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

Comparing IO-AIO/README (file contents):
Revision 1.17 by root, Mon Jun 26 14:53:55 2006 UTC vs.
Revision 1.43 by root, Sun Jan 10 23:44:02 2010 UTC

… …
3 3
4SYNOPSIS 4SYNOPSIS
5 use IO::AIO; 5 use IO::AIO;
6 6
7 aio_open "/etc/passwd", O_RDONLY, 0, sub { 7 aio_open "/etc/passwd", O_RDONLY, 0, sub {
8 my ($fh) = @_; 8 my $fh = shift
9 or die "/etc/passwd: $!";
9 ... 10 ...
10 }; 11 };
11 12
12 aio_unlink "/tmp/file", sub { }; 13 aio_unlink "/tmp/file", sub { };
13 14
14 aio_read $fh, 30000, 1024, $buffer, 0, sub { 15 aio_read $fh, 30000, 1024, $buffer, 0, sub {
15 $_[0] > 0 or die "read error: $!"; 16 $_[0] > 0 or die "read error: $!";
16 }; 17 };
17 18
18 # AnyEvent 19 # version 2+ has request and group objects
19 open my $fh, "<&=" . IO::AIO::poll_fileno or die "$!"; 20 use IO::AIO 2;
20 my $w = AnyEvent->io (fh => $fh, poll => 'r', cb => sub { IO::AIO::poll_cb });
21 21
22 # Event 22 aioreq_pri 4; # give next request a very high priority
23 Event->io (fd => IO::AIO::poll_fileno, 23 my $req = aio_unlink "/tmp/file", sub { };
24 poll => 'r', 24 $req->cancel; # cancel request if still in queue
25 cb => \&IO::AIO::poll_cb);
26 25
27 # Glib/Gtk2 26 my $grp = aio_group sub { print "all stats done\n" };
28 add_watch Glib::IO IO::AIO::poll_fileno, 27 add $grp aio_stat "..." for ...;
29 in => sub { IO::AIO::poll_cb; 1 };
30
31 # Tk
32 Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
33 readable => \&IO::AIO::poll_cb);
34
35 # Danga::Socket
36 Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
37 \&IO::AIO::poll_cb);
38 28
39DESCRIPTION 29DESCRIPTION
40 This module implements asynchronous I/O using whatever means your 30 This module implements asynchronous I/O using whatever means your
41 operating system supports. 31 operating system supports. It is implemented as an interface to "libeio"
32 (<http://software.schmorp.de/pkg/libeio.html>).
42 33
34 Asynchronous means that operations that can normally block your program
35 (e.g. reading from disk) will be done asynchronously: the operation will
36 still block, but you can do something else in the meantime. This is
37 extremely useful for programs that need to stay interactive even when
38 doing heavy I/O (GUI programs, high performance network servers etc.),
39 but can also be used to easily do operations in parallel that are
40 normally done sequentially, e.g. stat'ing many files, which is much
41 faster on a RAID volume or over NFS when you do a number of stat
42 operations concurrently.
43
44 While most of this works on all types of file descriptors (for example
45 sockets), using these functions on file descriptors that support
46 nonblocking operation (again, sockets, pipes etc.) is very inefficient.
47 Use an event loop for that (such as the EV module): IO::AIO will
48 naturally fit into such an event loop itself.
49
43 Currently, a number of threads are started that execute your read/writes 50 In this version, a number of threads are started that execute your
44 and signal their completion. You don't need thread support in your libc 51 requests and signal their completion. You don't need thread support in
45 or perl, and the threads created by this module will not be visible to 52 perl, and the threads created by this module will not be visible to
46 the pthreads library. In the future, this module might make use of the 53 perl. In the future, this module might make use of the native aio
47 native aio functions available on many operating systems. However, they 54 functions available on many operating systems. However, they are often
48 are often not well-supported (Linux doesn't allow them on normal files 55 not well-supported or restricted (GNU/Linux doesn't allow them on normal
49 currently, for example), and they would only support aio_read and 56 files currently, for example), and they would only support aio_read and
50 aio_write, so the remaining functionality would have to be implemented 57 aio_write, so the remaining functionality would have to be implemented
51 using threads anyway. 58 using threads anyway.
52 59
53 Although the module will work with in the presence of other threads, it 60 Although the module will work in the presence of other (Perl-) threads,
54 is currently not reentrant, so use appropriate locking yourself, always 61 it is currently not reentrant in any way, so use appropriate locking
55 call "poll_cb" from within the same thread, or never call "poll_cb" (or 62 yourself, always call "poll_cb" from within the same thread, or never
56 other "aio_" functions) recursively. 63 call "poll_cb" (or other "aio_" functions) recursively.
64
65 EXAMPLE
66 This is a simple example that uses the EV module and loads /etc/passwd
67 asynchronously:
68
69 use Fcntl;
70 use EV;
71 use IO::AIO;
72
73 # register the IO::AIO callback with EV
74 my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
75
76 # queue the request to open /etc/passwd
77 aio_open "/etc/passwd", O_RDONLY, 0, sub {
78 my $fh = shift
79 or die "error while opening: $!";
80
81 # stat'ing filehandles is generally non-blocking
82 my $size = -s $fh;
83
84 # queue a request to read the file
85 my $contents;
86 aio_read $fh, 0, $size, $contents, 0, sub {
87 $_[0] == $size
88 or die "short read: $!";
89
90 close $fh;
91
92 # file contents now in $contents
93 print $contents;
94
95 # exit event loop and program
96 EV::unloop;
97 };
98 };
99
100 # possibly queue up other requests, or open GUI windows,
101 # check for sockets etc. etc.
102
103 # process events as long as there are some:
104 EV::loop;
105
106REQUEST ANATOMY AND LIFETIME
107 Every "aio_*" function creates a request. which is a C data structure
108 not directly visible to Perl.
109
110 If called in non-void context, every request function returns a Perl
111 object representing the request. In void context, nothing is returned,
112 which saves a bit of memory.
