ViewVC Help
View File | Revision Log | Show Annotations | Download File
/cvs/IO-AIO/AIO.pm
(Generate patch)

Comparing IO-AIO/AIO.pm (file contents):
Revision 1.57 by root, Sun Oct 22 01:28:31 2006 UTC vs.
Revision 1.148 by root, Sat Jun 6 17:25:13 2009 UTC

5=head1 SYNOPSIS 5=head1 SYNOPSIS
6 6
7 use IO::AIO; 7 use IO::AIO;
8 8
9 aio_open "/etc/passwd", O_RDONLY, 0, sub { 9 aio_open "/etc/passwd", O_RDONLY, 0, sub {
10 my ($fh) = @_; 10 my $fh = shift
11 or die "/etc/passwd: $!";
11 ... 12 ...
12 }; 13 };
13 14
14 aio_unlink "/tmp/file", sub { }; 15 aio_unlink "/tmp/file", sub { };
15 16
18 }; 19 };
19 20
20 # version 2+ has request and group objects 21 # version 2+ has request and group objects
21 use IO::AIO 2; 22 use IO::AIO 2;
22 23
24 aioreq_pri 4; # give next request a very high priority
23 my $req = aio_unlink "/tmp/file", sub { }; 25 my $req = aio_unlink "/tmp/file", sub { };
24 $req->cancel; # cancel request if still in queue 26 $req->cancel; # cancel request if still in queue
25 27
26 my $grp = aio_group sub { print "all stats done\n" }; 28 my $grp = aio_group sub { print "all stats done\n" };
27 add $grp aio_stat "..." for ...; 29 add $grp aio_stat "..." for ...;
28 30
31 # AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...)
32 use AnyEvent::AIO;
33
29 # AnyEvent integration 34 # EV integration
30 open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!"; 35 my $w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
31 my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb });
32 36
33 # Event integration 37 # Event integration
34 Event->io (fd => IO::AIO::poll_fileno, 38 Event->io (fd => IO::AIO::poll_fileno,
35 poll => 'r', 39 poll => 'r',
36 cb => \&IO::AIO::poll_cb); 40 cb => \&IO::AIO::poll_cb);
50=head1 DESCRIPTION 54=head1 DESCRIPTION
51 55
52This module implements asynchronous I/O using whatever means your 56This module implements asynchronous I/O using whatever means your
53operating system supports. 57operating system supports.
54 58
59Asynchronous means that operations that can normally block your program
60(e.g. reading from disk) will be done asynchronously: the operation
61will still block, but you can do something else in the meantime. This
62is extremely useful for programs that need to stay interactive even
63when doing heavy I/O (GUI programs, high performance network servers
64etc.), but can also be used to easily do operations in parallel that are
65normally done sequentially, e.g. stat'ing many files, which is much faster
66on a RAID volume or over NFS when you do a number of stat operations
67concurrently.
68
69While most of this works on all types of file descriptors (for
70example sockets), using these functions on file descriptors that
71support nonblocking operation (again, sockets, pipes etc.) is very
72inefficient. Use an event loop for that (such as the L<Event|Event>
73module): IO::AIO will naturally fit into such an event loop itself.
74
55Currently, a number of threads are started that execute your read/writes 75In this version, a number of threads are started that execute your
56and signal their completion. You don't need thread support in your libc or 76requests and signal their completion. You don't need thread support
57perl, and the threads created by this module will not be visible to the 77in perl, and the threads created by this module will not be visible
58pthreads library. In the future, this module might make use of the native 78to perl. In the future, this module might make use of the native aio
59aio functions available on many operating systems. However, they are often 79functions available on many operating systems. However, they are often
60not well-supported (Linux doesn't allow them on normal files currently, 80not well-supported or restricted (GNU/Linux doesn't allow them on normal
61for example), and they would only support aio_read and aio_write, so the 81files currently, for example), and they would only support aio_read and
62remaining functionality would have to be implemented using threads anyway. 82aio_write, so the remaining functionality would have to be implemented
83using threads anyway.
63 84
64Although the module will work with in the presence of other threads, it is 85Although the module will work in the presence of other (Perl-) threads,
65currently not reentrant, so use appropriate locking yourself, always call 86it is currently not reentrant in any way, so use appropriate locking
66C<poll_cb> from within the same thread, or never call C<poll_cb> (or other 87yourself, always call C<poll_cb> from within the same thread, or never
67C<aio_> functions) recursively. 88call C<poll_cb> (or other C<aio_> functions) recursively.
89
90=head2 EXAMPLE
91
92This is a simple example that uses the Event module and loads
93F</etc/passwd> asynchronously:
94
95 use Fcntl;
96 use Event;
97 use IO::AIO;
98
99 # register the IO::AIO callback with Event
100 Event->io (fd => IO::AIO::poll_fileno,
101 poll => 'r',
102 cb => \&IO::AIO::poll_cb);
103
104 # queue the request to open /etc/passwd
105 aio_open "/etc/passwd", O_RDONLY, 0, sub {
106 my $fh = shift
107 or die "error while opening: $!";
108
109 # stat'ing filehandles is generally non-blocking
110 my $size = -s $fh;
111
112 # queue a request to read the file
113 my $contents;
114 aio_read $fh, 0, $size, $contents, 0, sub {
115 $_[0] == $size
116 or die "short read: $!";
117
118 close $fh;
119
120 # file contents now in $contents
121 print $contents;
122
123 # exit event loop and program
124 Event::unloop;
125 };
126 };
127
128 # possibly queue up other requests, or open GUI windows,
129 # check for sockets etc. etc.
130
131 # process events as long as there are some:
132 Event::loop;
133
134=head1 REQUEST ANATOMY AND LIFETIME
135
136Every C<aio_*> function creates a request. which is a C data structure not
137directly visible to Perl.
138
139If called in non-void context, every request function returns a Perl
140object representing the request. In void context, nothing is returned,
141which saves a bit of memory.
142
143The perl object is a fairly standard ref-to-hash object. The hash contents
144are not used by IO::AIO so you are free to store anything you like in it.
145
146During their existance, aio requests travel through the following states,
147in order:
148
149=over 4
150
151=item ready
152
153Immediately after a request is created it is put into the ready state,
154waiting for a thread to execute it.
155
156=item execute
157
158A thread has accepted the request for processing and is currently
159executing it (e.g. blocking in read).
160
161=item pending
162
163The request has been executed and is waiting for result processing.
164
165While request submission and execution is fully asynchronous, result
166processing is not and relies on the perl interpreter calling C<poll_cb>
167(or another function with the same effect).
168
169=item result
170
171The request results are processed synchronously by C<poll_cb>.
172
173The C<poll_cb> function will process all outstanding aio requests by
174calling their callbacks, freeing memory associated with them and managing
175any groups they are contained in.
176
177=item done
178
179Request has reached the end of its lifetime and holds no resources anymore
180(except possibly for the Perl object, but its connection to the actual
181aio request is severed and calling its methods will either do nothing or
182result in a runtime error).
