… | |
… | |
5 | =head1 SYNOPSIS |
5 | =head1 SYNOPSIS |
6 | |
6 | |
7 | use IO::AIO; |
7 | use IO::AIO; |
8 | |
8 | |
9 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
9 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
10 | my ($fh) = @_; |
10 | my $fh = shift |
|
|
11 | or die "/etc/passwd: $!"; |
11 | ... |
12 | ... |
12 | }; |
13 | }; |
13 | |
14 | |
14 | aio_unlink "/tmp/file", sub { }; |
15 | aio_unlink "/tmp/file", sub { }; |
15 | |
16 | |
… | |
… | |
25 | $req->cancel; # cancel request if still in queue |
26 | $req->cancel; # cancel request if still in queue |
26 | |
27 | |
27 | my $grp = aio_group sub { print "all stats done\n" }; |
28 | my $grp = aio_group sub { print "all stats done\n" }; |
28 | add $grp aio_stat "..." for ...; |
29 | add $grp aio_stat "..." for ...; |
29 | |
30 | |
|
|
31 | # AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...) |
|
|
32 | use AnyEvent::AIO; |
|
|
33 | |
30 | # AnyEvent integration |
34 | # EV integration |
31 | open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!"; |
35 | my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; |
32 | my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb }); |
|
|
33 | |
36 | |
34 | # Event integration |
37 | # Event integration |
35 | Event->io (fd => IO::AIO::poll_fileno, |
38 | Event->io (fd => IO::AIO::poll_fileno, |
36 | poll => 'r', |
39 | poll => 'r', |
37 | cb => \&IO::AIO::poll_cb); |
40 | cb => \&IO::AIO::poll_cb); |
… | |
… | |
49 | \&IO::AIO::poll_cb); |
52 | \&IO::AIO::poll_cb); |
50 | |
53 | |
51 | =head1 DESCRIPTION |
54 | =head1 DESCRIPTION |
52 | |
55 | |
53 | This module implements asynchronous I/O using whatever means your |
56 | This module implements asynchronous I/O using whatever means your |
54 | operating system supports. |
57 | operating system supports. It is implemented as an interface to C<libeio> |
|
|
58 | (L<http://software.schmorp.de/pkg/libeio.html>). |
|
|
59 | |
|
|
60 | Asynchronous means that operations that can normally block your program |
|
|
61 | (e.g. reading from disk) will be done asynchronously: the operation |
|
|
62 | will still block, but you can do something else in the meantime. This |
|
|
63 | is extremely useful for programs that need to stay interactive even |
|
|
64 | when doing heavy I/O (GUI programs, high performance network servers |
|
|
65 | etc.), but can also be used to easily do operations in parallel that are |
|
|
66 | normally done sequentially, e.g. stat'ing many files, which is much faster |
|
|
67 | on a RAID volume or over NFS when you do a number of stat operations |
|
|
68 | concurrently. |
|
|
69 | |
|
|
70 | While most of this works on all types of file descriptors (for |
|
|
71 | example sockets), using these functions on file descriptors that |
|
|
72 | support nonblocking operation (again, sockets, pipes etc.) is |
|
|
73 | very inefficient. Use an event loop for that (such as the L<EV> |
|
|
74 | module): IO::AIO will naturally fit into such an event loop itself. |
55 | |
75 | |
56 | In this version, a number of threads are started that execute your |
76 | In this version, a number of threads are started that execute your |
57 | requests and signal their completion. You don't need thread support |
77 | requests and signal their completion. You don't need thread support |
58 | in perl, and the threads created by this module will not be visible |
78 | in perl, and the threads created by this module will not be visible |
59 | to perl. In the future, this module might make use of the native aio |
79 | to perl. In the future, this module might make use of the native aio |
60 | functions available on many operating systems. However, they are often |
80 | functions available on many operating systems. However, they are often |
61 | not well-supported or restricted (Linux doesn't allow them on normal |
81 | not well-supported or restricted (GNU/Linux doesn't allow them on normal |
62 | files currently, for example), and they would only support aio_read and |
82 | files currently, for example), and they would only support aio_read and |
63 | aio_write, so the remaining functionality would have to be implemented |
83 | aio_write, so the remaining functionality would have to be implemented |
64 | using threads anyway. |
84 | using threads anyway. |
65 | |
85 | |
66 | Although the module will work with in the presence of other (Perl-) |
86 | Although the module will work in the presence of other (Perl-) threads, |
67 | threads, it is currently not reentrant in any way, so use appropriate |
87 | it is currently not reentrant in any way, so use appropriate locking |
68 | locking yourself, always call C<poll_cb> from within the same thread, or |
88 | yourself, always call C<poll_cb> from within the same thread, or never |
69 | never call C<poll_cb> (or other C<aio_> functions) recursively. |
89 | call C<poll_cb> (or other C<aio_> functions) recursively. |
|
|
90 | |
|
|
91 | =head2 EXAMPLE |
|
|
92 | |
|
|
93 | This is a simple example that uses the EV module and loads |
|
|
94 | F</etc/passwd> asynchronously: |
|
|
95 | |
|
|
96 | use Fcntl; |
|
|
97 | use EV; |
|
|
98 | use IO::AIO; |
|
|
99 | |
|
|
100 | # register the IO::AIO callback with EV |
|
|
101 | my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb; |
|
|
102 | |
|
|
103 | # queue the request to open /etc/passwd |
|
|
104 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
|
|
105 | my $fh = shift |
|
|
106 | or die "error while opening: $!"; |
|
|
107 | |
|
|
108 | # stat'ing filehandles is generally non-blocking |
|
|
109 | my $size = -s $fh; |
|
|
110 | |
|
|
111 | # queue a request to read the file |
|
|
112 | my $contents; |
|
|
113 | aio_read $fh, 0, $size, $contents, 0, sub { |
|
|
114 | $_[0] == $size |
|
|
115 | or die "short read: $!"; |
|
|
116 | |
|
|
117 | close $fh; |
|
|
118 | |
|
|
119 | # file contents now in $contents |
|
|
120 | print $contents; |
|
|
121 | |
|
|
122 | # exit event loop and program |
|
|
123 | EV::unloop; |
|
|
124 | }; |
|
|
125 | }; |
|
|
126 | |
|
|
127 | # possibly queue up other requests, or open GUI windows, |
|
|
128 | # check for sockets etc. etc. |
|
|
129 | |
|
|
130 | # process events as long as there are some: |
|
|
131 | EV::loop; |
70 | |
132 | |
71 | =head1 REQUEST ANATOMY AND LIFETIME |
133 | =head1 REQUEST ANATOMY AND LIFETIME |
72 | |
134 | |
73 | Every C<aio_*> function creates a request. which is a C data structure not |
135 | Every C<aio_*> function creates a request. which is a C data structure not |
74 | directly visible to Perl. |
136 | directly visible to Perl. |
… | |
… | |
116 | Request has reached the end of its lifetime and holds no resources anymore |
178 | Request has reached the end of its lifetime and holds no resources anymore |
117 | (except possibly for the Perl object, but its connection to the actual |
179 | (except possibly for the Perl object, but its connection to the actual |
118 | aio request is severed and calling its methods will either do nothing or |
180 | aio request is severed and calling its methods will either do nothing or |
119 | result in a runtime error). |
181 | result in a runtime error). |
120 | |
182 | |
|
|
183 | =back |
|
|
184 | |
121 | =cut |
185 | =cut |
122 | |
186 | |
123 | package IO::AIO; |
187 | package IO::AIO; |
124 | |
188 | |
125 | no warnings; |
189 | use Carp (); |
126 | use strict 'vars'; |
190 | |
|
|
191 | use common::sense; |
127 | |
192 | |
128 | use base 'Exporter'; |
193 | use base 'Exporter'; |
129 | |
194 | |
130 | BEGIN { |
195 | BEGIN { |
131 | our $VERSION = '2.0'; |
196 | our $VERSION = '3.3'; |
132 | |
197 | |
133 | our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat |
198 | our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close |
134 | aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink |
199 | aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx |
135 | aio_fsync aio_fdatasync aio_readahead aio_rename aio_link aio_move |
200 | aio_scandir aio_symlink aio_readlink aio_sync aio_fsync |
136 | aio_group aio_nop); |
201 | aio_fdatasync aio_sync_file_range aio_pathsync aio_readahead |
|
|
202 | aio_rename aio_link aio_move aio_copy aio_group |
|
|
203 | aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown |
|
|
204 | aio_chmod aio_utime aio_truncate); |
|
|
205 | |
137 | our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice)); |
206 | our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice)); |
138 | our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush |
207 | our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush |
139 | min_parallel max_parallel nreqs); |
208 | min_parallel max_parallel max_idle |
|
|
209 | nreqs nready npending nthreads |
|
|
210 | max_poll_time max_poll_reqs |
|
|
211 | sendfile fadvise); |
|
|
212 | |
|
|
213 | push @AIO_REQ, qw(aio_busy); # not exported |
140 | |
214 | |
141 | @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; |
215 | @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; |
142 | |
216 | |
143 | require XSLoader; |
217 | require XSLoader; |
144 | XSLoader::load ("IO::AIO", $VERSION); |
218 | XSLoader::load ("IO::AIO", $VERSION); |
145 | } |
219 | } |
146 | |
220 | |
147 | =head1 FUNCTIONS |
221 | =head1 FUNCTIONS |
148 | |
222 | |
149 | =head2 AIO FUNCTIONS |
223 | =head2 AIO REQUEST FUNCTIONS |
150 | |
224 | |
151 | All the C<aio_*> calls are more or less thin wrappers around the syscall |
225 | All the C<aio_*> calls are more or less thin wrappers around the syscall |