113
114 The perl object is a fairly standard ref-to-hash object. The hash
115 contents are not used by IO::AIO so you are free to store anything you
116 like in it.
117
118 During their existance, aio requests travel through the following
119 states, in order:
120
121 ready
122 Immediately after a request is created it is put into the ready
123 state, waiting for a thread to execute it.
124
125 execute
126 A thread has accepted the request for processing and is currently
127 executing it (e.g. blocking in read).
128
129 pending
130 The request has been executed and is waiting for result processing.
131
132 While request submission and execution is fully asynchronous, result
133 processing is not and relies on the perl interpreter calling
134 "poll_cb" (or another function with the same effect).
135
136 result
137 The request results are processed synchronously by "poll_cb".
138
139 The "poll_cb" function will process all outstanding aio requests by
140 calling their callbacks, freeing memory associated with them and
141 managing any groups they are contained in.
142
143 done
144 Request has reached the end of its lifetime and holds no resources
145 anymore (except possibly for the Perl object, but its connection to
146 the actual aio request is severed and calling its methods will
147 either do nothing or result in a runtime error).
57 148
58FUNCTIONS 149FUNCTIONS
150 QUICK OVERVIEW
151 This section simply lists the prototypes of the most important functions
152 for quick reference. See the following sections for function-by-function
153 documentation.
154
155 aio_open $pathname, $flags, $mode, $callback->($fh)
156 aio_close $fh, $callback->($status)
157 aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
158 aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
159 aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
160 aio_readahead $fh,$offset,$length, $callback->($retval)
161 aio_stat $fh_or_path, $callback->($status)
162 aio_lstat $fh, $callback->($status)
163 aio_statvfs $fh_or_path, $callback->($statvfs)
164 aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
165 aio_chown $fh_or_path, $uid, $gid, $callback->($status)
166 aio_truncate $fh_or_path, $offset, $callback->($status)
167 aio_chmod $fh_or_path, $mode, $callback->($status)
168 aio_unlink $pathname, $callback->($status)
169 aio_mknod $path, $mode, $dev, $callback->($status)
170 aio_link $srcpath, $dstpath, $callback->($status)
171 aio_symlink $srcpath, $dstpath, $callback->($status)
172 aio_readlink $path, $callback->($link)
173 aio_rename $srcpath, $dstpath, $callback->($status)
174 aio_mkdir $pathname, $mode, $callback->($status)
175 aio_rmdir $pathname, $callback->($status)
176 aio_readdir $pathname, $callback->($entries)
177 aio_readdirx $pathname, $flags, $callback->($entries, $flags)
178 IO::AIO::READDIR_DENTS IO::AIO::READDIR_DIRS_FIRST
179 IO::AIO::READDIR_STAT_ORDER IO::AIO::READDIR_FOUND_UNKNOWN
180 aio_load $path, $data, $callback->($status)
181 aio_copy $srcpath, $dstpath, $callback->($status)
182 aio_move $srcpath, $dstpath, $callback->($status)
183 aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
184 aio_rmtree $path, $callback->($status)
185 aio_sync $callback->($status)
186 aio_fsync $fh, $callback->($status)
187 aio_fdatasync $fh, $callback->($status)
188 aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
189 aio_pathsync $path, $callback->($status)
190 aio_msync $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
191 aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0, $callback->($status)
192 aio_group $callback->(...)
193 aio_nop $callback->()
194
195 $prev_pri = aioreq_pri [$pri]
196 aioreq_nice $pri_adjust
197
198 IO::AIO::poll_wait
199 IO::AIO::poll_cb
200 IO::AIO::poll
201 IO::AIO::flush
202 IO::AIO::max_poll_reqs $nreqs
203 IO::AIO::max_poll_time $seconds
204 IO::AIO::min_parallel $nthreads
205 IO::AIO::max_parallel $nthreads
206 IO::AIO::max_idle $nthreads
207 IO::AIO::max_outstanding $maxreqs
208 IO::AIO::nreqs
209 IO::AIO::nready
210 IO::AIO::npending
211
212 IO::AIO::sendfile $ofh, $ifh, $offset, $count
213 IO::AIO::fadvise $fh, $offset, $len, $advice
214 IO::AIO::mlockall $flags
215 IO::AIO::munlockall
216
59 AIO FUNCTIONS 217 AIO REQUEST FUNCTIONS
60 All the "aio_*" calls are more or less thin wrappers around the syscall 218 All the "aio_*" calls are more or less thin wrappers around the syscall
61 with the same name (sans "aio_"). The arguments are similar or 219 with the same name (sans "aio_"). The arguments are similar or
62 identical, and they all accept an additional (and optional) $callback 220 identical, and they all accept an additional (and optional) $callback
63 argument which must be a code reference. This code reference will get 221 argument which must be a code reference. This code reference will get
64 called with the syscall return code (e.g. most syscalls return -1 on 222 called with the syscall return code (e.g. most syscalls return -1 on
65 error, unlike perl, which usually delivers "false") as it's sole 223 error, unlike perl, which usually delivers "false") as its sole argument
66 argument when the given syscall has been executed asynchronously. 224 after the given syscall has been executed asynchronously.
67 225
68 All functions expecting a filehandle keep a copy of the filehandle 226 All functions expecting a filehandle keep a copy of the filehandle
69 internally until the request has finished. 227 internally until the request has finished.
70 228
229 All functions return request objects of type IO::AIO::REQ that allow
230 further manipulation of those requests while they are in-flight.
231
71 The pathnames you pass to these routines *must* be absolute and encoded 232 The pathnames you pass to these routines *must* be absolute and encoded
72 in byte form. The reason for the former is that at the time the request 233 as octets. The reason for the former is that at the time the request is
73 is being executed, the current working directory could have changed. 234 being executed, the current working directory could have changed.
74 Alternatively, you can make sure that you never change the current 235 Alternatively, you can make sure that you never change the current
75 working directory. 236 working directory anywhere in the program and then use relative paths.
