… | |
… | |
4 | |
4 | |
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", IO::AIO::O_RDONLY, 0, sub { |
10 | my $fh = shift |
10 | my $fh = shift |
11 | or die "/etc/passwd: $!"; |
11 | or die "/etc/passwd: $!"; |
12 | ... |
12 | ... |
13 | }; |
13 | }; |
14 | |
14 | |
… | |
… | |
26 | $req->cancel; # cancel request if still in queue |
26 | $req->cancel; # cancel request if still in queue |
27 | |
27 | |
28 | my $grp = aio_group sub { print "all stats done\n" }; |
28 | my $grp = aio_group sub { print "all stats done\n" }; |
29 | add $grp aio_stat "..." for ...; |
29 | add $grp aio_stat "..." for ...; |
30 | |
30 | |
31 | # AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...) |
|
|
32 | use AnyEvent::AIO; |
|
|
33 | |
|
|
34 | # EV integration |
|
|
35 | my $w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; |
|
|
36 | |
|
|
37 | # Event integration |
|
|
38 | Event->io (fd => IO::AIO::poll_fileno, |
|
|
39 | poll => 'r', |
|
|
40 | cb => \&IO::AIO::poll_cb); |
|
|
41 | |
|
|
42 | # Glib/Gtk2 integration |
|
|
43 | add_watch Glib::IO IO::AIO::poll_fileno, |
|
|
44 | in => sub { IO::AIO::poll_cb; 1 }; |
|
|
45 | |
|
|
46 | # Tk integration |
|
|
47 | Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "", |
|
|
48 | readable => \&IO::AIO::poll_cb); |
|
|
49 | |
|
|
50 | # Danga::Socket integration |
|
|
51 | Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => |
|
|
52 | \&IO::AIO::poll_cb); |
|
|
53 | |
|
|
54 | =head1 DESCRIPTION |
31 | =head1 DESCRIPTION |
55 | |
32 | |
56 | This module implements asynchronous I/O using whatever means your |
33 | This module implements asynchronous I/O using whatever means your |
57 | operating system supports. |
34 | operating system supports. It is implemented as an interface to C<libeio> |
|
|
35 | (L<http://software.schmorp.de/pkg/libeio.html>). |
58 | |
36 | |
59 | Asynchronous means that operations that can normally block your program |
37 | Asynchronous means that operations that can normally block your program |
60 | (e.g. reading from disk) will be done asynchronously: the operation |
38 | (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 |
39 | 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 |
40 | is extremely useful for programs that need to stay interactive even |
… | |
… | |
66 | on a RAID volume or over NFS when you do a number of stat operations |
44 | on a RAID volume or over NFS when you do a number of stat operations |
67 | concurrently. |
45 | concurrently. |
68 | |
46 | |
69 | While most of this works on all types of file descriptors (for |
47 | While most of this works on all types of file descriptors (for |
70 | example sockets), using these functions on file descriptors that |
48 | example sockets), using these functions on file descriptors that |
71 | support nonblocking operation (again, sockets, pipes etc.) is very |
49 | support nonblocking operation (again, sockets, pipes etc.) is |
72 | inefficient. Use an event loop for that (such as the L<Event|Event> |
50 | very inefficient. Use an event loop for that (such as the L<EV> |
73 | module): IO::AIO will naturally fit into such an event loop itself. |
51 | module): IO::AIO will naturally fit into such an event loop itself. |
74 | |
52 | |
75 | In this version, a number of threads are started that execute your |
53 | In this version, a number of threads are started that execute your |
76 | requests and signal their completion. You don't need thread support |
54 | requests and signal their completion. You don't need thread support |
77 | in perl, and the threads created by this module will not be visible |
55 | in perl, and the threads created by this module will not be visible |
… | |
… | |
87 | yourself, always call C<poll_cb> from within the same thread, or never |
65 | yourself, always call C<poll_cb> from within the same thread, or never |
88 | call C<poll_cb> (or other C<aio_> functions) recursively. |
66 | call C<poll_cb> (or other C<aio_> functions) recursively. |
89 | |
67 | |
90 | =head2 EXAMPLE |
68 | =head2 EXAMPLE |
91 | |
69 | |
92 | This is a simple example that uses the Event module and loads |
70 | This is a simple example that uses the EV module and loads |
93 | F</etc/passwd> asynchronously: |
71 | F</etc/passwd> asynchronously: |
94 | |
72 | |
95 | use Fcntl; |
|
|
96 | use Event; |
73 | use EV; |
97 | use IO::AIO; |
74 | use IO::AIO; |
98 | |
75 | |
99 | # register the IO::AIO callback with Event |
76 | # register the IO::AIO callback with EV |
100 | Event->io (fd => IO::AIO::poll_fileno, |
77 | my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; |
101 | poll => 'r', |
|
|
102 | cb => \&IO::AIO::poll_cb); |
|
|
103 | |
78 | |
104 | # queue the request to open /etc/passwd |
79 | # queue the request to open /etc/passwd |
105 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
80 | aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub { |
106 | my $fh = shift |
81 | my $fh = shift |
107 | or die "error while opening: $!"; |
82 | or die "error while opening: $!"; |
108 | |
83 | |
109 | # stat'ing filehandles is generally non-blocking |
84 | # stat'ing filehandles is generally non-blocking |
110 | my $size = -s $fh; |
85 | my $size = -s $fh; |
… | |
… | |
119 | |
94 | |
120 | # file contents now in $contents |
95 | # file contents now in $contents |
121 | print $contents; |
96 | print $contents; |
122 | |
97 | |
123 | # exit event loop and program |
98 | # exit event loop and program |
124 | Event::unloop; |
99 | EV::break; |
125 | }; |
100 | }; |
126 | }; |
101 | }; |
127 | |
102 | |
128 | # possibly queue up other requests, or open GUI windows, |
103 | # possibly queue up other requests, or open GUI windows, |
129 | # check for sockets etc. etc. |
104 | # check for sockets etc. etc. |
130 | |
105 | |
131 | # process events as long as there are some: |
106 | # process events as long as there are some: |
132 | Event::loop; |
107 | EV::run; |
133 | |
108 | |
134 | =head1 REQUEST ANATOMY AND LIFETIME |
109 | =head1 REQUEST ANATOMY AND LIFETIME |
135 | |
110 | |
136 | Every C<aio_*> function creates a request. which is a C data structure not |
111 | Every C<aio_*> function creates a request. which is a C data structure not |
137 | directly visible to Perl. |
112 | directly visible to Perl. |
… | |
… | |
187 | |
162 | |
188 | package IO::AIO; |
163 | package IO::AIO; |
189 | |
164 | |
190 | use Carp (); |
165 | use Carp (); |
191 | |
166 | |
192 | no warnings; |
167 | use common::sense; |
193 | use strict 'vars'; |
|
|
194 | |
168 | |
195 | use base 'Exporter'; |
169 | use base 'Exporter'; |
196 | |
170 | |
197 | BEGIN { |
171 | BEGIN { |
198 | our $VERSION = '3.07'; |
172 | our $VERSION = 4.33; |
199 | |
173 | |
200 | our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close |
174 | our @AIO_REQ = qw(aio_sendfile aio_seek aio_read aio_write aio_open aio_close |
201 | aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir |
175 | aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx |
202 | aio_scandir aio_symlink aio_readlink aio_sync aio_fsync |
176 | aio_scandir aio_symlink aio_readlink aio_realpath aio_fcntl aio_ioctl |
203 | aio_fdatasync aio_pathsync aio_readahead |
177 | aio_sync aio_fsync aio_syncfs aio_fdatasync aio_sync_file_range |
|
|
178 | aio_pathsync aio_readahead aio_fiemap aio_allocate |
204 | aio_rename aio_link aio_move aio_copy aio_group |
179 | aio_rename aio_link aio_move aio_copy aio_group |
205 | aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown |
180 | aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown |
206 | aio_chmod aio_utime aio_truncate); |
181 | aio_chmod aio_utime aio_truncate |
|
|
182 | aio_msync aio_mtouch aio_mlock aio_mlockall |
|
|
183 | aio_statvfs |
|
|
184 | aio_wd); |
207 | |
185 | |
208 | our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice)); |
186 | our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice)); |
209 | our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush |
187 | our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush |
210 | min_parallel max_parallel max_idle |
188 | min_parallel max_parallel max_idle idle_timeout |
211 | nreqs nready npending nthreads |
189 | nreqs nready npending nthreads |
212 | max_poll_time max_poll_reqs); |
190 | max_poll_time max_poll_reqs |
|
|
191 | sendfile fadvise madvise |
|
|
192 | mmap munmap munlock munlockall); |
|
|
193 | |
|
|
194 | push @AIO_REQ, qw(aio_busy); # not exported |
213 | |
195 | |
214 | @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; |
196 | @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; |
215 | |
197 | |
216 | require XSLoader; |
198 | require XSLoader; |
217 | XSLoader::load ("IO::AIO", $VERSION); |
199 | XSLoader::load ("IO::AIO", $VERSION); |
218 | } |
200 | } |
219 | |
201 | |
220 | =head1 FUNCTIONS |
202 | =head1 FUNCTIONS |
221 | |
203 | |
222 | =head2 AIO REQUEST FUNCTIONS |
204 | =head2 QUICK OVERVIEW |
|
|
205 | |
|
|
206 | This section simply lists the prototypes most of the functions for |
|
|
207 | quick reference. See the following sections for function-by-function |
|
|
208 | documentation. |
|
|
209 | |
|
|
210 | aio_wd $pathname, $callback->($wd) |
|
|
211 | aio_open $pathname, $flags, $mode, $callback->($fh) |
|
|
212 | aio_close $fh, $callback->($status) |
|
|
213 | aio_seek $fh,$offset,$whence, $callback->($offs) |
|
|
214 | aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
|
|
215 | aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
|
|
216 | aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) |
|
|
217 | aio_readahead $fh,$offset,$length, $callback->($retval) |
|
|
218 | aio_stat $fh_or_path, $callback->($status) |
|
|
219 | aio_lstat $fh, $callback->($status) |
|
|
220 | aio_statvfs $fh_or_path, $callback->($statvfs) |
|
|
221 | aio_utime $fh_or_path, $atime, $mtime, $callback->($status) |
|
|
222 | aio_chown $fh_or_path, $uid, $gid, $callback->($status) |
|
|
223 | aio_chmod $fh_or_path, $mode, $callback->($status) |
|
|
224 | aio_truncate $fh_or_path, $offset, $callback->($status) |
|
|
225 | aio_allocate $fh, $mode, $offset, $len, $callback->($status) |
|
|
226 | aio_fiemap $fh, $start, $length, $flags, $count, $cb->(\@extents) |
|
|
227 | aio_unlink $pathname, $callback->($status) |
|
|
228 | aio_mknod $pathname, $mode, $dev, $callback->($status) |
|
|
229 | aio_link $srcpath, $dstpath, $callback->($status) |
|
|
230 | aio_symlink $srcpath, $dstpath, $callback->($status) |
|
|
231 | aio_readlink $pathname, $callback->($link) |
|
|
232 | aio_realpath $pathname, $callback->($path) |
|
|
233 | aio_rename $srcpath, $dstpath, $callback->($status) |
|
|
234 | aio_mkdir $pathname, $mode, $callback->($status) |
|
|
235 | aio_rmdir $pathname, $callback->($status) |
|
|
236 | aio_readdir $pathname, $callback->($entries) |
|
|
237 | aio_readdirx $pathname, $flags, $callback->($entries, $flags) |
|
|
238 | IO::AIO::READDIR_DENTS IO::AIO::READDIR_DIRS_FIRST |
|
|
239 | IO::AIO::READDIR_STAT_ORDER IO::AIO::READDIR_FOUND_UNKNOWN |
|
|
240 | aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs) |
|
|
241 | aio_load $pathname, $data, $callback->($status) |
|
|
242 | aio_copy $srcpath, $dstpath, $callback->($status) |
|
|
243 | aio_move $srcpath, $dstpath, $callback->($status) |
|
|
244 | aio_rmtree $pathname, $callback->($status) |
|
|
245 | aio_fcntl $fh, $cmd, $arg, $callback->($status) |
|
|
246 | aio_ioctl $fh, $request, $buf, $callback->($status) |
|
|
247 | aio_sync $callback->($status) |
|
|
248 | aio_syncfs $fh, $callback->($status) |
|
|
249 | aio_fsync $fh, $callback->($status) |
|
|
250 | aio_fdatasync $fh, $callback->($status) |
|
|
251 | aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status) |
|
|
252 | aio_pathsync $pathname, $callback->($status) |
|
|
253 | aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status) |
|
|
254 | aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status) |
|
|
255 | aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status) |
|
|
256 | aio_mlockall $flags, $callback->($status) |
|
|
257 | aio_group $callback->(...) |
|
|
258 | aio_nop $callback->() |
|
|
259 | |
|
|
260 | $prev_pri = aioreq_pri [$pri] |
|
|
261 | aioreq_nice $pri_adjust |
|
|
262 | |
|
|
263 | IO::AIO::poll_wait |
|
|
264 | IO::AIO::poll_cb |
|
|
265 | IO::AIO::poll |
|
|
266 | IO::AIO::flush |
|
|
267 | IO::AIO::max_poll_reqs $nreqs |
|
|
268 | IO::AIO::max_poll_time $seconds |
|
|
269 | IO::AIO::min_parallel $nthreads |
|
|
270 | IO::AIO::max_parallel $nthreads |
|
|
271 | IO::AIO::max_idle $nthreads |
|
|
272 | IO::AIO::idle_timeout $seconds |
|
|
273 | IO::AIO::max_outstanding $maxreqs |
|
|
274 | IO::AIO::nreqs |
|
|
275 | IO::AIO::nready |
|
|
276 | IO::AIO::npending |
|
|
277 | |
|
|
278 | IO::AIO::sendfile $ofh, $ifh, $offset, $count |
|
|
279 | IO::AIO::fadvise $fh, $offset, $len, $advice |
|
|
280 | IO::AIO::mmap $scalar, $length, $prot, $flags[, $fh[, $offset]] |
|
|
281 | IO::AIO::munmap $scalar |
|
|
282 | IO::AIO::madvise $scalar, $offset, $length, $advice |
|
|
283 | IO::AIO::mprotect $scalar, $offset, $length, $protect |
|
|
284 | IO::AIO::munlock $scalar, $offset = 0, $length = undef |
|
|
285 | IO::AIO::munlockall |
|
|
286 | |
|
|
287 | =head2 API NOTES |
223 | |
288 | |
224 | All the C<aio_*> calls are more or less thin wrappers around the syscall |
289 | All the C<aio_*> calls are more or less thin wrappers around the syscall |