183
184=back
68 185
69=cut 186=cut
70 187
71package IO::AIO; 188package IO::AIO;
189
190use Carp ();
72 191
73no warnings; 192no warnings;
74use strict 'vars'; 193use strict 'vars';
75 194
76use base 'Exporter'; 195use base 'Exporter';
77 196
78BEGIN { 197BEGIN {
79 our $VERSION = '2.0'; 198 our $VERSION = '3.19';
80 199
81 our @EXPORT = qw(aio_sendfile aio_read aio_write aio_open aio_close aio_stat 200 our @AIO_REQ = qw(aio_sendfile aio_read aio_write aio_open aio_close
82 aio_lstat aio_unlink aio_rmdir aio_readdir aio_scandir aio_symlink 201 aio_stat aio_lstat aio_unlink aio_rmdir aio_readdir aio_readdirx
83 aio_fsync aio_fdatasync aio_readahead aio_rename aio_link aio_move 202 aio_scandir aio_symlink aio_readlink aio_sync aio_fsync
84 aio_group); 203 aio_fdatasync aio_sync_file_range aio_pathsync aio_readahead
85 our @EXPORT_OK = qw(poll_fileno poll_cb min_parallel max_parallel max_outstanding nreqs); 204 aio_rename aio_link aio_move aio_copy aio_group
205 aio_nop aio_mknod aio_load aio_rmtree aio_mkdir aio_chown
206 aio_chmod aio_utime aio_truncate);
207
208 our @EXPORT = (@AIO_REQ, qw(aioreq_pri aioreq_nice));
209 our @EXPORT_OK = qw(poll_fileno poll_cb poll_wait flush
210 min_parallel max_parallel max_idle
211 nreqs nready npending nthreads
212 max_poll_time max_poll_reqs);
213
214 push @AIO_REQ, qw(aio_busy); # not exported
86 215
87 @IO::AIO::GRP::ISA = 'IO::AIO::REQ'; 216 @IO::AIO::GRP::ISA = 'IO::AIO::REQ';
88 217
89 require XSLoader; 218 require XSLoader;
90 XSLoader::load ("IO::AIO", $VERSION); 219 XSLoader::load ("IO::AIO", $VERSION);
91} 220}
92 221
93=head1 FUNCTIONS 222=head1 FUNCTIONS
94 223
95=head2 AIO FUNCTIONS 224=head2 AIO REQUEST FUNCTIONS
96 225
97All the C<aio_*> calls are more or less thin wrappers around the syscall 226All the C<aio_*> calls are more or less thin wrappers around the syscall
98with the same name (sans C<aio_>). The arguments are similar or identical, 227with the same name (sans C<aio_>). The arguments are similar or identical,
99and they all accept an additional (and optional) C<$callback> argument 228and they all accept an additional (and optional) C<$callback> argument
100which must be a code reference. This code reference will get called with 229which must be a code reference. This code reference will get called with
101the syscall return code (e.g. most syscalls return C<-1> on error, unlike 230the syscall return code (e.g. most syscalls return C<-1> on error, unlike
102perl, which usually delivers "false") as it's sole argument when the given 231perl, which usually delivers "false") as its sole argument after the given
103syscall has been executed asynchronously. 232syscall has been executed asynchronously.
104 233
105All functions expecting a filehandle keep a copy of the filehandle 234All functions expecting a filehandle keep a copy of the filehandle
106internally until the request has finished. 235internally until the request has finished.
107 236
108All requests return objects of type L<IO::AIO::REQ> that allow further 237All functions return request objects of type L<IO::AIO::REQ> that allow
109manipulation of those requests while they are in-flight. 238further manipulation of those requests while they are in-flight.
110 239
111The pathnames you pass to these routines I<must> be absolute and 240The pathnames you pass to these routines I<must> be absolute and
112encoded in byte form. The reason for the former is that at the time the 241encoded as octets. The reason for the former is that at the time the
113request is being executed, the current working directory could have 242request is being executed, the current working directory could have
114changed. Alternatively, you can make sure that you never change the 243changed. Alternatively, you can make sure that you never change the
115current working directory. 244current working directory anywhere in the program and then use relative
245paths.
116 246
117To encode pathnames to byte form, either make sure you either: a) 247To encode pathnames as octets, either make sure you either: a) always pass
118always pass in filenames you got from outside (command line, readdir 248in filenames you got from outside (command line, readdir etc.) without
119etc.), b) are ASCII or ISO 8859-1, c) use the Encode module and encode 249tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module and encode
120your pathnames to the locale (or other) encoding in effect in the user 250your pathnames to the locale (or other) encoding in effect in the user
121environment, d) use Glib::filename_from_unicode on unicode filenames or e) 251environment, d) use Glib::filename_from_unicode on unicode filenames or e)
122use something else. 252use something else to ensure your scalar has the correct contents.
253
254This works, btw. independent of the internal UTF-8 bit, which IO::AIO
255handles correctly whether it is set or not.
123 256
124=over 4 257=over 4
258
259=item $prev_pri = aioreq_pri [$pri]
260
261Returns the priority value that would be used for the next request and, if
262C<$pri> is given, sets the priority for the next aio request.
263
264The default priority is C<0>, the minimum and maximum priorities are C<-4>
265and C<4>, respectively. Requests with higher priority will be serviced
266first.
267
268The priority will be reset to C<0> after each call to one of the C<aio_*>
269functions.
270
271Example: open a file with low priority, then read something from it with
272higher priority so the read request is serviced before other low priority
273open requests (potentially spamming the cache):
274
275 aioreq_pri -3;
276 aio_open ..., sub {
277 return unless $_[0];
278
279 aioreq_pri -2;
280 aio_read $_[0], ..., sub {
281 ...
282 };
283 };
284
285
286=item aioreq_nice $pri_adjust
287
288Similar to C<aioreq_pri>, but subtracts the given value from the current
289priority, so the effect is cumulative.
290
125 291
126=item aio_open $pathname, $flags, $mode, $callback->($fh) 292=item aio_open $pathname, $flags, $mode, $callback->($fh)
127 293
128Asynchronously open or create a file and call the callback with a newly 294Asynchronously open or create a file and call the callback with a newly
129created filehandle for the file. 295created filehandle for the file.
135list. They are the same as used by C<sysopen>. 301list. They are the same as used by C<sysopen>.
136 302
137Likewise, C<$mode> specifies the mode of the newly created file, if it 303Likewise, C<$mode> specifies the mode of the newly created file, if it
138didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>, 304didn't exist and C<O_CREAT> has been given, just like perl's C<sysopen>,
139except that it is mandatory (i.e. use C<0> if you don't create new files, 305except that it is mandatory (i.e. use C<0> if you don't create new files,
140and C<0666> or C<0777> if you do). 306and C<0666> or C<0777> if you do). Note that the C<$mode> will be modified
307by the umask in effect then the request is being executed, so better never
308change the umask.
141 309
142Example: 310Example:
143 311
144 aio_open "/etc/passwd", O_RDONLY, 0, sub { 312 aio_open "/etc/passwd", O_RDONLY, 0, sub {
145 if ($_[0]) { 313 if ($_[0]) {
148 } else { 316 } else {
149 die "open failed: $!\n"; 317 die "open failed: $!\n";
150 } 318 }
151 }; 319 };
152 320
321
153=item aio_close $fh, $callback->($status) 322=item aio_close $fh, $callback->($status)
154 323
155Asynchronously close a file and call the callback with the result 324Asynchronously close a file and call the callback with the result
156code. I<WARNING:> although accepted, you should not pass in a perl 325code.
157filehandle here, as perl will likely close the file descriptor another
158time when the filehandle is destroyed. Normally, you can safely call perls
159C<close> or just let filehandles go out of scope.
160 326
161This is supposed to be a bug in the API, so that might change. It's 327Unfortunately, you can't do this to perl. Perl I<insists> very strongly on
162therefore best to avoid this function. 328closing the file descriptor associated with the filehandle itself.
329
330Therefore, C<aio_close> will not close the filehandle - instead it will
331use dup2 to overwrite the file descriptor with the write-end of a pipe
332(the pipe fd will be created on demand and will be cached).
333
334Or in other words: the file descriptor will be closed, but it will not be
335free for reuse until the perl filehandle is closed.
336
337=cut
163 338
164=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) 339=item aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
165 340
166=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) 341=item aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
167 342
168Reads or writes C<length> bytes from the specified C<fh> and C<offset> 343Reads or writes C<$length> bytes from or to the specified C<$fh> and
169into the scalar given by C<data> and offset C<dataoffset> and calls the 344C<$offset> into the scalar given by C<$data> and offset C<$dataoffset>
170callback without the actual number of bytes read (or -1 on error, just 345and calls the callback without the actual number of bytes read (or -1 on
171like the syscall). 346error, just like the syscall).
347
348C<aio_read> will, like C<sysread>, shrink or grow the C<$data> scalar to
349offset plus the actual number of bytes read.
350
351If C<$offset> is undefined, then the current file descriptor offset will
352be used (and updated), otherwise the file descriptor offset will not be
353changed by these calls.
