1 |
root |
1.1 |
=head1 NAME |
2 |
|
|
|
3 |
|
|
IO::AIO - Asynchronous Input/Output |
4 |
|
|
|
5 |
|
|
=head1 SYNOPSIS |
6 |
|
|
|
7 |
|
|
use IO::AIO; |
8 |
|
|
|
9 |
root |
1.6 |
aio_open "/etc/passwd", O_RDONLY, 0, sub { |
10 |
|
|
my ($fh) = @_; |
11 |
|
|
... |
12 |
|
|
}; |
13 |
|
|
|
14 |
|
|
aio_unlink "/tmp/file", sub { }; |
15 |
|
|
|
16 |
|
|
aio_read $fh, 30000, 1024, $buffer, 0, sub { |
17 |
root |
1.8 |
$_[0] > 0 or die "read error: $!"; |
18 |
root |
1.6 |
}; |
19 |
|
|
|
20 |
root |
1.56 |
# version 2+ has request and group objects |
21 |
|
|
use IO::AIO 2; |
22 |
root |
1.52 |
|
23 |
|
|
my $req = aio_unlink "/tmp/file", sub { }; |
24 |
|
|
$req->cancel; # cancel request if still in queue |
25 |
|
|
|
26 |
root |
1.56 |
my $grp = aio_group sub { print "all stats done\n" }; |
27 |
|
|
add $grp aio_stat "..." for ...; |
28 |
|
|
|
29 |
|
|
# AnyEvent integration |
30 |
root |
1.42 |
open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!"; |
31 |
|
|
my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb }); |
32 |
|
|
|
33 |
root |
1.56 |
# Event integration |
34 |
root |
1.6 |
Event->io (fd => IO::AIO::poll_fileno, |
35 |
root |
1.7 |
poll => 'r', |
36 |
root |
1.6 |
cb => \&IO::AIO::poll_cb); |
37 |
|
|
|
38 |
root |
1.56 |
# Glib/Gtk2 integration |
39 |
root |
1.6 |
add_watch Glib::IO IO::AIO::poll_fileno, |
40 |
root |
1.22 |
in => sub { IO::AIO::poll_cb; 1 }; |
41 |
root |
1.6 |
|
42 |
root |
1.56 |
# Tk integration |
43 |
root |
1.6 |
Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "", |
44 |
|
|
readable => \&IO::AIO::poll_cb); |
45 |
|
|
|
46 |
root |
1.56 |
# Danga::Socket integration |
47 |
root |
1.11 |
Danga::Socket->AddOtherFds (IO::AIO::poll_fileno => |
48 |
|
|
\&IO::AIO::poll_cb); |
49 |
|
|
|
50 |
root |
1.1 |
=head1 DESCRIPTION |
51 |
|
|
|
52 |
|
|
This module implements asynchronous I/O using whatever means your |
53 |
root |
1.2 |
operating system supports. |
54 |
root |
1.1 |
|
55 |
root |
1.2 |
Currently, a number of threads are started that execute your read/writes |
56 |
|
|
and signal their completion. You don't need thread support in your libc or |
57 |
|
|
perl, and the threads created by this module will not be visible to the |
58 |
|
|
pthreads library. In the future, this module might make use of the native |
59 |
|
|
aio functions available on many operating systems. However, they are often |
60 |
|
|
not well-supported (Linux doesn't allow them on normal files currently, |
61 |
|
|
for example), and they would only support aio_read and aio_write, so the |
62 |
|
|
remaining functionality would have to be implemented using threads anyway. |
63 |
root |
1.1 |
|
64 |
|
|
Although the module will work with in the presence of other threads, it is |
65 |
root |
1.22 |
currently not reentrant, so use appropriate locking yourself, always call |
66 |
|
|
C<poll_cb> from within the same thread, or never call C<poll_cb> (or other |
67 |
|
|
C<aio_> functions) recursively. |
68 |
root |
1.1 |
|
69 |
|
|
=cut |
70 |
|
|
|
71 |
|
|
package IO::AIO; |
72 |
|
|
|
73 |
root |
1.23 |
no warnings; |
74 |
root |
1.51 |
use strict 'vars'; |
75 |
root |
1.23 |
|
76 |
root |
1.1 |
use base 'Exporter'; |
77 |
|
|
|
78 |
|
|
BEGIN { |
79 |
root |
1.55 |
our $VERSION = '2.0'; |
80 |
root |
1.1 |
|
81 |
root |
1.51 |
our @EXPORT = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat |
82 |
|
|
aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink |
83 |
root |
1.54 |
aio_fsync aio_fdatasync aio_readahead aio_rename aio_link aio_move |
84 |
|
|
aio_group); |
85 |
root |
1.51 |
our @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs); |
86 |
root |
1.1 |
|
87 |
root |
1.54 |
@IO::AIO::GRP::ISA = 'IO::AIO::REQ'; |
88 |
|
|
|
89 |
root |
1.1 |
require XSLoader; |
90 |
root |
1.51 |
XSLoader::load ("IO::AIO", $VERSION); |
91 |
root |
1.1 |
} |
92 |
|
|
|
93 |
root |
1.5 |
=head1 FUNCTIONS |
94 |
root |
1.1 |
|
95 |
root |
1.5 |
=head2 AIO FUNCTIONS |
96 |
root |
1.1 |
|
97 |
root |
1.5 |
All the C<aio_*> calls are more or less thin wrappers around the syscall |
98 |
|
|
with the same name (sans C<aio_>). The arguments are similar or identical, |
99 |
root |
1.14 |
and they all accept an additional (and optional) C<$callback> argument |
100 |
|
|
which must be a code reference. This code reference will get called with |
101 |
|