76 237
77 To encode pathnames to byte form, either make sure you either: a) always 238 To encode pathnames as octets, either make sure you either: a) always
78 pass in filenames you got from outside (command line, readdir etc.), b) 239 pass in filenames you got from outside (command line, readdir etc.)
79 are ASCII or ISO 8859-1, c) use the Encode module and encode your 240 without tinkering, b) are ASCII or ISO 8859-1, c) use the Encode module
80 pathnames to the locale (or other) encoding in effect in the user 241 and encode your pathnames to the locale (or other) encoding in effect in
81 environment, d) use Glib::filename_from_unicode on unicode filenames or 242 the user environment, d) use Glib::filename_from_unicode on unicode
82 e) use something else. 243 filenames or e) use something else to ensure your scalar has the correct
244 contents.
245
246 This works, btw. independent of the internal UTF-8 bit, which IO::AIO
247 handles correctly whether it is set or not.
248
249 $prev_pri = aioreq_pri [$pri]
250 Returns the priority value that would be used for the next request
251 and, if $pri is given, sets the priority for the next aio request.
252
253 The default priority is 0, the minimum and maximum priorities are -4
254 and 4, respectively. Requests with higher priority will be serviced
255 first.
256
257 The priority will be reset to 0 after each call to one of the
258 "aio_*" functions.
259
260 Example: open a file with low priority, then read something from it
261 with higher priority so the read request is serviced before other
262 low priority open requests (potentially spamming the cache):
263
264 aioreq_pri -3;
265 aio_open ..., sub {
266 return unless $_[0];
267
268 aioreq_pri -2;
269 aio_read $_[0], ..., sub {
270 ...
271 };
272 };
273
274 aioreq_nice $pri_adjust
275 Similar to "aioreq_pri", but subtracts the given value from the
276 current priority, so the effect is cumulative.
83 277
84 aio_open $pathname, $flags, $mode, $callback->($fh) 278 aio_open $pathname, $flags, $mode, $callback->($fh)
85 Asynchronously open or create a file and call the callback with a 279 Asynchronously open or create a file and call the callback with a
86 newly created filehandle for the file. 280 newly created filehandle for the file.
87 281
… …
92 They are the same as used by "sysopen". 286 They are the same as used by "sysopen".
93 287
94 Likewise, $mode specifies the mode of the newly created file, if it 288 Likewise, $mode specifies the mode of the newly created file, if it
95 didn't exist and "O_CREAT" has been given, just like perl's 289 didn't exist and "O_CREAT" has been given, just like perl's
96 "sysopen", except that it is mandatory (i.e. use 0 if you don't 290 "sysopen", except that it is mandatory (i.e. use 0 if you don't
97 create new files, and 0666 or 0777 if you do). 291 create new files, and 0666 or 0777 if you do). Note that the $mode
292 will be modified by the umask in effect then the request is being
293 executed, so better never change the umask.
98 294
99 Example: 295 Example:
100 296
101 aio_open "/etc/passwd", O_RDONLY, 0, sub { 297 aio_open "/etc/passwd", O_RDONLY, 0, sub {
102 if ($_[0]) { 298 if ($_[0]) {
… …
107 } 303 }
108 }; 304 };
109 305
110 aio_close $fh, $callback->($status) 306 aio_close $fh, $callback->($status)
111 Asynchronously close a file and call the callback with the result 307 Asynchronously close a file and call the callback with the result
112 code. *WARNING:* although accepted, you should not pass in a perl 308 code.
113 filehandle here, as perl will likely close the file descriptor
114 another time when the filehandle is destroyed. Normally, you can
115 safely call perls "close" or just let filehandles go out of scope.
116 309
117 This is supposed to be a bug in the API, so that might change. It's 310 Unfortunately, you can't do this to perl. Perl *insists* very
118 therefore best to avoid this function. 311 strongly on closing the file descriptor associated with the
312 filehandle itself.
313
314 Therefore, "aio_close" will not close the filehandle - instead it
315 will use dup2 to overwrite the file descriptor with the write-end of
316 a pipe (the pipe fd will be created on demand and will be cached).
317
318 Or in other words: the file descriptor will be closed, but it will
319 not be free for reuse until the perl filehandle is closed.
119 320
120 aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval) 321 aio_read $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
121 aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval) 322 aio_write $fh,$offset,$length, $data,$dataoffset, $callback->($retval)
122 Reads or writes "length" bytes from the specified "fh" and "offset" 323 Reads or writes $length bytes from or to the specified $fh and
123 into the scalar given by "data" and offset "dataoffset" and calls 324 $offset into the scalar given by $data and offset $dataoffset and
124 the callback without the actual number of bytes read (or -1 on 325 calls the callback without the actual number of bytes read (or -1 on
125 error, just like the syscall). 326 error, just like the syscall).
126 327
328 "aio_read" will, like "sysread", shrink or grow the $data scalar to
329 offset plus the actual number of bytes read.
330
331 If $offset is undefined, then the current file descriptor offset
332 will be used (and updated), otherwise the file descriptor offset
333 will not be changed by these calls.
334
335 If $length is undefined in "aio_write", use the remaining length of
336 $data.
337
338 If $dataoffset is less than zero, it will be counted from the end of
339 $data.
340
127 The $data scalar *MUST NOT* be modified in any way while the request 341 The $data scalar *MUST NOT* be modified in any way while the request
128 is outstanding. Modifying it can result in segfaults or WW3 (if the 342 is outstanding. Modifying it can result in segfaults or World War
129 necessary/optional hardware is installed). 343 III (if the necessary/optional hardware is installed).
130 344
131 Example: Read 15 bytes at offset 7 into scalar $buffer, starting at 345 Example: Read 15 bytes at offset 7 into scalar $buffer, starting at
132 offset 0 within the scalar: 346 offset 0 within the scalar:
133 347
134 aio_read $fh, 7, 15, $buffer, 0, sub { 348 aio_read $fh, 7, 15, $buffer, 0, sub {
135 $_[0] > 0 or die "read error: $!"; 349 $_[0] > 0 or die "read error: $!";
136 print "read $_[0] bytes: <$buffer>\n"; 350 print "read $_[0] bytes: <$buffer>\n";
137 }; 351 };
138
139 aio_move $srcpath, $dstpath, $callback->($status)
140 [EXPERIMENTAL]
141
142 Try to move the *file* (directories not supported as either source
143 or destination) from $srcpath to $dstpath and call the callback with
144 the 0 (error) or -1 ok.