354
355If C<$length> is undefined in C<aio_write>, use the remaining length of
356C<$data>.
357
358If C<$dataoffset> is less than zero, it will be counted from the end of
359C<$data>.
172 360
173The C<$data> scalar I<MUST NOT> be modified in any way while the request 361The C<$data> scalar I<MUST NOT> be modified in any way while the request
174is outstanding. Modifying it can result in segfaults or WW3 (if the 362is outstanding. Modifying it can result in segfaults or World War III (if
175necessary/optional hardware is installed). 363the necessary/optional hardware is installed).
176 364
177Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at 365Example: Read 15 bytes at offset 7 into scalar C<$buffer>, starting at
178offset C<0> within the scalar: 366offset C<0> within the scalar:
179 367
180 aio_read $fh, 7, 15, $buffer, 0, sub { 368 aio_read $fh, 7, 15, $buffer, 0, sub {
181 $_[0] > 0 or die "read error: $!"; 369 $_[0] > 0 or die "read error: $!";
182 print "read $_[0] bytes: <$buffer>\n"; 370 print "read $_[0] bytes: <$buffer>\n";
183 }; 371 };
184 372
185=item aio_move $srcpath, $dstpath, $callback->($status)
186
187Try to move the I<file> (directories not supported as either source or
188destination) from C<$srcpath> to C<$dstpath> and call the callback with
189the C<0> (error) or C<-1> ok.
190
191This is a composite request that tries to rename(2) the file first. If
192rename files with C<EXDEV>, it creates the destination file with mode 0200
193and copies the contents of the source file into it using C<aio_sendfile>,
194followed by restoring atime, mtime, access mode and uid/gid, in that
195order, and unlinking the C<$srcpath>.
196
197If an error occurs, the partial destination file will be unlinked, if
198possible, except when setting atime, mtime, access mode and uid/gid, where
199errors are being ignored.
200
201=cut
202
203sub aio_move($$$) {
204 my ($src, $dst, $cb) = @_;
205
206 my $grp = aio_group;
207
208 add $grp aio_rename $src, $dst, sub {
209 if ($_[0] && $! == EXDEV) {
210 add $grp aio_open $src, O_RDONLY, 0, sub {
211 if (my $src_fh = $_[0]) {
212 my @stat = stat $src_fh;
213
214 add $grp aio_open $dst, O_WRONLY, 0200, sub {
215 if (my $dst_fh = $_[0]) {
216 add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
217 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 add $grp aio_unlink $src, sub {
226 $cb->($_[0]);
227 };
228 } else {
229 my $errno = $!;
230 add $grp aio_unlink $dst, sub {
231 $! = $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
250 $grp
251}
252 373
253=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) 374=item aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
254 375
255Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts 376Tries to copy C<$length> bytes from C<$in_fh> to C<$out_fh>. It starts
256reading at byte offset C<$in_offset>, and starts writing at the current 377reading at byte offset C<$in_offset>, and starts writing at the current
270C<$in_fh> than are written, and there is no way to find out how many 391C<$in_fh> than are written, and there is no way to find out how many
271bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only 392bytes have been read from C<aio_sendfile> alone, as C<aio_sendfile> only
272provides the number of bytes written to C<$out_fh>. Only if the result 393provides the number of bytes written to C<$out_fh>. Only if the result
273value equals C<$length> one can assume that C<$length> bytes have been 394value equals C<$length> one can assume that C<$length> bytes have been
274read. 395read.
396
275 397
276=item aio_readahead $fh,$offset,$length, $callback->($retval) 398=item aio_readahead $fh,$offset,$length, $callback->($retval)
277 399
278C<aio_readahead> populates the page cache with data from a file so that 400C<aio_readahead> populates the page cache with data from a file so that
279subsequent reads from that file will not block on disk I/O. The C<$offset> 401subsequent reads from that file will not block on disk I/O. The C<$offset>
285file. The current file offset of the file is left unchanged. 407file. The current file offset of the file is left unchanged.
286 408
287If that syscall doesn't exist (likely if your OS isn't Linux) it will be 409If that syscall doesn't exist (likely if your OS isn't Linux) it will be
288emulated by simply reading the data, which would have a similar effect. 410emulated by simply reading the data, which would have a similar effect.
289 411
412
290=item aio_stat $fh_or_path, $callback->($status) 413=item aio_stat $fh_or_path, $callback->($status)
291 414
292=item aio_lstat $fh, $callback->($status) 415=item aio_lstat $fh, $callback->($status)
293 416
294Works like perl's C<stat> or C<lstat> in void context. The callback will 417Works like perl's C<stat> or C<lstat> in void context. The callback will
307 aio_stat "/etc/passwd", sub { 430 aio_stat "/etc/passwd", sub {
308 $_[0] and die "stat failed: $!"; 431 $_[0] and die "stat failed: $!";
309 print "size is ", -s _, "\n"; 432 print "size is ", -s _, "\n";
310 }; 433 };
311 434
435
436=item aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
437
438Works like perl's C<utime> function (including the special case of $atime
439and $mtime being undef). Fractional times are supported if the underlying
440syscalls support them.
441
442When called with a pathname, uses utimes(2) if available, otherwise
443utime(2). If called on a file descriptor, uses futimes(2) if available,
444otherwise returns ENOSYS, so this is not portable.
445
446Examples:
447
448 # set atime and mtime to current time (basically touch(1)):
449 aio_utime "path", undef, undef;
450 # set atime to current time and mtime to beginning of the epoch:
451 aio_utime "path", time, undef; # undef==0
452
453
454=item aio_chown $fh_or_path, $uid, $gid, $callback->($status)
455
456Works like perl's C<chown> function, except that C<undef> for either $uid
457or $gid is being interpreted as "do not change" (but -1 can also be used).
458
459Examples:
460
461 # same as "chown root path" in the shell:
462 aio_chown "path", 0, -1;
463 # same as above:
464 aio_chown "path", 0, undef;
465
466
467=item aio_truncate $fh_or_path, $offset, $callback->($status)
468
469Works like truncate(2) or ftruncate(2).
470
471
472=item aio_chmod $fh_or_path, $mode, $callback->($status)
473
474Works like perl's C<chmod> function.
475
476
312=item aio_unlink $pathname, $callback->($status) 477=item aio_unlink $pathname, $callback->($status)
313 478
314Asynchronously unlink (delete) a file and call the callback with the 479Asynchronously unlink (delete) a file and call the callback with the
315result code. 480result code.
316 481
482
483=item aio_mknod $path, $mode, $dev, $callback->($status)
484
485[EXPERIMENTAL]
486
487Asynchronously create a device node (or fifo). See mknod(2).
488
489The only (POSIX-) portable way of calling this function is:
490
491 aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ...
492
493
317=item aio_link $srcpath, $dstpath, $callback->($status) 494=item aio_link $srcpath, $dstpath, $callback->($status)
318 495
319Asynchronously create a new link to the existing object at C<$srcpath> at 496Asynchronously create a new link to the existing object at C<$srcpath> at
320the path C<$dstpath> and call the callback with the result code. 497the path C<$dstpath> and call the callback with the result code.
321 498
499
322=item aio_symlink $srcpath, $dstpath, $callback->($status) 500=item aio_symlink $srcpath, $dstpath, $callback->($status)
323 501
324Asynchronously create a new symbolic link to the existing object at C<$srcpath> at 502Asynchronously create a new symbolic link to the existing object at C<$srcpath> at
325the path C<$dstpath> and call the callback with the result code. 503the path C<$dstpath> and call the callback with the result code.
326 504
505
506=item aio_readlink $path, $callback->($link)
507
508Asynchronously read the symlink specified by C<$path> and pass it to
509the callback. If an error occurs, nothing or undef gets passed to the
510callback.
511
512
327=item aio_rename $srcpath, $dstpath, $callback->($status) 513=item aio_rename $srcpath, $dstpath, $callback->($status)
328 514
329Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as 515Asynchronously rename the object at C<$srcpath> to C<$dstpath>, just as
330rename(2) and call the callback with the result code. 516rename(2) and call the callback with the result code.