|
the syscall return code (e.g. most syscalls return C<-1> on error, unlike |
102 |
|
|
perl, which usually delivers "false") as it's sole argument when the given |
103 |
|
|
syscall has been executed asynchronously. |
104 |
root |
1.1 |
|
105 |
root |
1.23 |
All functions expecting a filehandle keep a copy of the filehandle |
106 |
|
|
internally until the request has finished. |
107 |
root |
1.1 |
|
108 |
root |
1.55 |
All requests return objects of type L<IO::AIO::REQ> that allow further |
109 |
|
|
manipulation of those requests while they are in-flight. |
110 |
root |
1.52 |
|
111 |
root |
1.28 |
The pathnames you pass to these routines I<must> be absolute and |
112 |
|
|
encoded in byte form. The reason for the former is that at the time the |
113 |
|
|
request is being executed, the current working directory could have |
114 |
|
|
changed. Alternatively, you can make sure that you never change the |
115 |
|
|
current working directory. |
116 |
|
|
|
117 |
|
|
To encode pathnames to byte form, either make sure you either: a) |
118 |
|
|
always pass in filenames you got from outside (command line, readdir |
119 |
|
|
etc.), b) are ASCII or ISO 8859-1, c) use the Encode module and encode |
120 |
|
|
your pathnames to the locale (or other) encoding in effect in the user |
121 |
|
|
environment, d) use Glib::filename_from_unicode on unicode filenames or e) |
122 |
|
|
use something else. |
123 |
root |
1.1 |
|
124 |
root |
1.5 |
=over 4 |
125 |
root |
1.1 |
|
126 |
root |
1.40 |
=item aio_open $pathname, $flags, $mode, $callback->($fh) |
127 |
root |
1.1 |
|
128 |
root |
1.2 |
Asynchronously open or create a file and call the callback with a newly |
129 |
|
|
created filehandle for the file. |
130 |
root |
1.1 |
|
131 |
|
|
The pathname passed to C<aio_open> must be absolute. See API NOTES, above, |
132 |
|
|
for an explanation. |
133 |
|
|
|
134 |
root |
1.20 |
The C<$flags> argument is a bitmask. See the C<Fcntl> module for a |
135 |
|
|
list. They are the same as used by C<sysopen>. |
136 |
|
|
|
137 |
|
|
Likewise, C<$mode> specifies the mode of the newly created file, if it |
138 |
|
|
didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>, |
139 |
|
|
except that it is mandatory (i.e. use C<0> if you don't create new files, |
140 |
|
|
and C<0666> or C<0777> if you do). |
141 |
root |
1.1 |
|
142 |
|
|
Example: |
143 |
|
|
|
144 |
|
|
aio_open "/etc/passwd", O_RDONLY, 0, sub { |
145 |
root |
1.2 |
if ($_[0]) { |
146 |
|
|
print "open successful, fh is $_[0]\n"; |
147 |
root |
1.1 |
... |
148 |
|
|
} else { |
149 |
|
|
die "open failed: $!\n"; |
150 |
|
|
} |
151 |
|
|
}; |
152 |
|
|
|
153 |
root |
1.40 |
=item aio_close $fh, $callback->($status) |
154 |
root |
1.1 |
|
155 |
root |
1.2 |
Asynchronously close a file and call the callback with the result |
156 |
|
|
code. I<WARNING:> although accepted, you should not pass in a perl |
157 |
root |
1.20 |
filehandle here, as perl will likely close the file descriptor another |
158 |
|
|
time when the filehandle is destroyed. Normally, you can safely call perls |
159 |
|
|
C<close> or just let filehandles go out of scope. |
160 |
|
|
|
161 |
|
|
This is supposed to be a bug in the API, so that might change. It's |
162 |
|
|
therefore best to avoid this function. |
163 |
root |
1.1 |
|
164 |
root |
1.40 |
=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
165 |
root |
1.1 |
|
166 |
root |
1.40 |
=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) |
167 |
root |
1.1 |
|
168 |
|
|
Reads or writes C<length> bytes from the specified C<fh> and C<offset> |
169 |
|
|
into the scalar given by C<data> and offset C<dataoffset> and calls the |
170 |
|
|
callback without the actual number of bytes read (or -1 on error, just |
171 |
|
|
like the syscall). |
172 |
|
|
|
173 |
root |
1.31 |
The C<$data> scalar I<MUST NOT> be modified in any way while the request |
174 |
|
|
is outstanding. Modifying it can result in segfaults or WW3 (if the |
175 |
|
|
necessary/optional hardware is installed). |
176 |
|
|
|
177 |
root |
1.17 |
Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at |
178 |
root |
1.1 |
offset C<0> within the scalar: |
179 |
|
|
|
180 |
|
|
aio_read $fh, 7, 15, $buffer, 0, sub { |
181 |
root |
1.9 |
$_[0] > 0 or die "read error: $!"; |
182 |
|
|
print "read $_[0] bytes: <$buffer>\n"; |
183 |
root |