225 | with the same name (sans C<aio_>). The arguments are similar or identical, |
290 | with the same name (sans C<aio_>). The arguments are similar or identical, |
226 | and they all accept an additional (and optional) C<$callback> argument |
291 | and they all accept an additional (and optional) C<$callback> argument |
227 | which must be a code reference. This code reference will get called with |
292 | which must be a code reference. This code reference will be called after |
228 | the syscall return code (e.g. most syscalls return C<-1> on error, unlike |
293 | the syscall has been executed in an asynchronous fashion. The results |
229 | perl, which usually delivers "false") as it's sole argument when the given |
294 | of the request will be passed as arguments to the callback (and, if an |
230 | syscall has been executed asynchronously. |
295 | error occured, in C<$!>) - for most requests the syscall return code (e.g. |
|
|
296 | most syscalls return C<-1> on error, unlike perl, which usually delivers |
|
|
297 | "false"). |
|
|
298 | |
|
|
299 | Some requests (such as C<aio_readdir>) pass the actual results and |
|
|
300 | communicate failures by passing C<undef>. |
231 | |
301 | |
232 | All functions expecting a filehandle keep a copy of the filehandle |
302 | All functions expecting a filehandle keep a copy of the filehandle |
233 | internally until the request has finished. |
303 | internally until the request has finished. |
234 | |
304 | |
235 | All functions return request objects of type L<IO::AIO::REQ> that allow |
305 | All functions return request objects of type L<IO::AIO::REQ> that allow |
236 | further manipulation of those requests while they are in-flight. |
306 | further manipulation of those requests while they are in-flight. |
237 | |
307 | |
238 | The pathnames you pass to these routines I<must> be absolute and |
308 | The pathnames you pass to these routines I<should> be absolute. The |
239 | encoded as octets. The reason for the former is that at the time the |
309 | reason for this is that at the time the request is being executed, the |
240 | request is being executed, the current working directory could have |
310 | current working directory could have changed. Alternatively, you can |
241 | changed. Alternatively, you can make sure that you never change the |
311 | make sure that you never change the current working directory anywhere |
242 | current working directory anywhere in the program and then use relative |
312 | in the program and then use relative paths. You can also take advantage |
243 | paths. |
313 | of IO::AIOs working directory abstraction, that lets you specify paths |
|
|
314 | relative to some previously-opened "working directory object" - see the |
|
|
315 | description of the C<IO::AIO::WD> class later in this document. |
244 | |
316 | |
245 | To encode pathnames as octets, either make sure you either: a) always pass |
317 | To encode pathnames as octets, either make sure you either: a) always pass |
246 | in filenames you got from outside (command line, readdir etc.) without |
318 | in filenames you got from outside (command line, readdir etc.) without |
247 | tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module and encode |
319 | tinkering, b) are in your native filesystem encoding, c) use the Encode |
248 | your pathnames to the locale (or other) encoding in effect in the user |
320 | module and encode your pathnames to the locale (or other) encoding in |
249 | environment, d) use Glib::filename_from_unicode on unicode filenames or e) |
321 | effect in the user environment, d) use Glib::filename_from_unicode on |
250 | use something else to ensure your scalar has the correct contents. |
322 | unicode filenames or e) use something else to ensure your scalar has the |
|
|
323 | correct contents. |
251 | |
324 | |
252 | This works, btw. independent of the internal UTF-8 bit, which IO::AIO |
325 | This works, btw. independent of the internal UTF-8 bit, which IO::AIO |
253 | handles correctly wether it is set or not. |
326 | handles correctly whether it is set or not. |
|
|
327 | |
|
|
328 | =head2 AIO REQUEST FUNCTIONS |
254 | |
329 | |
255 | =over 4 |
330 | =over 4 |
256 | |
331 | |
257 | =item $prev_pri = aioreq_pri [$pri] |
332 | =item $prev_pri = aioreq_pri [$pri] |
258 | |
333 | |
… | |
… | |
288 | |
363 | |
289 | |
364 | |
290 | =item aio_open $pathname, $flags, $mode, $callback->($fh) |
365 | =item aio_open $pathname, $flags, $mode, $callback->($fh) |
291 | |
366 | |
292 | Asynchronously open or create a file and call the callback with a newly |
367 | Asynchronously open or create a file and call the callback with a newly |
293 | created filehandle for the file. |
368 | created filehandle for the file (or C<undef> in case of an error). |
294 | |
369 | |
295 | The pathname passed to C<aio_open> must be absolute. See API NOTES, above, |
370 | The pathname passed to C<aio_open> must be absolute. See API NOTES, above, |
296 | for an explanation. |
371 | for an explanation. |
297 | |
372 | |
298 | The C<$flags> argument is a bitmask. See the C<Fcntl> module for a |
373 | The C<$flags> argument is a bitmask. See the C<Fcntl> module for a |
… | |
… | |
305 | by the umask in effect then the request is being executed, so better never |
380 | by the umask in effect then the request is being executed, so better never |
306 | change the umask. |
381 | change the umask. |
307 | |
382 | |
308 | Example: |
383 | Example: |
309 | |
384 | |
310 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
385 | aio_open "/etc/passwd", IO::AIO::O_RDONLY, 0, sub { |
311 | if ($_[0]) { |
386 | if ($_[0]) { |
312 | print "open successful, fh is $_[0]\n"; |
387 | print "open successful, fh is $_[0]\n"; |
313 | ... |
388 | ... |
314 | } else { |
389 | } else { |
315 | die "open failed: $!\n"; |
390 | die "open failed: $!\n"; |
316 | } |
391 | } |
317 | }; |
392 | }; |
318 | |
393 | |
|
|
394 | In addition to all the common open modes/flags (C<O_RDONLY>, C<O_WRONLY>, |
|
|
395 | C<O_RDWR>, C<O_CREAT>, C<O_TRUNC>, C<O_EXCL> and C<O_APPEND>), the |
|
|
396 | following POSIX and non-POSIX constants are available (missing ones on |
|
|
397 | your system are, as usual, C<0>): |
|
|
398 | |
|
|
399 | C<O_ASYNC>, C<O_DIRECT>, C<O_NOATIME>, C<O_CLOEXEC>, C<O_NOCTTY>, C<O_NOFOLLOW>, |
|
|
400 | C<O_NONBLOCK>, C<O_EXEC>, C<O_SEARCH>, C<O_DIRECTORY>, C<O_DSYNC>, |
|
|
401 | C<O_RSYNC>, C<O_SYNC>, C<O_PATH>, C<O_TMPFILE>, and C<O_TTY_INIT>. |
|
|
402 | |
319 | |
403 | |
320 | =item aio_close $fh, $callback->($status) |
404 | =item aio_close $fh, $callback->($status) |
321 | |
405 | |
322 | Asynchronously close a file and call the callback with the result |
406 | Asynchronously close a file and call the callback with the result |
323 | code. |
407 | code. |
… | |
… | |
332 | Or in other words: the file descriptor will be closed, but it will not be |
416 | Or in other words: the file descriptor will be closed, but it will not be |
333 | free for reuse until the perl filehandle is closed. |
417 | free for reuse until the perl filehandle is closed. |
334 | |
418 | |
335 | =cut |
419 | =cut |
336 | |
420 | |
|
|
421 | =item aio_seek $fh, $offset, $whence, $callback->($offs) |
|
|
422 | |
|
|
423 | Seeks the filehandle to the new C<$offset>, similarly to perl's |
|
|
424 | C<sysseek>. The C<$whence> can use the traditional values (C<0> for |
|
|
425 | C<IO::AIO::SEEK_SET>, C<1> for C<IO::AIO::SEEK_CUR> or C<2> for |
|
|
426 | C<IO::AIO::SEEK_END>). |
|
|
427 | |
|
|
428 | The resulting absolute offset will be passed to the callback, or C<-1> in |
|
|
429 | case of an error. |
|
|
430 | |
|
|
431 | In theory, the C<$whence> constants could be different than the |
|
|
432 | corresponding values from L<Fcntl>, but perl guarantees they are the same, |
|
|
433 | so don't panic. |
|
|
434 | |
|
|
435 | As a GNU/Linux (and maybe Solaris) extension, also the constants |
|
|
436 | C<IO::AIO::SEEK_DATA> and C<IO::AIO::SEEK_HOLE> are available, if they |
|
|
437 | could be found. No guarantees about suitability for use in C<aio_seek> or |
|
|
438 | Perl's C<sysseek> can be made though, although I would naively assume they |
|
|
439 | "just work". |
|
|
440 | |
337 | =item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
441 | =item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
338 | |
442 | |
339 | =item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
443 | =item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
340 | |
444 | |
341 | Reads or writes C<$length> bytes from the specified C<$fh> and C<$offset> |
445 | Reads or writes C<$length> bytes from or to the specified C<$fh> and |
342 | into the scalar given by C<$data> and offset C<$dataoffset> and calls the |
446 | C<$offset> into the scalar given by C<$data> and offset C<$dataoffset> |
343 | callback without the actual number of bytes read (or -1 on error, just |
447 | and calls the callback without the actual number of bytes read (or -1 on |
344 | like the syscall). |
448 | error, just like the syscall). |
|
|
449 | |
|
|
450 | C<aio_read> will, like C<sysread>, shrink or grow the C<$data> scalar to |
|
|
451 | offset plus the actual number of bytes read. |
345 | |
452 | |
346 | If C<$offset> is undefined, then the current file descriptor offset will |
453 | If C<$offset> is undefined, then the current file descriptor offset will |
347 | be used (and updated), otherwise the file descriptor offset will not be |
454 | be used (and updated), otherwise the file descriptor offset will not be |
348 | changed by these calls. |
455 | changed by these calls. |
349 | |
456 | |
350 | If C<$length> is undefined in C<aio_write>, use the remaining length of C<$data>. |
457 | If C<$length> is undefined in C<aio_write>, use the remaining length of |
|
|
458 | C<$data>. |
351 | |
459 | |
352 | If C<$dataoffset> is less than zero, it will be counted from the end of |
460 | If C<$dataoffset> is less than zero, it will be counted from the end of |
353 | C<$data>. |
461 | C<$data>. |
354 | |
462 | |
355 | The C<$data> scalar I<MUST NOT> be modified in any way while the request |
463 | The C<$data> scalar I<MUST NOT> be modified in any way while the request |
… | |
… | |
369 | |
477 | |
370 | Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts |
478 | Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts |
371 | reading at byte offset C<$in_offset>, and starts writing at the current |
479 | reading at byte offset C<$in_offset>, and starts writing at the current |
372 | file offset of C<$out_fh>. Because of that, it is not safe to issue more |
480 | file offset of C<$out_fh>. Because of that, it is not safe to issue more |
373 | than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each |
481 | than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each |
374 | other. |
482 | other. The same C<$in_fh> works fine though, as this function does not |
|
|
483 | move or use the file offset of C<$in_fh>. |
375 | |
484 | |
|
|
485 | Please note that C<aio_sendfile> can read more bytes from C<$in_fh> than |
|
|
486 | are written, and there is no way to find out how many more bytes have been |
|
|
487 | read from C<aio_sendfile> alone, as C<aio_sendfile> only provides the |
|
|
488 | number of bytes written to C<$out_fh>. Only if the result value equals |
|
|
489 | C<$length> one can assume that C<$length> bytes have been read. |
|
|
490 | |
|
|
491 | Unlike with other C<aio_> functions, it makes a lot of sense to use |
|
|
492 | C<aio_sendfile> on non-blocking sockets, as long as one end (typically |
|
|
493 | the C<$in_fh>) is a file - the file I/O will then be asynchronous, while |
|
|
494 | the socket I/O will be non-blocking. Note, however, that you can run |
|
|
495 | into a trap where C<aio_sendfile> reads some data with readahead, then |
|
|
496 | fails to write all data, and when the socket is ready the next time, the |
|
|
497 | data in the cache is already lost, forcing C<aio_sendfile> to again hit |
|
|
498 | the disk. Explicit C<aio_read> + C<aio_write> let's you better control |
|
|
499 | resource usage. |
|
|
500 | |
376 | This call tries to make use of a native C<sendfile> syscall to provide |
501 | This call tries to make use of a native C<sendfile>-like syscall to |
377 | zero-copy operation. For this to work, C<$out_fh> should refer to a |
502 | provide zero-copy operation. For this to work, C<$out_fh> should refer to |
378 | socket, and C<$in_fh> should refer to mmap'able file. |
503 | a socket, and C<$in_fh> should refer to an mmap'able file. |
379 | |
504 | |
380 | If the native sendfile call fails or is not implemented, it will be |
505 | If a native sendfile cannot be found or it fails with C<ENOSYS>, |
381 | emulated, so you can call C<aio_sendfile> on any type of filehandle |
506 | C<EINVAL>, C<ENOTSUP>, C<EOPNOTSUPP>, C<EAFNOSUPPORT>, C<EPROTOTYPE> or |
|
|
507 | C<ENOTSOCK>, it will be emulated, so you can call C<aio_sendfile> on any |
382 | regardless of the limitations of the operating system. |
508 | type of filehandle regardless of the limitations of the operating system. |
383 | |
509 | |
384 | Please note, however, that C<aio_sendfile> can read more bytes from |
510 | As native sendfile syscalls (as practically any non-POSIX interface hacked |
385 | C<$in_fh> than are written, and there is no way to find out how many |