152 | with the same name (sans C<aio_>). The arguments are similar or identical, |
226 | with the same name (sans C<aio_>). The arguments are similar or identical, |
153 | and they all accept an additional (and optional) C<$callback> argument |
227 | and they all accept an additional (and optional) C<$callback> argument |
154 | which must be a code reference. This code reference will get called with |
228 | which must be a code reference. This code reference will get called with |
155 | the syscall return code (e.g. most syscalls return C<-1> on error, unlike |
229 | the syscall return code (e.g. most syscalls return C<-1> on error, unlike |
156 | perl, which usually delivers "false") as it's sole argument when the given |
230 | perl, which usually delivers "false") as its sole argument after the given |
157 | syscall has been executed asynchronously. |
231 | syscall has been executed asynchronously. |
158 | |
232 | |
159 | All functions expecting a filehandle keep a copy of the filehandle |
233 | All functions expecting a filehandle keep a copy of the filehandle |
160 | internally until the request has finished. |
234 | internally until the request has finished. |
161 | |
235 | |
162 | All requests return objects of type L<IO::AIO::REQ> that allow further |
236 | All functions return request objects of type L<IO::AIO::REQ> that allow |
163 | manipulation of those requests while they are in-flight. |
237 | further manipulation of those requests while they are in-flight. |
164 | |
238 | |
165 | The pathnames you pass to these routines I<must> be absolute and |
239 | The pathnames you pass to these routines I<must> be absolute and |
166 | encoded in byte form. The reason for the former is that at the time the |
240 | encoded as octets. The reason for the former is that at the time the |
167 | request is being executed, the current working directory could have |
241 | request is being executed, the current working directory could have |
168 | changed. Alternatively, you can make sure that you never change the |
242 | changed. Alternatively, you can make sure that you never change the |
169 | current working directory. |
243 | current working directory anywhere in the program and then use relative |
|
|
244 | paths. |
170 | |
245 | |
171 | To encode pathnames to byte form, either make sure you either: a) |
246 | To encode pathnames as octets, either make sure you either: a) always pass |
172 | always pass in filenames you got from outside (command line, readdir |
247 | in filenames you got from outside (command line, readdir etc.) without |
173 | etc.), b) are ASCII or ISO 8859-1, c) use the Encode module and encode |
248 | tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module and encode |
174 | your pathnames to the locale (or other) encoding in effect in the user |
249 | your pathnames to the locale (or other) encoding in effect in the user |
175 | environment, d) use Glib::filename_from_unicode on unicode filenames or e) |
250 | environment, d) use Glib::filename_from_unicode on unicode filenames or e) |
176 | use something else. |
251 | use something else to ensure your scalar has the correct contents. |
|
|
252 | |
|
|
253 | This works, btw. independent of the internal UTF-8 bit, which IO::AIO |
|
|
254 | handles correctly whether it is set or not. |
177 | |
255 | |
178 | =over 4 |
256 | =over 4 |
179 | |
257 | |
180 | =item aioreq_pri $pri |
258 | =item $prev_pri = aioreq_pri [$pri] |
181 | |
259 | |
182 | Sets the priority for the next aio request. The default priority |
260 | Returns the priority value that would be used for the next request and, if |
|
|
261 | C<$pri> is given, sets the priority for the next aio request. |
|
|
262 | |
183 | is C<0>, the minimum and maximum priorities are C<-4> and C<4>, |
263 | The default priority is C<0>, the minimum and maximum priorities are C<-4> |
184 | respectively. Requests with higher priority will be serviced first. |
264 | and C<4>, respectively. Requests with higher priority will be serviced |
|
|
265 | first. |
185 | |
266 | |
186 | The priority will be reset to C<0> after each call to one of the C<aio_> |
267 | The priority will be reset to C<0> after each call to one of the C<aio_*> |
187 | functions. |
268 | functions. |
188 | |
269 | |
189 | Example: open a file with low priority, then read something from it with |
270 | Example: open a file with low priority, then read something from it with |
190 | higher priority so the read request is serviced before other low priority |
271 | higher priority so the read request is serviced before other low priority |
191 | open requests (potentially spamming the cache): |
272 | open requests (potentially spamming the cache): |
… | |
… | |
198 | aio_read $_[0], ..., sub { |
279 | aio_read $_[0], ..., sub { |
199 | ... |
280 | ... |
200 | }; |
281 | }; |
201 | }; |
282 | }; |
202 | |
283 | |
|
|
284 | |
203 | =item aioreq_nice $pri_adjust |
285 | =item aioreq_nice $pri_adjust |
204 | |
286 | |
205 | Similar to C<aioreq_pri>, but subtracts the given value from the current |
287 | Similar to C<aioreq_pri>, but subtracts the given value from the current |
206 | priority, so effects are cumulative. |
288 | priority, so the effect is cumulative. |
|
|
289 | |
207 | |
290 | |
208 | =item aio_open $pathname, $flags, $mode, $callback->($fh) |
291 | =item aio_open $pathname, $flags, $mode, $callback->($fh) |
209 | |
292 | |
210 | Asynchronously open or create a file and call the callback with a newly |
293 | Asynchronously open or create a file and call the callback with a newly |
211 | created filehandle for the file. |
294 | created filehandle for the file. |
… | |
… | |
217 | list. They are the same as used by C<sysopen>. |
300 | list. They are the same as used by C<sysopen>. |
218 | |
301 | |
219 | Likewise, C<$mode> specifies the mode of the newly created file, if it |
302 | Likewise, C<$mode> specifies the mode of the newly created file, if it |
220 | didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>, |
303 | didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>, |
221 | except that it is mandatory (i.e. use C<0> if you don't create new files, |
304 | except that it is mandatory (i.e. use C<0> if you don't create new files, |
222 | and C<0666> or C<0777> if you do). |
305 | and C<0666> or C<0777> if you do). Note that the C<$mode> will be modified |
|
|
306 | by the umask in effect then the request is being executed, so better never |
|
|
307 | change the umask. |
223 | |
308 | |
224 | Example: |
309 | Example: |
225 | |
310 | |
226 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
311 | aio_open "/etc/passwd", O_RDONLY, 0, sub { |
227 | if ($_[0]) { |
312 | if ($_[0]) { |
… | |
… | |
230 | } else { |
315 | } else { |
231 | die "open failed: $!\n"; |
316 | die "open failed: $!\n"; |
232 | } |
317 | } |
233 | }; |
318 | }; |
234 | |
319 | |
|
|
320 | |
235 | =item aio_close $fh, $callback->($status) |
321 | =item aio_close $fh, $callback->($status) |
236 | |
322 | |
237 | Asynchronously close a file and call the callback with the result |
323 | Asynchronously close a file and call the callback with the result |
238 | code. I<WARNING:> although accepted, you should not pass in a perl |
324 | code. |
239 | filehandle here, as perl will likely close the file descriptor another |
|
|
240 | time when the filehandle is destroyed. Normally, you can safely call perls |
|
|
241 | C<close> or just let filehandles go out of scope. |
|
|
242 | |
325 | |
243 | This is supposed to be a bug in the API, so that might change. It's |
326 | Unfortunately, you can't do this to perl. Perl I<insists> very strongly on |
244 | therefore best to avoid this function. |
327 | closing the file descriptor associated with the filehandle itself. |
|
|
328 | |
|
|
329 | Therefore, C<aio_close> will not close the filehandle - instead it will |
|
|
330 | use dup2 to overwrite the file descriptor with the write-end of a pipe |
|
|
331 | (the pipe fd will be created on demand and will be cached). |
|
|
332 | |
|
|
333 | Or in other words: the file descriptor will be closed, but it will not be |
|
|
334 | free for reuse until the perl filehandle is closed. |
|
|
335 | |
|
|
336 | =cut |
245 | |
337 | |
246 | =item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
338 | =item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
247 | |
339 | |
248 | =item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
340 | =item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
249 | |
341 | |
250 | Reads or writes C<length> bytes from the specified C<fh> and C<offset> |
342 | Reads or writes C<$length> bytes from or to the specified C<$fh> and |
251 | into the scalar given by C<data> and offset C<dataoffset> and calls the |
343 | C<$offset> into the scalar given by C<$data> and offset C<$dataoffset> |
252 | callback without the actual number of bytes read (or -1 on error, just |
344 | and calls the callback without the actual number of bytes read (or -1 on |
253 | like the syscall). |
345 | error, just like the syscall). |
|
|
346 | |
|
|
347 | C<aio_read> will, like C<sysread>, shrink or grow the C<$data> scalar to |
|
|
348 | offset plus the actual number of bytes read. |
|
|
349 | |
|
|
350 | If C<$offset> is undefined, then the current file descriptor offset will |
|
|
351 | be used (and updated), otherwise the file descriptor offset will not be |
|
|
352 | changed by these calls. |
|
|
353 | |
|
|
354 | If C<$length> is undefined in C<aio_write>, use the remaining length of |
|
|
355 | C<$data>. |