1.1 |
}; |
184 |
|
|
|
185 |
root |
1.50 |
=item aio_move $srcpath, $dstpath, $callback->($status) |
186 |
|
|
|
187 |
root |
1.52 |
Try to move the I<file> (directories not supported as either source or |
188 |
|
|
destination) from C<$srcpath> to C<$dstpath> and call the callback with |
189 |
|
|
the C<0> (error) or C<-1> ok. |
190 |
root |
1.50 |
|
191 |
|
|
This is a composite request that tries to rename(2) the file first. If |
192 |
|
|
rename files with C<EXDEV>, it creates the destination file with mode 0200 |
193 |
|
|
and copies the contents of the source file into it using C<aio_sendfile>, |
194 |
|
|
followed by restoring atime, mtime, access mode and uid/gid, in that |
195 |
|
|
order, and unlinking the C<$srcpath>. |
196 |
|
|
|
197 |
|
|
If an error occurs, the partial destination file will be unlinked, if |
198 |
|
|
possible, except when setting atime, mtime, access mode and uid/gid, where |
199 |
|
|
errors are being ignored. |
200 |
|
|
|
201 |
|
|
=cut |
202 |
|
|
|
203 |
|
|
sub aio_move($$$) { |
204 |
|
|
my ($src, $dst, $cb) = @_; |
205 |
|
|
|
206 |
root |
1.55 |
my $grp = aio_group; |
207 |
|
|
|
208 |
|
|
add $grp aio_rename $src, $dst, sub { |
209 |
root |
1.51 |
if ($_[0] && $! == EXDEV) { |
210 |
root |
1.55 |
add $grp aio_open $src, O_RDONLY, 0, sub { |
211 |
root |
1.50 |
if (my $src_fh = $_[0]) { |
212 |
|
|
my @stat = stat $src_fh; |
213 |
|
|
|
214 |
root |
1.55 |
add $grp aio_open $dst, O_WRONLY, 0200, sub { |
215 |
root |
1.50 |
if (my $dst_fh = $_[0]) { |
216 |
root |
1.55 |
add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub { |
217 |
root |
1.50 |
close $src_fh; |
218 |
|
|
|
219 |
|
|
if ($_[0] == $stat[7]) { |
220 |
|
|
utime $stat[8], $stat[9], $dst; |
221 |
|
|
chmod $stat[2] & 07777, $dst_fh; |
222 |
|
|
chown $stat[4], $stat[5], $dst_fh; |
223 |
|
|
close $dst_fh; |
224 |
|
|
|
225 |
root |
1.55 |
add $grp aio_unlink $src, sub { |
226 |
root |
1.50 |
$cb->($_[0]); |
227 |
|
|
}; |
228 |
|
|
} else { |
229 |
|
|
my $errno = $!; |
230 |
root |
1.55 |
add $grp aio_unlink $dst, sub { |
231 |
root |
1.50 |
$! = $errno; |
232 |
|
|
$cb->(-1); |
233 |
|
|
}; |
234 |
|
|
} |
235 |
|
|
}; |
236 |
|
|
} else { |
237 |
|
|
$cb->(-1); |
238 |
|
|
} |
239 |
|
|
}, |
240 |
|
|
|
241 |
|
|
} else { |
242 |
|
|
$cb->(-1); |
243 |
|
|
} |
244 |
|
|
}; |
245 |
|
|
} else { |
246 |
|
|
$cb->($_[0]); |
247 |
|
|
} |
248 |
|
|
}; |
249 |
root |
1.55 |
|
250 |
|
|
$grp |
251 |
root |
1.50 |
} |
252 |
|
|
|
253 |
root |
1.40 |
=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) |
254 |
root |
1.35 |
|
255 |
|
|
Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts |
256 |
|
|
reading at byte offset C<$in_offset>, and starts writing at the current |
257 |
|
|
file offset of C<$out_fh>. Because of that, it is not safe to issue more |
258 |
|
|
than one C<aio_sendfile> per C<$out_fh>, as they will interfere with each |
259 |
|
|
other. |
260 |
|
|
|
261 |
|
|
This call tries to make use of a native C<sendfile> syscall to provide |
262 |
|
|
zero-copy operation. For this to work, C<$out_fh> should refer to a |
263 |
|
|
socket, and C<$in_fh> should refer to mmap'able file. |
264 |
|
|
|
265 |
|
|
If the native sendfile call fails or is not implemented, it will be |
266 |
root |
1.36 |
emulated, so you can call C<aio_sendfile> on any type of filehandle |
267 |
|
|
regardless of the limitations of the operating system. |
268 |
root |
1.35 |
|
269 |
|
|
Please note, however, that C<aio_sendfile> can read more bytes from |
270 |
|
|
C<$in_fh> than are written, and there is no way to find out how many |
271 |
root |
1.36 |
bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only |
272 |
|
|
provides the number of bytes written to C<$out_fh>. Only if the result |
273 |
|
|
value equals C<$length> one can assume that C<$length> bytes have been |
274 |
|
|
read. |
275 |
root |
1.35 |
|
276 |
root |
1.40 |
=item aio_readahead $fh,$offset,$length, $callback->($retval) |
277 |
root |
1.1 |
|
278 |
root |
1.20 |
C<aio_readahead> populates the page cache with data from a file so that |
279 |
root |
1.1 |
subsequent reads from that file will not block on disk I/O. The C<$offset> |
280 |
|
|
argument specifies the starting point from which data is to be read and |
281 |
|
|
C<$length> specifies the number of bytes to be read. I/O is performed in |