511 | together in a hurry to improve benchmark numbers) tend to be rather buggy |
386 | bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only |
512 | on many systems, this implementation tries to work around some known bugs |
387 | provides the number of bytes written to C<$out_fh>. Only if the result |
513 | in Linux and FreeBSD kernels (probably others, too), but that might fail, |
388 | value equals C<$length> one can assume that C<$length> bytes have been |
514 | so you really really should check the return value of C<aio_sendfile> - |
389 | read. |
515 | fewre bytes than expected might have been transferred. |
390 | |
516 | |
391 | |
517 | |
392 | =item aio_readahead $fh,$offset,$length, $callback->($retval) |
518 | =item aio_readahead $fh,$offset,$length, $callback->($retval) |
393 | |
519 | |
394 | C<aio_readahead> populates the page cache with data from a file so that |
520 | C<aio_readahead> populates the page cache with data from a file so that |
… | |
… | |
417 | |
543 | |
418 | Currently, the stats are always 64-bit-stats, i.e. instead of returning an |
544 | Currently, the stats are always 64-bit-stats, i.e. instead of returning an |
419 | error when stat'ing a large file, the results will be silently truncated |
545 | error when stat'ing a large file, the results will be silently truncated |
420 | unless perl itself is compiled with large file support. |
546 | unless perl itself is compiled with large file support. |
421 | |
547 | |
|
|
548 | To help interpret the mode and dev/rdev stat values, IO::AIO offers the |
|
|
549 | following constants and functions (if not implemented, the constants will |
|
|
550 | be C<0> and the functions will either C<croak> or fall back on traditional |
|
|
551 | behaviour). |
|
|
552 | |
|
|
553 | C<S_IFMT>, C<S_IFIFO>, C<S_IFCHR>, C<S_IFBLK>, C<S_IFLNK>, C<S_IFREG>, |
|
|
554 | C<S_IFDIR>, C<S_IFWHT>, C<S_IFSOCK>, C<IO::AIO::major $dev_t>, |
|
|
555 | C<IO::AIO::minor $dev_t>, C<IO::AIO::makedev $major, $minor>. |
|
|
556 | |
422 | Example: Print the length of F</etc/passwd>: |
557 | Example: Print the length of F</etc/passwd>: |
423 | |
558 | |
424 | aio_stat "/etc/passwd", sub { |
559 | aio_stat "/etc/passwd", sub { |
425 | $_[0] and die "stat failed: $!"; |
560 | $_[0] and die "stat failed: $!"; |
426 | print "size is ", -s _, "\n"; |
561 | print "size is ", -s _, "\n"; |
427 | }; |
562 | }; |
428 | |
563 | |
429 | |
564 | |
|
|
565 | =item aio_statvfs $fh_or_path, $callback->($statvfs) |
|
|
566 | |
|
|
567 | Works like the POSIX C<statvfs> or C<fstatvfs> syscalls, depending on |
|
|
568 | whether a file handle or path was passed. |
|
|
569 | |
|
|
570 | On success, the callback is passed a hash reference with the following |
|
|
571 | members: C<bsize>, C<frsize>, C<blocks>, C<bfree>, C<bavail>, C<files>, |
|
|
572 | C<ffree>, C<favail>, C<fsid>, C<flag> and C<namemax>. On failure, C<undef> |
|
|
573 | is passed. |
|
|
574 | |
|
|
575 | The following POSIX IO::AIO::ST_* constants are defined: C<ST_RDONLY> and |
|
|
576 | C<ST_NOSUID>. |
|
|
577 | |
|
|
578 | The following non-POSIX IO::AIO::ST_* flag masks are defined to |
|
|
579 | their correct value when available, or to C<0> on systems that do |
|
|
580 | not support them: C<ST_NODEV>, C<ST_NOEXEC>, C<ST_SYNCHRONOUS>, |
|
|
581 | C<ST_MANDLOCK>, C<ST_WRITE>, C<ST_APPEND>, C<ST_IMMUTABLE>, C<ST_NOATIME>, |
|
|
582 | C<ST_NODIRATIME> and C<ST_RELATIME>. |
|
|
583 | |
|
|
584 | Example: stat C</wd> and dump out the data if successful. |
|
|
585 | |
|
|
586 | aio_statvfs "/wd", sub { |
|
|
587 | my $f = $_[0] |
|
|
588 | or die "statvfs: $!"; |
|
|
589 | |
|
|
590 | use Data::Dumper; |
|
|
591 | say Dumper $f; |
|
|
592 | }; |
|
|
593 | |
|
|
594 | # result: |
|
|
595 | { |
|
|
596 | bsize => 1024, |
|
|
597 | bfree => 4333064312, |
|
|
598 | blocks => 10253828096, |
|
|
599 | files => 2050765568, |
|
|
600 | flag => 4096, |
|
|
601 | favail => 2042092649, |
|
|
602 | bavail => 4333064312, |
|
|
603 | ffree => 2042092649, |
|
|
604 | namemax => 255, |
|
|
605 | frsize => 1024, |
|
|
606 | fsid => 1810 |
|
|
607 | } |
|
|
608 | |
|
|
609 | Here is a (likely partial - send me updates!) list of fsid values used by |
|
|
610 | Linux - it is safe to hardcode these when C<$^O> is C<linux>: |
|
|
611 | |
|
|
612 | 0x0000adf5 adfs |
|
|
613 | 0x0000adff affs |
|
|
614 | 0x5346414f afs |
|
|
615 | 0x09041934 anon-inode filesystem |
|
|
616 | 0x00000187 autofs |
|
|
617 | 0x42465331 befs |
|
|
618 | 0x1badface bfs |
|
|
619 | 0x42494e4d binfmt_misc |
|
|
620 | 0x9123683e btrfs |
|
|
621 | 0x0027e0eb cgroupfs |
|
|
622 | 0xff534d42 cifs |
|
|
623 | 0x73757245 coda |
|
|
624 | 0x012ff7b7 coh |
|
|
625 | 0x28cd3d45 cramfs |
|
|
626 | 0x453dcd28 cramfs-wend (wrong endianness) |
|
|
627 | 0x64626720 debugfs |
|
|
628 | 0x00001373 devfs |
|
|
629 | 0x00001cd1 devpts |
|
|
630 | 0x0000f15f ecryptfs |
|
|
631 | 0x00414a53 efs |
|
|
632 | 0x0000137d ext |
|
|
633 | 0x0000ef53 ext2/ext3/ext4 |
|
|
634 | 0x0000ef51 ext2 |
|
|
635 | 0xf2f52010 f2fs |
|
|
636 | 0x00004006 fat |
|
|
637 | 0x65735546 fuseblk |
|
|
638 | 0x65735543 fusectl |
|
|
639 | 0x0bad1dea futexfs |
|
|
640 | 0x01161970 gfs2 |
|
|
641 | 0x47504653 gpfs |
|
|
642 | 0x00004244 hfs |
|
|
643 | 0xf995e849 hpfs |
|
|
644 | 0x00c0ffee hostfs |
|
|
645 | 0x958458f6 hugetlbfs |
|
|
646 | 0x2bad1dea inotifyfs |
|
|
647 | 0x00009660 isofs |
|
|
648 | 0x000072b6 jffs2 |
|
|
649 | 0x3153464a jfs |
|
|
650 | 0x6b414653 k-afs |
|
|
651 | 0x0bd00bd0 lustre |
|
|
652 | 0x0000137f minix |
|
|
653 | 0x0000138f minix 30 char names |
|
|
654 | 0x00002468 minix v2 |
|
|
655 | 0x00002478 minix v2 30 char names |
|
|
656 | 0x00004d5a minix v3 |
|
|
657 | 0x19800202 mqueue |
|
|
658 | 0x00004d44 msdos |
|
|
659 | 0x0000564c novell |
|
|
660 | 0x00006969 nfs |
|
|
661 | 0x6e667364 nfsd |
|
|
662 | 0x00003434 nilfs |
|
|
663 | 0x5346544e ntfs |
|
|
664 | 0x00009fa1 openprom |
|
|
665 | 0x7461636F ocfs2 |
|
|
666 | 0x00009fa0 proc |
|
|
667 | 0x6165676c pstorefs |
|
|
668 | 0x0000002f qnx4 |
|
|
669 | 0x68191122 qnx6 |
|
|
670 | 0x858458f6 ramfs |
|
|
671 | 0x52654973 reiserfs |
|
|
672 | 0x00007275 romfs |
|
|
673 | 0x67596969 rpc_pipefs |
|
|
674 | 0x73636673 securityfs |
|
|
675 | 0xf97cff8c selinux |
|
|
676 | 0x0000517b smb |
|
|
677 | 0x534f434b sockfs |
|
|
678 | 0x73717368 squashfs |
|
|
679 | 0x62656572 sysfs |
|
|
680 | 0x012ff7b6 sysv2 |
|
|
681 | 0x012ff7b5 sysv4 |
|
|
682 | 0x01021994 tmpfs |
|
|
683 | 0x15013346 udf |
|
|
684 | 0x00011954 ufs |
|
|
685 | 0x54190100 ufs byteswapped |
|
|
686 | 0x00009fa2 usbdevfs |
|
|
687 | 0x01021997 v9fs |
|
|
688 | 0xa501fcf5 vxfs |
|
|
689 | 0xabba1974 xenfs |
|
|
690 | 0x012ff7b4 xenix |
|
|
691 | 0x58465342 xfs |
|
|
692 | 0x012fd16d xia |
|
|
693 | |
430 | =item aio_utime $fh_or_path, $atime, $mtime, $callback->($status) |
694 | =item aio_utime $fh_or_path, $atime, $mtime, $callback->($status) |
431 | |
695 | |
432 | Works like perl's C<utime> function (including the special case of $atime |
696 | Works like perl's C<utime> function (including the special case of $atime |
433 | and $mtime being undef). Fractional times are supported if the underlying |
697 | and $mtime being undef). Fractional times are supported if the underlying |
434 | syscalls support them. |
698 | syscalls support them. |
… | |
… | |
461 | =item aio_truncate $fh_or_path, $offset, $callback->($status) |
725 | =item aio_truncate $fh_or_path, $offset, $callback->($status) |
462 | |
726 | |
463 | Works like truncate(2) or ftruncate(2). |
727 | Works like truncate(2) or ftruncate(2). |
464 | |
728 | |
465 | |
729 | |
|
|
730 | =item aio_allocate $fh, $mode, $offset, $len, $callback->($status) |
|
|
731 | |
|
|
732 | Allocates or frees disk space according to the C<$mode> argument. See the |
|
|
733 | linux C<fallocate> documentation for details. |
|
|
734 | |
|
|
735 | C<$mode> is usually C<0> or C<IO::AIO::FALLOC_FL_KEEP_SIZE> to allocate |
|
|
736 | space, or C<IO::AIO::FALLOC_FL_PUNCH_HOLE | IO::AIO::FALLOC_FL_KEEP_SIZE>, |
|
|
737 | to deallocate a file range. |
|
|
738 | |
|
|
739 | IO::AIO also supports C<FALLOC_FL_COLLAPSE_RANGE>, to remove a range |
|
|
740 | (without leaving a hole) and C<FALLOC_FL_ZERO_RANGE>, to zero a range (see |
|
|
741 | your L<fallocate(2)> manpage). |
|
|
742 | |
|
|
743 | The file system block size used by C<fallocate> is presumably the |
|
|
744 | C<f_bsize> returned by C<statvfs>. |
|
|
745 | |
|
|
746 | If C<fallocate> isn't available or cannot be emulated (currently no |
|
|
747 | emulation will be attempted), passes C<-1> and sets C<$!> to C<ENOSYS>. |
|
|
748 | |
|
|
749 | |
466 | =item aio_chmod $fh_or_path, $mode, $callback->($status) |
750 | =item aio_chmod $fh_or_path, $mode, $callback->($status) |
467 | |
751 | |
468 | Works like perl's C<chmod> function. |
752 | Works like perl's C<chmod> function. |
469 | |
753 | |
470 | |
754 | |
… | |
… | |
472 | |
756 | |
473 | Asynchronously unlink (delete) a file and call the callback with the |
757 | Asynchronously unlink (delete) a file and call the callback with the |
474 | result code. |
758 | result code. |
475 | |
759 | |
476 | |
760 | |
477 | =item aio_mknod $path, $mode, $dev, $callback->($status) |
761 | =item aio_mknod $pathname, $mode, $dev, $callback->($status) |
478 | |
762 | |
479 | [EXPERIMENTAL] |
763 | [EXPERIMENTAL] |
480 | |
764 | |
481 | Asynchronously create a device node (or fifo). See mknod(2). |
765 | Asynchronously create a device node (or fifo). See mknod(2). |
482 | |
766 | |
483 | The only (POSIX-) portable way of calling this function is: |
767 | The only (POSIX-) portable way of calling this function is: |
484 | |
768 | |
485 | aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ... |
769 | aio_mknod $pathname, IO::AIO::S_IFIFO | $mode, 0, sub { ... |
486 | |
770 | |
|
|
771 | See C<aio_stat> for info about some potentially helpful extra constants |
|
|
772 | and functions. |
487 | |
773 | |
488 | =item aio_link $srcpath, $dstpath, $callback->($status) |
774 | =item aio_link $srcpath, $dstpath, $callback->($status) |
489 | |
775 | |
490 | Asynchronously create a new link to the existing object at C<$srcpath> at |
776 | Asynchronously create a new link to the existing object at C<$srcpath> at |
491 | the path C<$dstpath> and call the callback with the result code. |
777 | the path C<$dstpath> and call the callback with the result code. |
… | |
… | |
495 | |
781 | |
496 | Asynchronously create a new symbolic link to the existing object at C<$srcpath> at |
782 | Asynchronously create a new symbolic link to the existing object at C<$srcpath> at |
497 | the path C<$dstpath> and call the callback with the result code. |
783 | the path C<$dstpath> and call the callback with the result code. |
498 | |
784 | |
499 | |
785 | |
500 | =item aio_readlink $path, $callback->($link) |
786 | =item aio_readlink $pathname, $callback->($link) |
501 | |
787 | |
502 | Asynchronously read the symlink specified by C<$path> and pass it to |
788 | Asynchronously read the symlink specified by C<$path> and pass it to |
503 | the callback. If an error occurs, nothing or undef gets passed to the |
789 | the callback. If an error occurs, nothing or undef gets passed to the |
504 | callback. |
790 | callback. |
505 | |
791 | |
506 | |
792 | |
|
|
793 | =item aio_realpath $pathname, $callback->($path) |
|
|
794 | |
|
|
795 | Asynchronously make the path absolute and resolve any symlinks in |
|
|
796 | C<$path>. The resulting path only consists of directories (same as |
|
|
797 | L<Cwd::realpath>). |
|
|
798 | |
|
|
799 | This request can be used to get the absolute path of the current working |
|
|
800 | directory by passing it a path of F<.> (a single dot). |
|
|
801 | |
|
|
802 | |
507 | =item aio_rename $srcpath, $dstpath, $callback->($status) |
803 | =item aio_rename $srcpath, $dstpath, $callback->($status) |
508 | |
804 | |
509 | Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as |
805 | Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as |
510 | rename(2) and call the callback with the result code. |
806 | rename(2) and call the callback with the result code. |
|
|
807 | |
|
|
808 | On systems that support the AIO::WD working directory abstraction |
|
|
809 | natively, the case C<[$wd, "."]> as C<$srcpath> is specialcased - instead |
|
|
810 | of failing, C<rename> is called on the absolute path of C<$wd>. |
511 | |
811 | |
512 | |
812 | |
513 | =item aio_mkdir $pathname, $mode, $callback->($status) |
813 | =item aio_mkdir $pathname, $mode, $callback->($status) |
514 | |
814 | |
515 | Asynchronously mkdir (create) a directory and call the callback with |
815 | Asynchronously mkdir (create) a directory and call the callback with |
… | |
… | |
520 | =item aio_rmdir $pathname, $callback->($status) |
820 | =item aio_rmdir $pathname, $callback->($status) |
521 | |
821 | |
522 | Asynchronously rmdir (delete) a directory and call the callback with the |
822 | Asynchronously rmdir (delete) a directory and call the callback with the |
523 | result code. |
823 | result code. |
524 | |
824 | |
|
|
825 | On systems that support the AIO::WD working directory abstraction |
|
|
826 | natively, the case C<[$wd, "."]> is specialcased - instead of failing, |
|
|
827 | C<rmdir> is called on the absolute path of C<$wd>. |
|
|
828 | |
525 | |
829 | |