145
146 This is a composite request that tries to rename(2) the file first.
147 If rename files with "EXDEV", it creates the destination file with
148 mode 0200 and copies the contents of the source file into it using
149 "aio_sendfile", followed by restoring atime, mtime, access mode and
150 uid/gid, in that order, and unlinking the $srcpath.
151
152 If an error occurs, the partial destination file will be unlinked,
153 if possible, except when setting atime, mtime, access mode and
154 uid/gid, where errors are being ignored.
155 352
156 aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval) 353 aio_sendfile $out_fh, $in_fh, $in_offset, $length, $callback->($retval)
157 Tries to copy $length bytes from $in_fh to $out_fh. It starts 354 Tries to copy $length bytes from $in_fh to $out_fh. It starts
158 reading at byte offset $in_offset, and starts writing at the current 355 reading at byte offset $in_offset, and starts writing at the current
159 file offset of $out_fh. Because of that, it is not safe to issue 356 file offset of $out_fh. Because of that, it is not safe to issue
160 more than one "aio_sendfile" per $out_fh, as they will interfere 357 more than one "aio_sendfile" per $out_fh, as they will interfere
161 with each other. 358 with each other.
162 359
163 This call tries to make use of a native "sendfile" syscall to 360 This call tries to make use of a native "sendfile" syscall to
164 provide zero-copy operation. For this to work, $out_fh should refer 361 provide zero-copy operation. For this to work, $out_fh should refer
165 to a socket, and $in_fh should refer to mmap'able file. 362 to a socket, and $in_fh should refer to an mmap'able file.
166 363
167 If the native sendfile call fails or is not implemented, it will be 364 If a native sendfile cannot be found or it fails with "ENOSYS",
365 "ENOTSUP", "EOPNOTSUPP", "EAFNOSUPPORT", "EPROTOTYPE" or "ENOTSOCK",
168 emulated, so you can call "aio_sendfile" on any type of filehandle 366 it will be emulated, so you can call "aio_sendfile" on any type of
169 regardless of the limitations of the operating system. 367 filehandle regardless of the limitations of the operating system.
170 368
171 Please note, however, that "aio_sendfile" can read more bytes from 369 Please note, however, that "aio_sendfile" can read more bytes from
172 $in_fh than are written, and there is no way to find out how many 370 $in_fh than are written, and there is no way to find out how many
173 bytes have been read from "aio_sendfile" alone, as "aio_sendfile" 371 bytes have been read from "aio_sendfile" alone, as "aio_sendfile"
174 only provides the number of bytes written to $out_fh. Only if the 372 only provides the number of bytes written to $out_fh. Only if the
… …
209 aio_stat "/etc/passwd", sub { 407 aio_stat "/etc/passwd", sub {
210 $_[0] and die "stat failed: $!"; 408 $_[0] and die "stat failed: $!";
211 print "size is ", -s _, "\n"; 409 print "size is ", -s _, "\n";
212 }; 410 };
213 411
412 aio_statvfs $fh_or_path, $callback->($statvfs)
413 Works like the POSIX "statvfs" or "fstatvfs" syscalls, depending on
414 whether a file handle or path was passed.
415
416 On success, the callback is passed a hash reference with the
417 following members: "bsize", "frsize", "blocks", "bfree", "bavail",
418 "files", "ffree", "favail", "fsid", "flag" and "namemax". On
419 failure, "undef" is passed.
420
421 The following POSIX IO::AIO::ST_* constants are defined: "ST_RDONLY"
422 and "ST_NOSUID".
423
424 The following non-POSIX IO::AIO::ST_* flag masks are defined to
425 their correct value when available, or to 0 on systems that do not
426 support them: "ST_NODEV", "ST_NOEXEC", "ST_SYNCHRONOUS",
427 "ST_MANDLOCK", "ST_WRITE", "ST_APPEND", "ST_IMMUTABLE",
428 "ST_NOATIME", "ST_NODIRATIME" and "ST_RELATIME".
429
430 Example: stat "/wd" and dump out the data if successful.
431
432 aio_statvfs "/wd", sub {
433 my $f = $_[0]
434 or die "statvfs: $!";
435
436 use Data::Dumper;
437 say Dumper $f;
438 };
439
440 # result:
441 {
442 bsize => 1024,
443 bfree => 4333064312,
444 blocks => 10253828096,
445 files => 2050765568,
446 flag => 4096,
447 favail => 2042092649,
448 bavail => 4333064312,
449 ffree => 2042092649,
450 namemax => 255,
451 frsize => 1024,
452 fsid => 1810
453 }
454
455 aio_utime $fh_or_path, $atime, $mtime, $callback->($status)
456 Works like perl's "utime" function (including the special case of
457 $atime and $mtime being undef). Fractional times are supported if
458 the underlying syscalls support them.
459
460 When called with a pathname, uses utimes(2) if available, otherwise
461 utime(2). If called on a file descriptor, uses futimes(2) if
462 available, otherwise returns ENOSYS, so this is not portable.
463
464 Examples:
465
466 # set atime and mtime to current time (basically touch(1)):
467 aio_utime "path", undef, undef;
468 # set atime to current time and mtime to beginning of the epoch:
469 aio_utime "path", time, undef; # undef==0
470
471 aio_chown $fh_or_path, $uid, $gid, $callback->($status)
472 Works like perl's "chown" function, except that "undef" for either
473 $uid or $gid is being interpreted as "do not change" (but -1 can
474 also be used).