282 |
|
|
whole pages, so that offset is effectively rounded down to a page boundary |
283 |
|
|
and bytes are read up to the next page boundary greater than or equal to |
284 |
root |
1.20 |
(off-set+length). C<aio_readahead> does not read beyond the end of the |
285 |
root |
1.1 |
file. The current file offset of the file is left unchanged. |
286 |
|
|
|
287 |
root |
1.26 |
If that syscall doesn't exist (likely if your OS isn't Linux) it will be |
288 |
|
|
emulated by simply reading the data, which would have a similar effect. |
289 |
|
|
|
290 |
root |
1.40 |
=item aio_stat $fh_or_path, $callback->($status) |
291 |
root |
1.1 |
|
292 |
root |
1.40 |
=item aio_lstat $fh, $callback->($status) |
293 |
root |
1.1 |
|
294 |
|
|
Works like perl's C<stat> or C<lstat> in void context. The callback will |
295 |
|
|
be called after the stat and the results will be available using C<stat _> |
296 |
|
|
or C<-s _> etc... |
297 |
|
|
|
298 |
|
|
The pathname passed to C<aio_stat> must be absolute. See API NOTES, above, |
299 |
|
|
for an explanation. |
300 |
|
|
|
301 |
|
|
Currently, the stats are always 64-bit-stats, i.e. instead of returning an |
302 |
|
|
error when stat'ing a large file, the results will be silently truncated |
303 |
|
|
unless perl itself is compiled with large file support. |
304 |
|
|
|
305 |
|
|
Example: Print the length of F</etc/passwd>: |
306 |
|
|
|
307 |
|
|
aio_stat "/etc/passwd", sub { |
308 |
|
|
$_[0] and die "stat failed: $!"; |
309 |
|
|
print "size is ", -s _, "\n"; |
310 |
|
|
}; |
311 |
|
|
|
312 |
root |
1.40 |
=item aio_unlink $pathname, $callback->($status) |
313 |
root |
1.1 |
|
314 |
|
|
Asynchronously unlink (delete) a file and call the callback with the |
315 |
|
|
result code. |
316 |
|
|
|
317 |
root |
1.50 |
=item aio_link $srcpath, $dstpath, $callback->($status) |
318 |
|
|
|
319 |
|
|
Asynchronously create a new link to the existing object at C<$srcpath> at |
320 |
|
|
the path C<$dstpath> and call the callback with the result code. |
321 |
|
|
|
322 |
|
|
=item aio_symlink $srcpath, $dstpath, $callback->($status) |
323 |
|
|
|
324 |
|
|
Asynchronously create a new symbolic link to the existing object at C<$srcpath> at |
325 |
|
|
the path C<$dstpath> and call the callback with the result code. |
326 |
|
|
|
327 |
|
|
=item aio_rename $srcpath, $dstpath, $callback->($status) |
328 |
|
|
|
329 |
|
|
Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as |
330 |
|
|
rename(2) and call the callback with the result code. |
331 |
|
|
|
332 |
root |
1.40 |
=item aio_rmdir $pathname, $callback->($status) |
333 |
root |
1.27 |
|
334 |
|
|
Asynchronously rmdir (delete) a directory and call the callback with the |
335 |
|
|
result code. |
336 |
|
|
|
337 |
root |
1.46 |
=item aio_readdir $pathname, $callback->($entries) |
338 |
root |
1.37 |
|
339 |
|
|
Unlike the POSIX call of the same name, C<aio_readdir> reads an entire |
340 |
|
|
directory (i.e. opendir + readdir + closedir). The entries will not be |
341 |
|
|
sorted, and will B<NOT> include the C<.> and C<..> entries. |
342 |
|
|
|
343 |
|
|
The callback a single argument which is either C<undef> or an array-ref |
344 |
|
|
with the filenames. |
345 |
|
|
|
346 |
root |
1.40 |
=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) |
347 |
|
|
|
348 |
root |
1.52 |
Scans a directory (similar to C<aio_readdir>) but additionally tries to |
349 |
|
|
separate the entries of directory C<$path> into two sets of names, ones |
350 |
|
|
you can recurse into (directories or links to them), and ones you cannot |
351 |
|
|
recurse into (everything else). |
352 |
|
|
|
353 |
|
|
C<aio_scandir> is a composite request that consists of many sub |
354 |
|
|
requests. C<$maxreq> specifies the maximum number of outstanding aio |
355 |
|
|
requests that this function generates. If it is C<< <= 0 >>, then a |
356 |
root |
1.40 |
suitable default will be chosen (currently 8). |
357 |
|
|
|
358 |
|
|
On error, the callback is called without arguments, otherwise it receives |
359 |
|
|
two array-refs with path-relative entry names. |
360 |
|
|
|
361 |
|
|
Example: |
362 |
|
|
|
363 |
|
|
aio_scandir $dir, 0, sub { |
364 |
|
|
my ($dirs, $nondirs) = @_; |
365 |
|
|
print "real directories: @$dirs\n"; |
366 |
|
|
print "everything else: @$nondirs\n"; |
367 |
|
|
}; |
368 |
|
|
|
369 |
|
|