331 517
518
519=item aio_mkdir $pathname, $mode, $callback->($status)
520
521Asynchronously mkdir (create) a directory and call the callback with
522the result code. C<$mode> will be modified by the umask at the time the
523request is executed, so do not change your umask.
524
525
332=item aio_rmdir $pathname, $callback->($status) 526=item aio_rmdir $pathname, $callback->($status)
333 527
334Asynchronously rmdir (delete) a directory and call the callback with the 528Asynchronously rmdir (delete) a directory and call the callback with the
335result code. 529result code.
530
336 531
337=item aio_readdir $pathname, $callback->($entries) 532=item aio_readdir $pathname, $callback->($entries)
338 533
339Unlike the POSIX call of the same name, C<aio_readdir> reads an entire 534Unlike the POSIX call of the same name, C<aio_readdir> reads an entire
340directory (i.e. opendir + readdir + closedir). The entries will not be 535directory (i.e. opendir + readdir + closedir). The entries will not be
341sorted, and will B<NOT> include the C<.> and C<..> entries. 536sorted, and will B<NOT> include the C<.> and C<..> entries.
342 537
343The callback a single argument which is either C<undef> or an array-ref 538The callback is passed a single argument which is either C<undef> or an
344with the filenames. 539array-ref with the filenames.
540
541
542=item aio_readdirx $pathname, $flags, $callback->($entries, $flags)
543
544Quite similar to C<aio_readdir>, but the C<$flags> argument allows to tune
545behaviour and output format. In case of an error, C<$entries> will be
546C<undef>.
547
548The flags are a combination of the following constants, ORed together (the
549flags will also be passed to the callback, possibly modified):
550
551=over 4
552
553=item AIO::READDIR_DENTS
554
555When this flag is off, then the callback gets an arrayref with of names
556only (as with C<aio_readdir>), otherwise it gets an arrayref with
557C<[$name, $inode, $type]> arrayrefs, each describing a single directory
558entry in more detail.
559
560C<$name> is the name of the entry.
561
562C<$inode> is the inode number (which might not be exact on systems with 64
563bit inode numbers and 32 bit perls). On systems that do not deliver the
564inode information, this will always be zero.
565
566C<$type> is one of the C<AIO::DT_xxx> constants:
567
568C<AIO::DT_UNKNOWN>, C<AIO::DT_FIFO>, C<AIO::DT_CHR>, C<AIO::DT_DIR>,
569C<AIO::DT_BLK>, C<AIO::DT_REG>, C<AIO::DT_LNK>, C<AIO::DT_SOCK>,
570C<AIO::DT_WHT>.
571
572C<AIO::DT_UNKNOWN> means just that: readdir does not know. If you need to
573know, you have to run stat yourself. Also, for speed reasons, the C<$type>
574scalars are read-only: you can not modify them.
575
576=item AIO::READDIR_DIRS_FIRST
577
578When this flag is set, then the names will be returned in an order where
579likely directories come first. This is useful when you need to quickly
580find directories, or you want to find all directories while avoiding to
581stat() each entry.
582
583=item AIO::READDIR_STAT_ORDER
584
585When this flag is set, then the names will be returned in an order
586suitable for stat()'ing each one. That is, when you plan to stat()
587all files in the given directory, then the returned order will likely
588be fastest.
589
590If both this flag and IO::READDIR_DIRS_FIRST are specified, then the
591likely dirs come first, resulting in a less optimal stat order.
592
593=item AIO::READDIR_FOUND_UNKNOWN
594
595This flag should not be set when calling C<aio_readdirx>. Instead, it
596is being set by C<aio_readdirx>, when any of the C<$type>'s found were
597C<AIO::DT_UNKNOWN>. The absense of this flag therefore indicates that all
598C<$type>'s are known, which can be used to speed up some algorithms.
599
600=back
601
602
603=item aio_load $path, $data, $callback->($status)
604
605This is a composite request that tries to fully load the given file into
606memory. Status is the same as with aio_read.
607
608=cut
609
610sub aio_load($$;$) {
611 my ($path, undef, $cb) = @_;
612 my $data = \$_[1];
613
614 my $pri = aioreq_pri;
615 my $grp = aio_group $cb;
616
617 aioreq_pri $pri;
618 add $grp aio_open $path, O_RDONLY, 0, sub {
619 my $fh = shift
620 or return $grp->result (-1);
621
622 aioreq_pri $pri;
623 add $grp aio_read $fh, 0, (-s $fh), $$data, 0, sub {
624 $grp->result ($_[0]);
625 };
626 };
627
628 $grp
629}
630
631=item aio_copy $srcpath, $dstpath, $callback->($status)
632
633Try to copy the I<file> (directories not supported as either source or
634destination) from C<$srcpath> to C<$dstpath> and call the callback with
635the C<0> (error) or C<-1> ok.
636
637This is a composite request that creates the destination file with
638mode 0200 and copies the contents of the source file into it using
639C<aio_sendfile>, followed by restoring atime, mtime, access mode and
640uid/gid, in that order.
641
642If an error occurs, the partial destination file will be unlinked, if
643possible, except when setting atime, mtime, access mode and uid/gid, where
644errors are being ignored.
645
646=cut
647
648sub aio_copy($$;$) {
649 my ($src, $dst, $cb) = @_;
650
651 my $pri = aioreq_pri;
652 my $grp = aio_group $cb;
653
654 aioreq_pri $pri;
655 add $grp aio_open $src, O_RDONLY, 0, sub {
656 if (my $src_fh = $_[0]) {
657 my @stat = stat $src_fh; # hmm, might bock over nfs?
658
659 aioreq_pri $pri;
660 add $grp aio_open $dst, O_CREAT | O_WRONLY | O_TRUNC, 0200, sub {
661 if (my $dst_fh = $_[0]) {
662 aioreq_pri $pri;
663 add $grp aio_sendfile $dst_fh, $src_fh, 0, $stat[7], sub {
664 if ($_[0] == $stat[7]) {
665 $grp->result (0);
666 close $src_fh;
667
668 my $ch = sub {
669 aioreq_pri $pri;
670 add $grp aio_chmod $dst_fh, $stat[2] & 07777, sub {
671 aioreq_pri $pri;
672 add $grp aio_chown $dst_fh, $stat[4], $stat[5], sub {
673 aioreq_pri $pri;
674 add $grp aio_close $dst_fh;
675 }
676 };
677 };
678
679 aioreq_pri $pri;
680 add $grp aio_utime $dst_fh, $stat[8], $stat[9], sub {
681 if ($_[0] < 0 && $! == ENOSYS) {
682 aioreq_pri $pri;
683 add $grp aio_utime $dst, $stat[8], $stat[9], $ch;
684 } else {
685 $ch->();
686 }
687 };
688 } else {
689 $grp->result (-1);
690 close $src_fh;
691 close $dst_fh;
692
693 aioreq $pri;
694 add $grp aio_unlink $dst;
695 }
696 };
697 } else {
698 $grp->result (-1);
699 }
700 },
701
702 } else {
703 $grp->result (-1);
704 }
705 };
706
707 $grp
708}
709
710=item aio_move $srcpath, $dstpath, $callback->($status)
711
712Try to move the I<file> (directories not supported as either source or
713destination) from C<$srcpath> to C<$dstpath> and call the callback with
714the C<0> (error) or C<-1> ok.
715
716This is a composite request that tries to rename(2) the file first; if
717rename fails with C<EXDEV>, it copies the file with C<aio_copy> and, if
718that is successful, unlinks the C<$srcpath>.