526 | =item aio_readdir $pathname, $callback->($entries) |
830 | =item aio_readdir $pathname, $callback->($entries) |
527 | |
831 | |
528 | Unlike the POSIX call of the same name, C<aio_readdir> reads an entire |
832 | Unlike the POSIX call of the same name, C<aio_readdir> reads an entire |
529 | directory (i.e. opendir + readdir + closedir). The entries will not be |
833 | directory (i.e. opendir + readdir + closedir). The entries will not be |
530 | sorted, and will B<NOT> include the C<.> and C<..> entries. |
834 | sorted, and will B<NOT> include the C<.> and C<..> entries. |
531 | |
835 | |
532 | The callback a single argument which is either C<undef> or an array-ref |
836 | The callback is passed a single argument which is either C<undef> or an |
533 | with the filenames. |
837 | array-ref with the filenames. |
534 | |
838 | |
535 | |
839 | |
|
|
840 | =item aio_readdirx $pathname, $flags, $callback->($entries, $flags) |
|
|
841 | |
|
|
842 | Quite similar to C<aio_readdir>, but the C<$flags> argument allows one to |
|
|
843 | tune behaviour and output format. In case of an error, C<$entries> will be |
|
|
844 | C<undef>. |
|
|
845 | |
|
|
846 | The flags are a combination of the following constants, ORed together (the |
|
|
847 | flags will also be passed to the callback, possibly modified): |
|
|
848 | |
|
|
849 | =over 4 |
|
|
850 | |
|
|
851 | =item IO::AIO::READDIR_DENTS |
|
|
852 | |
|
|
853 | When this flag is off, then the callback gets an arrayref consisting of |
|
|
854 | names only (as with C<aio_readdir>), otherwise it gets an arrayref with |
|
|
855 | C<[$name, $type, $inode]> arrayrefs, each describing a single directory |
|
|
856 | entry in more detail. |
|
|
857 | |
|
|
858 | C<$name> is the name of the entry. |
|
|
859 | |
|
|
860 | C<$type> is one of the C<IO::AIO::DT_xxx> constants: |
|
|
861 | |
|
|
862 | C<IO::AIO::DT_UNKNOWN>, C<IO::AIO::DT_FIFO>, C<IO::AIO::DT_CHR>, C<IO::AIO::DT_DIR>, |
|
|
863 | C<IO::AIO::DT_BLK>, C<IO::AIO::DT_REG>, C<IO::AIO::DT_LNK>, C<IO::AIO::DT_SOCK>, |
|
|
864 | C<IO::AIO::DT_WHT>. |
|
|
865 | |
|
|
866 | C<IO::AIO::DT_UNKNOWN> means just that: readdir does not know. If you need to |
|
|
867 | know, you have to run stat yourself. Also, for speed reasons, the C<$type> |
|
|
868 | scalars are read-only: you can not modify them. |
|
|
869 | |
|
|
870 | C<$inode> is the inode number (which might not be exact on systems with 64 |
|
|
871 | bit inode numbers and 32 bit perls). This field has unspecified content on |
|
|
872 | systems that do not deliver the inode information. |
|
|
873 | |
|
|
874 | =item IO::AIO::READDIR_DIRS_FIRST |
|
|
875 | |
|
|
876 | When this flag is set, then the names will be returned in an order where |
|
|
877 | likely directories come first, in optimal stat order. This is useful when |
|
|
878 | you need to quickly find directories, or you want to find all directories |
|
|
879 | while avoiding to stat() each entry. |
|
|
880 | |
|
|
881 | If the system returns type information in readdir, then this is used |
|
|
882 | to find directories directly. Otherwise, likely directories are names |
|
|
883 | beginning with ".", or otherwise names with no dots, of which names with |
|
|
884 | short names are tried first. |
|
|
885 | |
|
|
886 | =item IO::AIO::READDIR_STAT_ORDER |
|
|
887 | |
|
|
888 | When this flag is set, then the names will be returned in an order |
|
|
889 | suitable for stat()'ing each one. That is, when you plan to stat() |
|
|
890 | all files in the given directory, then the returned order will likely |
|
|
891 | be fastest. |
|
|
892 | |
|
|
893 | If both this flag and C<IO::AIO::READDIR_DIRS_FIRST> are specified, then |
|
|
894 | the likely dirs come first, resulting in a less optimal stat order. |
|
|
895 | |
|
|
896 | =item IO::AIO::READDIR_FOUND_UNKNOWN |
|
|
897 | |
|
|
898 | This flag should not be set when calling C<aio_readdirx>. Instead, it |
|
|
899 | is being set by C<aio_readdirx>, when any of the C<$type>'s found were |
|
|
900 | C<IO::AIO::DT_UNKNOWN>. The absence of this flag therefore indicates that all |
|
|
901 | C<$type>'s are known, which can be used to speed up some algorithms. |
|
|
902 | |
|
|
903 | =back |
|
|
904 | |
|
|
905 | |
536 | =item aio_load $path, $data, $callback->($status) |
906 | =item aio_load $pathname, $data, $callback->($status) |
537 | |
907 | |
538 | This is a composite request that tries to fully load the given file into |
908 | This is a composite request that tries to fully load the given file into |
539 | memory. Status is the same as with aio_read. |
909 | memory. Status is the same as with aio_read. |
540 | |
910 | |
541 | =cut |
911 | =cut |
… | |
… | |
563 | |
933 | |
564 | =item aio_copy $srcpath, $dstpath, $callback->($status) |
934 | =item aio_copy $srcpath, $dstpath, $callback->($status) |
565 | |
935 | |
566 | Try to copy the I<file> (directories not supported as either source or |
936 | Try to copy the I<file> (directories not supported as either source or |
567 | destination) from C<$srcpath> to C<$dstpath> and call the callback with |
937 | destination) from C<$srcpath> to C<$dstpath> and call the callback with |
568 | the C<0> (error) or C<-1> ok. |
938 | a status of C<0> (ok) or C<-1> (error, see C<$!>). |
569 | |
939 | |
570 | This is a composite request that creates the destination file with |
940 | This is a composite request that creates the destination file with |
571 | mode 0200 and copies the contents of the source file into it using |
941 | mode 0200 and copies the contents of the source file into it using |
572 | C<aio_sendfile>, followed by restoring atime, mtime, access mode and |
942 | C<aio_sendfile>, followed by restoring atime, mtime, access mode and |
573 | uid/gid, in that order. |
943 | uid/gid, in that order. |
… | |
… | |
585 | my $grp = aio_group $cb; |
955 | my $grp = aio_group $cb; |
586 | |
956 | |
587 | aioreq_pri $pri; |
957 | aioreq_pri $pri; |
588 | add $grp aio_open $src, O_RDONLY, 0, sub { |
958 | add $grp aio_open $src, O_RDONLY, 0, sub { |
589 | if (my $src_fh = $_[0]) { |
959 | if (my $src_fh = $_[0]) { |
590 | my @stat = stat $src_fh; |
960 | my @stat = stat $src_fh; # hmm, might block over nfs? |
591 | |
961 | |
592 | aioreq_pri $pri; |
962 | aioreq_pri $pri; |
593 | add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub { |
963 | add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub { |
594 | if (my $dst_fh = $_[0]) { |
964 | if (my $dst_fh = $_[0]) { |
595 | aioreq_pri $pri; |
965 | aioreq_pri $pri; |
596 | add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub { |
966 | add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub { |
597 | if ($_[0] == $stat[7]) { |
967 | if ($_[0] == $stat[7]) { |
598 | $grp->result (0); |
968 | $grp->result (0); |
599 | close $src_fh; |
969 | close $src_fh; |
600 | |
970 | |
601 | # those should not normally block. should. should. |
971 | my $ch = sub { |
602 | utime $stat[8], $stat[9], $dst; |
972 | aioreq_pri $pri; |
603 | chmod $stat[2] & 07777, $dst_fh; |
973 | add $grp aio_chmod $dst_fh, $stat[2] & 07777, sub { |
604 | chown $stat[4], $stat[5], $dst_fh; |
974 | aioreq_pri $pri; |
|
|
975 | add $grp aio_chown $dst_fh, $stat[4], $stat[5], sub { |
|
|
976 | aioreq_pri $pri; |
|
|
977 | add $grp aio_close $dst_fh; |
|
|
978 | } |
|
|
979 | }; |
|
|
980 | }; |
605 | |
981 | |
606 | aioreq_pri $pri; |
982 | aioreq_pri $pri; |
607 | add $grp aio_close $dst_fh; |
983 | add $grp aio_utime $dst_fh, $stat[8], $stat[9], sub { |
|
|
984 | if ($_[0] < 0 && $! == ENOSYS) { |
|
|
985 | aioreq_pri $pri; |
|
|
986 | add $grp aio_utime $dst, $stat[8], $stat[9], $ch; |
|
|
987 | } else { |
|
|
988 | $ch->(); |
|
|
989 | } |
|
|
990 | }; |
608 | } else { |
991 | } else { |
609 | $grp->result (-1); |
992 | $grp->result (-1); |
610 | close $src_fh; |
993 | close $src_fh; |
611 | close $dst_fh; |
994 | close $dst_fh; |
612 | |
995 | |
… | |
… | |
629 | |
1012 | |
630 | =item aio_move $srcpath, $dstpath, $callback->($status) |
1013 | =item aio_move $srcpath, $dstpath, $callback->($status) |
631 | |
1014 | |
632 | Try to move the I<file> (directories not supported as either source or |
1015 | Try to move the I<file> (directories not supported as either source or |
633 | destination) from C<$srcpath> to C<$dstpath> and call the callback with |
1016 | destination) from C<$srcpath> to C<$dstpath> and call the callback with |
634 | the C<0> (error) or C<-1> ok. |
1017 | a status of C<0> (ok) or C<-1> (error, see C<$!>). |
635 | |
1018 | |
636 | This is a composite request that tries to rename(2) the file first. If |
1019 | This is a composite request that tries to rename(2) the file first; if |
637 | rename files with C<EXDEV>, it copies the file with C<aio_copy> and, if |
1020 | rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if |
638 | that is successful, unlinking the C<$srcpath>. |
1021 | that is successful, unlinks the C<$srcpath>. |
639 | |
1022 | |
640 | =cut |
1023 | =cut |
641 | |
1024 | |
642 | sub aio_move($$;$) { |
1025 | sub aio_move($$;$) { |
643 | my ($src, $dst, $cb) = @_; |
1026 | my ($src, $dst, $cb) = @_; |
… | |
… | |
650 | if ($_[0] && $! == EXDEV) { |
1033 | if ($_[0] && $! == EXDEV) { |
651 | aioreq_pri $pri; |
1034 | aioreq_pri $pri; |
652 | add $grp aio_copy $src, $dst, sub { |
1035 | add $grp aio_copy $src, $dst, sub { |
653 | $grp->result ($_[0]); |
1036 | $grp->result ($_[0]); |
654 | |
1037 | |
655 | if (!$_[0]) { |
1038 | unless ($_[0]) { |
656 | aioreq_pri $pri; |
1039 | aioreq_pri $pri; |
657 | add $grp aio_unlink $src; |
1040 | add $grp aio_unlink $src; |
658 | } |
1041 | } |
659 | }; |
1042 | }; |
660 | } else { |
1043 | } else { |
… | |
… | |
663 | }; |
1046 | }; |
664 | |
1047 | |
665 | $grp |
1048 | $grp |
666 | } |
1049 | } |
667 | |
1050 | |
668 | =item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) |
1051 | =item aio_scandir $pathname, $maxreq, $callback->($dirs, $nondirs) |
669 | |
1052 | |
670 | Scans a directory (similar to C<aio_readdir>) but additionally tries to |
1053 | Scans a directory (similar to C<aio_readdir>) but additionally tries to |
671 | efficiently separate the entries of directory C<$path> into two sets of |
1054 | efficiently separate the entries of directory C<$path> into two sets of |
672 | names, directories you can recurse into (directories), and ones you cannot |
1055 | names, directories you can recurse into (directories), and ones you cannot |
673 | recurse into (everything else, including symlinks to directories). |
1056 | recurse into (everything else, including symlinks to directories). |
… | |
… | |
690 | |
1073 | |
691 | Implementation notes. |
1074 | Implementation notes. |
692 | |
1075 | |
693 | The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can. |
1076 | The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can. |
694 | |
1077 | |
|
|
1078 | If readdir returns file type information, then this is used directly to |
|
|
1079 | find directories. |
|
|
1080 | |
695 | After reading the directory, the modification time, size etc. of the |
1081 | Otherwise, after reading the directory, the modification time, size etc. |
696 | directory before and after the readdir is checked, and if they match (and |
1082 | of the directory before and after the readdir is checked, and if they |
697 | isn't the current time), the link count will be used to decide how many |
1083 | match (and isn't the current time), the link count will be used to decide |
698 | entries are directories (if >= 2). Otherwise, no knowledge of the number |
1084 | how many entries are directories (if >= 2). Otherwise, no knowledge of the |
699 | of subdirectories will be assumed. |
1085 | number of subdirectories will be assumed. |
700 | |
1086 | |
701 | Then entries will be sorted into likely directories (everything without |
1087 | Then entries will be sorted into likely directories a non-initial dot |
702 | a non-initial dot currently) and likely non-directories (everything |
1088 | currently) and likely non-directories (see C<aio_readdirx>). Then every |
703 | else). Then every entry plus an appended C</.> will be C<stat>'ed, |
1089 | entry plus an appended C</.> will be C<stat>'ed, likely directories first, |
704 | likely directories first. If that succeeds, it assumes that the entry |
1090 | in order of their inode numbers. If that succeeds, it assumes that the |
705 | is a directory or a symlink to directory (which will be checked |
1091 | entry is a directory or a symlink to directory (which will be checked |
706 | seperately). This is often faster than stat'ing the entry itself because |
1092 | separately). This is often faster than stat'ing the entry itself because |
707 | filesystems might detect the type of the entry without reading the inode |
1093 | filesystems might detect the type of the entry without reading the inode |
708 | data (e.g. ext2fs filetype feature). |
1094 | data (e.g. ext2fs filetype feature), even on systems that cannot return |
|
|
1095 | the filetype information on readdir. |
709 | |
1096 | |
710 | If the known number of directories (link count - 2) has been reached, the |
1097 | If the known number of directories (link count - 2) has been reached, the |
711 | rest of the entries is assumed to be non-directories. |
1098 | rest of the entries is assumed to be non-directories. |
712 | |
1099 | |