Implementation notes. |
370 |
|
|
|
371 |
|
|
The C<aio_readdir> cannot be avoided, but C<stat()>'ing every entry can. |
372 |
|
|
|
373 |
|
|
After reading the directory, the modification time, size etc. of the |
374 |
root |
1.52 |
directory before and after the readdir is checked, and if they match (and |
375 |
|
|
isn't the current time), the link count will be used to decide how many |
376 |
|
|
entries are directories (if >= 2). Otherwise, no knowledge of the number |
377 |
|
|
of subdirectories will be assumed. |
378 |
|
|
|
379 |
|
|
Then entries will be sorted into likely directories (everything without |
380 |
|
|
a non-initial dot currently) and likely non-directories (everything |
381 |
|
|
else). Then every entry plus an appended C</.> will be C<stat>'ed, |
382 |
|
|
likely directories first. If that succeeds, it assumes that the entry |
383 |
|
|
is a directory or a symlink to directory (which will be checked |
384 |
|
|
seperately). This is often faster than stat'ing the entry itself because |
385 |
|
|
filesystems might detect the type of the entry without reading the inode |
386 |
|
|
data (e.g. ext2fs filetype feature). |
387 |
|
|
|
388 |
|
|
If the known number of directories (link count - 2) has been reached, the |
389 |
|
|
rest of the entries is assumed to be non-directories. |
390 |
|
|
|
391 |
|
|
This only works with certainty on POSIX (= UNIX) filesystems, which |
392 |
|
|
fortunately are the vast majority of filesystems around. |
393 |
|
|
|
394 |
|
|
It will also likely work on non-POSIX filesystems with reduced efficiency |
395 |
|
|
as those tend to return 0 or 1 as link counts, which disables the |
396 |
|
|
directory counting heuristic. |
397 |
root |
1.40 |
|
398 |
|
|
=cut |
399 |
|
|
|
400 |
|
|
sub aio_scandir($$$) { |
401 |
|
|
my ($path, $maxreq, $cb) = @_; |
402 |
|
|
|
403 |
root |
1.55 |
my $grp = aio_group; |
404 |
|
|
|
405 |
root |
1.40 |
$maxreq = 8 if $maxreq <= 0; |
406 |
|
|
|
407 |
|
|
# stat once |
408 |
root |
1.55 |
add $grp aio_stat $path, sub { |
409 |
root |
1.47 |
return $cb->() if $_[0]; |
410 |
root |
1.52 |
my $now = time; |
411 |
root |
1.40 |
my $hash1 = join ":", (stat _)[0,1,3,7,9]; |
412 |
|
|
|
413 |
|
|
# read the directory entries |
414 |
root |
1.55 |
add $grp aio_readdir $path, sub { |
415 |
root |
1.40 |
my $entries = shift |
416 |
|
|
or return $cb->(); |
417 |
|
|
|
418 |
|
|
# stat the dir another time |
419 |
root |
1.55 |
add $grp aio_stat $path, sub { |
420 |
root |
1.40 |
my $hash2 = join ":", (stat _)[0,1,3,7,9]; |
421 |
|
|
|
422 |
|
|
my $ndirs; |
423 |
|
|
|
424 |
|
|
# take the slow route if anything looks fishy |
425 |
root |
1.52 |
if ($hash1 ne $hash2 or (stat _)[9] == $now) { |
426 |
root |
1.40 |
$ndirs = -1; |
427 |
|
|
} else { |
428 |
|
|
# if nlink == 2, we are finished |
429 |
|
|
# on non-posix-fs's, we rely on nlink < 2 |
430 |
|
|
$ndirs = (stat _)[3] - 2 |
431 |
root |
1.43 |
or return $cb->([], $entries); |
432 |
root |
1.40 |
} |
433 |
|
|
|
434 |
|
|
# sort into likely dirs and likely nondirs |
435 |
|
|
# dirs == files without ".", short entries first |
436 |
|
|
$entries = [map $_->[0], |
437 |
|
|
sort { $b->[1] cmp $a->[1] } |
438 |
|
|
map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length], |
439 |
|
|
@$entries]; |
440 |
|
|
|
441 |
|
|
my (@dirs, @nondirs); |
442 |
|
|
|
443 |
|
|
my ($statcb, $schedcb); |
444 |
|
|
my $nreq = 0; |
445 |
|
|
|
446 |
|
|
$schedcb = sub { |
447 |
|
|
if (@$entries) { |
448 |
|
|
if ($nreq < $maxreq) { |
449 |
|
|
my $ent = pop @$entries; |
450 |
|
|
$nreq++; |
451 |
root |
1.55 |
add $grp aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) }; |
452 |
root |
1.40 |
} |
453 |
|
|
} elsif (!$nreq) { |
454 |
|
|
# finished |
455 |
|
|
undef $statcb; |
456 |
|
|
undef $schedcb; |
457 |
root |
1.45 |
$cb->(\@dirs, \@nondirs) if $cb; |
458 |
root |
1.40 |
undef $cb; |
459 |
|
|
} |
460 |
|
|
}; |
461 |
|
|
$statcb = sub { |
462 |
|
|
my ($status, $entry) = @_; |
463 |
|
|
|
464 |
|
|
if ($status < 0) { |
465 |
|
|
$nreq--; |
466 |
|
|
push @nondirs, $entry; |
467 |
|
|
&$schedcb; |
468 |
|
|
} else { |
469 |
|
|
# need to check for real directory |
470 |
root |
1.55 |
add $grp aio_lstat "$path/$entry", sub { |
471 |
root |
1.40 |
$nreq--; |
472 |
|
|
|
473 |
|
|
if (-d _) { |
474 |
|
|
push @dirs, $entry; |
475 |
|
|
|
476 |
|
|