719
720=cut
721
722sub aio_move($$;$) {
723 my ($src, $dst, $cb) = @_;
724
725 my $pri = aioreq_pri;
726 my $grp = aio_group $cb;
727
728 aioreq_pri $pri;
729 add $grp aio_rename $src, $dst, sub {
730 if ($_[0] && $! == EXDEV) {
731 aioreq_pri $pri;
732 add $grp aio_copy $src, $dst, sub {
733 $grp->result ($_[0]);
734
735 if (!$_[0]) {
736 aioreq_pri $pri;
737 add $grp aio_unlink $src;
738 }
739 };
740 } else {
741 $grp->result ($_[0]);
742 }
743 };
744
745 $grp
746}
345 747
346=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) 748=item aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
347 749
348Scans a directory (similar to C<aio_readdir>) but additionally tries to 750Scans a directory (similar to C<aio_readdir>) but additionally tries to
349separate the entries of directory C<$path> into two sets of names, ones 751efficiently separate the entries of directory C<$path> into two sets of
350you can recurse into (directories or links to them), and ones you cannot 752names, directories you can recurse into (directories), and ones you cannot
351recurse into (everything else). 753recurse into (everything else, including symlinks to directories).
352 754
353C<aio_scandir> is a composite request that consists of many sub 755C<aio_scandir> is a composite request that creates of many sub requests_
354requests. C<$maxreq> specifies the maximum number of outstanding aio 756C<$maxreq> specifies the maximum number of outstanding aio requests that
355requests that this function generates. If it is C<< <= 0 >>, then a 757this function generates. If it is C<< <= 0 >>, then a suitable default
356suitable default will be chosen (currently 8). 758will be chosen (currently 4).
357 759
358On error, the callback is called without arguments, otherwise it receives 760On error, the callback is called without arguments, otherwise it receives
359two array-refs with path-relative entry names. 761two array-refs with path-relative entry names.
360 762
361Example: 763Example:
395as those tend to return 0 or 1 as link counts, which disables the 797as those tend to return 0 or 1 as link counts, which disables the
396directory counting heuristic. 798directory counting heuristic.
397 799
398=cut 800=cut
399 801
400sub aio_scandir($$$) { 802sub aio_scandir($$;$) {
401 my ($path, $maxreq, $cb) = @_; 803 my ($path, $maxreq, $cb) = @_;
402 804
805 my $pri = aioreq_pri;
806
403 my $grp = aio_group; 807 my $grp = aio_group $cb;
404 808
405 $maxreq = 8 if $maxreq <= 0; 809 $maxreq = 4 if $maxreq <= 0;
406 810
407 # stat once 811 # stat once
812 aioreq_pri $pri;
408 add $grp aio_stat $path, sub { 813 add $grp aio_stat $path, sub {
409 return $cb->() if $_[0]; 814 return $grp->result () if $_[0];
410 my $now = time; 815 my $now = time;
411 my $hash1 = join ":", (stat _)[0,1,3,7,9]; 816 my $hash1 = join ":", (stat _)[0,1,3,7,9];
412 817
413 # read the directory entries 818 # read the directory entries
819 aioreq_pri $pri;
414 add $grp aio_readdir $path, sub { 820 add $grp aio_readdirx $path, READDIR_DIRS_FIRST, sub {
415 my $entries = shift 821 my $entries = shift
416 or return $cb->(); 822 or return $grp->result ();
417 823
418 # stat the dir another time 824 # stat the dir another time
825 aioreq_pri $pri;
419 add $grp aio_stat $path, sub { 826 add $grp aio_stat $path, sub {
420 my $hash2 = join ":", (stat _)[0,1,3,7,9]; 827 my $hash2 = join ":", (stat _)[0,1,3,7,9];
421 828
422 my $ndirs; 829 my $ndirs;
423 830
426 $ndirs = -1; 833 $ndirs = -1;
427 } else { 834 } else {
428 # if nlink == 2, we are finished 835 # if nlink == 2, we are finished
429 # on non-posix-fs's, we rely on nlink < 2 836 # on non-posix-fs's, we rely on nlink < 2
430 $ndirs = (stat _)[3] - 2 837 $ndirs = (stat _)[3] - 2
431 or return $cb->([], $entries); 838 or return $grp->result ([], $entries);
432 } 839 }
433 840
434 # sort into likely dirs and likely nondirs 841 # sort into likely dirs and likely nondirs
435 # dirs == files without ".", short entries first 842 # dirs == files without ".", short entries first
436 $entries = [map $_->[0], 843 $entries = [map $_->[0],
438 map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length], 845 map [$_, sprintf "%s%04d", (/.\./ ? "1" : "0"), length],
439 @$entries]; 846 @$entries];
440 847
441 my (@dirs, @nondirs); 848 my (@dirs, @nondirs);
442 849
443 my ($statcb, $schedcb); 850 my $statgrp = add $grp aio_group sub {
444 my $nreq = 0; 851 $grp->result (\@dirs, \@nondirs);
852 };
445 853
446 $schedcb = sub { 854 limit $statgrp $maxreq;
447 if (@$entries) { 855 feed $statgrp sub {
448 if ($nreq < $maxreq) { 856 return unless @$entries;
449 my $ent = pop @$entries; 857 my $entry = pop @$entries;
858
859 aioreq_pri $pri;
860 add $statgrp aio_stat "$path/$entry/.", sub {
861 if ($_[0] < 0) {
862 push @nondirs, $entry;
863 } else {
864 # need to check for real directory
865 aioreq_pri $pri;
866 add $statgrp aio_lstat "$path/$entry", sub {
867 if (-d _) {
868 push @dirs, $entry;
869
870 unless (--$ndirs) {
871 push @nondirs, @$entries;
872 feed $statgrp;
873 }
874 } else {
875 push @nondirs, $entry;
876 }
450 $nreq++; 877 }
451 add $grp aio_stat "$path/$ent/.", sub { $statcb->($_[0], $ent) };
452 } 878 }
453 } elsif (!$nreq) {
454 # finished
455 undef $statcb;
456 undef $schedcb;
457 $cb->(\@dirs, \@nondirs) if $cb;
458 undef $cb;
459 } 879 };
460 }; 880 };
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 add $grp aio_lstat "$path/$entry", sub {
471 $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 }; 881 };
491 }; 882 };
492 }; 883 };
493 884
494 $grp 885 $grp
495} 886}
496 887
888=item aio_rmtree $path, $callback->($status)
889
890Delete a directory tree starting (and including) C<$path>, return the
891status of the final C<rmdir> only. This is a composite request that
892uses C<aio_scandir> to recurse into and rmdir directories, and unlink
893everything else.
894
895=cut
896
897sub aio_rmtree;
898sub aio_rmtree($;$) {
899 my ($path, $cb) = @_;
900
901 my $pri = aioreq_pri;
902 my $grp = aio_group $cb;
903
904 aioreq_pri $pri;
905 add $grp aio_scandir $path, 0, sub {
906 my ($dirs, $nondirs) = @_;
907
908 my $dirgrp = aio_group sub {
909 add $grp aio_rmdir $path, sub {
910 $grp->result ($_[0]);
911 };
912 };
913
914 (aioreq_pri $pri), add $dirgrp aio_rmtree "$path/$_" for @$dirs;
915 (aioreq_pri $pri), add $dirgrp aio_unlink "$path/$_" for @$nondirs;
916
917 add $grp $dirgrp;
918 };
919
920 $grp
921}
922
923=item aio_sync $callback->($status)
924
925Asynchronously call sync and call the callback when finished.
926
497=item aio_fsync $fh, $callback->($status) 927=item aio_fsync $fh, $callback->($status)
498 928
499Asynchronously call fsync on the given filehandle and call the callback 929Asynchronously call fsync on the given filehandle and call the callback
500with the fsync result code. 930with the fsync result code.
501 931
505callback with the fdatasync result code. 935callback with the fdatasync result code.
506 936
507If this call isn't available because your OS lacks it or it couldn't be 937If this call isn't available because your OS lacks it or it couldn't be
508detected, it will be emulated by calling C<fsync> instead. 938detected, it will be emulated by calling C<fsync> instead.
509 939
940=item aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
941
942Sync the data portion of the file specified by C<$offset> and C<$length>
943to disk (but NOT the metadata), by calling the Linux-specific
944sync_file_range call. If sync_file_range is not available or it returns
945ENOSYS, then fdatasync or fsync is being substituted.
