limit for the group: The feeder will be called whenever |
|
|
695 | the group contains less than this many requests. |
|
|
696 | |
|
|
697 | Setting the limit to C<0> will pause the feeding process. |
|
|
698 | |
|
|
699 | =back |
|
|
700 | |
196 | =head2 SUPPORT FUNCTIONS |
701 | =head2 SUPPORT FUNCTIONS |
197 | |
702 | |
198 | =over 4 |
703 | =over 4 |
199 | |
704 | |
200 | =item $fileno = IO::AIO::poll_fileno |
705 | =item $fileno = IO::AIO::poll_fileno |
201 | |
706 | |
202 | Return the I<request result pipe filehandle>. This filehandle must be |
707 | 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 |
708 | 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 |
709 | select, see below or the SYNOPSIS). If the pipe becomes readable you have |
205 | C<poll_cb> to check the results. |
710 | to call C<poll_cb> to check the results. |
206 | |
711 | |
207 | See C<poll_cb> for an example. |
712 | See C<poll_cb> for an example. |
208 | |
713 | |
209 | =item IO::AIO::poll_cb |
714 | =item IO::AIO::poll_cb |
210 | |
715 | |
211 | Process all outstanding events on the result pipe. You have to call this |
716 | Process all outstanding events on the result pipe. You have to call this |
212 | regularly. Returns the number of events processed. Returns immediately |
717 | regularly. Returns the number of events processed. Returns immediately |
213 | when no events are outstanding. |
718 | when no events are outstanding. |
214 | |
719 | |
215 | You can use Event to multiplex, e.g.: |
720 | Example: Install an Event watcher that automatically calls |
|
|
721 | IO::AIO::poll_cb with high priority: |
216 | |
722 | |
217 | Event->io (fd => IO::AIO::poll_fileno, |
723 | Event->io (fd => IO::AIO::poll_fileno, |
218 | poll => 'r', async => 1, |
724 | poll => 'r', async => 1, |
219 | cb => \&IO::AIO::poll_cb); |
725 | cb => \&IO::AIO::poll_cb); |
220 | |
726 | |
221 | =item IO::AIO::poll_wait |
727 | =item IO::AIO::poll_wait |
222 | |
728 | |
223 | Wait till the result filehandle becomes ready for reading (simply does a |
729 | Wait till the result filehandle becomes ready for reading (simply does a |
224 | select on the filehandle. This is useful if you want to synchronously wait |
730 | C<select> on the filehandle. This is useful if you want to synchronously wait |
225 | for some requests to finish). |
731 | for some requests to finish). |
226 | |
732 | |
227 | See C<nreqs> for an example. |
733 | See C<nreqs> for an example. |
228 | |
734 | |
229 | =item IO::AIO::nreqs |
735 | =item IO::AIO::nreqs |
230 | |
736 | |
231 | Returns the number of requests currently outstanding. |
737 | Returns the number of requests currently outstanding (i.e. for which their |
|
|
738 | callback has not been invoked yet). |
232 | |
739 | |
233 | Example: wait till there are no outstanding requests anymore: |
740 | Example: wait till there are no outstanding requests anymore: |
234 | |
741 | |
235 | IO::AIO::poll_wait, IO::AIO::poll_cb |
742 | IO::AIO::poll_wait, IO::AIO::poll_cb |
236 | while IO::AIO::nreqs; |
743 | while IO::AIO::nreqs; |
… | |
… | |
253 | IO::AIO::poll_wait, IO::AIO::poll_cb |
760 | IO::AIO::poll_wait, IO::AIO::poll_cb |
254 | if IO::AIO::nreqs; |
761 | if IO::AIO::nreqs; |
255 | |
762 | |
256 | =item IO::AIO::min_parallel $nthreads |
763 | =item IO::AIO::min_parallel $nthreads |
257 | |
764 | |
258 | Set the minimum number of AIO threads to C<$nthreads>. The default is |
765 | Set the minimum number of AIO threads to C<$nthreads>. The current |
259 | C<1>, which means a single asynchronous operation can be done at one time |
766 | default is C<8>, which means eight asynchronous operations can execute |
260 | (the number of outstanding operations, however, is unlimited). |
767 | concurrently at any one time (the number of outstanding requests, |
|
|
768 | however, is unlimited). |
261 | |
769 | |
|
|
770 | IO::AIO starts threads only on demand, when an AIO request is queued and |
|
|
771 | no free thread exists. |
|
|
772 | |
262 | It is recommended to keep the number of threads low, as some Linux |
773 | It is recommended to keep the number of threads relatively low, as some |
263 | kernel versions will scale negatively with the number of threads (higher |
774 | Linux kernel versions will scale negatively with the number of threads |
264 | parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32 |
775 | (higher parallelity => MUCH higher latency). With current Linux 2.6 |
265 | threads should be fine. |
776 | versions, 4-32 threads should be fine. |
266 | |
777 | |
267 | Under normal circumstances you don't need to call this function, as this |
778 | Under most circumstances you don't need to call this function, as the |
268 | module automatically starts some threads (the exact number might change, |
779 | module selects a default that is suitable for low to moderate load. |
269 | and is currently 4). |
|
|
270 | |
780 | |
271 | =item IO::AIO::max_parallel $nthreads |
781 | =item IO::AIO::max_parallel $nthreads |
272 | |
782 | |
273 | Sets the maximum number of AIO threads to C<$nthreads>. If more than |