if (!--$ndirs) { |
477 |
|
|
push @nondirs, @$entries; |
478 |
|
|
$entries = []; |
479 |
|
|
} |
480 |
|
|
} else { |
481 |
|
|
push @nondirs, $entry; |
482 |
|
|
} |
483 |
|
|
|
484 |
|
|
&$schedcb; |
485 |
|
|
} |
486 |
|
|
} |
487 |
|
|
}; |
488 |
|
|
|
489 |
|
|
&$schedcb while @$entries && $nreq < $maxreq; |
490 |
|
|
}; |
491 |
|
|
}; |
492 |
|
|
}; |
493 |
root |
1.55 |
|
494 |
|
|
$grp |
495 |
root |
1.40 |
} |
496 |
|
|
|
497 |
|
|
=item aio_fsync $fh, $callback->($status) |
498 |
root |
1.1 |
|
499 |
|
|
Asynchronously call fsync on the given filehandle and call the callback |
500 |
|
|
with the fsync result code. |
501 |
|
|
|
502 |
root |
1.40 |
=item aio_fdatasync $fh, $callback->($status) |
503 |
root |
1.1 |
|
504 |
|
|
Asynchronously call fdatasync on the given filehandle and call the |
505 |
root |
1.26 |
callback with the fdatasync result code. |
506 |
|
|
|
507 |
|
|
If this call isn't available because your OS lacks it or it couldn't be |
508 |
|
|
detected, it will be emulated by calling C<fsync> instead. |
509 |
root |
1.1 |
|
510 |
root |
1.54 |
=item aio_group $callback->() |
511 |
|
|
|
512 |
root |
1.55 |
[EXPERIMENTAL] |
513 |
|
|
|
514 |
|
|
This is a very special aio request: Instead of doing something, it is a |
515 |
|
|
container for other aio requests, which is useful if you want to bundle |
516 |
|
|
many requests into a single, composite, request. |
517 |
|
|
|
518 |
|
|
Returns an object of class L<IO::AIO::GRP>. See its documentation below |
519 |
|
|
for more info. |
520 |
|
|
|
521 |
|
|
Example: |
522 |
|
|
|
523 |
|
|
my $grp = aio_group sub { |
524 |
|
|
print "all stats done\n"; |
525 |
|
|
}; |
526 |
|
|
|
527 |
|
|
add $grp |
528 |
|
|
(aio_stat ...), |
529 |
|
|
(aio_stat ...), |
530 |
|
|
...; |
531 |
|
|
|
532 |
root |
1.56 |
=item IO::AIO::aio_sleep $fractional_seconds, $callback->() *NOT EXPORTED* |
533 |
root |
1.54 |
|
534 |
|
|
Mainly used for debugging and benchmarking, this aio request puts one of |
535 |
|
|
the request workers to sleep for the given time. |
536 |
|
|
|
537 |
root |
1.56 |
While it is theoretically handy to have simple I/O scheduling requests |
538 |
|
|
like sleep and file handle readable/writable, the overhead this creates |
539 |
|
|
is immense, so do not use this function except to put your application |
540 |
|
|
under artificial I/O pressure. |
541 |
|
|
|
542 |
root |
1.5 |
=back |
543 |
|
|
|
544 |
root |
1.53 |
=head2 IO::AIO::REQ CLASS |
545 |
root |
1.52 |
|
546 |
|
|
All non-aggregate C<aio_*> functions return an object of this class when |
547 |
|
|
called in non-void context. |
548 |
|
|
|
549 |
|
|
A request always moves through the following five states in its lifetime, |
550 |
|
|
in order: B<ready> (request has been created, but has not been executed |
551 |
|
|
yet), B<execute> (request is currently being executed), B<pending> |
552 |
|
|
(request has been executed but callback has not been called yet), |
553 |
|
|
B<result> (results are being processed synchronously, includes calling the |
554 |
|
|
callback) and B<done> (request has reached the end of its lifetime and |
555 |
|
|
holds no resources anymore). |
556 |
|
|
|
557 |
|
|
=over 4 |
558 |
|
|
|
559 |
|
|
=item $req->cancel |
560 |
|
|
|
561 |
|
|
Cancels the request, if possible. Has the effect of skipping execution |
562 |
|
|
when entering the B<execute> state and skipping calling the callback when |
563 |
|
|
entering the the B<result> state, but will leave the request otherwise |
564 |
|
|
untouched. That means that requests that currently execute will not be |
565 |
|
|
stopped and resources held by the request will not be freed prematurely. |
566 |
|
|
|
567 |
|
|
=back |
568 |
|
|
|
569 |
root |
1.55 |
=head2 IO::AIO::GRP CLASS |
570 |
|
|
|
571 |
|
|
This class is a subclass of L<IO::AIO::REQ>, so all its methods apply to |
572 |
|
|
objects of this class, too. |
573 |
|
|
|
574 |
|
|
A IO::AIO::GRP object is a special request that can contain multiple other |
575 |
|
|
aio requests. |
576 |
|
|
|
577 |
|
|
You create one by calling the C<aio_group> constructing function with a |
578 |
|
|
callback that will be called when all contained requests have entered the |
579 |
|
|
C<done> state: |
580 |
|
|
|
581 |
|
|
my $grp = aio_group sub { |
582 |
|
|
print "all requests are done\n"; |
583 |
|
|
}; |
584 |
|
|
|