|
|
356 | |
|
|
357 | If C<$dataoffset> is less than zero, it will be counted from the end of |
|
|
358 | C<$data>. |
254 | |
359 | |
255 | The C<$data> scalar I<MUST NOT> be modified in any way while the request |
360 | The C<$data> scalar I<MUST NOT> be modified in any way while the request |
256 | is outstanding. Modifying it can result in segfaults or WW3 (if the |
361 | is outstanding. Modifying it can result in segfaults or World War III (if |
257 | necessary/optional hardware is installed). |
362 | the necessary/optional hardware is installed). |
258 | |
363 | |
259 | Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at |
364 | Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at |
260 | offset C<0> within the scalar: |
365 | offset C<0> within the scalar: |
261 | |
366 | |
262 | aio_read $fh, 7, 15, $buffer, 0, sub { |
367 | aio_read $fh, 7, 15, $buffer, 0, sub { |
263 | $_[0] > 0 or die "read error: $!"; |
368 | $_[0] > 0 or die "read error: $!"; |
264 | print "read $_[0] bytes: <$buffer>\n"; |
369 | print "read $_[0] bytes: <$buffer>\n"; |
265 | }; |
370 | }; |
266 | |
371 | |
267 | =item aio_move $srcpath, $dstpath, $callback->($status) |
|
|
268 | |
|
|
269 | Try to move the I<file> (directories not supported as either source or |
|
|
270 | destination) from C<$srcpath> to C<$dstpath> and call the callback with |
|
|
271 | the C<0> (error) or C<-1> ok. |
|
|
272 | |
|
|
273 | This is a composite request that tries to rename(2) the file first. If |
|
|
274 | rename files with C<EXDEV>, it creates the destination file with mode 0200 |
|
|
275 | and copies the contents of the source file into it using C<aio_sendfile>, |
|
|
276 | followed by restoring atime, mtime, access mode and uid/gid, in that |
|
|
277 | order, and unlinking the C<$srcpath>. |
|
|
278 | |
|
|
279 | If an error occurs, the partial destination file will be unlinked, if |
|
|
280 | possible, except when setting atime, mtime, access mode and uid/gid, where |
|
|
281 | errors are being ignored. |
|
|
282 | |
|
|
283 | =cut |
|
|
284 | |
|
|
285 | sub aio_move($$$) { |
|
|
286 | my ($src, $dst, $cb) = @_; |
|
|
287 | |
|
|
288 | my $grp = aio_group $cb; |
|
|
289 | |
|
|
290 | add $grp aio_rename $src, $dst, sub { |
|
|
291 | if ($_[0] && $! == EXDEV) { |
|
|
292 | add $grp aio_open $src, O_RDONLY, 0, sub { |
|
|
293 | if (my $src_fh = $_[0]) { |
|
|
294 | my @stat = stat $src_fh; |
|
|
295 | |
|
|
296 | add $grp aio_open $dst, O_WRONLY, 0200, sub { |
|
|
297 | if (my $dst_fh = $_[0]) { |
|
|
298 | add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub { |
|
|
299 | close $src_fh; |
|
|
300 | |
|
|
301 | if ($_[0] == $stat[7]) { |
|
|
302 | utime $stat[8], $stat[9], $dst; |
|
|
303 | chmod $stat[2] & 07777, $dst_fh; |
|
|
304 | chown $stat[4], $stat[5], $dst_fh; |
|
|
305 | close $dst_fh; |
|
|
306 | |
|
|
307 | add $grp aio_unlink $src, sub { |
|
|
308 | $grp->result ($_[0]); |
|
|
309 | }; |
|
|
310 | } else { |
|
|
311 | my $errno = $!; |
|
|
312 | add $grp aio_unlink $dst, sub { |
|
|
313 | $! = $errno; |
|
|
314 | $grp->result (-1); |
|
|
315 | }; |
|
|
316 | } |
|
|
317 | }; |
|
|
318 | } else { |
|
|
319 | $grp->result (-1); |
|
|
320 | } |
|
|
321 | }, |
|
|
322 | |
|
|
323 | } else { |
|
|
324 | $grp->result (-1); |
|
|
325 | } |
|
|
326 | }; |
|
|
327 | } else { |
|
|
328 | $grp->result ($_[0]); |
|
|
329 | } |
|
|
330 | }; |
|
|
331 | |
|
|
332 | $grp |
|
|
333 | } |
|
|
334 | |
372 | |
335 | =item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) |
373 | =item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) |
336 | |
374 | |
337 | Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts |
375 | Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts |
338 | reading at byte offset C<$in_offset>, and starts writing at the current |
376 | reading at byte offset C<$in_offset>, and starts writing at the current |
… | |
… | |
352 | C<$in_fh> than are written, and there is no way to find out how many |
390 | C<$in_fh> than are written, and there is no way to find out how many |
353 | bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only |
391 | bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only |
354 | provides the number of bytes written to C<$out_fh>. Only if the result |
392 | provides the number of bytes written to C<$out_fh>. Only if the result |
355 | value equals C<$length> one can assume that C<$length> bytes have been |
393 | value equals C<$length> one can assume that C<$length> bytes have been |
356 | read. |
394 | read. |
|
|
395 | |
357 | |
396 | |
358 | =item aio_readahead $fh,$offset,$length, $callback->($retval) |
397 | =item aio_readahead $fh,$offset,$length, $callback->($retval) |
359 | |
398 | |
360 | C<aio_readahead> populates the page cache with data from a file so that |
399 | C<aio_readahead> populates the page cache with data from a file so that |
361 | subsequent reads from that file will not block on disk I/O. The C<$offset> |
400 | subsequent reads from that file will not block on disk I/O. The C<$offset> |
… | |
… | |
367 | file. The current file offset of the file is left unchanged. |
406 | file. The current file offset of the file is left unchanged. |
368 | |
407 | |
369 | If that syscall doesn't exist (likely if your OS isn't Linux) it will be |
408 | If that syscall doesn't exist (likely if your OS isn't Linux) it will be |
370 | emulated by simply reading the data, which would have a similar effect. |
409 | emulated by simply reading the data, which would have a similar effect. |
371 | |
410 | |
|
|
411 | |
372 | =item aio_stat $fh_or_path, $callback->($status) |
412 | =item aio_stat $fh_or_path, $callback->($status) |
373 | |
413 | |
374 | =item aio_lstat $fh, $callback->($status) |
414 | =item aio_lstat $fh, $callback->($status) |
375 | |
415 | |
376 | Works like perl's C<stat> or C<lstat> in void context. The callback will |
416 | Works like perl's C<stat> or C<lstat> in void context. The callback will |
… | |
… | |
389 | aio_stat "/etc/passwd", sub { |
429 | aio_stat "/etc/passwd", sub { |
390 | $_[0] and die "stat failed: $!"; |
430 | $_[0] and die "stat failed: $!"; |
391 | print "size is ", -s _, "\n"; |
431 | print "size is ", -s _, "\n"; |
392 | }; |
432 | }; |
393 | |
433 | |
|
|
434 | |
|
|
435 | =item aio_utime $fh_or_path, $atime, $mtime, $callback->($status) |
|
|
436 | |
|
|
437 | Works like perl's C<utime> function (including the special case of $atime |
|
|
438 | and $mtime being undef). Fractional times are supported if the underlying |
|
|
439 | syscalls support them. |
|
|
440 | |
|
|
441 | When called with a pathname, uses utimes(2) if available, otherwise |
|
|
442 | utime(2). If called on a file descriptor, uses futimes(2) if available, |
|
|
443 | otherwise returns ENOSYS, so this is not portable. |
|
|
444 | |
|
|
445 | Examples: |
|
|
446 | |
|
|
447 | # set atime and mtime to current time (basically touch(1)): |
|
|
448 | aio_utime "path", undef, undef; |
|
|
449 | # set atime to current time and mtime to beginning of the epoch: |
|
|
450 | aio_utime "path", time, undef; # undef==0 |
|
|
451 | |
|
|
452 | |
|
|
453 | =item aio_chown $fh_or_path, $uid, $gid, $callback->($status) |
|
|
454 | |
|
|
455 | Works like perl's C<chown> function, except that C<undef> for either $uid |
|
|
456 | or $gid is being interpreted as "do not change" (but -1 can also be used). |
|
|
457 | |
|
|
458 | Examples: |
|
|
459 | |
|
|
460 | # same as "chown root path" in the shell: |
|
|
461 | aio_chown "path", 0, -1; |
|
|
462 | # same as above: |
|
|
463 | aio_chown "path", 0, undef; |
|
|
464 | |
|
|
465 | |
|
|
466 | =item aio_truncate $fh_or_path, $offset, $callback->($status) |
|
|
467 | |
|
|
468 | Works like truncate(2) or ftruncate(2). |
|
|
469 | |
|
|
470 | |
|
|
471 | =item aio_chmod $fh_or_path, $mode, $callback->($status) |
|
|
472 | |
|
|
473 | Works like perl's C<chmod> function. |
|
|
474 | |
|
|
475 | |
394 | =item aio_unlink $pathname, $callback->($status) |
476 | =item aio_unlink $pathname, $callback->($status) |
395 | |
477 | |
396 | Asynchronously unlink (delete) a file and call the callback with the |
478 | Asynchronously unlink (delete) a file and call the callback with the |
397 | result code. |
479 | result code. |
398 | |
480 | |
|
|
481 | |
|
|
482 | =item aio_mknod $path, $mode, $dev, $callback->($status) |
|
|
483 | |
|
|
484 | [EXPERIMENTAL] |
|
|
485 | |
|
|
486 | Asynchronously create a device node (or fifo). See mknod(2). |
|
|
487 | |
|
|
488 | The only (POSIX-) portable way of calling this function is: |
|
|
489 | |
|
|
490 | aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ... |
|
|
491 | |
|
|
492 | |
399 | =item aio_link $srcpath, $dstpath, $callback->($status) |
493 | =item aio_link $srcpath, $dstpath, $callback->($status) |
400 | |
494 | |
401 | Asynchronously create a new link to the existing object at C<$srcpath> at |
495 | Asynchronously create a new link to the existing object at C<$srcpath> at |
402 | the path C<$dstpath> and call the callback with the result code. |
496 | the path C<$dstpath> and call the callback with the result code. |
403 | |
497 | |
|
|
498 | |
404 | =item aio_symlink $srcpath, $dstpath, $callback->($status) |
499 | =item aio_symlink $srcpath, $dstpath, $callback->($status) |
405 | |
500 | |
406 | Asynchronously create a new symbolic link to the existing object at C<$srcpath> at |
501 | Asynchronously create a new symbolic link to the existing object at C<$srcpath> at |
407 | the path C<$dstpath> and call the callback with the result code. |