475
476 Examples:
477
478 # same as "chown root path" in the shell:
479 aio_chown "path", 0, -1;
480 # same as above:
481 aio_chown "path", 0, undef;
482
483 aio_truncate $fh_or_path, $offset, $callback->($status)
484 Works like truncate(2) or ftruncate(2).
485
486 aio_chmod $fh_or_path, $mode, $callback->($status)
487 Works like perl's "chmod" function.
488
214 aio_unlink $pathname, $callback->($status) 489 aio_unlink $pathname, $callback->($status)
215 Asynchronously unlink (delete) a file and call the callback with the 490 Asynchronously unlink (delete) a file and call the callback with the
216 result code. 491 result code.
492
493 aio_mknod $path, $mode, $dev, $callback->($status)
494 [EXPERIMENTAL]
495
496 Asynchronously create a device node (or fifo). See mknod(2).
497
498 The only (POSIX-) portable way of calling this function is:
499
500 aio_mknod $path, IO::AIO::S_IFIFO | $mode, 0, sub { ...
217 501
218 aio_link $srcpath, $dstpath, $callback->($status) 502 aio_link $srcpath, $dstpath, $callback->($status)
219 Asynchronously create a new link to the existing object at $srcpath 503 Asynchronously create a new link to the existing object at $srcpath
220 at the path $dstpath and call the callback with the result code. 504 at the path $dstpath and call the callback with the result code.
221 505
222 aio_symlink $srcpath, $dstpath, $callback->($status) 506 aio_symlink $srcpath, $dstpath, $callback->($status)
223 Asynchronously create a new symbolic link to the existing object at 507 Asynchronously create a new symbolic link to the existing object at
224 $srcpath at the path $dstpath and call the callback with the result 508 $srcpath at the path $dstpath and call the callback with the result
225 code. 509 code.
226 510
511 aio_readlink $path, $callback->($link)
512 Asynchronously read the symlink specified by $path and pass it to
513 the callback. If an error occurs, nothing or undef gets passed to
514 the callback.
515
227 aio_rename $srcpath, $dstpath, $callback->($status) 516 aio_rename $srcpath, $dstpath, $callback->($status)
228 Asynchronously rename the object at $srcpath to $dstpath, just as 517 Asynchronously rename the object at $srcpath to $dstpath, just as
229 rename(2) and call the callback with the result code. 518 rename(2) and call the callback with the result code.
519
520 aio_mkdir $pathname, $mode, $callback->($status)
521 Asynchronously mkdir (create) a directory and call the callback with
522 the result code. $mode will be modified by the umask at the time the
523 request is executed, so do not change your umask.
230 524
231 aio_rmdir $pathname, $callback->($status) 525 aio_rmdir $pathname, $callback->($status)
232 Asynchronously rmdir (delete) a directory and call the callback with 526 Asynchronously rmdir (delete) a directory and call the callback with
233 the result code. 527 the result code.
234 528
235 aio_readdir $pathname, $callback->($entries) 529 aio_readdir $pathname, $callback->($entries)
236 Unlike the POSIX call of the same name, "aio_readdir" reads an 530 Unlike the POSIX call of the same name, "aio_readdir" reads an
237 entire directory (i.e. opendir + readdir + closedir). The entries 531 entire directory (i.e. opendir + readdir + closedir). The entries
238 will not be sorted, and will NOT include the "." and ".." entries. 532 will not be sorted, and will NOT include the "." and ".." entries.
239 533
240 The callback a single argument which is either "undef" or an 534 The callback is passed a single argument which is either "undef" or
241 array-ref with the filenames. 535 an array-ref with the filenames.
536
537 aio_readdirx $pathname, $flags, $callback->($entries, $flags)
538 Quite similar to "aio_readdir", but the $flags argument allows to
539 tune behaviour and output format. In case of an error, $entries will
540 be "undef".
541
542 The flags are a combination of the following constants, ORed
543 together (the flags will also be passed to the callback, possibly
544 modified):
545
546 IO::AIO::READDIR_DENTS
547 When this flag is off, then the callback gets an arrayref with
548 of names only (as with "aio_readdir"), otherwise it gets an
549 arrayref with "[$name, $type, $inode]" arrayrefs, each
550 describing a single directory entry in more detail.
551
552 $name is the name of the entry.
553
554 $type is one of the "IO::AIO::DT_xxx" constants:
555
556 "IO::AIO::DT_UNKNOWN", "IO::AIO::DT_FIFO", "IO::AIO::DT_CHR",
557 "IO::AIO::DT_DIR", "IO::AIO::DT_BLK", "IO::AIO::DT_REG",
558 "IO::AIO::DT_LNK", "IO::AIO::DT_SOCK", "IO::AIO::DT_WHT".
559
560 "IO::AIO::DT_UNKNOWN" means just that: readdir does not know. If
561 you need to know, you have to run stat yourself. Also, for speed
562 reasons, the $type scalars are read-only: you can not modify
563 them.
564
565 $inode is the inode number (which might not be exact on systems
566 with 64 bit inode numbers and 32 bit perls). This field has
567 unspecified content on systems that do not deliver the inode
568 information.
569
570 IO::AIO::READDIR_DIRS_FIRST
571 When this flag is set, then the names will be returned in an
572 order where likely directories come first. This is useful when
573 you need to quickly find directories, or you want to find all
574 directories while avoiding to stat() each entry.
575
576 If the system returns type information in readdir, then this is
577 used to find directories directly. Otherwise, likely directories
578 are files beginning with ".", or otherwise files with no dots,
579 of which files with short names are tried first.
580
581 IO::AIO::READDIR_STAT_ORDER
582 When this flag is set, then the names will be returned in an
583 order suitable for stat()'ing each one. That is, when you plan
584 to stat() all files in the given directory, then the returned
585 order will likely be fastest.
586
587 If both this flag and "IO::AIO::READDIR_DIRS_FIRST" are
588 specified, then the likely dirs come first, resulting in a less
589 optimal stat order.
590
591 IO::AIO::READDIR_FOUND_UNKNOWN
592 This flag should not be set when calling "aio_readdirx".
593 Instead, it is being set by "aio_readdirx", when any of the
594 $type's found were "IO::AIO::DT_UNKNOWN". The absense of this
595 flag therefore indicates that all $type's are known, which can
596 be used to speed up some algorithms.