585 |
|
|
You add requests by calling the C<add> method with one or more |
586 |
|
|
C<IO::AIO::REQ> objects: |
587 |
|
|
|
588 |
|
|
$grp->add (aio_unlink "..."); |
589 |
|
|
|
590 |
|
|
add $grp aio_stat "...", sub { ... }; |
591 |
|
|
|
592 |
|
|
This makes it very easy to create composite requests (see the source of |
593 |
|
|
C<aio_move> for an application) that work and feel like simple requests. |
594 |
|
|
|
595 |
|
|
The IO::AIO::GRP objects will be cleaned up during calls to |
596 |
|
|
C<IO::AIO::poll_cb>, just like any other request. |
597 |
|
|
|
598 |
|
|
They can be canceled like any other request. Canceling will cancel not |
599 |
|
|
just the request itself, but also all requests it contains. |
600 |
|
|
|
601 |
|
|
They can also can also be added to other IO::AIO::GRP objects. |
602 |
|
|
|
603 |
|
|
Their lifetime, simplified, looks like this: when they are empty, they |
604 |
|
|
will finish very quickly. If they contain only requests that are in the |
605 |
|
|
C<done> state, they will also finish. Otherwise they will continue to |
606 |
|
|
exist. |
607 |
|
|
|
608 |
root |
1.57 |
That means after creating a group you have some time to add requests. And |
609 |
|
|
in the callbacks of those requests, you can add further requests to the |
610 |
|
|
group. And only when all those requests have finished will the the group |
611 |
|
|
itself finish. |
612 |
|
|
|
613 |
root |
1.55 |
=over 4 |
614 |
|
|
|
615 |
|
|
=item $grp->add (...) |
616 |
|
|
|
617 |
|
|
=item add $grp ... |
618 |
|
|
|
619 |
root |
1.57 |
Add one or more requests to the group. Any type of L<IO::AIO::REQ> can |
620 |
|
|
be added, including other groups, as long as you do not create circular |
621 |
|
|
dependencies. |
622 |
|
|
|
623 |
|
|
Returns all its arguments. |
624 |
root |
1.55 |
|
625 |
|
|
=back |
626 |
|
|
|
627 |
root |
1.5 |
=head2 SUPPORT FUNCTIONS |
628 |
|
|
|
629 |
|
|
=over 4 |
630 |
|
|
|
631 |
|
|
=item $fileno = IO::AIO::poll_fileno |
632 |
|
|
|
633 |
root |
1.20 |
Return the I<request result pipe file descriptor>. This filehandle must be |
634 |
|
|
polled for reading by some mechanism outside this module (e.g. Event or |
635 |
|
|
select, see below or the SYNOPSIS). If the pipe becomes readable you have |
636 |
|
|
to call C<poll_cb> to check the results. |
637 |
root |
1.5 |
|
638 |
|
|
See C<poll_cb> for an example. |
639 |
|
|
|
640 |
|
|
=item IO::AIO::poll_cb |
641 |
|
|
|
642 |
|
|
Process all outstanding events on the result pipe. You have to call this |
643 |
|
|
regularly. Returns the number of events processed. Returns immediately |
644 |
|
|
when no events are outstanding. |
645 |
|
|
|
646 |
root |
1.20 |
Example: Install an Event watcher that automatically calls |
647 |
|
|
IO::AIO::poll_cb with high priority: |
648 |
root |
1.5 |
|
649 |
|
|
Event->io (fd => IO::AIO::poll_fileno, |
650 |
|
|
poll => 'r', async => 1, |
651 |
|
|
cb => \&IO::AIO::poll_cb); |
652 |
|
|
|
653 |
|
|
=item IO::AIO::poll_wait |
654 |
|
|
|
655 |
|
|
Wait till the result filehandle becomes ready for reading (simply does a |
656 |
root |
1.20 |
C<select> on the filehandle. This is useful if you want to synchronously wait |
657 |
root |
1.5 |
for some requests to finish). |
658 |
|
|
|
659 |
|
|
See C<nreqs> for an example. |
660 |
|
|
|
661 |
|
|
=item IO::AIO::nreqs |
662 |
|
|
|
663 |
root |
1.20 |
Returns the number of requests currently outstanding (i.e. for which their |
664 |
|
|
callback has not been invoked yet). |
665 |
root |
1.5 |
|
666 |
|
|
Example: wait till there are no outstanding requests anymore: |
667 |
|
|
|
668 |
|
|
IO::AIO::poll_wait, IO::AIO::poll_cb |
669 |
|
|
while IO::AIO::nreqs; |
670 |
|
|
|
671 |
root |
1.12 |
=item IO::AIO::flush |
672 |
|
|
|
673 |
|
|
Wait till all outstanding AIO requests have been handled. |
674 |
|
|
|
675 |
root |
1.13 |
Strictly equivalent to: |
676 |
|
|
|
677 |
|
|
IO::AIO::poll_wait, IO::AIO::poll_cb |
678 |
|
|
while IO::AIO::nreqs; |
679 |
|
|
|
680 |
|
|
=item IO::AIO::poll |
681 |
|
|
|
682 |
|
|
Waits until some requests have been handled. |
683 |
|
|
|
684 |
|
|
Strictly equivalent to: |
685 |
|
|
|
686 |
|
|
IO::AIO::poll_wait, IO::AIO::poll_cb |
687 |
|
|
if IO::AIO::nreqs; |
688 |
|
|
|
689 |
root |
1.5 |
=item IO::AIO::min_parallel $nthreads |
690 |
|
|
|
691 |
root |
1.34 |