713 | This only works with certainty on POSIX (= UNIX) filesystems, which |
1100 | This only works with certainty on POSIX (= UNIX) filesystems, which |
… | |
… | |
726 | |
1113 | |
727 | my $grp = aio_group $cb; |
1114 | my $grp = aio_group $cb; |
728 | |
1115 | |
729 | $maxreq = 4 if $maxreq <= 0; |
1116 | $maxreq = 4 if $maxreq <= 0; |
730 | |
1117 | |
731 | # stat once |
1118 | # get a wd object |
732 | aioreq_pri $pri; |
1119 | aioreq_pri $pri; |
733 | add $grp aio_stat $path, sub { |
1120 | add $grp aio_wd $path, sub { |
|
|
1121 | $_[0] |
734 | return $grp->result () if $_[0]; |
1122 | or return $grp->result (); |
735 | my $now = time; |
|
|
736 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
|
|
737 | |
1123 | |
738 | # read the directory entries |
1124 | my $wd = [shift, "."]; |
|
|
1125 | |
|
|
1126 | # stat once |
739 | aioreq_pri $pri; |
1127 | aioreq_pri $pri; |
740 | add $grp aio_readdir $path, sub { |
1128 | add $grp aio_stat $wd, sub { |
741 | my $entries = shift |
|
|
742 | or return $grp->result (); |
1129 | return $grp->result () if $_[0]; |
|
|
1130 | my $now = time; |
|
|
1131 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
743 | |
1132 | |
744 | # stat the dir another time |
1133 | # read the directory entries |
745 | aioreq_pri $pri; |
1134 | aioreq_pri $pri; |
|
|
1135 | add $grp aio_readdirx $wd, READDIR_DIRS_FIRST, sub { |
|
|
1136 | my $entries = shift |
|
|
1137 | or return $grp->result (); |
|
|
1138 | |
|
|
1139 | # stat the dir another time |
|
|
1140 | aioreq_pri $pri; |
746 | add $grp aio_stat $path, sub { |
1141 | add $grp aio_stat $wd, sub { |
747 | my $hash2 = join ":", (stat _)[0,1,3,7,9]; |
1142 | my $hash2 = join ":", (stat _)[0,1,3,7,9]; |
748 | |
1143 | |
749 | my $ndirs; |
1144 | my $ndirs; |
750 | |
1145 | |
751 | # take the slow route if anything looks fishy |
1146 | # take the slow route if anything looks fishy |
752 | if ($hash1 ne $hash2 or (stat _)[9] == $now) { |
1147 | if ($hash1 ne $hash2 or (stat _)[9] == $now) { |
753 | $ndirs = -1; |
1148 | $ndirs = -1; |
754 | } else { |
1149 | } else { |
755 | # if nlink == 2, we are finished |
1150 | # if nlink == 2, we are finished |
756 | # on non-posix-fs's, we rely on nlink < 2 |
1151 | # for non-posix-fs's, we rely on nlink < 2 |
757 | $ndirs = (stat _)[3] - 2 |
1152 | $ndirs = (stat _)[3] - 2 |
758 | or return $grp->result ([], $entries); |
1153 | or return $grp->result ([], $entries); |
759 | } |
1154 | } |
760 | |
1155 | |
761 | # sort into likely dirs and likely nondirs |
|
|
762 | # dirs == files without ".", short entries first |
|
|
763 | $entries = [map $_->[0], |
|
|
764 | sort { $b->[1] cmp $a->[1] } |
|
|
765 | map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length], |
|
|
766 | @$entries]; |
|
|
767 | |
|
|
768 | my (@dirs, @nondirs); |
1156 | my (@dirs, @nondirs); |
769 | |
1157 | |
770 | my $statgrp = add $grp aio_group sub { |
1158 | my $statgrp = add $grp aio_group sub { |
771 | $grp->result (\@dirs, \@nondirs); |
1159 | $grp->result (\@dirs, \@nondirs); |
772 | }; |
1160 | }; |
773 | |
1161 | |
774 | limit $statgrp $maxreq; |
1162 | limit $statgrp $maxreq; |
775 | feed $statgrp sub { |
1163 | feed $statgrp sub { |
776 | return unless @$entries; |
1164 | return unless @$entries; |
777 | my $entry = pop @$entries; |
1165 | my $entry = shift @$entries; |
778 | |
1166 | |
779 | aioreq_pri $pri; |
1167 | aioreq_pri $pri; |
|
|
1168 | $wd->[1] = "$entry/."; |
780 | add $statgrp aio_stat "$path/$entry/.", sub { |
1169 | add $statgrp aio_stat $wd, sub { |
781 | if ($_[0] < 0) { |
1170 | if ($_[0] < 0) { |
782 | push @nondirs, $entry; |
1171 | push @nondirs, $entry; |
783 | } else { |
1172 | } else { |
784 | # need to check for real directory |
1173 | # need to check for real directory |
785 | aioreq_pri $pri; |
1174 | aioreq_pri $pri; |
|
|
1175 | $wd->[1] = $entry; |
786 | add $statgrp aio_lstat "$path/$entry", sub { |
1176 | add $statgrp aio_lstat $wd, sub { |
787 | if (-d _) { |
1177 | if (-d _) { |
788 | push @dirs, $entry; |
1178 | push @dirs, $entry; |
789 | |
1179 | |
790 | unless (--$ndirs) { |
1180 | unless (--$ndirs) { |
791 | push @nondirs, @$entries; |
1181 | push @nondirs, @$entries; |
792 | feed $statgrp; |
1182 | feed $statgrp; |
|
|
1183 | } |
|
|
1184 | } else { |
|
|
1185 | push @nondirs, $entry; |
793 | } |
1186 | } |
794 | } else { |
|
|
795 | push @nondirs, $entry; |
|
|
796 | } |
1187 | } |
797 | } |
1188 | } |
798 | } |
1189 | }; |
799 | }; |
1190 | }; |
800 | }; |
1191 | }; |
801 | }; |
1192 | }; |
802 | }; |
1193 | }; |
803 | }; |
1194 | }; |
804 | |
1195 | |
805 | $grp |
1196 | $grp |
806 | } |
1197 | } |
807 | |
1198 | |
808 | =item aio_rmtree $path, $callback->($status) |
1199 | =item aio_rmtree $pathname, $callback->($status) |
809 | |
1200 | |
810 | Delete a directory tree starting (and including) C<$path>, return the |
1201 | Delete a directory tree starting (and including) C<$path>, return the |
811 | status of the final C<rmdir> only. This is a composite request that |
1202 | status of the final C<rmdir> only. This is a composite request that |
812 | uses C<aio_scandir> to recurse into and rmdir directories, and unlink |
1203 | uses C<aio_scandir> to recurse into and rmdir directories, and unlink |
813 | everything else. |
1204 | everything else. |
814 | |
1205 | |
815 | =cut |
1206 | =cut |
816 | |
1207 | |
… | |
… | |
838 | }; |
1229 | }; |
839 | |
1230 | |
840 | $grp |
1231 | $grp |
841 | } |
1232 | } |
842 | |
1233 | |
|
|
1234 | =item aio_fcntl $fh, $cmd, $arg, $callback->($status) |
|
|
1235 | |
|
|
1236 | =item aio_ioctl $fh, $request, $buf, $callback->($status) |
|
|
1237 | |
|
|
1238 | These work just like the C<fcntl> and C<ioctl> built-in functions, except |
|
|
1239 | they execute asynchronously and pass the return value to the callback. |
|
|
1240 | |
|
|
1241 | Both calls can be used for a lot of things, some of which make more sense |
|
|
1242 | to run asynchronously in their own thread, while some others make less |
|
|
1243 | sense. For example, calls that block waiting for external events, such |
|
|
1244 | as locking, will also lock down an I/O thread while it is waiting, which |
|
|
1245 | can deadlock the whole I/O system. At the same time, there might be no |
|
|
1246 | alternative to using a thread to wait. |
|
|
1247 | |
|
|
1248 | So in general, you should only use these calls for things that do |
|
|
1249 | (filesystem) I/O, not for things that wait for other events (network, |
|
|
1250 | other processes), although if you are careful and know what you are doing, |
|
|
1251 | you still can. |
|
|
1252 | |
843 | =item aio_sync $callback->($status) |
1253 | =item aio_sync $callback->($status) |
844 | |
1254 | |
845 | Asynchronously call sync and call the callback when finished. |
1255 | Asynchronously call sync and call the callback when finished. |
846 | |
1256 | |
847 | =item aio_fsync $fh, $callback->($status) |
1257 | =item aio_fsync $fh, $callback->($status) |
… | |
… | |
855 | callback with the fdatasync result code. |
1265 | callback with the fdatasync result code. |
856 | |
1266 | |
857 | If this call isn't available because your OS lacks it or it couldn't be |
1267 | If this call isn't available because your OS lacks it or it couldn't be |
858 | detected, it will be emulated by calling C<fsync> instead. |
1268 | detected, it will be emulated by calling C<fsync> instead. |
859 | |
1269 | |
|
|
1270 | =item aio_syncfs $fh, $callback->($status) |
|
|
1271 | |
|
|
1272 | Asynchronously call the syncfs syscall to sync the filesystem associated |
|
|
1273 | to the given filehandle and call the callback with the syncfs result |
|
|
1274 | code. If syncfs is not available, calls sync(), but returns C<-1> and sets |
|
|
1275 | errno to C<ENOSYS> nevertheless. |
|
|
1276 | |
|
|
1277 | =item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status) |
|
|
1278 | |
|
|
1279 | Sync the data portion of the file specified by C<$offset> and C<$length> |
|
|
1280 | to disk (but NOT the metadata), by calling the Linux-specific |
|
|
1281 | sync_file_range call. If sync_file_range is not available or it returns |
|
|
1282 | ENOSYS, then fdatasync or fsync is being substituted. |
|
|
1283 | |
|
|
1284 | C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>, |
|
|
1285 | C<IO::AIO::SYNC_FILE_RANGE_WRITE> and |
|
|
1286 | C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range |
|
|
1287 | manpage for details. |
|
|
1288 | |
860 | =item aio_pathsync $path, $callback->($status) |
1289 | =item aio_pathsync $pathname, $callback->($status) |
861 | |
1290 | |
862 | This request tries to open, fsync and close the given path. This is a |
1291 | This request tries to open, fsync and close the given path. This is a |
863 | composite request intended to sync directories after directory operations |
1292 | composite request intended to sync directories after directory operations |
864 | (E.g. rename). This might not work on all operating systems or have any |
1293 | (E.g. rename). This might not work on all operating systems or have any |
865 | specific effect, but usually it makes sure that directory changes get |
1294 | specific effect, but usually it makes sure that directory changes get |
866 | written to disc. It works for anything that can be opened for read-only, |
1295 | written to disc. It works for anything that can be opened for read-only, |
867 | not just directories. |
1296 | not just directories. |
|
|
1297 | |
|
|
1298 | Future versions of this function might fall back to other methods when |
|
|
1299 | C<fsync> on the directory fails (such as calling C<sync>). |
868 | |
1300 | |
869 | Passes C<0> when everything went ok, and C<-1> on error. |
1301 | Passes C<0> when everything went ok, and C<-1> on error. |
870 | |
1302 | |
871 | =cut |
1303 | =cut |
872 | |
1304 | |
… | |
… | |
893 | }; |
1325 | }; |
894 | |
1326 | |
895 | $grp |
1327 | $grp |
896 | } |
1328 | } |
897 | |
1329 | |
|
|
1330 | =item aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status) |
|
|
1331 | |
|
|
1332 | This is a rather advanced IO::AIO call, which only works on mmap(2)ed |
|
|
1333 | scalars (see the C<IO::AIO::mmap> function, although it also works on data |
|
|
1334 | scalars managed by the L<Sys::Mmap> or L<Mmap> modules, note that the |
|
|
1335 | scalar must only be modified in-place while an aio operation is pending on |
|
|
1336 | it). |
|
|
1337 | |
|
|
1338 | It calls the C<msync> function of your OS, if available, with the memory |
|
|
1339 | area starting at C<$offset> in the string and ending C<$length> bytes |
|
|
1340 | later. If C<$length> is negative, counts from the end, and if C<$length> |
|
|
1341 | is C<undef>, then it goes till the end of the string. The flags can be |
|
|
1342 | a combination of C<IO::AIO::MS_ASYNC>, C<IO::AIO::MS_INVALIDATE> and |
|
|
1343 | C<IO::AIO::MS_SYNC>. |
|
|
1344 | |
|
|
1345 | =item aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status) |
|
|
1346 | |
|
|
1347 | This is a rather advanced IO::AIO call, which works best on mmap(2)ed |
|
|
1348 | scalars. |
|
|
1349 | |
|
|
1350 | It touches (reads or writes) all memory pages in the specified |
|
|
1351 | range inside the scalar. All caveats and parameters are the same |
|
|
1352 | as for C<aio_msync>, above, except for flags, which must be either |
|
|
1353 | C<0> (which reads all pages and ensures they are instantiated) or |
|
|
1354 | C<IO::AIO::MT_MODIFY>, which modifies the memory pages (by reading and |
|
|
1355 | writing an octet from it, which dirties the page). |
|
|
1356 | |
|
|
1357 | =item aio_mlock $scalar, $offset = 0, $length = undef, $callback->($status) |
|
|
1358 | |
|
|
1359 | This is a rather advanced IO::AIO call, which works best on mmap(2)ed |
|
|
1360 | scalars. |
|
|
1361 | |
|
|
1362 | It reads in all the pages of the underlying storage into memory (if any) |
|
|
1363 | and locks them, so they are not getting swapped/paged out or removed. |
|
|
1364 | |
|
|
1365 | If C<$length> is undefined, then the scalar will be locked till the end. |
|
|
1366 | |
|
|
1367 | On systems that do not implement C<mlock>, this function returns C<-1> |
|
|
1368 | and sets errno to C<ENOSYS>. |
|
|
1369 | |
|
|
1370 | Note that the corresponding C<munlock> is synchronous and is |
|
|
1371 | documented under L<MISCELLANEOUS FUNCTIONS>. |
|
|
1372 | |
|
|
1373 | Example: open a file, mmap and mlock it - both will be undone when |
|
|
1374 | C<$data> gets destroyed. |
|
|
1375 | |
|
|
1376 | open my $fh, "<", $path or die "$path: $!"; |
|
|
1377 | my $data; |
|
|
1378 | IO::AIO::mmap $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh; |
|
|
1379 | aio_mlock $data; # mlock in background |
|
|
1380 | |
|
|
1381 | =item aio_mlockall $flags, $callback->($status) |
|
|
1382 | |
|
|
1383 | Calls the C<mlockall> function with the given C<$flags> (a combination of |
|
|
1384 | C<IO::AIO::MCL_CURRENT> and C<IO::AIO::MCL_FUTURE>). |
|
|
1385 | |
|
|
1386 | On systems that do not implement C<mlockall>, this function returns C<-1> |
|
|
1387 | and sets errno to C<ENOSYS>. |
|
|
1388 | |
|
|
1389 | Note that the corresponding C<munlockall> is synchronous and is |
|
|
1390 | documented under L<MISCELLANEOUS FUNCTIONS>. |
|
|
1391 | |
|
|
1392 | Example: asynchronously lock all current and future pages into memory. |
|
|
1393 | |
|
|
1394 | aio_mlockall IO::AIO::MCL_FUTURE; |