946
947C<$flags> can be a combination of C<IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE>,
948C<IO::AIO::SYNC_FILE_RANGE_WRITE> and
949C<IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER>: refer to the sync_file_range
950manpage for details.
951
952=item aio_pathsync $path, $callback->($status)
953
954This request tries to open, fsync and close the given path. This is a
955composite request intended to sync directories after directory operations
956(E.g. rename). This might not work on all operating systems or have any
957specific effect, but usually it makes sure that directory changes get
958written to disc. It works for anything that can be opened for read-only,
959not just directories.
960
961Passes C<0> when everything went ok, and C<-1> on error.
962
963=cut
964
965sub aio_pathsync($;$) {
966 my ($path, $cb) = @_;
967
968 my $pri = aioreq_pri;
969 my $grp = aio_group $cb;
970
971 aioreq_pri $pri;
972 add $grp aio_open $path, O_RDONLY, 0, sub {
973 my ($fh) = @_;
974 if ($fh) {
975 aioreq_pri $pri;
976 add $grp aio_fsync $fh, sub {
977 $grp->result ($_[0]);
978
979 aioreq_pri $pri;
980 add $grp aio_close $fh;
981 };
982 } else {
983 $grp->result (-1);
984 }
985 };
986
987 $grp
988}
989
510=item aio_group $callback->() 990=item aio_group $callback->(...)
511
512[EXPERIMENTAL]
513 991
514This is a very special aio request: Instead of doing something, it is a 992This is a very special aio request: Instead of doing something, it is a
515container for other aio requests, which is useful if you want to bundle 993container for other aio requests, which is useful if you want to bundle
516many requests into a single, composite, request. 994many requests into a single, composite, request with a definite callback
995and the ability to cancel the whole request with its subrequests.
517 996
518Returns an object of class L<IO::AIO::GRP>. See its documentation below 997Returns an object of class L<IO::AIO::GRP>. See its documentation below
519for more info. 998for more info.
520 999
521Example: 1000Example:
527 add $grp 1006 add $grp
528 (aio_stat ...), 1007 (aio_stat ...),
529 (aio_stat ...), 1008 (aio_stat ...),
530 ...; 1009 ...;
531 1010
1011=item aio_nop $callback->()
1012
1013This is a special request - it does nothing in itself and is only used for
1014side effects, such as when you want to add a dummy request to a group so
1015that finishing the requests in the group depends on executing the given
1016code.
1017
1018While this request does nothing, it still goes through the execution
1019phase and still requires a worker thread. Thus, the callback will not
1020be executed immediately but only after other requests in the queue have
1021entered their execution phase. This can be used to measure request
1022latency.
1023
532=item IO::AIO::aio_sleep $fractional_seconds, $callback->() *NOT EXPORTED* 1024=item IO::AIO::aio_busy $fractional_seconds, $callback->() *NOT EXPORTED*
533 1025
534Mainly used for debugging and benchmarking, this aio request puts one of 1026Mainly used for debugging and benchmarking, this aio request puts one of
535the request workers to sleep for the given time. 1027the request workers to sleep for the given time.
536 1028
537While it is theoretically handy to have simple I/O scheduling requests 1029While it is theoretically handy to have simple I/O scheduling requests
538like sleep and file handle readable/writable, the overhead this creates 1030like sleep and file handle readable/writable, the overhead this creates is
539is immense, so do not use this function except to put your application 1031immense (it blocks a thread for a long time) so do not use this function
540under artificial I/O pressure. 1032except to put your application under artificial I/O pressure.
541 1033
542=back 1034=back
543 1035
544=head2 IO::AIO::REQ CLASS 1036=head2 IO::AIO::REQ CLASS
545 1037
546All non-aggregate C<aio_*> functions return an object of this class when 1038All non-aggregate C<aio_*> functions return an object of this class when
547called in non-void context. 1039called in non-void context.
548 1040
549A request always moves through the following five states in its lifetime,
550in order: B<ready> (request has been created, but has not been executed
551yet), B<execute> (request is currently being executed), B<pending>
552(request has been executed but callback has not been called yet),
553B<result> (results are being processed synchronously, includes calling the
554callback) and B<done> (request has reached the end of its lifetime and
555holds no resources anymore).
556
557=over 4 1041=over 4
558 1042
559=item $req->cancel 1043=item cancel $req
560 1044
561Cancels the request, if possible. Has the effect of skipping execution 1045Cancels the request, if possible. Has the effect of skipping execution
562when entering the B<execute> state and skipping calling the callback when 1046when entering the B<execute> state and skipping calling the callback when
563entering the the B<result> state, but will leave the request otherwise 1047entering the the B<result> state, but will leave the request otherwise
564untouched. That means that requests that currently execute will not be 1048untouched. That means that requests that currently execute will not be
565stopped and resources held by the request will not be freed prematurely. 1049stopped and resources held by the request will not be freed prematurely.
566 1050
1051=item cb $req $callback->(...)
1052
1053Replace (or simply set) the callback registered to the request.
1054
567=back 1055=back
568 1056
569=head2 IO::AIO::GRP CLASS 1057=head2 IO::AIO::GRP CLASS
570 1058
571This class is a subclass of L<IO::AIO::REQ>, so all its methods apply to 1059This class is a subclass of L<IO::AIO::REQ>, so all its methods apply to
585You add requests by calling the C<add> method with one or more 1073You add requests by calling the C<add> method with one or more
586C<IO::AIO::REQ> objects: 1074C<IO::AIO::REQ> objects:
587 1075
588 $grp->add (aio_unlink "..."); 1076 $grp->add (aio_unlink "...");
589 1077
590 add $grp aio_stat "...", sub { ... }; 1078 add $grp aio_stat "...", sub {
1079 $_[0] or return $grp->result ("error");
1080
1081 # add another request dynamically, if first succeeded
1082 add $grp aio_open "...", sub {
1083 $grp->result ("ok");
1084 };
1085 };
591 1086
592This makes it very easy to create composite requests (see the source of 1087This makes it very easy to create composite requests (see the source of
593C<aio_move> for an application) that work and feel like simple requests. 1088C<aio_move> for an application) that work and feel like simple requests.
594 1089
1090=over 4
1091
595The IO::AIO::GRP objects will be cleaned up during calls to 1092=item * The IO::AIO::GRP objects will be cleaned up during calls to
596C<IO::AIO::poll_cb>, just like any other request. 1093C<IO::AIO::poll_cb>, just like any other request.
597 1094
598They can be canceled like any other request. Canceling will cancel not 1095=item * They can be canceled like any other request. Canceling will cancel not
599just the request itself, but also all requests it contains. 1096only the request itself, but also all requests it contains.
600 1097
601They can also can also be added to other IO::AIO::GRP objects. 1098=item * They can also can also be added to other IO::AIO::GRP objects.
1099
1100=item * You must not add requests to a group from within the group callback (or
1101any later time).
1102
1103=back
602 1104
603Their lifetime, simplified, looks like this: when they are empty, they 1105Their lifetime, simplified, looks like this: when they are empty, they
604will finish very quickly. If they contain only requests that are in the 1106will finish very quickly. If they contain only requests that are in the
605C<done> state, they will also finish. Otherwise they will continue to 1107C<done> state, they will also finish. Otherwise they will continue to
606exist. 1108exist.
607 1109
608That means after creating a group you have some time to add requests. And 1110That means after creating a group you have some time to add requests
609in the callbacks of those requests, you can add further requests to the 1111(precisely before the callback has been invoked, which is only done within
610group. And only when all those requests have finished will the the group 1112the C<poll_cb>). And in the callbacks of those requests, you can add
611itself finish. 1113further requests to the group. And only when all those requests have
1114finished will the the group itself finish.
612 1115
613=over 4 1116=over 4
614 1117
1118=item add $grp ...
1119
615=item $grp->add (...) 1120=item $grp->add (...)
616
617=item add $grp ...