597
598 aio_load $path, $data, $callback->($status)
599 This is a composite request that tries to fully load the given file
600 into memory. Status is the same as with aio_read.
601
602 aio_copy $srcpath, $dstpath, $callback->($status)
603 Try to copy the *file* (directories not supported as either source
604 or destination) from $srcpath to $dstpath and call the callback with
605 a status of 0 (ok) or -1 (error, see $!).
606
607 This is a composite request that creates the destination file with
608 mode 0200 and copies the contents of the source file into it using
609 "aio_sendfile", followed by restoring atime, mtime, access mode and
610 uid/gid, in that order.
611
612 If an error occurs, the partial destination file will be unlinked,
613 if possible, except when setting atime, mtime, access mode and
614 uid/gid, where errors are being ignored.
615
616 aio_move $srcpath, $dstpath, $callback->($status)
617 Try to move the *file* (directories not supported as either source
618 or destination) from $srcpath to $dstpath and call the callback with
619 a status of 0 (ok) or -1 (error, see $!).
620
621 This is a composite request that tries to rename(2) the file first;
622 if rename fails with "EXDEV", it copies the file with "aio_copy"
623 and, if that is successful, unlinks the $srcpath.
242 624
243 aio_scandir $path, $maxreq, $callback->($dirs, $nondirs) 625 aio_scandir $path, $maxreq, $callback->($dirs, $nondirs)
244 Scans a directory (similar to "aio_readdir") and tries to separate 626 Scans a directory (similar to "aio_readdir") but additionally tries
245 the entries of directory $path into two sets of names, ones you can 627 to efficiently separate the entries of directory $path into two sets
246 recurse into (directories), and ones you cannot recurse into 628 of names, directories you can recurse into (directories), and ones
247 (everything else). 629 you cannot recurse into (everything else, including symlinks to
630 directories).
248 631
249 "aio_scandir" is a composite request that consists of many 632 "aio_scandir" is a composite request that creates of many sub
250 aio-primitives. $maxreq specifies the maximum number of outstanding 633 requests_ $maxreq specifies the maximum number of outstanding aio
251 aio requests that this function generates. If it is "<= 0", then a 634 requests that this function generates. If it is "<= 0", then a
252 suitable default will be chosen (currently 8). 635 suitable default will be chosen (currently 4).
253 636
254 On error, the callback is called without arguments, otherwise it 637 On error, the callback is called without arguments, otherwise it
255 receives two array-refs with path-relative entry names. 638 receives two array-refs with path-relative entry names.
256 639
257 Example: 640 Example:
… …
265 Implementation notes. 648 Implementation notes.
266 649
267 The "aio_readdir" cannot be avoided, but "stat()"'ing every entry 650 The "aio_readdir" cannot be avoided, but "stat()"'ing every entry
268 can. 651 can.
269 652
653 If readdir returns file type information, then this is used directly
654 to find directories.
655
270 After reading the directory, the modification time, size etc. of the 656 Otherwise, after reading the directory, the modification time, size
271 directory before and after the readdir is checked, and if they 657 etc. of the directory before and after the readdir is checked, and
272 match, the link count will be used to decide how many entries are 658 if they match (and isn't the current time), the link count will be
273 directories (if >= 2). Otherwise, no knowledge of the number of 659 used to decide how many entries are directories (if >= 2).
274 subdirectories will be assumed. 660 Otherwise, no knowledge of the number of subdirectories will be
661 assumed.
275 662
276 Then entires will be sorted into likely directories (everything 663 Then entries will be sorted into likely directories a non-initial
277 without a non-initial dot) and likely non-directories (everything 664 dot currently) and likely non-directories (see "aio_readdirx"). Then
278 else). Then every entry + "/." will be "stat"'ed, likely directories 665 every entry plus an appended "/." will be "stat"'ed, likely
279 first. This is often faster because filesystems might detect the 666 directories first, in order of their inode numbers. If that
667 succeeds, it assumes that the entry is a directory or a symlink to
668 directory (which will be checked seperately). This is often faster
669 than stat'ing the entry itself because filesystems might detect the
280 type of the entry without reading the inode data (e.g. ext2fs 670 type of the entry without reading the inode data (e.g. ext2fs
281 filetype feature). If that succeeds, it assumes that the entry is a 671 filetype feature), even on systems that cannot return the filetype
282 directory or a symlink to directory (which will be checked 672 information on readdir.
283 seperately).
284 673
285 If the known number of directories has been reached, the rest of the 674 If the known number of directories (link count - 2) has been
286 entries is assumed to be non-directories. 675 reached, the rest of the entries is assumed to be non-directories.
676
677 This only works with certainty on POSIX (= UNIX) filesystems, which
678 fortunately are the vast majority of filesystems around.
679
680 It will also likely work on non-POSIX filesystems with reduced
681 efficiency as those tend to return 0 or 1 as link counts, which
682 disables the directory counting heuristic.
683
684 aio_rmtree $path, $callback->($status)
685 Delete a directory tree starting (and including) $path, return the
686 status of the final "rmdir" only. This is a composite request that
687 uses "aio_scandir" to recurse into and rmdir directories, and unlink
688 everything else.
689
690 aio_sync $callback->($status)
691 Asynchronously call sync and call the callback when finished.
287 692
288 aio_fsync $fh, $callback->($status) 693 aio_fsync $fh, $callback->($status)
289 Asynchronously call fsync on the given filehandle and call the 694 Asynchronously call fsync on the given filehandle and call the
290 callback with the fsync result code. 695 callback with the fsync result code.
291 696
… …
294 callback with the fdatasync result code. 699 callback with the fdatasync result code.
295 700
296 If this call isn't available because your OS lacks it or it couldn't 701 If this call isn't available because your OS lacks it or it couldn't
297 be detected, it will be emulated by calling "fsync" instead. 702 be detected, it will be emulated by calling "fsync" instead.