|
|
1395 | |
|
|
1396 | =item aio_fiemap $fh, $start, $length, $flags, $count, $cb->(\@extents) |
|
|
1397 | |
|
|
1398 | Queries the extents of the given file (by calling the Linux C<FIEMAP> |
|
|
1399 | ioctl, see L<http://cvs.schmorp.de/IO-AIO/doc/fiemap.txt> for details). If |
|
|
1400 | the ioctl is not available on your OS, then this request will fail with |
|
|
1401 | C<ENOSYS>. |
|
|
1402 | |
|
|
1403 | C<$start> is the starting offset to query extents for, C<$length> is the |
|
|
1404 | size of the range to query - if it is C<undef>, then the whole file will |
|
|
1405 | be queried. |
|
|
1406 | |
|
|
1407 | C<$flags> is a combination of flags (C<IO::AIO::FIEMAP_FLAG_SYNC> or |
|
|
1408 | C<IO::AIO::FIEMAP_FLAG_XATTR> - C<IO::AIO::FIEMAP_FLAGS_COMPAT> is also |
|
|
1409 | exported), and is normally C<0> or C<IO::AIO::FIEMAP_FLAG_SYNC> to query |
|
|
1410 | the data portion. |
|
|
1411 | |
|
|
1412 | C<$count> is the maximum number of extent records to return. If it is |
|
|
1413 | C<undef>, then IO::AIO queries all extents of the range. As a very special |
|
|
1414 | case, if it is C<0>, then the callback receives the number of extents |
|
|
1415 | instead of the extents themselves (which is unreliable, see below). |
|
|
1416 | |
|
|
1417 | If an error occurs, the callback receives no arguments. The special |
|
|
1418 | C<errno> value C<IO::AIO::EBADR> is available to test for flag errors. |
|
|
1419 | |
|
|
1420 | Otherwise, the callback receives an array reference with extent |
|
|
1421 | structures. Each extent structure is an array reference itself, with the |
|
|
1422 | following members: |
|
|
1423 | |
|
|
1424 | [$logical, $physical, $length, $flags] |
|
|
1425 | |
|
|
1426 | Flags is any combination of the following flag values (typically either C<0> |
|
|
1427 | or C<IO::AIO::FIEMAP_EXTENT_LAST> (1)): |
|
|
1428 | |
|
|
1429 | C<IO::AIO::FIEMAP_EXTENT_LAST>, C<IO::AIO::FIEMAP_EXTENT_UNKNOWN>, |
|
|
1430 | C<IO::AIO::FIEMAP_EXTENT_DELALLOC>, C<IO::AIO::FIEMAP_EXTENT_ENCODED>, |
|
|
1431 | C<IO::AIO::FIEMAP_EXTENT_DATA_ENCRYPTED>, C<IO::AIO::FIEMAP_EXTENT_NOT_ALIGNED>, |
|
|
1432 | C<IO::AIO::FIEMAP_EXTENT_DATA_INLINE>, C<IO::AIO::FIEMAP_EXTENT_DATA_TAIL>, |
|
|
1433 | C<IO::AIO::FIEMAP_EXTENT_UNWRITTEN>, C<IO::AIO::FIEMAP_EXTENT_MERGED> or |
|
|
1434 | C<IO::AIO::FIEMAP_EXTENT_SHARED>. |
|
|
1435 | |
|
|
1436 | At the time of this writing (Linux 3.2), this requets is unreliable unless |
|
|
1437 | C<$count> is C<undef>, as the kernel has all sorts of bugs preventing |
|
|
1438 | it to return all extents of a range for files with large number of |
|
|
1439 | extents. The code works around all these issues if C<$count> is undef. |
|
|
1440 | |
898 | =item aio_group $callback->(...) |
1441 | =item aio_group $callback->(...) |
899 | |
1442 | |
900 | This is a very special aio request: Instead of doing something, it is a |
1443 | This is a very special aio request: Instead of doing something, it is a |
901 | container for other aio requests, which is useful if you want to bundle |
1444 | container for other aio requests, which is useful if you want to bundle |
902 | many requests into a single, composite, request with a definite callback |
1445 | many requests into a single, composite, request with a definite callback |
… | |
… | |
939 | immense (it blocks a thread for a long time) so do not use this function |
1482 | immense (it blocks a thread for a long time) so do not use this function |
940 | except to put your application under artificial I/O pressure. |
1483 | except to put your application under artificial I/O pressure. |
941 | |
1484 | |
942 | =back |
1485 | =back |
943 | |
1486 | |
|
|
1487 | |
|
|
1488 | =head2 IO::AIO::WD - multiple working directories |
|
|
1489 | |
|
|
1490 | Your process only has one current working directory, which is used by all |
|
|
1491 | threads. This makes it hard to use relative paths (some other component |
|
|
1492 | could call C<chdir> at any time, and it is hard to control when the path |
|
|
1493 | will be used by IO::AIO). |
|
|
1494 | |
|
|
1495 | One solution for this is to always use absolute paths. This usually works, |
|
|
1496 | but can be quite slow (the kernel has to walk the whole path on every |
|
|
1497 | access), and can also be a hassle to implement. |
|
|
1498 | |
|
|
1499 | Newer POSIX systems have a number of functions (openat, fdopendir, |
|
|
1500 | futimensat and so on) that make it possible to specify working directories |
|
|
1501 | per operation. |
|
|
1502 | |
|
|
1503 | For portability, and because the clowns who "designed", or shall I write, |
|
|
1504 | perpetrated this new interface were obviously half-drunk, this abstraction |
|
|
1505 | cannot be perfect, though. |
|
|
1506 | |
|
|
1507 | IO::AIO allows you to convert directory paths into a so-called IO::AIO::WD |
|
|
1508 | object. This object stores the canonicalised, absolute version of the |
|
|
1509 | path, and on systems that allow it, also a directory file descriptor. |
|
|
1510 | |
|
|
1511 | Everywhere where a pathname is accepted by IO::AIO (e.g. in C<aio_stat> |
|
|
1512 | or C<aio_unlink>), one can specify an array reference with an IO::AIO::WD |
|
|
1513 | object and a pathname instead (or the IO::AIO::WD object alone, which |
|
|
1514 | gets interpreted as C<[$wd, "."]>). If the pathname is absolute, the |
|
|
1515 | IO::AIO::WD object is ignored, otherwise the pathname is resolved relative |
|
|
1516 | to that IO::AIO::WD object. |
|
|
1517 | |
|
|
1518 | For example, to get a wd object for F</etc> and then stat F<passwd> |
|
|
1519 | inside, you would write: |
|
|
1520 | |
|
|
1521 | aio_wd "/etc", sub { |
|
|
1522 | my $etcdir = shift; |
|
|
1523 | |
|
|
1524 | # although $etcdir can be undef on error, there is generally no reason |
|
|
1525 | # to check for errors here, as aio_stat will fail with ENOENT |
|
|
1526 | # when $etcdir is undef. |
|
|
1527 | |
|
|
1528 | aio_stat [$etcdir, "passwd"], sub { |
|
|
1529 | # yay |
|
|
1530 | }; |
|
|
1531 | }; |
|
|
1532 | |
|
|
1533 | The fact that C<aio_wd> is a request and not a normal function shows that |
|
|
1534 | creating an IO::AIO::WD object is itself a potentially blocking operation, |
|
|
1535 | which is why it is done asynchronously. |
|
|
1536 | |
|
|
1537 | To stat the directory obtained with C<aio_wd> above, one could write |
|
|
1538 | either of the following three request calls: |
|
|
1539 | |
|
|
1540 | aio_lstat "/etc" , sub { ... # pathname as normal string |
|
|
1541 | aio_lstat [$wd, "."], sub { ... # "." relative to $wd (i.e. $wd itself) |
|
|
1542 | aio_lstat $wd , sub { ... # shorthand for the previous |
|
|
1543 | |
|
|
1544 | As with normal pathnames, IO::AIO keeps a copy of the working directory |
|
|
1545 | object and the pathname string, so you could write the following without |
|
|
1546 | causing any issues due to C<$path> getting reused: |
|
|
1547 | |
|
|
1548 | my $path = [$wd, undef]; |
|
|
1549 | |
|
|
1550 | for my $name (qw(abc def ghi)) { |
|
|
1551 | $path->[1] = $name; |
|
|
1552 | aio_stat $path, sub { |
|
|
1553 | # ... |
|
|
1554 | }; |
|
|
1555 | } |
|
|
1556 | |
|
|
1557 | There are some caveats: when directories get renamed (or deleted), the |
|
|
1558 | pathname string doesn't change, so will point to the new directory (or |
|
|
1559 | nowhere at all), while the directory fd, if available on the system, |
|
|
1560 | will still point to the original directory. Most functions accepting a |
|
|
1561 | pathname will use the directory fd on newer systems, and the string on |
|
|
1562 | older systems. Some functions (such as realpath) will always rely on the |
|
|
1563 | string form of the pathname. |
|
|
1564 | |
|
|
1565 | So this functionality is mainly useful to get some protection against |
|
|
1566 | C<chdir>, to easily get an absolute path out of a relative path for future |
|
|
1567 | reference, and to speed up doing many operations in the same directory |
|
|
1568 | (e.g. when stat'ing all files in a directory). |
|
|
1569 | |
|
|
1570 | The following functions implement this working directory abstraction: |
|
|
1571 | |
|
|
1572 | =over 4 |
|
|
1573 | |
|
|
1574 | =item aio_wd $pathname, $callback->($wd) |
|
|
1575 | |
|
|
1576 | Asynchonously canonicalise the given pathname and convert it to an |
|
|
1577 | IO::AIO::WD object representing it. If possible and supported on the |
|
|
1578 | system, also open a directory fd to speed up pathname resolution relative |
|
|
1579 | to this working directory. |
|
|
1580 | |
|
|
1581 | If something goes wrong, then C<undef> is passwd to the callback instead |
|
|
1582 | of a working directory object and C<$!> is set appropriately. Since |
|
|
1583 | passing C<undef> as working directory component of a pathname fails the |
|
|
1584 | request with C<ENOENT>, there is often no need for error checking in the |
|
|
1585 | C<aio_wd> callback, as future requests using the value will fail in the |
|
|
1586 | expected way. |
|
|
1587 | |
|
|
1588 | =item IO::AIO::CWD |
|
|
1589 | |
|
|
1590 | This is a compiletime constant (object) that represents the process |
|
|
1591 | current working directory. |
|
|
1592 | |
|
|
1593 | Specifying this object as working directory object for a pathname is as if |
|
|
1594 | the pathname would be specified directly, without a directory object. For |
|
|
1595 | example, these calls are functionally identical: |
|
|
1596 | |
|
|
1597 | aio_stat "somefile", sub { ... }; |
|
|
1598 | aio_stat [IO::AIO::CWD, "somefile"], sub { ... }; |
|
|
1599 | |
|
|
1600 | =back |
|
|
1601 | |
|
|
1602 | To recover the path associated with an IO::AIO::WD object, you can use |
|
|
1603 | C<aio_realpath>: |
|
|
1604 | |
|
|
1605 | aio_realpath $wd, sub { |
|
|
1606 | warn "path is $_[0]\n"; |
|
|
1607 | }; |
|
|
1608 | |
|
|
1609 | Currently, C<aio_statvfs> always, and C<aio_rename> and C<aio_rmdir> |
|
|
1610 | sometimes, fall back to using an absolue path. |
|
|
1611 | |
944 | =head2 IO::AIO::REQ CLASS |
1612 | =head2 IO::AIO::REQ CLASS |
945 | |
1613 | |
946 | All non-aggregate C<aio_*> functions return an object of this class when |
1614 | All non-aggregate C<aio_*> functions return an object of this class when |
947 | called in non-void context. |
1615 | called in non-void context. |
948 | |
1616 | |
… | |
… | |
951 | =item cancel $req |
1619 | =item cancel $req |
952 | |
1620 | |
953 | Cancels the request, if possible. Has the effect of skipping execution |
1621 | Cancels the request, if possible. Has the effect of skipping execution |
954 | when entering the B<execute> state and skipping calling the callback when |
1622 | when entering the B<execute> state and skipping calling the callback when |
955 | entering the the B<result> state, but will leave the request otherwise |
1623 | entering the the B<result> state, but will leave the request otherwise |
956 | untouched. That means that requests that currently execute will not be |
1624 | untouched (with the exception of readdir). That means that requests that |
957 | stopped and resources held by the request will not be freed prematurely. |
1625 | currently execute will not be stopped and resources held by the request |
|
|
1626 | will not be freed prematurely. |
958 | |
1627 | |
959 | =item cb $req $callback->(...) |
1628 | =item cb $req $callback->(...) |
960 | |
1629 | |
961 | Replace (or simply set) the callback registered to the request. |
1630 | Replace (or simply set) the callback registered to the request. |
962 | |
1631 | |
… | |
… | |
1036 | =item $grp->cancel_subs |
1705 | =item $grp->cancel_subs |
1037 | |
1706 | |
1038 | Cancel all subrequests and clears any feeder, but not the group request |
1707 | Cancel all subrequests and clears any feeder, but not the group request |
1039 | itself. Useful when you queued a lot of events but got a result early. |
1708 | itself. Useful when you queued a lot of events but got a result early. |
1040 | |
1709 | |
|
|
1710 | The group request will finish normally (you cannot add requests to the |
|
|
1711 | group). |
|
|
1712 | |
1041 | =item $grp->result (...) |
1713 | =item $grp->result (...) |
1042 | |
1714 | |
1043 | Set the result value(s) that will be passed to the group callback when all |
1715 | Set the result value(s) that will be passed to the group callback when all |
1044 | subrequests have finished and set the groups errno to the current value |
1716 | subrequests have finished and set the groups errno to the current value |
1045 | of errno (just like calling C<errno> without an error number). By default, |
1717 | of errno (just like calling C<errno> without an error number). By default, |
… | |
… | |
1060 | =item feed $grp $callback->($grp) |
1732 | =item feed $grp $callback->($grp) |
1061 | |
1733 | |
1062 | Sets a feeder/generator on this group: every group can have an attached |
1734 | Sets a feeder/generator on this group: every group can have an attached |
1063 | generator that generates requests if idle. The idea behind this is that, |
1735 | generator that generates requests if idle. The idea behind this is that, |
1064 | although you could just queue as many requests as you want in a group, |
1736 | although you could just queue as many requests as you want in a group, |
1065 | this might starve other requests for a potentially long time. For |