502 | the path C<$dstpath> and call the callback with the result code. |
408 | |
503 | |
|
|
504 | |
|
|
505 | =item aio_readlink $path, $callback->($link) |
|
|
506 | |
|
|
507 | Asynchronously read the symlink specified by C<$path> and pass it to |
|
|
508 | the callback. If an error occurs, nothing or undef gets passed to the |
|
|
509 | callback. |
|
|
510 | |
|
|
511 | |
409 | =item aio_rename $srcpath, $dstpath, $callback->($status) |
512 | =item aio_rename $srcpath, $dstpath, $callback->($status) |
410 | |
513 | |
411 | Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as |
514 | Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as |
412 | rename(2) and call the callback with the result code. |
515 | rename(2) and call the callback with the result code. |
413 | |
516 | |
|
|
517 | |
|
|
518 | =item aio_mkdir $pathname, $mode, $callback->($status) |
|
|
519 | |
|
|
520 | Asynchronously mkdir (create) a directory and call the callback with |
|
|
521 | the result code. C<$mode> will be modified by the umask at the time the |
|
|
522 | request is executed, so do not change your umask. |
|
|
523 | |
|
|
524 | |
414 | =item aio_rmdir $pathname, $callback->($status) |
525 | =item aio_rmdir $pathname, $callback->($status) |
415 | |
526 | |
416 | Asynchronously rmdir (delete) a directory and call the callback with the |
527 | Asynchronously rmdir (delete) a directory and call the callback with the |
417 | result code. |
528 | result code. |
|
|
529 | |
418 | |
530 | |
419 | =item aio_readdir $pathname, $callback->($entries) |
531 | =item aio_readdir $pathname, $callback->($entries) |
420 | |
532 | |
421 | Unlike the POSIX call of the same name, C<aio_readdir> reads an entire |
533 | Unlike the POSIX call of the same name, C<aio_readdir> reads an entire |
422 | directory (i.e. opendir + readdir + closedir). The entries will not be |
534 | directory (i.e. opendir + readdir + closedir). The entries will not be |
423 | sorted, and will B<NOT> include the C<.> and C<..> entries. |
535 | sorted, and will B<NOT> include the C<.> and C<..> entries. |
424 | |
536 | |
425 | The callback a single argument which is either C<undef> or an array-ref |
537 | The callback is passed a single argument which is either C<undef> or an |
426 | with the filenames. |
538 | array-ref with the filenames. |
|
|
539 | |
|
|
540 | |
|
|
541 | =item aio_readdirx $pathname, $flags, $callback->($entries, $flags) |
|
|
542 | |
|
|
543 | Quite similar to C<aio_readdir>, but the C<$flags> argument allows to tune |
|
|
544 | behaviour and output format. In case of an error, C<$entries> will be |
|
|
545 | C<undef>. |
|
|
546 | |
|
|
547 | The flags are a combination of the following constants, ORed together (the |
|
|
548 | flags will also be passed to the callback, possibly modified): |
|
|
549 | |
|
|
550 | =over 4 |
|
|
551 | |
|
|
552 | =item IO::AIO::READDIR_DENTS |
|
|
553 | |
|
|
554 | When this flag is off, then the callback gets an arrayref with of names |
|
|
555 | only (as with C<aio_readdir>), otherwise it gets an arrayref with |
|
|
556 | C<[$name, $type, $inode]> arrayrefs, each describing a single directory |
|
|
557 | entry in more detail. |
|
|
558 | |
|
|
559 | C<$name> is the name of the entry. |
|
|
560 | |
|
|
561 | C<$type> is one of the C<IO::AIO::DT_xxx> constants: |
|
|
562 | |
|
|
563 | C<IO::AIO::DT_UNKNOWN>, C<IO::AIO::DT_FIFO>, C<IO::AIO::DT_CHR>, C<IO::AIO::DT_DIR>, |
|
|
564 | C<IO::AIO::DT_BLK>, C<IO::AIO::DT_REG>, C<IO::AIO::DT_LNK>, C<IO::AIO::DT_SOCK>, |
|
|
565 | C<IO::AIO::DT_WHT>. |
|
|
566 | |
|
|
567 | C<IO::AIO::DT_UNKNOWN> means just that: readdir does not know. If you need to |
|
|
568 | know, you have to run stat yourself. Also, for speed reasons, the C<$type> |
|
|
569 | scalars are read-only: you can not modify them. |
|
|
570 | |
|
|
571 | C<$inode> is the inode number (which might not be exact on systems with 64 |
|
|
572 | bit inode numbers and 32 bit perls). This field has unspecified content on |
|
|
573 | systems that do not deliver the inode information. |
|
|
574 | |
|
|
575 | =item IO::AIO::READDIR_DIRS_FIRST |
|
|
576 | |
|
|
577 | When this flag is set, then the names will be returned in an order where |
|
|
578 | likely directories come first. This is useful when you need to quickly |
|
|
579 | find directories, or you want to find all directories while avoiding to |
|
|
580 | stat() each entry. |
|
|
581 | |
|
|
582 | If the system returns type information in readdir, then this is used |
|
|
583 | to find directories directly. Otherwise, likely directories are files |
|
|
584 | beginning with ".", or otherwise files with no dots, of which files with |
|
|
585 | short names are tried first. |
|
|
586 | |
|
|
587 | =item IO::AIO::READDIR_STAT_ORDER |
|
|
588 | |
|
|
589 | When this flag is set, then the names will be returned in an order |
|
|
590 | suitable for stat()'ing each one. That is, when you plan to stat() |
|
|
591 | all files in the given directory, then the returned order will likely |
|
|
592 | be fastest. |
|
|
593 | |
|
|
594 | If both this flag and C<IO::AIO::READDIR_DIRS_FIRST> are specified, then |
|
|
595 | the likely dirs come first, resulting in a less optimal stat order. |
|
|
596 | |
|
|
597 | =item IO::AIO::READDIR_FOUND_UNKNOWN |
|
|
598 | |
|
|
599 | This flag should not be set when calling C<aio_readdirx>. Instead, it |
|
|
600 | is being set by C<aio_readdirx>, when any of the C<$type>'s found were |
|
|
601 | C<IO::AIO::DT_UNKNOWN>. The absense of this flag therefore indicates that all |
|
|
602 | C<$type>'s are known, which can be used to speed up some algorithms. |
|
|
603 | |
|
|
604 | =back |
|
|
605 | |
|
|
606 | |
|
|
607 | =item aio_load $path, $data, $callback->($status) |
|
|
608 | |
|
|
609 | This is a composite request that tries to fully load the given file into |
|
|
610 | memory. Status is the same as with aio_read. |
|
|
611 | |
|
|
612 | =cut |
|
|
613 | |
|
|
614 | sub aio_load($$;$) { |
|
|
615 | my ($path, undef, $cb) = @_; |
|
|
616 | my $data = \$_[1]; |
|
|
617 | |
|
|
618 | my $pri = aioreq_pri; |
|
|
619 | my $grp = aio_group $cb; |
|
|
620 | |
|
|
621 | aioreq_pri $pri; |
|
|
622 | add $grp aio_open $path, O_RDONLY, 0, sub { |
|
|
623 | my $fh = shift |
|
|
624 | or return $grp->result (-1); |
|
|
625 | |
|
|
626 | aioreq_pri $pri; |
|
|
627 | add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub { |
|
|
628 | $grp->result ($_[0]); |
|
|
629 | }; |
|
|
630 | }; |
|
|
631 | |
|
|
632 | $grp |
|
|
633 | } |
|
|
634 | |
|
|
635 | =item aio_copy $srcpath, $dstpath, $callback->($status) |
|
|
636 | |
|
|
637 | Try to copy the I<file> (directories not supported as either source or |
|
|
638 | destination) from C<$srcpath> to C<$dstpath> and call the callback with |
|
|
639 | the C<0> (error) or C<-1> ok. |
|
|
640 | |
|
|
641 | This is a composite request that creates the destination file with |
|
|
642 | mode 0200 and copies the contents of the source file into it using |
|
|
643 | C<aio_sendfile>, followed by restoring atime, mtime, access mode and |
|
|
644 | uid/gid, in that order. |
|
|
645 | |
|
|
646 | If an error occurs, the partial destination file will be unlinked, if |
|
|
647 | possible, except when setting atime, mtime, access mode and uid/gid, where |
|
|
648 | errors are being ignored. |
|
|
649 | |
|
|
650 | =cut |
|
|
651 | |
|
|
652 | sub aio_copy($$;$) { |
|
|
653 | my ($src, $dst, $cb) = @_; |
|
|
654 | |
|
|
655 | my $pri = aioreq_pri; |
|
|
656 | my $grp = aio_group $cb; |
|
|
657 | |
|
|
658 | aioreq_pri $pri; |
|
|
659 | add $grp aio_open $src, O_RDONLY, 0, sub { |
|
|
660 | if (my $src_fh = $_[0]) { |
|
|
661 | my @stat = stat $src_fh; # hmm, might bock over nfs? |
|
|
662 | |
|
|
663 | aioreq_pri $pri; |
|
|
664 | add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub { |
|
|
665 | if (my $dst_fh = $_[0]) { |
|
|
666 | aioreq_pri $pri; |
|
|
667 | add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub { |
|
|
668 | if ($_[0] == $stat[7]) { |
|
|
669 | $grp->result (0); |
|
|
670 | close $src_fh; |
|
|
671 | |
|
|
672 | my $ch = sub { |
|
|
673 | aioreq_pri $pri; |
|
|
674 | add $grp aio_chmod $dst_fh, $stat[2] & 07777, sub { |
|
|
675 | aioreq_pri $pri; |
|
|
676 | add $grp aio_chown $dst_fh, $stat[4], $stat[5], sub { |
|
|
677 | aioreq_pri $pri; |
|
|
678 | add $grp aio_close $dst_fh; |
|
|
679 | } |
|
|
680 | }; |
|
|
681 | }; |
|
|
682 | |
|
|
683 | aioreq_pri $pri; |
|
|
684 | add $grp aio_utime $dst_fh, $stat[8], $stat[9], sub { |
|
|
685 | if ($_[0] < 0 && $! == ENOSYS) { |
|
|
686 | aioreq_pri $pri; |
|
|
687 | add $grp aio_utime $dst, $stat[8], $stat[9], $ch; |
|
|
688 | } else { |
|
|
689 | $ch->(); |
|
|
690 | } |
|
|
691 | }; |
|
|
692 | } else { |
|
|
693 | $grp->result (-1); |
|
|
694 | close $src_fh; |
|
|
695 | close $dst_fh; |
|
|
696 | |
|
|
697 | aioreq $pri; |
|
|
698 | add $grp aio_unlink $dst; |
|
|
699 | } |
|
|
700 | }; |
|
|
701 | } else { |
|
|
702 | $grp->result (-1); |
|
|
703 | } |
|
|
704 | }, |
|
|
705 | |
|
|
706 | } else { |
|
|
707 | $grp->result (-1); |
|
|
708 | } |
|
|
709 | }; |
|
|
710 | |
|
|
711 | $grp |
|
|
712 | } |
|
|
713 | |
|
|
714 | =item aio_move $srcpath, $dstpath, $callback->($status) |
|
|
715 | |
|
|
716 | Try to move the I<file> (directories not supported as either source or |
|
|
717 | destination) from C<$srcpath> to C<$dstpath> and call the callback with |
|
|
718 | the C<0> (error) or C<-1> ok. |
|
|
719 | |
|
|
720 | This is a composite request that tries to rename(2) the file first; if |