298 703
704 aio_sync_file_range $fh, $offset, $nbytes, $flags, $callback->($status)
705 Sync the data portion of the file specified by $offset and $length
706 to disk (but NOT the metadata), by calling the Linux-specific
707 sync_file_range call. If sync_file_range is not available or it
708 returns ENOSYS, then fdatasync or fsync is being substituted.
709
710 $flags can be a combination of
711 "IO::AIO::SYNC_FILE_RANGE_WAIT_BEFORE",
712 "IO::AIO::SYNC_FILE_RANGE_WRITE" and
713 "IO::AIO::SYNC_FILE_RANGE_WAIT_AFTER": refer to the sync_file_range
714 manpage for details.
715
716 aio_pathsync $path, $callback->($status)
717 This request tries to open, fsync and close the given path. This is
718 a composite request intended to sync directories after directory
719 operations (E.g. rename). This might not work on all operating
720 systems or have any specific effect, but usually it makes sure that
721 directory changes get written to disc. It works for anything that
722 can be opened for read-only, not just directories.
723
724 Future versions of this function might fall back to other methods
725 when "fsync" on the directory fails (such as calling "sync").
726
727 Passes 0 when everything went ok, and -1 on error.
728
729 aio_msync $scalar, $offset = 0, $length = undef, flags = 0,
730 $callback->($status)
731 This is a rather advanced IO::AIO call, which only works on
732 mmap(2)ed scalars (see the "IO::AIO::mmap" function, although it
733 also works on data scalars managed by the Sys::Mmap or Mmap modules,
734 note that the scalar must only be modified in-place while an aio
735 operation is pending on it).
736
737 It calls the "msync" function of your OS, if available, with the
738 memory area starting at $offset in the string and ending $length
739 bytes later. If $length is negative, counts from the end, and if
740 $length is "undef", then it goes till the end of the string. The
741 flags can be a combination of "IO::AIO::MS_ASYNC",
742 "IO::AIO::MS_INVALIDATE" and "IO::AIO::MS_SYNC".
743
744 aio_mtouch $scalar, $offset = 0, $length = undef, flags = 0,
745 $callback->($status)
746 This is a rather advanced IO::AIO call, which works best on
747 mmap(2)ed scalars.
748
749 It touches (reads or writes) all memory pages in the specified range
750 inside the scalar. All caveats and parameters are the same as for
751 "aio_msync", above, except for flags, which must be either 0 (which
752 reads all pages and ensures they are instantiated) or
753 "IO::AIO::MT_MODIFY", which modifies the memory page s(by reading
754 and writing an octet from it, which dirties the page).
755
756 aio_group $callback->(...)
757 This is a very special aio request: Instead of doing something, it
758 is a container for other aio requests, which is useful if you want
759 to bundle many requests into a single, composite, request with a
760 definite callback and the ability to cancel the whole request with
761 its subrequests.
762
763 Returns an object of class IO::AIO::GRP. See its documentation below
764 for more info.
765
766 Example:
767
768 my $grp = aio_group sub {
769 print "all stats done\n";
770 };
771
772 add $grp
773 (aio_stat ...),
774 (aio_stat ...),
775 ...;
776
777 aio_nop $callback->()
778 This is a special request - it does nothing in itself and is only
779 used for side effects, such as when you want to add a dummy request
780 to a group so that finishing the requests in the group depends on
781 executing the given code.
782
783 While this request does nothing, it still goes through the execution
784 phase and still requires a worker thread. Thus, the callback will
785 not be executed immediately but only after other requests in the
786 queue have entered their execution phase. This can be used to
787 measure request latency.
788
789 IO::AIO::aio_busy $fractional_seconds, $callback->() *NOT EXPORTED*
790 Mainly used for debugging and benchmarking, this aio request puts
791 one of the request workers to sleep for the given time.
792
793 While it is theoretically handy to have simple I/O scheduling
794 requests like sleep and file handle readable/writable, the overhead
795 this creates is immense (it blocks a thread for a long time) so do
796 not use this function except to put your application under
797 artificial I/O pressure.
798
799 IO::AIO::REQ CLASS
800 All non-aggregate "aio_*" functions return an object of this class when
801 called in non-void context.
802
803 cancel $req
804 Cancels the request, if possible. Has the effect of skipping
805 execution when entering the execute state and skipping calling the
806 callback when entering the the result state, but will leave the
807 request otherwise untouched (with the exception of readdir). That
808 means that requests that currently execute will not be stopped and
809 resources held by the request will not be freed prematurely.
810
811 cb $req $callback->(...)
812 Replace (or simply set) the callback registered to the request.
813
814 IO::AIO::GRP CLASS
815 This class is a subclass of IO::AIO::REQ, so all its methods apply to
816 objects of this class, too.
817
818 A IO::AIO::GRP object is a special request that can contain multiple
819 other aio requests.
820
821 You create one by calling the "aio_group" constructing function with a
822 callback that will be called when all contained requests have entered
823 the "done" state:
824
825 my $grp = aio_group sub {
826 print "all requests are done\n";
827 };
828
829 You add requests by calling the "add" method with one or more
830 "IO::AIO::REQ" objects:
831
832 $grp->add (aio_unlink "...");
833
834 add $grp aio_stat "...", sub {
835 $_[0] or return $grp->result ("error");
836
837 # add another request dynamically, if first succeeded
838 add $grp aio_open "...", sub {
839 $grp->result ("ok");
840 };
841 };
842
843 This makes it very easy to create composite requests (see the source of
844 "aio_move" for an application) that work and feel like simple requests.
845
846 * The IO::AIO::GRP objects will be cleaned up during calls to
847 "IO::AIO::poll_cb", just like any other request.
848
849 * They can be canceled like any other request. Canceling will cancel
850 not only the request itself, but also all requests it contains.
851
852 * They can also can also be added to other IO::AIO::GRP objects.
853
854 * You must not add requests to a group from within the group callback
855 (or any later time).