Set the minimum number of AIO threads to C<$nthreads>. The current default |
692 |
|
|
is C<4>, which means four asynchronous operations can be done at one time |
693 |
root |
1.5 |
(the number of outstanding operations, however, is unlimited). |
694 |
|
|
|
695 |
root |
1.34 |
IO::AIO starts threads only on demand, when an AIO request is queued and |
696 |
|
|
no free thread exists. |
697 |
|
|
|
698 |
root |
1.5 |
It is recommended to keep the number of threads low, as some Linux |
699 |
|
|
kernel versions will scale negatively with the number of threads (higher |
700 |
|
|
parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32 |
701 |
|
|
threads should be fine. |
702 |
|
|
|
703 |
root |
1.34 |
Under most circumstances you don't need to call this function, as the |
704 |
|
|
module selects a default that is suitable for low to moderate load. |
705 |
root |
1.5 |
|
706 |
|
|
=item IO::AIO::max_parallel $nthreads |
707 |
|
|
|
708 |
root |
1.34 |
Sets the maximum number of AIO threads to C<$nthreads>. If more than the |
709 |
|
|
specified number of threads are currently running, this function kills |
710 |
|
|
them. This function blocks until the limit is reached. |
711 |
|
|
|
712 |
|
|
While C<$nthreads> are zero, aio requests get queued but not executed |
713 |
|
|
until the number of threads has been increased again. |
714 |
root |
1.5 |
|
715 |
|
|
This module automatically runs C<max_parallel 0> at program end, to ensure |
716 |
|
|
that all threads are killed and that there are no outstanding requests. |
717 |
|
|
|
718 |
|
|
Under normal circumstances you don't need to call this function. |
719 |
|
|
|
720 |
|
|
=item $oldnreqs = IO::AIO::max_outstanding $nreqs |
721 |
|
|
|
722 |
|
|
Sets the maximum number of outstanding requests to C<$nreqs>. If you |
723 |
|
|
try to queue up more than this number of requests, the caller will block until |
724 |
|
|
some requests have been handled. |
725 |
|
|
|
726 |
|
|
The default is very large, so normally there is no practical limit. If you |
727 |
root |
1.34 |
queue up many requests in a loop it often improves speed if you set |
728 |
root |
1.5 |
this to a relatively low number, such as C<100>. |
729 |
|
|
|
730 |
|
|
Under normal circumstances you don't need to call this function. |
731 |
|
|
|
732 |
|
|
=back |
733 |
|
|
|
734 |
root |
1.1 |
=cut |
735 |
|
|
|
736 |
root |
1.2 |
# support function to convert a fd into a perl filehandle |
737 |
|
|
sub _fd2fh { |
738 |
|
|
return undef if $_[0] < 0; |
739 |
|
|
|
740 |
root |
1.23 |
# try to generate nice filehandles |
741 |
|
|
my $sym = "IO::AIO::fd#$_[0]"; |
742 |
|
|
local *$sym; |
743 |
root |
1.25 |
|
744 |
root |
1.27 |
open *$sym, "+<&=$_[0]" # usually works under any unix |
745 |
|
|
or open *$sym, "<&=$_[0]" # cygwin needs this |
746 |
|
|
or open *$sym, ">&=$_[0]" # or this |
747 |
root |
1.2 |
or return undef; |
748 |
|
|
|
749 |
root |
1.23 |
*$sym |
750 |
root |
1.2 |
} |
751 |
|
|
|
752 |
root |
1.1 |
min_parallel 4; |
753 |
|
|
|
754 |
|
|
END { |
755 |
|
|
max_parallel 0; |
756 |
|
|
} |
757 |
|
|
|
758 |
|
|
1; |
759 |
|
|
|
760 |
root |
1.27 |
=head2 FORK BEHAVIOUR |
761 |
|
|
|
762 |
root |
1.52 |
This module should do "the right thing" when the process using it forks: |
763 |
|
|
|
764 |
root |
1.34 |
Before the fork, IO::AIO enters a quiescent state where no requests |
765 |
|
|
can be added in other threads and no results will be processed. After |
766 |
|
|
the fork the parent simply leaves the quiescent state and continues |
767 |
|
|
request/result processing, while the child clears the request/result |
768 |
|
|
queue (so the requests started before the fork will only be handled in |
769 |
root |
1.52 |
the parent). Threads will be started on demand until the limit ste in the |
770 |
root |
1.34 |
parent process has been reached again. |
771 |
root |
1.27 |
|
772 |
root |
1.52 |
In short: the parent will, after a short pause, continue as if fork had |
773 |
|
|
not been called, while the child will act as if IO::AIO has not been used |
774 |
|
|
yet. |
775 |
|
|
|
776 |
root |
1.1 |
=head1 SEE ALSO |
777 |
|
|
|
778 |
root |
1.52 |
L<Coro>, L<Linux::AIO> (obsolete). |
779 |
root |
1.1 |
|
780 |
|
|
=head1 AUTHOR |
781 |
|
|
|
782 |
|
|
Marc Lehmann <schmorp@schmorp.de> |
783 |
|
|
http://home.schmorp.de/ |
784 |
|
|
|
785 |
|
|
=cut |
786 |
|
|
|