|
|
721 | rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if |
|
|
722 | that is successful, unlinks the C<$srcpath>. |
|
|
723 | |
|
|
724 | =cut |
|
|
725 | |
|
|
726 | sub aio_move($$;$) { |
|
|
727 | my ($src, $dst, $cb) = @_; |
|
|
728 | |
|
|
729 | my $pri = aioreq_pri; |
|
|
730 | my $grp = aio_group $cb; |
|
|
731 | |
|
|
732 | aioreq_pri $pri; |
|
|
733 | add $grp aio_rename $src, $dst, sub { |
|
|
734 | if ($_[0] && $! == EXDEV) { |
|
|
735 | aioreq_pri $pri; |
|
|
736 | add $grp aio_copy $src, $dst, sub { |
|
|
737 | $grp->result ($_[0]); |
|
|
738 | |
|
|
739 | if (!$_[0]) { |
|
|
740 | aioreq_pri $pri; |
|
|
741 | add $grp aio_unlink $src; |
|
|
742 | } |
|
|
743 | }; |
|
|
744 | } else { |
|
|
745 | $grp->result ($_[0]); |
|
|
746 | } |
|
|
747 | }; |
|
|
748 | |
|
|
749 | $grp |
|
|
750 | } |
427 | |
751 | |
428 | =item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) |
752 | =item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) |
429 | |
753 | |
430 | Scans a directory (similar to C<aio_readdir>) but additionally tries to |
754 | Scans a directory (similar to C<aio_readdir>) but additionally tries to |
431 | efficiently separate the entries of directory C<$path> into two sets of |
755 | efficiently separate the entries of directory C<$path> into two sets of |
… | |
… | |
433 | recurse into (everything else, including symlinks to directories). |
757 | recurse into (everything else, including symlinks to directories). |
434 | |
758 | |
435 | C<aio_scandir> is a composite request that creates of many sub requests_ |
759 | C<aio_scandir> is a composite request that creates of many sub requests_ |
436 | C<$maxreq> specifies the maximum number of outstanding aio requests that |
760 | C<$maxreq> specifies the maximum number of outstanding aio requests that |
437 | this function generates. If it is C<< <= 0 >>, then a suitable default |
761 | this function generates. If it is C<< <= 0 >>, then a suitable default |
438 | will be chosen (currently 6). |
762 | will be chosen (currently 4). |
439 | |
763 | |
440 | On error, the callback is called without arguments, otherwise it receives |
764 | On error, the callback is called without arguments, otherwise it receives |
441 | two array-refs with path-relative entry names. |
765 | two array-refs with path-relative entry names. |
442 | |
766 | |
443 | Example: |
767 | Example: |
… | |
… | |
450 | |
774 | |
451 | Implementation notes. |
775 | Implementation notes. |
452 | |
776 | |
453 | The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can. |
777 | The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can. |
454 | |
778 | |
|
|
779 | If readdir returns file type information, then this is used directly to |
|
|
780 | find directories. |
|
|
781 | |
455 | After reading the directory, the modification time, size etc. of the |
782 | Otherwise, after reading the directory, the modification time, size etc. |
456 | directory before and after the readdir is checked, and if they match (and |
783 | of the directory before and after the readdir is checked, and if they |
457 | isn't the current time), the link count will be used to decide how many |
784 | match (and isn't the current time), the link count will be used to decide |
458 | entries are directories (if >= 2). Otherwise, no knowledge of the number |
785 | how many entries are directories (if >= 2). Otherwise, no knowledge of the |
459 | of subdirectories will be assumed. |
786 | number of subdirectories will be assumed. |
460 | |
787 | |
461 | Then entries will be sorted into likely directories (everything without |
788 | Then entries will be sorted into likely directories a non-initial dot |
462 | a non-initial dot currently) and likely non-directories (everything |
789 | currently) and likely non-directories (see C<aio_readdirx>). Then every |
463 | else). Then every entry plus an appended C</.> will be C<stat>'ed, |
790 | entry plus an appended C</.> will be C<stat>'ed, likely directories first, |
464 | likely directories first. If that succeeds, it assumes that the entry |
791 | in order of their inode numbers. If that succeeds, it assumes that the |
465 | is a directory or a symlink to directory (which will be checked |
792 | entry is a directory or a symlink to directory (which will be checked |
466 | seperately). This is often faster than stat'ing the entry itself because |
793 | seperately). This is often faster than stat'ing the entry itself because |
467 | filesystems might detect the type of the entry without reading the inode |
794 | filesystems might detect the type of the entry without reading the inode |
468 | data (e.g. ext2fs filetype feature). |
795 | data (e.g. ext2fs filetype feature), even on systems that cannot return |
|
|
796 | the filetype information on readdir. |
469 | |
797 | |
470 | If the known number of directories (link count - 2) has been reached, the |
798 | If the known number of directories (link count - 2) has been reached, the |
471 | rest of the entries is assumed to be non-directories. |
799 | rest of the entries is assumed to be non-directories. |
472 | |
800 | |
473 | This only works with certainty on POSIX (= UNIX) filesystems, which |
801 | This only works with certainty on POSIX (= UNIX) filesystems, which |
… | |
… | |
477 | as those tend to return 0 or 1 as link counts, which disables the |
805 | as those tend to return 0 or 1 as link counts, which disables the |
478 | directory counting heuristic. |
806 | directory counting heuristic. |
479 | |
807 | |
480 | =cut |
808 | =cut |
481 | |
809 | |
482 | sub aio_scandir($$$) { |
810 | sub aio_scandir($$;$) { |
483 | my ($path, $maxreq, $cb) = @_; |
811 | my ($path, $maxreq, $cb) = @_; |
484 | |
812 | |
|
|
813 | my $pri = aioreq_pri; |
|
|
814 | |
485 | my $grp = aio_group $cb; |
815 | my $grp = aio_group $cb; |
486 | |
816 | |
487 | $maxreq = 6 if $maxreq <= 0; |
817 | $maxreq = 4 if $maxreq <= 0; |
488 | |
818 | |
489 | # stat once |
819 | # stat once |
|
|
820 | aioreq_pri $pri; |
490 | add $grp aio_stat $path, sub { |
821 | add $grp aio_stat $path, sub { |
491 | return $grp->result () if $_[0]; |
822 | return $grp->result () if $_[0]; |
492 | my $now = time; |
823 | my $now = time; |
493 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
824 | my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
494 | |
825 | |
495 | # read the directory entries |
826 | # read the directory entries |
|
|
827 | aioreq_pri $pri; |
496 | add $grp aio_readdir $path, sub { |
828 | add $grp aio_readdirx $path, READDIR_DIRS_FIRST, sub { |
497 | my $entries = shift |
829 | my $entries = shift |
498 | or return $grp->result (); |
830 | or return $grp->result (); |
499 | |
831 | |
500 | # stat the dir another time |
832 | # stat the dir another time |
|
|
833 | aioreq_pri $pri; |
501 | add $grp aio_stat $path, sub { |
834 | add $grp aio_stat $path, sub { |
502 | my $hash2 = join ":", (stat _)[0,1,3,7,9]; |
835 | my $hash2 = join ":", (stat _)[0,1,3,7,9]; |
503 | |
836 | |
504 | my $ndirs; |
837 | my $ndirs; |
505 | |
838 | |
506 | # take the slow route if anything looks fishy |
839 | # take the slow route if anything looks fishy |
507 | if ($hash1 ne $hash2 or (stat _)[9] == $now) { |
840 | if ($hash1 ne $hash2 or (stat _)[9] == $now) { |
508 | $ndirs = -1; |
841 | $ndirs = -1; |
509 | } else { |
842 | } else { |
510 | # if nlink == 2, we are finished |
843 | # if nlink == 2, we are finished |
511 | # on non-posix-fs's, we rely on nlink < 2 |
844 | # for non-posix-fs's, we rely on nlink < 2 |
512 | $ndirs = (stat _)[3] - 2 |
845 | $ndirs = (stat _)[3] - 2 |
513 | or return $grp->result ([], $entries); |
846 | or return $grp->result ([], $entries); |
514 | } |
847 | } |
515 | |
848 | |
516 | # sort into likely dirs and likely nondirs |
|
|
517 | # dirs == files without ".", short entries first |
|
|
518 | $entries = [map $_->[0], |
|
|
519 | sort { $b->[1] cmp $a->[1] } |
|
|
520 | map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length], |
|
|
521 | @$entries]; |
|
|
522 | |
|
|
523 | my (@dirs, @nondirs); |
849 | my (@dirs, @nondirs); |
524 | |
850 | |
525 | my $statgrp = add $grp aio_group sub { |
851 | my $statgrp = add $grp aio_group sub { |
526 | $grp->result (\@dirs, \@nondirs); |
852 | $grp->result (\@dirs, \@nondirs); |
527 | }; |
853 | }; |
528 | |
854 | |
529 | limit $statgrp $maxreq; |
855 | limit $statgrp $maxreq; |
530 | feed $statgrp sub { |
856 | feed $statgrp sub { |
531 | return unless @$entries; |
857 | return unless @$entries; |
532 | my $entry = pop @$entries; |
858 | my $entry = shift @$entries; |
533 | |
859 | |
|
|
860 | aioreq_pri $pri; |
534 | add $statgrp aio_stat "$path/$entry/.", sub { |
861 | add $statgrp aio_stat "$path/$entry/.", sub { |
535 | if ($_[0] < 0) { |
862 | if ($_[0] < 0) { |
536 | push @nondirs, $entry; |
863 | push @nondirs, $entry; |
537 | } else { |
864 | } else { |
538 | # need to check for real directory |
865 | # need to check for real directory |
|
|
866 | aioreq_pri $pri; |
539 | add $statgrp aio_lstat "$path/$entry", sub { |
867 | add $statgrp aio_lstat "$path/$entry", sub { |
540 | if (-d _) { |
868 | if (-d _) { |
541 | push @dirs, $entry; |
869 | push @dirs, $entry; |
542 | |
870 | |
543 | unless (--$ndirs) { |
871 | unless (--$ndirs) { |
… | |
… | |
556 | }; |
884 | }; |
557 | |
885 | |
558 | $grp |
886 | $grp |
559 | } |
887 | } |
560 | |
888 | |
|
|
889 | =item aio_rmtree $path, $callback->($status) |
|
|
890 | |
|
|
891 | Delete a directory tree starting (and including) C<$path>, return the |