1737 | this might starve other requests for a potentially long time. For example, |
1066 | example, C<aio_scandir> might generate hundreds of thousands C<aio_stat> |
1738 | C<aio_scandir> might generate hundreds of thousands of C<aio_stat> |
1067 | requests, delaying any later requests for a long time. |
1739 | requests, delaying any later requests for a long time. |
1068 | |
1740 | |
1069 | To avoid this, and allow incremental generation of requests, you can |
1741 | To avoid this, and allow incremental generation of requests, you can |
1070 | instead a group and set a feeder on it that generates those requests. The |
1742 | instead a group and set a feeder on it that generates those requests. The |
1071 | feed callback will be called whenever there are few enough (see C<limit>, |
1743 | feed callback will be called whenever there are few enough (see C<limit>, |
… | |
… | |
1076 | not impose any limits). |
1748 | not impose any limits). |
1077 | |
1749 | |
1078 | If the feed does not queue more requests when called, it will be |
1750 | If the feed does not queue more requests when called, it will be |
1079 | automatically removed from the group. |
1751 | automatically removed from the group. |
1080 | |
1752 | |
1081 | If the feed limit is C<0>, it will be set to C<2> automatically. |
1753 | If the feed limit is C<0> when this method is called, it will be set to |
|
|
1754 | C<2> automatically. |
1082 | |
1755 | |
1083 | Example: |
1756 | Example: |
1084 | |
1757 | |
1085 | # stat all files in @files, but only ever use four aio requests concurrently: |
1758 | # stat all files in @files, but only ever use four aio requests concurrently: |
1086 | |
1759 | |
… | |
… | |
1098 | Sets the feeder limit for the group: The feeder will be called whenever |
1771 | Sets the feeder limit for the group: The feeder will be called whenever |
1099 | the group contains less than this many requests. |
1772 | the group contains less than this many requests. |
1100 | |
1773 | |
1101 | Setting the limit to C<0> will pause the feeding process. |
1774 | Setting the limit to C<0> will pause the feeding process. |
1102 | |
1775 | |
|
|
1776 | The default value for the limit is C<0>, but note that setting a feeder |
|
|
1777 | automatically bumps it up to C<2>. |
|
|
1778 | |
1103 | =back |
1779 | =back |
1104 | |
1780 | |
1105 | =head2 SUPPORT FUNCTIONS |
1781 | =head2 SUPPORT FUNCTIONS |
1106 | |
1782 | |
1107 | =head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION |
1783 | =head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION |
… | |
… | |
1109 | =over 4 |
1785 | =over 4 |
1110 | |
1786 | |
1111 | =item $fileno = IO::AIO::poll_fileno |
1787 | =item $fileno = IO::AIO::poll_fileno |
1112 | |
1788 | |
1113 | Return the I<request result pipe file descriptor>. This filehandle must be |
1789 | Return the I<request result pipe file descriptor>. This filehandle must be |
1114 | polled for reading by some mechanism outside this module (e.g. Event or |
1790 | polled for reading by some mechanism outside this module (e.g. EV, Glib, |
1115 | select, see below or the SYNOPSIS). If the pipe becomes readable you have |
1791 | select and so on, see below or the SYNOPSIS). If the pipe becomes readable |
1116 | to call C<poll_cb> to check the results. |
1792 | you have to call C<poll_cb> to check the results. |
1117 | |
1793 | |
1118 | See C<poll_cb> for an example. |
1794 | See C<poll_cb> for an example. |
1119 | |
1795 | |
1120 | =item IO::AIO::poll_cb |
1796 | =item IO::AIO::poll_cb |
1121 | |
1797 | |
1122 | Process some outstanding events on the result pipe. You have to call this |
1798 | Process some requests that have reached the result phase (i.e. they have |
1123 | regularly. Returns C<0> if all events could be processed, or C<-1> if it |
1799 | been executed but the results are not yet reported). You have to call |
1124 | returned earlier for whatever reason. Returns immediately when no events |
1800 | this "regularly" to finish outstanding requests. |
1125 | are outstanding. The amount of events processed depends on the settings of |
|
|
1126 | C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>. |
|
|
1127 | |
1801 | |
|
|
1802 | Returns C<0> if all events could be processed (or there were no |
|
|
1803 | events to process), or C<-1> if it returned earlier for whatever |
|
|
1804 | reason. Returns immediately when no events are outstanding. The amount |
|
|
1805 | of events processed depends on the settings of C<IO::AIO::max_poll_req>, |
|
|
1806 | C<IO::AIO::max_poll_time> and C<IO::AIO::max_outstanding>. |
|
|
1807 | |
1128 | If not all requests were processed for whatever reason, the filehandle |
1808 | If not all requests were processed for whatever reason, the poll file |
1129 | will still be ready when C<poll_cb> returns, so normally you don't have to |
1809 | descriptor will still be ready when C<poll_cb> returns, so normally you |
1130 | do anything special to have it called later. |
1810 | don't have to do anything special to have it called later. |
|
|
1811 | |
|
|
1812 | Apart from calling C<IO::AIO::poll_cb> when the event filehandle becomes |
|
|
1813 | ready, it can be beneficial to call this function from loops which submit |
|
|
1814 | a lot of requests, to make sure the results get processed when they become |
|
|
1815 | available and not just when the loop is finished and the event loop takes |
|
|
1816 | over again. This function returns very fast when there are no outstanding |
|
|
1817 | requests. |
1131 | |
1818 | |
1132 | Example: Install an Event watcher that automatically calls |
1819 | Example: Install an Event watcher that automatically calls |
1133 | IO::AIO::poll_cb with high priority: |
1820 | IO::AIO::poll_cb with high priority (more examples can be found in the |
|
|
1821 | SYNOPSIS section, at the top of this document): |
1134 | |
1822 | |
1135 | Event->io (fd => IO::AIO::poll_fileno, |
1823 | Event->io (fd => IO::AIO::poll_fileno, |
1136 | poll => 'r', async => 1, |
1824 | poll => 'r', async => 1, |
1137 | cb => \&IO::AIO::poll_cb); |
1825 | cb => \&IO::AIO::poll_cb); |
|
|
1826 | |
|
|
1827 | =item IO::AIO::poll_wait |
|
|
1828 | |
|
|
1829 | Wait until either at least one request is in the result phase or no |
|
|
1830 | requests are outstanding anymore. |
|
|
1831 | |
|
|
1832 | This is useful if you want to synchronously wait for some requests to |
|
|
1833 | become ready, without actually handling them. |
|
|
1834 | |
|
|
1835 | See C<nreqs> for an example. |
|
|
1836 | |
|
|
1837 | =item IO::AIO::poll |
|
|
1838 | |
|
|
1839 | Waits until some requests have been handled. |
|
|
1840 | |
|
|
1841 | Returns the number of requests processed, but is otherwise strictly |
|
|
1842 | equivalent to: |
|
|
1843 | |
|
|
1844 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
1845 | |
|
|
1846 | =item IO::AIO::flush |
|
|
1847 | |
|
|
1848 | Wait till all outstanding AIO requests have been handled. |
|
|
1849 | |
|
|
1850 | Strictly equivalent to: |
|
|
1851 | |
|
|
1852 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
1853 | while IO::AIO::nreqs; |
1138 | |
1854 | |
1139 | =item IO::AIO::max_poll_reqs $nreqs |
1855 | =item IO::AIO::max_poll_reqs $nreqs |
1140 | |
1856 | |
1141 | =item IO::AIO::max_poll_time $seconds |
1857 | =item IO::AIO::max_poll_time $seconds |
1142 | |
1858 | |
… | |
… | |
1167 | # use a low priority so other tasks have priority |
1883 | # use a low priority so other tasks have priority |
1168 | Event->io (fd => IO::AIO::poll_fileno, |
1884 | Event->io (fd => IO::AIO::poll_fileno, |
1169 | poll => 'r', nice => 1, |
1885 | poll => 'r', nice => 1, |
1170 | cb => &IO::AIO::poll_cb); |
1886 | cb => &IO::AIO::poll_cb); |
1171 | |
1887 | |
1172 | =item IO::AIO::poll_wait |
|
|
1173 | |
|
|
1174 | If there are any outstanding requests and none of them in the result |
|
|
1175 | phase, wait till the result filehandle becomes ready for reading (simply |
|
|
1176 | does a C<select> on the filehandle. This is useful if you want to |
|
|
1177 | synchronously wait for some requests to finish). |
|
|
1178 | |
|
|
1179 | See C<nreqs> for an example. |
|
|
1180 | |
|
|
1181 | =item IO::AIO::poll |
|
|
1182 | |
|
|
1183 | Waits until some requests have been handled. |
|
|
1184 | |
|
|
1185 | Returns the number of requests processed, but is otherwise strictly |
|
|
1186 | equivalent to: |
|
|
1187 | |
|
|
1188 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
1189 | |
|
|
1190 | =item IO::AIO::flush |
|
|
1191 | |
|
|
1192 | Wait till all outstanding AIO requests have been handled. |
|
|
1193 | |
|
|
1194 | Strictly equivalent to: |
|
|
1195 | |
|
|
1196 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
1197 | while IO::AIO::nreqs; |
|
|
1198 | |
|
|
1199 | =back |
1888 | =back |
1200 | |
1889 | |
1201 | =head3 CONTROLLING THE NUMBER OF THREADS |
1890 | =head3 CONTROLLING THE NUMBER OF THREADS |
1202 | |
1891 | |
1203 | =over |
1892 | =over |
… | |
… | |
1236 | |
1925 | |
1237 | Under normal circumstances you don't need to call this function. |
1926 | Under normal circumstances you don't need to call this function. |
1238 | |
1927 | |
1239 | =item IO::AIO::max_idle $nthreads |
1928 | =item IO::AIO::max_idle $nthreads |
1240 | |
1929 | |
1241 | Limit the number of threads (default: 4) that are allowed to idle (i.e., |
1930 | Limit the number of threads (default: 4) that are allowed to idle |
1242 | threads that did not get a request to process within 10 seconds). That |
1931 | (i.e., threads that did not get a request to process within the idle |
1243 | means if a thread becomes idle while C<$nthreads> other threads are also |
1932 | timeout (default: 10 seconds). That means if a thread becomes idle while |
1244 | idle, it will free its resources and exit. |
1933 | C<$nthreads> other threads are also idle, it will free its resources and |
|
|
1934 | exit. |
1245 | |
1935 | |
1246 | This is useful when you allow a large number of threads (e.g. 100 or 1000) |
1936 | This is useful when you allow a large number of threads (e.g. 100 or 1000) |
1247 | to allow for extremely high load situations, but want to free resources |
1937 | to allow for extremely high load situations, but want to free resources |
1248 | under normal circumstances (1000 threads can easily consume 30MB of RAM). |
1938 | under normal circumstances (1000 threads can easily consume 30MB of RAM). |
1249 | |
1939 | |
1250 | The default is probably ok in most situations, especially if thread |
1940 | The default is probably ok in most situations, especially if thread |
1251 | creation is fast. If thread creation is very slow on your system you might |
1941 | creation is fast. If thread creation is very slow on your system you might |
1252 | want to use larger values. |
1942 | want to use larger values. |
1253 | |
1943 | |
|
|
1944 | =item IO::AIO::idle_timeout $seconds |
|
|
1945 | |
|
|
1946 | Sets the minimum idle timeout (default 10) after which worker threads are |
|
|
1947 | allowed to exit. SEe C<IO::AIO::max_idle>. |
|
|
1948 | |
1254 | =item IO::AIO::max_outstanding $maxreqs |
1949 | =item IO::AIO::max_outstanding $maxreqs |
|
|
1950 | |
|
|
1951 | Sets the maximum number of outstanding requests to C<$nreqs>. If |
|
|
1952 | you do queue up more than this number of requests, the next call to |
|
|
1953 | C<IO::AIO::poll_cb> (and other functions calling C<poll_cb>, such as |
|
|
1954 | C<IO::AIO::flush> or C<IO::AIO::poll>) will block until the limit is no |
|
|
1955 | longer exceeded. |
|
|
1956 | |
|
|
1957 | In other words, this setting does not enforce a queue limit, but can be |
|
|
1958 | used to make poll functions block if the limit is exceeded. |
1255 | |
1959 | |
1256 | This is a very bad function to use in interactive programs because it |
1960 | This is a very bad function to use in interactive programs because it |
1257 | blocks, and a bad way to reduce concurrency because it is inexact: Better |
1961 | blocks, and a bad way to reduce concurrency because it is inexact: Better |
1258 | use an C<aio_group> together with a feed callback. |
1962 | use an C<aio_group> together with a feed callback. |
1259 | |
1963 | |
1260 | Sets the maximum number of outstanding requests to C<$nreqs>. If you |
1964 | Its main use is in scripts without an event loop - when you want to stat |
1261 | do queue up more than this number of requests, the next call to the |
1965 | a lot of files, you can write somehting like this: |
1262 | C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>) |
|
|
1263 | function will block until the limit is no longer exceeded. |
|
|
1264 | |
1966 | |
1265 | The default value is very large, so there is no practical limit on the |
1967 | IO::AIO::max_outstanding 32; |
1266 | number of outstanding requests. |
|
|
1267 | |
1968 | |
1268 | You can still queue as many requests as you want. Therefore, |
1969 | for my $path (...) { |
1269 | C<max_outstanding> is mainly useful in simple scripts (with low values) or |
1970 | aio_stat $path , ...; |
1270 | as a stop gap to shield against fatal memory overflow (with large values). |
1971 | IO::AIO::poll_cb; |
|
|
1972 | } |
|
|
1973 | |
|
|
1974 | IO::AIO::flush; |
|
|
1975 | |
|
|
1976 | The call to C<poll_cb> inside the loop will normally return instantly, but |
|
|
1977 | as soon as more thna C<32> reqeusts are in-flight, it will block until |
|
|