618 1121
619Add one or more requests to the group. Any type of L<IO::AIO::REQ> can 1122Add one or more requests to the group. Any type of L<IO::AIO::REQ> can
620be added, including other groups, as long as you do not create circular 1123be added, including other groups, as long as you do not create circular
621dependencies. 1124dependencies.
622 1125
623Returns all its arguments. 1126Returns all its arguments.
624 1127
1128=item $grp->cancel_subs
1129
1130Cancel all subrequests and clears any feeder, but not the group request
1131itself. Useful when you queued a lot of events but got a result early.
1132
1133=item $grp->result (...)
1134
1135Set the result value(s) that will be passed to the group callback when all
1136subrequests have finished and set the groups errno to the current value
1137of errno (just like calling C<errno> without an error number). By default,
1138no argument will be passed and errno is zero.
1139
1140=item $grp->errno ([$errno])
1141
1142Sets the group errno value to C<$errno>, or the current value of errno
1143when the argument is missing.
1144
1145Every aio request has an associated errno value that is restored when
1146the callback is invoked. This method lets you change this value from its
1147default (0).
1148
1149Calling C<result> will also set errno, so make sure you either set C<$!>
1150before the call to C<result>, or call c<errno> after it.
1151
1152=item feed $grp $callback->($grp)
1153
1154Sets a feeder/generator on this group: every group can have an attached
1155generator that generates requests if idle. The idea behind this is that,
1156although you could just queue as many requests as you want in a group,
1157this might starve other requests for a potentially long time. For example,
1158C<aio_scandir> might generate hundreds of thousands C<aio_stat> requests,
1159delaying any later requests for a long time.
1160
1161To avoid this, and allow incremental generation of requests, you can
1162instead a group and set a feeder on it that generates those requests. The
1163feed callback will be called whenever there are few enough (see C<limit>,
1164below) requests active in the group itself and is expected to queue more
1165requests.
1166
1167The feed callback can queue as many requests as it likes (i.e. C<add> does
1168not impose any limits).
1169
1170If the feed does not queue more requests when called, it will be
1171automatically removed from the group.
1172
1173If the feed limit is C<0> when this method is called, it will be set to
1174C<2> automatically.
1175
1176Example:
1177
1178 # stat all files in @files, but only ever use four aio requests concurrently:
1179
1180 my $grp = aio_group sub { print "finished\n" };
1181 limit $grp 4;
1182 feed $grp sub {
1183 my $file = pop @files
1184 or return;
1185
1186 add $grp aio_stat $file, sub { ... };
1187 };
1188
1189=item limit $grp $num
1190
1191Sets the feeder limit for the group: The feeder will be called whenever
1192the group contains less than this many requests.
1193
1194Setting the limit to C<0> will pause the feeding process.
1195
1196The default value for the limit is C<0>, but note that setting a feeder
1197automatically bumps it up to C<2>.
1198
625=back 1199=back
626 1200
627=head2 SUPPORT FUNCTIONS 1201=head2 SUPPORT FUNCTIONS
1202
1203=head3 EVENT PROCESSING AND EVENT LOOP INTEGRATION
628 1204
629=over 4 1205=over 4
630 1206
631=item $fileno = IO::AIO::poll_fileno 1207=item $fileno = IO::AIO::poll_fileno
632 1208
637 1213
638See C<poll_cb> for an example. 1214See C<poll_cb> for an example.
639 1215
640=item IO::AIO::poll_cb 1216=item IO::AIO::poll_cb
641 1217
642Process all outstanding events on the result pipe. You have to call this 1218Process some outstanding events on the result pipe. You have to call this
643regularly. Returns the number of events processed. Returns immediately 1219regularly. Returns C<0> if all events could be processed, or C<-1> if it
644when no events are outstanding. 1220returned earlier for whatever reason. Returns immediately when no events
1221are outstanding. The amount of events processed depends on the settings of
1222C<IO::AIO::max_poll_req> and C<IO::AIO::max_poll_time>.
1223
1224If not all requests were processed for whatever reason, the filehandle
1225will still be ready when C<poll_cb> returns, so normally you don't have to
1226do anything special to have it called later.
645 1227
646Example: Install an Event watcher that automatically calls 1228Example: Install an Event watcher that automatically calls
647IO::AIO::poll_cb with high priority: 1229IO::AIO::poll_cb with high priority:
648 1230
649 Event->io (fd => IO::AIO::poll_fileno, 1231 Event->io (fd => IO::AIO::poll_fileno,
650 poll => 'r', async => 1, 1232 poll => 'r', async => 1,
651 cb => \&IO::AIO::poll_cb); 1233 cb => \&IO::AIO::poll_cb);
652 1234
1235=item IO::AIO::max_poll_reqs $nreqs
1236
1237=item IO::AIO::max_poll_time $seconds
1238
1239These set the maximum number of requests (default C<0>, meaning infinity)
1240that are being processed by C<IO::AIO::poll_cb> in one call, respectively
1241the maximum amount of time (default C<0>, meaning infinity) spent in
1242C<IO::AIO::poll_cb> to process requests (more correctly the mininum amount
1243of time C<poll_cb> is allowed to use).
1244
1245Setting C<max_poll_time> to a non-zero value creates an overhead of one
1246syscall per request processed, which is not normally a problem unless your
1247callbacks are really really fast or your OS is really really slow (I am
1248not mentioning Solaris here). Using C<max_poll_reqs> incurs no overhead.
1249
1250Setting these is useful if you want to ensure some level of
1251interactiveness when perl is not fast enough to process all requests in
1252time.
1253
1254For interactive programs, values such as C<0.01> to C<0.1> should be fine.
1255
1256Example: Install an Event watcher that automatically calls
1257IO::AIO::poll_cb with low priority, to ensure that other parts of the
1258program get the CPU sometimes even under high AIO load.
1259
1260 # try not to spend much more than 0.1s in poll_cb
1261 IO::AIO::max_poll_time 0.1;
1262
1263 # use a low priority so other tasks have priority
1264 Event->io (fd => IO::AIO::poll_fileno,
1265 poll => 'r', nice => 1,
1266 cb => &IO::AIO::poll_cb);
1267
653=item IO::AIO::poll_wait 1268=item IO::AIO::poll_wait
654 1269
1270If there are any outstanding requests and none of them in the result
655Wait till the result filehandle becomes ready for reading (simply does a 1271phase, wait till the result filehandle becomes ready for reading (simply
656C<select> on the filehandle. This is useful if you want to synchronously wait 1272does a C<select> on the filehandle. This is useful if you want to
657for some requests to finish). 1273synchronously wait for some requests to finish).
658 1274
659See C<nreqs> for an example. 1275See C<nreqs> for an example.
660 1276
1277=item IO::AIO::poll
1278
1279Waits until some requests have been handled.
1280
1281Returns the number of requests processed, but is otherwise strictly
1282equivalent to:
1283
1284 IO::AIO::poll_wait, IO::AIO::poll_cb
1285
661=item IO::AIO::nreqs 1286=item IO::AIO::flush
662 1287
663Returns the number of requests currently outstanding (i.e. for which their 1288Wait till all outstanding AIO requests have been handled.
664callback has not been invoked yet).
665 1289
666Example: wait till there are no outstanding requests anymore: 1290Strictly equivalent to:
667 1291
668 IO::AIO::poll_wait, IO::AIO::poll_cb 1292 IO::AIO::poll_wait, IO::AIO::poll_cb
669 while IO::AIO::nreqs; 1293 while IO::AIO::nreqs;
670 1294
671=item IO::AIO::flush 1295=back
672 1296
673Wait till all outstanding AIO requests have been handled. 1297=head3 CONTROLLING THE NUMBER OF THREADS
674 1298
675Strictly equivalent to: 1299=over
676
677 IO::AIO::poll_wait, IO::AIO::poll_cb
678 while IO::AIO::nreqs;
679
680=item IO::AIO::poll
681
682Waits until some requests have been handled.