|
|
892 | status of the final C<rmdir> only. This is a composite request that |
|
|
893 | uses C<aio_scandir> to recurse into and rmdir directories, and unlink |
|
|
894 | everything else. |
|
|
895 | |
|
|
896 | =cut |
|
|
897 | |
|
|
898 | sub aio_rmtree; |
|
|
899 | sub aio_rmtree($;$) { |
|
|
900 | my ($path, $cb) = @_; |
|
|
901 | |
|
|
902 | my $pri = aioreq_pri; |
|
|
903 | my $grp = aio_group $cb; |
|
|
904 | |
|
|
905 | aioreq_pri $pri; |
|
|
906 | add $grp aio_scandir $path, 0, sub { |
|
|
907 | my ($dirs, $nondirs) = @_; |
|
|
908 | |
|
|
909 | my $dirgrp = aio_group sub { |
|
|
910 | add $grp aio_rmdir $path, sub { |
|
|
911 | $grp->result ($_[0]); |
|
|
912 | }; |
|
|
913 | }; |
|
|
914 | |
|
|
915 | (aioreq_pri $pri), add $dirgrp aio_rmtree "$path/$_" for @$dirs; |
|
|
916 | (aioreq_pri $pri), add $dirgrp aio_unlink "$path/$_" for @$nondirs; |
|
|
917 | |
|
|
918 | add $grp $dirgrp; |
|
|
919 | }; |
|
|
920 | |
|
|
921 | $grp |
|
|
922 | } |
|
|
923 | |
|
|
924 | =item aio_sync $callback->($status) |
|
|
925 | |
|
|
926 | Asynchronously call sync and call the callback when finished. |
|
|
927 | |
561 | =item aio_fsync $fh, $callback->($status) |
928 | =item aio_fsync $fh, $callback->($status) |
562 | |
929 | |
563 | Asynchronously call fsync on the given filehandle and call the callback |
930 | Asynchronously call fsync on the given filehandle and call the callback |
564 | with the fsync result code. |
931 | with the fsync result code. |
565 | |
932 | |
… | |
… | |
568 | Asynchronously call fdatasync on the given filehandle and call the |
935 | Asynchronously call fdatasync on the given filehandle and call the |
569 | callback with the fdatasync result code. |
936 | callback with the fdatasync result code. |
570 | |
937 | |
571 | If this call isn't available because your OS lacks it or it couldn't be |
938 | If this call isn't available because your OS lacks it or it couldn't be |
572 | detected, it will be emulated by calling C<fsync> instead. |
939 | detected, it will be emulated by calling C<fsync> instead. |
|
|
940 | |
|
|
941 | =item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status) |
|
|
942 | |
|
|
943 | Sync the data portion of the file specified by C<$offset> and C<$length> |
|
|
944 | to disk (but NOT the metadata), by calling the Linux-specific |
|
|
945 | sync_file_range call. If sync_file_range is not available or it returns |
|
|
946 | ENOSYS, then fdatasync or fsync is being substituted. |
|
|
947 | |
|
|
948 | C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>, |
|
|
949 | C<IO::AIO::SYNC_FILE_RANGE_WRITE> and |
|
|
950 | C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range |
|
|
951 | manpage for details. |
|
|
952 | |
|
|
953 | =item aio_pathsync $path, $callback->($status) |
|
|
954 | |
|
|
955 | This request tries to open, fsync and close the given path. This is a |
|
|
956 | composite request intended to sync directories after directory operations |
|
|
957 | (E.g. rename). This might not work on all operating systems or have any |
|
|
958 | specific effect, but usually it makes sure that directory changes get |
|
|
959 | written to disc. It works for anything that can be opened for read-only, |
|
|
960 | not just directories. |
|
|
961 | |
|
|
962 | Future versions of this function might fall back to other methods when |
|
|
963 | C<fsync> on the directory fails (such as calling C<sync>). |
|
|
964 | |
|
|
965 | Passes C<0> when everything went ok, and C<-1> on error. |
|
|
966 | |
|
|
967 | =cut |
|
|
968 | |
|
|
969 | sub aio_pathsync($;$) { |
|
|
970 | my ($path, $cb) = @_; |
|
|
971 | |
|
|
972 | my $pri = aioreq_pri; |
|
|
973 | my $grp = aio_group $cb; |
|
|
974 | |
|
|
975 | aioreq_pri $pri; |
|
|
976 | add $grp aio_open $path, O_RDONLY, 0, sub { |
|
|
977 | my ($fh) = @_; |
|
|
978 | if ($fh) { |
|
|
979 | aioreq_pri $pri; |
|
|
980 | add $grp aio_fsync $fh, sub { |
|
|
981 | $grp->result ($_[0]); |
|
|
982 | |
|
|
983 | aioreq_pri $pri; |
|
|
984 | add $grp aio_close $fh; |
|
|
985 | }; |
|
|
986 | } else { |
|
|
987 | $grp->result (-1); |
|
|
988 | } |
|
|
989 | }; |
|
|
990 | |
|
|
991 | $grp |
|
|
992 | } |
573 | |
993 | |
574 | =item aio_group $callback->(...) |
994 | =item aio_group $callback->(...) |
575 | |
995 | |
576 | This is a very special aio request: Instead of doing something, it is a |
996 | This is a very special aio request: Instead of doing something, it is a |
577 | container for other aio requests, which is useful if you want to bundle |
997 | container for other aio requests, which is useful if you want to bundle |
… | |
… | |
627 | =item cancel $req |
1047 | =item cancel $req |
628 | |
1048 | |
629 | Cancels the request, if possible. Has the effect of skipping execution |
1049 | Cancels the request, if possible. Has the effect of skipping execution |
630 | when entering the B<execute> state and skipping calling the callback when |
1050 | when entering the B<execute> state and skipping calling the callback when |
631 | entering the the B<result> state, but will leave the request otherwise |
1051 | entering the the B<result> state, but will leave the request otherwise |
632 | untouched. That means that requests that currently execute will not be |
1052 | untouched (with the exception of readdir). That means that requests that |
633 | stopped and resources held by the request will not be freed prematurely. |
1053 | currently execute will not be stopped and resources held by the request |
|
|
1054 | will not be freed prematurely. |
634 | |
1055 | |
635 | =item cb $req $callback->(...) |
1056 | =item cb $req $callback->(...) |
636 | |
1057 | |
637 | Replace (or simply set) the callback registered to the request. |
1058 | Replace (or simply set) the callback registered to the request. |
638 | |
1059 | |
… | |
… | |
689 | Their lifetime, simplified, looks like this: when they are empty, they |
1110 | Their lifetime, simplified, looks like this: when they are empty, they |
690 | will finish very quickly. If they contain only requests that are in the |
1111 | will finish very quickly. If they contain only requests that are in the |
691 | C<done> state, they will also finish. Otherwise they will continue to |
1112 | C<done> state, they will also finish. Otherwise they will continue to |
692 | exist. |
1113 | exist. |
693 | |
1114 | |
694 | That means after creating a group you have some time to add requests. And |
1115 | That means after creating a group you have some time to add requests |
695 | in the callbacks of those requests, you can add further requests to the |
1116 | (precisely before the callback has been invoked, which is only done within |
696 | group. And only when all those requests have finished will the the group |
1117 | the C<poll_cb>). And in the callbacks of those requests, you can add |
697 | itself finish. |
1118 | further requests to the group. And only when all those requests have |
|
|
1119 | finished will the the group itself finish. |
698 | |
1120 | |
699 | =over 4 |
1121 | =over 4 |
700 | |
1122 | |
701 | =item add $grp ... |
1123 | =item add $grp ... |
702 | |
1124 | |
… | |
… | |
714 | itself. Useful when you queued a lot of events but got a result early. |
1136 | itself. Useful when you queued a lot of events but got a result early. |
715 | |
1137 | |
716 | =item $grp->result (...) |
1138 | =item $grp->result (...) |
717 | |
1139 | |
718 | Set the result value(s) that will be passed to the group callback when all |
1140 | Set the result value(s) that will be passed to the group callback when all |
719 | subrequests have finished. By default, no argument will be passed. |
1141 | subrequests have finished and set the groups errno to the current value |
|
|
1142 | of errno (just like calling C<errno> without an error number). By default, |
|
|
1143 | no argument will be passed and errno is zero. |
|
|
1144 | |
|
|
1145 | =item $grp->errno ([$errno]) |
|
|
1146 | |
|
|
1147 | Sets the group errno value to C<$errno>, or the current value of errno |
|
|
1148 | when the argument is missing. |
|
|
1149 | |
|
|
1150 | Every aio request has an associated errno value that is restored when |
|
|
1151 | the callback is invoked. This method lets you change this value from its |
|
|
1152 | default (0). |
|
|
1153 | |
|
|
1154 | Calling C<result> will also set errno, so make sure you either set C<$!> |
|
|
1155 | before the call to C<result>, or call c<errno> after it. |
720 | |
1156 | |
721 | =item feed $grp $callback->($grp) |
1157 | =item feed $grp $callback->($grp) |
722 | |
1158 | |
723 | Sets a feeder/generator on this group: every group can have an attached |
1159 | Sets a feeder/generator on this group: every group can have an attached |
724 | generator that generates requests if idle. The idea behind this is that, |
1160 | generator that generates requests if idle. The idea behind this is that, |
725 | although you could just queue as many requests as you want in a group, |
1161 | although you could just queue as many requests as you want in a group, |
726 | this might starve other requests for a potentially long time. For |
1162 | this might starve other requests for a potentially long time. For example, |
727 | example, C<aio_scandir> might generate hundreds of thousands C<aio_stat> |
1163 | C<aio_scandir> might generate hundreds of thousands C<aio_stat> requests, |
728 | requests, delaying any later requests for a long time. |
1164 | delaying any later requests for a long time. |
729 | |
1165 | |