783 | Sets the maximum number of AIO threads to C<$nthreads>. If more than the |
274 | the specified number of threads are currently running, kill them. This |
784 | specified number of threads are currently running, this function kills |
275 | function blocks until the limit is reached. |
785 | them. This function blocks until the limit is reached. |
|
|
786 | |
|
|
787 | While C<$nthreads> are zero, aio requests get queued but not executed |
|
|
788 | until the number of threads has been increased again. |
276 | |
789 | |
277 | This module automatically runs C<max_parallel 0> at program end, to ensure |
790 | 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. |
791 | that all threads are killed and that there are no outstanding requests. |
279 | |
792 | |
280 | Under normal circumstances you don't need to call this function. |
793 | Under normal circumstances you don't need to call this function. |
281 | |
794 | |
282 | =item $oldnreqs = IO::AIO::max_outstanding $nreqs |
795 | =item $oldnreqs = IO::AIO::max_outstanding $nreqs |
|
|
796 | |
|
|
797 | [DEPRECATED] |
283 | |
798 | |
284 | Sets the maximum number of outstanding requests to C<$nreqs>. If you |
799 | 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 |
800 | try to queue up more than this number of requests, the caller will block until |
286 | some requests have been handled. |
801 | some requests have been handled. |
287 | |
802 | |
288 | The default is very large, so normally there is no practical limit. If you |
803 | 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 |
804 | queue up many requests in a loop it often improves speed if you set |
290 | this to a relatively low number, such as C<100>. |
805 | this to a relatively low number, such as C<100>. |
|
|
806 | |
|
|
807 | This function does not work well together with C<aio_group>'s, and their |
|
|
808 | feeder interface is better suited to limiting concurrency, so do not use |
|
|
809 | this function. |
291 | |
810 | |
292 | Under normal circumstances you don't need to call this function. |
811 | Under normal circumstances you don't need to call this function. |
293 | |
812 | |
294 | =back |
813 | =back |
295 | |
814 | |
… | |
… | |
297 | |
816 | |
298 | # support function to convert a fd into a perl filehandle |
817 | # support function to convert a fd into a perl filehandle |
299 | sub _fd2fh { |
818 | sub _fd2fh { |
300 | return undef if $_[0] < 0; |
819 | return undef if $_[0] < 0; |
301 | |
820 | |
302 | # try to be perl5.6-compatible |
821 | # try to generate nice filehandles |
303 | local *AIO_FH; |
822 | my $sym = "IO::AIO::fd#$_[0]"; |
304 | open AIO_FH, "+<&=$_[0]" |
823 | local *$sym; |
|
|
824 | |
|
|
825 | open *$sym, "+<&=$_[0]" # usually works under any unix |
|
|
826 | or open *$sym, "<&=$_[0]" # cygwin needs this |
|
|
827 | or open *$sym, ">&=$_[0]" # or this |
305 | or return undef; |
828 | or return undef; |
306 | |
829 | |
307 | *AIO_FH |
830 | *$sym |
308 | } |
831 | } |
309 | |
832 | |
310 | min_parallel 4; |
833 | min_parallel 8; |
311 | |
834 | |
312 | END { |
835 | END { |
313 | max_parallel 0; |
836 | max_parallel 0; |
314 | } |
837 | } |
315 | |
838 | |
316 | 1; |
839 | 1; |
317 | |
840 | |
|
|
841 | =head2 FORK BEHAVIOUR |
|
|
842 | |
|
|
843 | This module should do "the right thing" when the process using it forks: |
|
|
844 | |
|
|
845 | Before the fork, IO::AIO enters a quiescent state where no requests |
|
|
846 | can be added in other threads and no results will be processed. After |
|
|
847 | the fork the parent simply leaves the quiescent state and continues |
|
|
848 | request/result processing, while the child clears the request/result |
|
|
849 | queue (so the requests started before the fork will only be handled in |
|
|
850 | the parent). Threads will be started on demand until the limit ste in the |
|
|
851 | parent process has been reached again. |
|
|
852 | |
|
|
853 | In short: the parent will, after a short pause, continue as if fork had |
|
|
854 | not been called, while the child will act as if IO::AIO has not been used |
|
|
855 | yet. |
|
|
856 | |
|
|
857 | =head2 MEMORY USAGE |
|
|
858 | |
|
|
859 | Each aio request uses - depending on your architecture - around 128 bytes |
|
|
860 | of memory. In addition, stat requests need a stat buffer (possibly a few |
|
|
861 | hundred bytes). Perl scalars and other data passed into aio requests will |
|
|
862 | also be locked. |
|
|
863 | |
|
|
864 | This is now awfully much, so queuing lots of requests is not usually a |
|
|
865 | problem. |
|
|
866 | |
|
|
867 | Each thread needs a stack area which is usually around 16k, sometimes much |
|
|
868 | larger, depending on the OS. |
|
|
869 | |
318 | =head1 SEE ALSO |
870 | =head1 SEE ALSO |
319 | |
871 | |
320 | L<Coro>, L<Linux::AIO>. |
872 | L<Coro>, L<Linux::AIO> (obsolete). |
321 | |
873 | |
322 | =head1 AUTHOR |
874 | =head1 AUTHOR |
323 | |
875 | |
324 | Marc Lehmann <schmorp@schmorp.de> |
876 | Marc Lehmann <schmorp@schmorp.de> |
325 | http://home.schmorp.de/ |
877 | http://home.schmorp.de/ |