1978 | some requests have been handled. This keeps the loop from pushing a large |
|
|
1979 | number of C<aio_stat> requests onto the queue. |
|
|
1980 | |
|
|
1981 | The default value for C<max_outstanding> is very large, so there is no |
|
|
1982 | practical limit on the number of outstanding requests. |
1271 | |
1983 | |
1272 | =back |
1984 | =back |
1273 | |
1985 | |
1274 | =head3 STATISTICAL INFORMATION |
1986 | =head3 STATISTICAL INFORMATION |
1275 | |
1987 | |
… | |
… | |
1295 | Returns the number of requests currently in the pending state (executed, |
2007 | Returns the number of requests currently in the pending state (executed, |
1296 | but not yet processed by poll_cb). |
2008 | but not yet processed by poll_cb). |
1297 | |
2009 | |
1298 | =back |
2010 | =back |
1299 | |
2011 | |
|
|
2012 | =head3 MISCELLANEOUS FUNCTIONS |
|
|
2013 | |
|
|
2014 | IO::AIO implements some functions that are useful when you want to use |
|
|
2015 | some "Advanced I/O" function not available to in Perl, without going the |
|
|
2016 | "Asynchronous I/O" route. Many of these have an asynchronous C<aio_*> |
|
|
2017 | counterpart. |
|
|
2018 | |
|
|
2019 | =over 4 |
|
|
2020 | |
|
|
2021 | =item IO::AIO::sendfile $ofh, $ifh, $offset, $count |
|
|
2022 | |
|
|
2023 | Calls the C<eio_sendfile_sync> function, which is like C<aio_sendfile>, |
|
|
2024 | but is blocking (this makes most sense if you know the input data is |
|
|
2025 | likely cached already and the output filehandle is set to non-blocking |
|
|
2026 | operations). |
|
|
2027 | |
|
|
2028 | Returns the number of bytes copied, or C<-1> on error. |
|
|
2029 | |
|
|
2030 | =item IO::AIO::fadvise $fh, $offset, $len, $advice |
|
|
2031 | |
|
|
2032 | Simply calls the C<posix_fadvise> function (see its |
|
|
2033 | manpage for details). The following advice constants are |
|
|
2034 | available: C<IO::AIO::FADV_NORMAL>, C<IO::AIO::FADV_SEQUENTIAL>, |
|
|
2035 | C<IO::AIO::FADV_RANDOM>, C<IO::AIO::FADV_NOREUSE>, |
|
|
2036 | C<IO::AIO::FADV_WILLNEED>, C<IO::AIO::FADV_DONTNEED>. |
|
|
2037 | |
|
|
2038 | On systems that do not implement C<posix_fadvise>, this function returns |
|
|
2039 | ENOSYS, otherwise the return value of C<posix_fadvise>. |
|
|
2040 | |
|
|
2041 | =item IO::AIO::madvise $scalar, $offset, $len, $advice |
|
|
2042 | |
|
|
2043 | Simply calls the C<posix_madvise> function (see its |
|
|
2044 | manpage for details). The following advice constants are |
|
|
2045 | available: C<IO::AIO::MADV_NORMAL>, C<IO::AIO::MADV_SEQUENTIAL>, |
|
|
2046 | C<IO::AIO::MADV_RANDOM>, C<IO::AIO::MADV_WILLNEED>, C<IO::AIO::MADV_DONTNEED>. |
|
|
2047 | |
|
|
2048 | On systems that do not implement C<posix_madvise>, this function returns |
|
|
2049 | ENOSYS, otherwise the return value of C<posix_madvise>. |
|
|
2050 | |
|
|
2051 | =item IO::AIO::mprotect $scalar, $offset, $len, $protect |
|
|
2052 | |
|
|
2053 | Simply calls the C<mprotect> function on the preferably AIO::mmap'ed |
|
|
2054 | $scalar (see its manpage for details). The following protect |
|
|
2055 | constants are available: C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_READ>, |
|
|
2056 | C<IO::AIO::PROT_WRITE>, C<IO::AIO::PROT_EXEC>. |
|
|
2057 | |
|
|
2058 | On systems that do not implement C<mprotect>, this function returns |
|
|
2059 | ENOSYS, otherwise the return value of C<mprotect>. |
|
|
2060 | |
|
|
2061 | =item IO::AIO::mmap $scalar, $length, $prot, $flags, $fh[, $offset] |
|
|
2062 | |
|
|
2063 | Memory-maps a file (or anonymous memory range) and attaches it to the |
|
|
2064 | given C<$scalar>, which will act like a string scalar. Returns true on |
|
|
2065 | success, and false otherwise. |
|
|
2066 | |
|
|
2067 | The only operations allowed on the scalar are C<substr>/C<vec> that don't |
|
|
2068 | change the string length, and most read-only operations such as copying it |
|
|
2069 | or searching it with regexes and so on. |
|
|
2070 | |
|
|
2071 | Anything else is unsafe and will, at best, result in memory leaks. |
|
|
2072 | |
|
|
2073 | The memory map associated with the C<$scalar> is automatically removed |
|
|
2074 | when the C<$scalar> is destroyed, or when the C<IO::AIO::mmap> or |
|
|
2075 | C<IO::AIO::munmap> functions are called. |
|
|
2076 | |
|
|
2077 | This calls the C<mmap>(2) function internally. See your system's manual |
|
|
2078 | page for details on the C<$length>, C<$prot> and C<$flags> parameters. |
|
|
2079 | |
|
|
2080 | The C<$length> must be larger than zero and smaller than the actual |
|
|
2081 | filesize. |
|
|
2082 | |
|
|
2083 | C<$prot> is a combination of C<IO::AIO::PROT_NONE>, C<IO::AIO::PROT_EXEC>, |
|
|
2084 | C<IO::AIO::PROT_READ> and/or C<IO::AIO::PROT_WRITE>, |
|
|
2085 | |
|
|
2086 | C<$flags> can be a combination of |
|
|
2087 | C<IO::AIO::MAP_SHARED> or |
|
|
2088 | C<IO::AIO::MAP_PRIVATE>, |
|
|
2089 | or a number of system-specific flags (when not available, the are C<0>): |
|
|
2090 | C<IO::AIO::MAP_ANONYMOUS> (which is set to C<MAP_ANON> if your system only provides this constant), |
|
|
2091 | C<IO::AIO::MAP_LOCKED>, |
|
|
2092 | C<IO::AIO::MAP_NORESERVE>, |
|
|
2093 | C<IO::AIO::MAP_POPULATE>, |
|
|
2094 | C<IO::AIO::MAP_NONBLOCK>, |
|
|
2095 | C<IO::AIO::MAP_FIXED>, |
|
|
2096 | C<IO::AIO::MAP_GROWSDOWN>, |
|
|
2097 | C<IO::AIO::MAP_32BIT>, |
|
|
2098 | C<IO::AIO::MAP_HUGETLB> or |
|
|
2099 | C<IO::AIO::MAP_STACK>. |
|
|
2100 | |
|
|
2101 | If C<$fh> is C<undef>, then a file descriptor of C<-1> is passed. |
|
|
2102 | |
|
|
2103 | C<$offset> is the offset from the start of the file - it generally must be |
|
|
2104 | a multiple of C<IO::AIO::PAGESIZE> and defaults to C<0>. |
|
|
2105 | |
|
|
2106 | Example: |
|
|
2107 | |
|
|
2108 | use Digest::MD5; |
|
|
2109 | use IO::AIO; |
|
|
2110 | |
|
|
2111 | open my $fh, "<verybigfile" |
|
|
2112 | or die "$!"; |
|
|
2113 | |
|
|
2114 | IO::AIO::mmap my $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh |
|
|
2115 | or die "verybigfile: $!"; |
|
|
2116 | |
|
|
2117 | my $fast_md5 = md5 $data; |
|
|
2118 | |
|
|
2119 | =item IO::AIO::munmap $scalar |
|
|
2120 | |
|
|
2121 | Removes a previous mmap and undefines the C<$scalar>. |
|
|
2122 | |
|
|
2123 | =item IO::AIO::munlock $scalar, $offset = 0, $length = undef |
|
|
2124 | |
|
|
2125 | Calls the C<munlock> function, undoing the effects of a previous |
|
|
2126 | C<aio_mlock> call (see its description for details). |
|
|
2127 | |
|
|
2128 | =item IO::AIO::munlockall |
|
|
2129 | |
|
|
2130 | Calls the C<munlockall> function. |
|
|
2131 | |
|
|
2132 | On systems that do not implement C<munlockall>, this function returns |
|
|
2133 | ENOSYS, otherwise the return value of C<munlockall>. |
|
|
2134 | |
|
|
2135 | =item IO::AIO::splice $r_fh, $r_off, $w_fh, $w_off, $length, $flags |
|
|
2136 | |
|
|
2137 | Calls the GNU/Linux C<splice(2)> syscall, if available. If C<$r_off> or |
|
|
2138 | C<$w_off> are C<undef>, then C<NULL> is passed for these, otherwise they |
|
|
2139 | should be the file offset. |
|
|
2140 | |
|
|
2141 | C<$r_fh> and C<$w_fh> should not refer to the same file, as splice might |
|
|
2142 | silently corrupt the data in this case. |
|
|
2143 | |
|
|
2144 | The following symbol flag values are available: C<IO::AIO::SPLICE_F_MOVE>, |
|
|
2145 | C<IO::AIO::SPLICE_F_NONBLOCK>, C<IO::AIO::SPLICE_F_MORE> and |
|
|
2146 | C<IO::AIO::SPLICE_F_GIFT>. |
|
|
2147 | |
|
|
2148 | See the C<splice(2)> manpage for details. |
|
|
2149 | |
|
|
2150 | =item IO::AIO::tee $r_fh, $w_fh, $length, $flags |
|
|
2151 | |
|
|
2152 | Calls the GNU/Linux C<tee(2)> syscall, see its manpage and the |
|
|
2153 | description for C<IO::AIO::splice> above for details. |
|
|
2154 | |
|
|
2155 | =item $actual_size = IO::AIO::pipesize $r_fh[, $new_size] |
|
|
2156 | |
|
|
2157 | Attempts to query or change the pipe buffer size. Obviously works only |
|
|
2158 | on pipes, and currently works only on GNU/Linux systems, and fails with |
|
|
2159 | C<-1>/C<ENOSYS> everywhere else. If anybody knows how to influence pipe buffer |
|
|
2160 | size on other systems, drop me a note. |
|
|
2161 | |
|
|
2162 | =item ($rfh, $wfh) = IO::AIO::pipe2 [$flags] |
|
|
2163 | |
|
|
2164 | This is a direct interface to the Linux L<pipe2(2)> system call. If |
|
|
2165 | C<$flags> is missing or C<0>, then this should be the same as a call to |
|
|
2166 | perl's built-in C<pipe> function and create a new pipe, and works on |
|
|
2167 | systems that lack the pipe2 syscall. On win32, this case invokes C<_pipe |
|
|
2168 | (..., 4096, O_BINARY)>. |
|
|
2169 | |
|
|
2170 | If C<$flags> is non-zero, it tries to invoke the pipe2 system call with |
|
|
2171 | the given flags (Linux 2.6.27, glibc 2.9). |
|
|
2172 | |
|
|
2173 | On success, the read and write file handles are returned. |
|
|
2174 | |
|
|
2175 | On error, nothing will be returned. If the pipe2 syscall is missing and |
|
|
2176 | C<$flags> is non-zero, fails with C<ENOSYS>. |
|
|
2177 | |
|
|
2178 | Please refer to L<pipe2(2)> for more info on the C<$flags>, but at the |
|
|
2179 | time of this writing, C<IO::AIO::O_CLOEXEC>, C<IO::AIO::O_NONBLOCK> and |
|
|
2180 | C<IO::AIO::O_DIRECT> (Linux 3.4, for packet-based pipes) were supported. |
|
|
2181 | |
|
|
2182 | =back |
|
|
2183 | |
1300 | =cut |
2184 | =cut |
1301 | |
2185 | |
1302 | min_parallel 8; |
2186 | min_parallel 8; |
1303 | |
2187 | |
1304 | END { flush } |
2188 | END { flush } |
1305 | |
2189 | |
1306 | 1; |
2190 | 1; |
1307 | |
2191 | |
|
|
2192 | =head1 EVENT LOOP INTEGRATION |
|
|
2193 | |
|
|
2194 | It is recommended to use L<AnyEvent::AIO> to integrate IO::AIO |
|
|
2195 | automatically into many event loops: |
|
|
2196 | |
|
|
2197 | # AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...) |
|
|
2198 | use AnyEvent::AIO; |
|
|
2199 | |
|
|
2200 | You can also integrate IO::AIO manually into many event loops, here are |
|
|
2201 | some examples of how to do this: |
|
|
2202 | |
|
|
2203 | # EV integration |
|
|
2204 | my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; |
|
|
2205 | |
|
|
2206 | # Event integration |
|
|
2207 | Event->io (fd => IO::AIO::poll_fileno, |
|
|
2208 | poll => 'r', |
|
|
2209 | cb => \&IO::AIO::poll_cb); |
|
|
2210 | |
|
|
2211 | # Glib/Gtk2 integration |
|
|
2212 | add_watch Glib::IO IO::AIO::poll_fileno, |
|
|
2213 | in => sub { IO::AIO::poll_cb; 1 }; |
|
|
2214 | |
|
|
2215 | # Tk integration |
|
|
2216 | Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "", |
|
|
2217 | readable => \&IO::AIO::poll_cb); |
|
|
2218 | |
|
|
2219 | # Danga::Socket integration |
|
|
2220 | Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => |
|
|
2221 | \&IO::AIO::poll_cb); |
|
|
2222 | |
1308 | =head2 FORK BEHAVIOUR |
2223 | =head2 FORK BEHAVIOUR |
1309 | |
2224 | |
1310 | This module should do "the right thing" when the process using it forks: |
2225 | Usage of pthreads in a program changes the semantics of fork |
|
|
2226 | considerably. Specifically, only async-safe functions can be called after |
|
|
2227 | fork. Perl doesn't know about this, so in general, you cannot call fork |
|
|
2228 | with defined behaviour in perl if pthreads are involved. IO::AIO uses |
|
|
2229 | pthreads, so this applies, but many other extensions and (for inexplicable |
|
|
2230 | reasons) perl itself often is linked against pthreads, so this limitation |
|
|
2231 | applies to quite a lot of perls. |
1311 | |
2232 | |
1312 | Before the fork, IO::AIO enters a quiescent state where no requests |
2233 | This module no longer tries to fight your OS, or POSIX. That means IO::AIO |
1313 | can be added in other threads and no results will be processed. After |
2234 | only works in the process that loaded it. Forking is fully supported, but |
1314 | the fork the parent simply leaves the quiescent state and continues |
2235 | using IO::AIO in the child is not. |
1315 | request/result processing, while the child frees the request/result queue |
|
|
1316 | (so that the requests started before the fork will only be handled in the |
|
|
1317 | parent). Threads will be started on demand until the limit set in the |
|
|
1318 | parent process has been reached again. |
|
|
1319 | |
2236 | |
1320 | In short: the parent will, after a short pause, continue as if fork had |
2237 | You might get around by not I<using> IO::AIO before (or after) |
1321 | not been called, while the child will act as if IO::AIO has not been used |
2238 | forking. You could also try to call the L<IO::AIO::reinit> function in the |
1322 | yet. |
2239 | child: |
|
|
2240 | |
|
|
2241 | =over 4 |
|
|
2242 | |
|
|
2243 | =item IO::AIO::reinit |
|
|
2244 | |
|
|
2245 | Abandons all current requests and I/O threads and simply reinitialises all |
|
|
2246 | data structures. This is not an operation supported by any standards, but |
|
|
2247 | happens to work on GNU/Linux and some newer BSD systems. |
|
|
2248 | |
|
|
2249 | The only reasonable use for this function is to call it after forking, if |
|
|
2250 | C<IO::AIO> was used in the parent. Calling it while IO::AIO is active in |
|
|
2251 | the process will result in undefined behaviour. Calling it at any time |
|
|
2252 | will also result in any undefined (by POSIX) behaviour. |
|
|
2253 | |
|
|
2254 | =back |
1323 | |
2255 | |
1324 | =head2 MEMORY USAGE |
2256 | =head2 MEMORY USAGE |
1325 | |
2257 | |
1326 | Per-request usage: |
2258 | Per-request usage: |
1327 | |
2259 | |