730 | To avoid this, and allow incremental generation of requests, you can |
1166 | To avoid this, and allow incremental generation of requests, you can |
731 | instead a group and set a feeder on it that generates those requests. The |
1167 | instead a group and set a feeder on it that generates those requests. The |
732 | feed callback will be called whenever there are few enough (see C<limit>, |
1168 | feed callback will be called whenever there are few enough (see C<limit>, |
733 | below) requests active in the group itself and is expected to queue more |
1169 | below) requests active in the group itself and is expected to queue more |
… | |
… | |
737 | not impose any limits). |
1173 | not impose any limits). |
738 | |
1174 | |
739 | If the feed does not queue more requests when called, it will be |
1175 | If the feed does not queue more requests when called, it will be |
740 | automatically removed from the group. |
1176 | automatically removed from the group. |
741 | |
1177 | |
742 | If the feed limit is C<0>, it will be set to C<2> automatically. |
1178 | If the feed limit is C<0> when this method is called, it will be set to |
|
|
1179 | C<2> automatically. |
743 | |
1180 | |
744 | Example: |
1181 | Example: |
745 | |
1182 | |
746 | # stat all files in @files, but only ever use four aio requests concurrently: |
1183 | # stat all files in @files, but only ever use four aio requests concurrently: |
747 | |
1184 | |
… | |
… | |
759 | Sets the feeder limit for the group: The feeder will be called whenever |
1196 | Sets the feeder limit for the group: The feeder will be called whenever |
760 | the group contains less than this many requests. |
1197 | the group contains less than this many requests. |
761 | |
1198 | |
762 | Setting the limit to C<0> will pause the feeding process. |
1199 | Setting the limit to C<0> will pause the feeding process. |
763 | |
1200 | |
|
|
1201 | The default value for the limit is C<0>, but note that setting a feeder |
|
|
1202 | automatically bumps it up to C<2>. |
|
|
1203 | |
764 | =back |
1204 | =back |
765 | |
1205 | |
766 | =head2 SUPPORT FUNCTIONS |
1206 | =head2 SUPPORT FUNCTIONS |
767 | |
1207 | |
|
|
1208 | =head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION |
|
|
1209 | |
768 | =over 4 |
1210 | =over 4 |
769 | |
1211 | |
770 | =item $fileno = IO::AIO::poll_fileno |
1212 | =item $fileno = IO::AIO::poll_fileno |
771 | |
1213 | |
772 | Return the I<request result pipe file descriptor>. This filehandle must be |
1214 | Return the I<request result pipe file descriptor>. This filehandle must be |
773 | polled for reading by some mechanism outside this module (e.g. Event or |
1215 | polled for reading by some mechanism outside this module (e.g. EV, Glib, |
774 | select, see below or the SYNOPSIS). If the pipe becomes readable you have |
1216 | select and so on, see below or the SYNOPSIS). If the pipe becomes readable |
775 | to call C<poll_cb> to check the results. |
1217 | you have to call C<poll_cb> to check the results. |
776 | |
1218 | |
777 | See C<poll_cb> for an example. |
1219 | See C<poll_cb> for an example. |
778 | |
1220 | |
779 | =item IO::AIO::poll_cb |
1221 | =item IO::AIO::poll_cb |
780 | |
1222 | |
781 | Process all outstanding events on the result pipe. You have to call this |
1223 | Process some outstanding events on the result pipe. You have to call this |
782 | regularly. Returns the number of events processed. Returns immediately |
1224 | regularly. Returns C<0> if all events could be processed, or C<-1> if it |
783 | when no events are outstanding. |
1225 | returned earlier for whatever reason. Returns immediately when no events |
|
|
1226 | are outstanding. The amount of events processed depends on the settings of |
|
|
1227 | C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>. |
784 | |
1228 | |
785 | If not all requests were processed for whatever reason, the filehandle |
1229 | If not all requests were processed for whatever reason, the filehandle |
786 | will still be ready when C<poll_cb> returns. |
1230 | will still be ready when C<poll_cb> returns, so normally you don't have to |
|
|
1231 | do anything special to have it called later. |
787 | |
1232 | |
788 | Example: Install an Event watcher that automatically calls |
1233 | Example: Install an Event watcher that automatically calls |
789 | IO::AIO::poll_cb with high priority: |
1234 | IO::AIO::poll_cb with high priority (more examples can be found in the |
|
|
1235 | SYNOPSIS section, at the top of this document): |
790 | |
1236 | |
791 | Event->io (fd => IO::AIO::poll_fileno, |
1237 | Event->io (fd => IO::AIO::poll_fileno, |
792 | poll => 'r', async => 1, |
1238 | poll => 'r', async => 1, |
793 | cb => \&IO::AIO::poll_cb); |
1239 | cb => \&IO::AIO::poll_cb); |
794 | |
1240 | |
795 | =item IO::AIO::poll_some $max_requests |
1241 | =item IO::AIO::max_poll_reqs $nreqs |
796 | |
1242 | |
797 | Similar to C<poll_cb>, but only processes up to C<$max_requests> requests |
1243 | =item IO::AIO::max_poll_time $seconds |
798 | at a time. |
|
|
799 | |
1244 | |
800 | Useful if you want to ensure some level of interactiveness when perl is |
1245 | These set the maximum number of requests (default C<0>, meaning infinity) |
801 | not fast enough to process all requests in time. |
1246 | that are being processed by C<IO::AIO::poll_cb> in one call, respectively |
|
|
1247 | the maximum amount of time (default C<0>, meaning infinity) spent in |
|
|
1248 | C<IO::AIO::poll_cb> to process requests (more correctly the mininum amount |
|
|
1249 | of time C<poll_cb> is allowed to use). |
|
|
1250 | |
|
|
1251 | Setting C<max_poll_time> to a non-zero value creates an overhead of one |
|
|
1252 | syscall per request processed, which is not normally a problem unless your |
|
|
1253 | callbacks are really really fast or your OS is really really slow (I am |
|
|
1254 | not mentioning Solaris here). Using C<max_poll_reqs> incurs no overhead. |
|
|
1255 | |
|
|
1256 | Setting these is useful if you want to ensure some level of |
|
|
1257 | interactiveness when perl is not fast enough to process all requests in |
|
|
1258 | time. |
|
|
1259 | |
|
|
1260 | For interactive programs, values such as C<0.01> to C<0.1> should be fine. |
802 | |
1261 | |
803 | Example: Install an Event watcher that automatically calls |
1262 | Example: Install an Event watcher that automatically calls |
804 | IO::AIO::poll_some with low priority, to ensure that other parts of the |
1263 | IO::AIO::poll_cb with low priority, to ensure that other parts of the |
805 | program get the CPU sometimes even under high AIO load. |
1264 | program get the CPU sometimes even under high AIO load. |
806 | |
1265 | |
|
|
1266 | # try not to spend much more than 0.1s in poll_cb |
|
|
1267 | IO::AIO::max_poll_time 0.1; |
|
|
1268 | |
|
|
1269 | # use a low priority so other tasks have priority |
807 | Event->io (fd => IO::AIO::poll_fileno, |
1270 | Event->io (fd => IO::AIO::poll_fileno, |
808 | poll => 'r', nice => 1, |
1271 | poll => 'r', nice => 1, |
809 | cb => sub { IO::AIO::poll_some 256 }); |
1272 | cb => &IO::AIO::poll_cb); |
810 | |
1273 | |
811 | =item IO::AIO::poll_wait |
1274 | =item IO::AIO::poll_wait |
812 | |
1275 | |
|
|
1276 | If there are any outstanding requests and none of them in the result |
813 | Wait till the result filehandle becomes ready for reading (simply does a |
1277 | phase, wait till the result filehandle becomes ready for reading (simply |
814 | C<select> on the filehandle. This is useful if you want to synchronously wait |
1278 | does a C<select> on the filehandle. This is useful if you want to |
815 | for some requests to finish). |
1279 | synchronously wait for some requests to finish). |
816 | |
1280 | |
817 | See C<nreqs> for an example. |
1281 | See C<nreqs> for an example. |
818 | |
1282 | |
|
|
1283 | =item IO::AIO::poll |
|
|
1284 | |
|
|
1285 | Waits until some requests have been handled. |
|
|
1286 | |
|
|
1287 | Returns the number of requests processed, but is otherwise strictly |
|
|
1288 | equivalent to: |
|
|
1289 | |
|
|
1290 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
1291 | |
819 | =item IO::AIO::nreqs |
1292 | =item IO::AIO::flush |
820 | |
1293 | |
821 | Returns the number of requests currently outstanding (i.e. for which their |
1294 | Wait till all outstanding AIO requests have been handled. |
822 | callback has not been invoked yet). |
|
|
823 | |
1295 | |
824 | Example: wait till there are no outstanding requests anymore: |
1296 | Strictly equivalent to: |
825 | |
1297 | |
826 | IO::AIO::poll_wait, IO::AIO::poll_cb |
1298 | IO::AIO::poll_wait, IO::AIO::poll_cb |
827 | while IO::AIO::nreqs; |
1299 | while IO::AIO::nreqs; |
828 | |
1300 | |
829 | =item IO::AIO::flush |
1301 | =back |
830 | |
1302 | |
831 | Wait till all outstanding AIO requests have been handled. |
1303 | =head3 CONTROLLING THE NUMBER OF THREADS |
832 | |
1304 | |
833 | Strictly equivalent to: |
1305 | =over |
834 | |
|
|
835 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
836 | while IO::AIO::nreqs; |
|
|
837 | |
|
|
838 | =item IO::AIO::poll |
|
|
839 | |
|
|
840 | Waits until some requests have been handled. |
|
|
841 | |
|
|
842 | Strictly equivalent to: |
|
|
843 | |
|
|
844 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
845 | if IO::AIO::nreqs; |
|
|
846 | |
1306 | |
847 | =item IO::AIO::min_parallel $nthreads |
1307 | =item IO::AIO::min_parallel $nthreads |
848 | |
1308 | |
849 | Set the minimum number of AIO threads to C<$nthreads>. The current |