683
684Strictly equivalent to:
685
686 IO::AIO::poll_wait, IO::AIO::poll_cb
687 if IO::AIO::nreqs;
688 1300
689=item IO::AIO::min_parallel $nthreads 1301=item IO::AIO::min_parallel $nthreads
690 1302
691Set the minimum number of AIO threads to C<$nthreads>. The current default 1303Set the minimum number of AIO threads to C<$nthreads>. The current
692is C<4>, which means four asynchronous operations can be done at one time 1304default is C<8>, which means eight asynchronous operations can execute
693(the number of outstanding operations, however, is unlimited). 1305concurrently at any one time (the number of outstanding requests,
1306however, is unlimited).
694 1307
695IO::AIO starts threads only on demand, when an AIO request is queued and 1308IO::AIO starts threads only on demand, when an AIO request is queued and
696no free thread exists. 1309no free thread exists. Please note that queueing up a hundred requests can
1310create demand for a hundred threads, even if it turns out that everything
1311is in the cache and could have been processed faster by a single thread.
697 1312
698It is recommended to keep the number of threads low, as some Linux 1313It is recommended to keep the number of threads relatively low, as some
699kernel versions will scale negatively with the number of threads (higher 1314Linux kernel versions will scale negatively with the number of threads
700parallelity => MUCH higher latency). With current Linux 2.6 versions, 4-32 1315(higher parallelity => MUCH higher latency). With current Linux 2.6
701threads should be fine. 1316versions, 4-32 threads should be fine.
702 1317
703Under most circumstances you don't need to call this function, as the 1318Under most circumstances you don't need to call this function, as the
704module selects a default that is suitable for low to moderate load. 1319module selects a default that is suitable for low to moderate load.
705 1320
706=item IO::AIO::max_parallel $nthreads 1321=item IO::AIO::max_parallel $nthreads
715This module automatically runs C<max_parallel 0> at program end, to ensure 1330This module automatically runs C<max_parallel 0> at program end, to ensure
716that all threads are killed and that there are no outstanding requests. 1331that all threads are killed and that there are no outstanding requests.
717 1332
718Under normal circumstances you don't need to call this function. 1333Under normal circumstances you don't need to call this function.
719 1334
1335=item IO::AIO::max_idle $nthreads
1336
1337Limit the number of threads (default: 4) that are allowed to idle (i.e.,
1338threads that did not get a request to process within 10 seconds). That
1339means if a thread becomes idle while C<$nthreads> other threads are also
1340idle, it will free its resources and exit.
1341
1342This is useful when you allow a large number of threads (e.g. 100 or 1000)
1343to allow for extremely high load situations, but want to free resources
1344under normal circumstances (1000 threads can easily consume 30MB of RAM).
1345
1346The default is probably ok in most situations, especially if thread
1347creation is fast. If thread creation is very slow on your system you might
1348want to use larger values.
1349
720=item $oldnreqs = IO::AIO::max_outstanding $nreqs 1350=item IO::AIO::max_outstanding $maxreqs
1351
1352This is a very bad function to use in interactive programs because it
1353blocks, and a bad way to reduce concurrency because it is inexact: Better
1354use an C<aio_group> together with a feed callback.
721 1355
722Sets the maximum number of outstanding requests to C<$nreqs>. If you 1356Sets the maximum number of outstanding requests to C<$nreqs>. If you
723try to queue up more than this number of requests, the caller will block until 1357do queue up more than this number of requests, the next call to the
724some requests have been handled. 1358C<poll_cb> (and C<poll_some> and other functions calling C<poll_cb>)
1359function will block until the limit is no longer exceeded.
725 1360
726The default is very large, so normally there is no practical limit. If you 1361The default value is very large, so there is no practical limit on the
727queue up many requests in a loop it often improves speed if you set 1362number of outstanding requests.
728this to a relatively low number, such as C<100>.
729 1363
730Under normal circumstances you don't need to call this function. 1364You can still queue as many requests as you want. Therefore,
1365C<max_outstanding> is mainly useful in simple scripts (with low values) or
1366as a stop gap to shield against fatal memory overflow (with large values).
731 1367
732=back 1368=back
733 1369
1370=head3 STATISTICAL INFORMATION
1371
1372=over
1373
1374=item IO::AIO::nreqs
1375
1376Returns the number of requests currently in the ready, execute or pending
1377states (i.e. for which their callback has not been invoked yet).
1378
1379Example: wait till there are no outstanding requests anymore:
1380
1381 IO::AIO::poll_wait, IO::AIO::poll_cb
1382 while IO::AIO::nreqs;
1383
1384=item IO::AIO::nready
1385
1386Returns the number of requests currently in the ready state (not yet
1387executed).
1388
1389=item IO::AIO::npending
1390
1391Returns the number of requests currently in the pending state (executed,
1392but not yet processed by poll_cb).
1393
1394=back
1395
734=cut 1396=cut
735 1397
736# support function to convert a fd into a perl filehandle
737sub _fd2fh {
738 return undef if $_[0] < 0;
739
740 # try to generate nice filehandles
741 my $sym = "IO::AIO::fd#$_[0]";
742 local *$sym;
743
744 open *$sym, "+<&=$_[0]" # usually works under any unix
745 or open *$sym, "<&=$_[0]" # cygwin needs this
746 or open *$sym, ">&=$_[0]" # or this
747 or return undef;
748
749 *$sym
750}
751
752min_parallel 4; 1398min_parallel 8;
753 1399
754END { 1400END { flush }
755 max_parallel 0;
756}
757 1401
7581; 14021;
759 1403
760=head2 FORK BEHAVIOUR 1404=head2 FORK BEHAVIOUR
761 1405
762This module should do "the right thing" when the process using it forks: 1406This module should do "the right thing" when the process using it forks:
763 1407
764Before the fork, IO::AIO enters a quiescent state where no requests 1408Before the fork, IO::AIO enters a quiescent state where no requests
765can be added in other threads and no results will be processed. After 1409can be added in other threads and no results will be processed. After
766the fork the parent simply leaves the quiescent state and continues 1410the fork the parent simply leaves the quiescent state and continues
767request/result processing, while the child clears the request/result 1411request/result processing, while the child frees the request/result queue
768queue (so the requests started before the fork will only be handled in 1412(so that the requests started before the fork will only be handled in the
769the parent). Threads will be started on demand until the limit ste in the 1413parent). Threads will be started on demand until the limit set in the
770parent process has been reached again. 1414parent process has been reached again.
771 1415
772In short: the parent will, after a short pause, continue as if fork had 1416In short: the parent will, after a short pause, continue as if fork had
773not been called, while the child will act as if IO::AIO has not been used 1417not been called, while the child will act as if IO::AIO has not been used
774yet. 1418yet.
775 1419
1420=head2 MEMORY USAGE
1421
1422Per-request usage:
1423
1424Each aio request uses - depending on your architecture - around 100-200
1425bytes of memory. In addition, stat requests need a stat buffer (possibly
1426a few hundred bytes), readdir requires a result buffer and so on. Perl
1427scalars and other data passed into aio requests will also be locked and
1428will consume memory till the request has entered the done state.
1429
1430This is not awfully much, so queuing lots of requests is not usually a
1431problem.
1432
1433Per-thread usage:
1434
1435In the execution phase, some aio requests require more memory for
1436temporary buffers, and each thread requires a stack and other data
1437structures (usually around 16k-128k, depending on the OS).
1438
1439=head1 KNOWN BUGS
1440
1441Known bugs will be fixed in the next release.
1442
776=head1 SEE ALSO 1443=head1 SEE ALSO
777 1444
778L<Coro>, L<Linux::AIO> (obsolete). 1445L<AnyEvent::AIO> for easy integration into event loops, L<Coro::AIO> for a
1446more natural syntax.
779 1447
780=head1 AUTHOR 1448=head1 AUTHOR
781 1449
782 Marc Lehmann <schmorp@schmorp.de> 1450 Marc Lehmann <schmorp@schmorp.de>
783 http://home.schmorp.de/ 1451 http://home.schmorp.de/

Diff Legend

Removed lines
+ Added lines
< Changed lines
> Changed lines