1309 | Set the minimum number of AIO threads to C<$nthreads>. The current |
850 | default is C<8>, which means eight asynchronous operations can execute |
1310 | default is C<8>, which means eight asynchronous operations can execute |
851 | concurrently at any one time (the number of outstanding requests, |
1311 | concurrently at any one time (the number of outstanding requests, |
852 | however, is unlimited). |
1312 | however, is unlimited). |
853 | |
1313 | |
854 | IO::AIO starts threads only on demand, when an AIO request is queued and |
1314 | IO::AIO starts threads only on demand, when an AIO request is queued and |
855 | no free thread exists. |
1315 | no free thread exists. Please note that queueing up a hundred requests can |
|
|
1316 | create demand for a hundred threads, even if it turns out that everything |
|
|
1317 | is in the cache and could have been processed faster by a single thread. |
856 | |
1318 | |
857 | It is recommended to keep the number of threads relatively low, as some |
1319 | It is recommended to keep the number of threads relatively low, as some |
858 | Linux kernel versions will scale negatively with the number of threads |
1320 | Linux kernel versions will scale negatively with the number of threads |
859 | (higher parallelity => MUCH higher latency). With current Linux 2.6 |
1321 | (higher parallelity => MUCH higher latency). With current Linux 2.6 |
860 | versions, 4-32 threads should be fine. |
1322 | versions, 4-32 threads should be fine. |
… | |
… | |
874 | This module automatically runs C<max_parallel 0> at program end, to ensure |
1336 | This module automatically runs C<max_parallel 0> at program end, to ensure |
875 | that all threads are killed and that there are no outstanding requests. |
1337 | that all threads are killed and that there are no outstanding requests. |
876 | |
1338 | |
877 | Under normal circumstances you don't need to call this function. |
1339 | Under normal circumstances you don't need to call this function. |
878 | |
1340 | |
|
|
1341 | =item IO::AIO::max_idle $nthreads |
|
|
1342 | |
|
|
1343 | Limit the number of threads (default: 4) that are allowed to idle (i.e., |
|
|
1344 | threads that did not get a request to process within 10 seconds). That |
|
|
1345 | means if a thread becomes idle while C<$nthreads> other threads are also |
|
|
1346 | idle, it will free its resources and exit. |
|
|
1347 | |
|
|
1348 | This is useful when you allow a large number of threads (e.g. 100 or 1000) |
|
|
1349 | to allow for extremely high load situations, but want to free resources |
|
|
1350 | under normal circumstances (1000 threads can easily consume 30MB of RAM). |
|
|
1351 | |
|
|
1352 | The default is probably ok in most situations, especially if thread |
|
|
1353 | creation is fast. If thread creation is very slow on your system you might |
|
|
1354 | want to use larger values. |
|
|
1355 | |
879 | =item $oldnreqs = IO::AIO::max_outstanding $nreqs |
1356 | =item IO::AIO::max_outstanding $maxreqs |
880 | |
1357 | |
881 | [REMOVED] |
1358 | This is a very bad function to use in interactive programs because it |
|
|
1359 | blocks, and a bad way to reduce concurrency because it is inexact: Better |
|
|
1360 | use an C<aio_group> together with a feed callback. |
882 | |
1361 | |
883 | Pre-2.x versions used max_outstanding for a crude request queue length limit. |
|
|
884 | |
|
|
885 | In 2.x+ you are advised to use a group and a feeder to limit |
|
|
886 | concurrency. The max_outstanding feature ran very unstable (endless |
|
|
887 | recursions causing segfaults, bad interaction with groups etc.) and was |
|
|
888 | removed. |
|
|
889 | |
|
|
890 | I am deeply sorry, but I am still on the hunt for a good limiting interface. |
|
|
891 | |
|
|
892 | Original description was as follows: |
|
|
893 | |
|
|
894 | Sets the maximum number of outstanding requests to C<$nreqs>. If you try |
1362 | Sets the maximum number of outstanding requests to C<$nreqs>. If you |
895 | to queue up more than this number of requests, the caller will block until |
1363 | do queue up more than this number of requests, the next call to the |
896 | some requests have been handled. |
1364 | C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>) |
|
|
1365 | function will block until the limit is no longer exceeded. |
|
|
1366 | |
|
|
1367 | The default value is very large, so there is no practical limit on the |
|
|
1368 | number of outstanding requests. |
|
|
1369 | |
|
|
1370 | You can still queue as many requests as you want. Therefore, |
|
|
1371 | C<max_outstanding> is mainly useful in simple scripts (with low values) or |
|
|
1372 | as a stop gap to shield against fatal memory overflow (with large values). |
897 | |
1373 | |
898 | =back |
1374 | =back |
899 | |
1375 | |
|
|
1376 | =head3 STATISTICAL INFORMATION |
|
|
1377 | |
|
|
1378 | =over |
|
|
1379 | |
|
|
1380 | =item IO::AIO::nreqs |
|
|
1381 | |
|
|
1382 | Returns the number of requests currently in the ready, execute or pending |
|
|
1383 | states (i.e. for which their callback has not been invoked yet). |
|
|
1384 | |
|
|
1385 | Example: wait till there are no outstanding requests anymore: |
|
|
1386 | |
|
|
1387 | IO::AIO::poll_wait, IO::AIO::poll_cb |
|
|
1388 | while IO::AIO::nreqs; |
|
|
1389 | |
|
|
1390 | =item IO::AIO::nready |
|
|
1391 | |
|
|
1392 | Returns the number of requests currently in the ready state (not yet |
|
|
1393 | executed). |
|
|
1394 | |
|
|
1395 | =item IO::AIO::npending |
|
|
1396 | |
|
|
1397 | Returns the number of requests currently in the pending state (executed, |
|
|
1398 | but not yet processed by poll_cb). |
|
|
1399 | |
|
|
1400 | =back |
|
|
1401 | |
|
|
1402 | =head3 MISCELLANEOUS FUNCTIONS |
|
|
1403 | |
|
|
1404 | IO::AIO implements some functions that might be useful, but are not |
|
|
1405 | asynchronous. |
|
|
1406 | |
|
|
1407 | =over 4 |
|
|
1408 | |
|
|
1409 | =item IO::AIO::sendfile $ofh, $ifh, $offset, $count |
|
|
1410 | |
|
|
1411 | Calls the C<eio_sendfile_sync> function, which is like C<aio_sendfile>, |
|
|
1412 | but is blocking (this makes most sense if you know the input data is |
|
|
1413 | likely cached already and the output filehandle is set to non-blocking |
|
|
1414 | operations). |
|
|
1415 | |
|
|
1416 | Returns the number of bytes copied, or C<-1> on error. |
|
|
1417 | |
|
|
1418 | =item IO::AIO::fadvise $fh, $offset, $len, $advice |
|
|
1419 | |
|
|
1420 | Simply calls the C<posix_fadvise> function (see it's |
|
|
1421 | manpage for details). The following advice constants are |
|
|
1422 | avaiable: C<IO::AIO::FADV_NORMAL>, C<IO::AIO::FADV_SEQUENTIAL>, |
|
|
1423 | C<IO::AIO::FADV_RANDOM>, C<IO::AIO::FADV_NOREUSE>, |
|
|
1424 | C<IO::AIO::FADV_WILLNEED>, C<IO::AIO::FADV_DONTNEED>. |
|
|
1425 | |
|
|
1426 | On systems that do not implement C<posix_fadvise>, this function returns |
|
|
1427 | ENOSYS, otherwise the return value of C<posix_fadvise>. |
|
|
1428 | |
|
|
1429 | =back |
|
|
1430 | |
900 | =cut |
1431 | =cut |
901 | |
1432 | |
902 | # support function to convert a fd into a perl filehandle |
|
|
903 | sub _fd2fh { |
|
|
904 | return undef if $_[0] < 0; |
|
|
905 | |
|
|
906 | # try to generate nice filehandles |
|
|
907 | my $sym = "IO::AIO::fd#$_[0]"; |
|
|
908 | local *$sym; |
|
|
909 | |
|
|
910 | open *$sym, "+<&=$_[0]" # usually works under any unix |
|
|
911 | or open *$sym, "<&=$_[0]" # cygwin needs this |
|
|
912 | or open *$sym, ">&=$_[0]" # or this |
|
|
913 | or return undef; |
|
|
914 | |
|
|
915 | *$sym |
|
|
916 | } |
|
|
917 | |
|
|
918 | min_parallel 8; |
1433 | min_parallel 8; |
919 | |
1434 | |
920 | END { |
1435 | END { flush } |
921 | max_parallel 0; |
|
|
922 | } |
|
|
923 | |
1436 | |
924 | 1; |
1437 | 1; |
925 | |
1438 | |
926 | =head2 FORK BEHAVIOUR |
1439 | =head2 FORK BEHAVIOUR |
927 | |
1440 | |
… | |
… | |
947 | bytes of memory. In addition, stat requests need a stat buffer (possibly |
1460 | bytes of memory. In addition, stat requests need a stat buffer (possibly |
948 | a few hundred bytes), readdir requires a result buffer and so on. Perl |
1461 | a few hundred bytes), readdir requires a result buffer and so on. Perl |
949 | scalars and other data passed into aio requests will also be locked and |
1462 | scalars and other data passed into aio requests will also be locked and |
950 | will consume memory till the request has entered the done state. |
1463 | will consume memory till the request has entered the done state. |
951 | |
1464 | |
952 | This is now awfully much, so queuing lots of requests is not usually a |
1465 | This is not awfully much, so queuing lots of requests is not usually a |
953 | problem. |
1466 | problem. |
954 | |
1467 | |
955 | Per-thread usage: |
1468 | Per-thread usage: |
956 | |
1469 | |
957 | In the execution phase, some aio requests require more memory for |
1470 | In the execution phase, some aio requests require more memory for |
… | |
… | |
962 | |
1475 | |
963 | Known bugs will be fixed in the next release. |
1476 | Known bugs will be fixed in the next release. |
964 | |
1477 | |
965 | =head1 SEE ALSO |
1478 | =head1 SEE ALSO |
966 | |
1479 | |
967 | L<Coro::AIO>. |
1480 | L<AnyEvent::AIO> for easy integration into event loops, L<Coro::AIO> for a |
|
|
1481 | more natural syntax. |
968 | |
1482 | |
969 | =head1 AUTHOR |
1483 | =head1 AUTHOR |
970 | |
1484 | |
971 | Marc Lehmann <schmorp@schmorp.de> |
1485 | Marc Lehmann <schmorp@schmorp.de> |
972 | http://home.schmorp.de/ |
1486 | http://home.schmorp.de/ |