856
857 Their lifetime, simplified, looks like this: when they are empty, they
858 will finish very quickly. If they contain only requests that are in the
859 "done" state, they will also finish. Otherwise they will continue to
860 exist.
861
862 That means after creating a group you have some time to add requests
863 (precisely before the callback has been invoked, which is only done
864 within the "poll_cb"). And in the callbacks of those requests, you can
865 add further requests to the group. And only when all those requests have
866 finished will the the group itself finish.
867
868 add $grp ...
869 $grp->add (...)
870 Add one or more requests to the group. Any type of IO::AIO::REQ can
871 be added, including other groups, as long as you do not create
872 circular dependencies.
873
874 Returns all its arguments.
875
876 $grp->cancel_subs
877 Cancel all subrequests and clears any feeder, but not the group
878 request itself. Useful when you queued a lot of events but got a
879 result early.
880
881 The group request will finish normally (you cannot add requests to
882 the group).
883
884 $grp->result (...)
885 Set the result value(s) that will be passed to the group callback
886 when all subrequests have finished and set the groups errno to the
887 current value of errno (just like calling "errno" without an error
888 number). By default, no argument will be passed and errno is zero.
889
890 $grp->errno ([$errno])
891 Sets the group errno value to $errno, or the current value of errno
892 when the argument is missing.
893
894 Every aio request has an associated errno value that is restored
895 when the callback is invoked. This method lets you change this value
896 from its default (0).
897
898 Calling "result" will also set errno, so make sure you either set $!
899 before the call to "result", or call c<errno> after it.
900
901 feed $grp $callback->($grp)
902 Sets a feeder/generator on this group: every group can have an
903 attached generator that generates requests if idle. The idea behind
904 this is that, although you could just queue as many requests as you
905 want in a group, this might starve other requests for a potentially
906 long time. For example, "aio_scandir" might generate hundreds of
907 thousands "aio_stat" requests, delaying any later requests for a
908 long time.
909
910 To avoid this, and allow incremental generation of requests, you can
911 instead a group and set a feeder on it that generates those
912 requests. The feed callback will be called whenever there are few
913 enough (see "limit", below) requests active in the group itself and
914 is expected to queue more requests.
915
916 The feed callback can queue as many requests as it likes (i.e. "add"
917 does not impose any limits).
918
919 If the feed does not queue more requests when called, it will be
920 automatically removed from the group.
921
922 If the feed limit is 0 when this method is called, it will be set to
923 2 automatically.
924
925 Example:
926
927 # stat all files in @files, but only ever use four aio requests concurrently:
928
929 my $grp = aio_group sub { print "finished\n" };
930 limit $grp 4;
931 feed $grp sub {
932 my $file = pop @files
933 or return;
934
935 add $grp aio_stat $file, sub { ... };
936 };
937
938 limit $grp $num
939 Sets the feeder limit for the group: The feeder will be called
940 whenever the group contains less than this many requests.
941
942 Setting the limit to 0 will pause the feeding process.
943
944 The default value for the limit is 0, but note that setting a feeder
945 automatically bumps it up to 2.
946
299 SUPPORT FUNCTIONS 947 SUPPORT FUNCTIONS
948 EVENT PROCESSING AND EVENT LOOP INTEGRATION
300 $fileno = IO::AIO::poll_fileno 949 $fileno = IO::AIO::poll_fileno
301 Return the *request result pipe file descriptor*. This filehandle 950 Return the *request result pipe file descriptor*. This filehandle
302 must be polled for reading by some mechanism outside this module 951 must be polled for reading by some mechanism outside this module
303 (e.g. Event or select, see below or the SYNOPSIS). If the pipe 952 (e.g. EV, Glib, select and so on, see below or the SYNOPSIS). If the
304 becomes readable you have to call "poll_cb" to check the results. 953 pipe becomes readable you have to call "poll_cb" to check the
954 results.
305 955
306 See "poll_cb" for an example. 956 See "poll_cb" for an example.
307 957
308 IO::AIO::poll_cb 958 IO::AIO::poll_cb
309 Process all outstanding events on the result pipe. You have to call 959 Process some outstanding events on the result pipe. You have to call
310 this regularly. Returns the number of events processed. Returns 960 this regularly. Returns 0 if all events could be processed, or -1 if
311 immediately when no events are outstanding. 961 it returned earlier for whatever reason. Returns immediately when no
962 events are outstanding. The amount of events processed depends on
963 the settings of "IO::AIO::max_poll_req" and
964 "IO::AIO::max_poll_time".
965
966 If not all requests were processed for whatever reason, the
967 filehandle will still be ready when "poll_cb" returns, so normally
968 you don't have to do anything special to have it called later.
312 969
313 Example: Install an Event watcher that automatically calls 970 Example: Install an Event watcher that automatically calls
314 IO::AIO::poll_cb with high priority: 971 IO::AIO::poll_cb with high priority (more examples can be found in
972 the SYNOPSIS section, at the top of this document):
315 973
316 Event->io (fd => IO::AIO::poll_fileno, 974 Event->io (fd => IO::AIO::poll_fileno,
317 poll => 'r', async => 1, 975 poll => 'r', async => 1,
318 cb => \&IO::AIO::poll_cb); 976 cb => \&IO::AIO::poll_cb);
319 977
320 IO::AIO::poll_wait 978 IO::AIO::poll_wait
979 If there are any outstanding requests and none of them in the result
321 Wait till the result filehandle becomes ready for reading (simply 980 phase, wait till the result filehandle becomes ready for reading
322 does a "select" on the filehandle. This is useful if you want to 981 (simply does a "select" on the filehandle. This is useful if you
323 synchronously wait for some requests to finish). 982 want to synchronously wait for some requests to finish).
324 983
325 See "nreqs" for an example. 984 See "nreqs" for an example.
326 985
986 IO::AIO::poll
987 Waits until some requests have been handled.
988
989 Returns the number of requests processed, but is otherwise strictly
990 equivalent to:
991
992 IO::AIO::poll_wait, IO::AIO::poll_cb
993
327 IO::AIO::nreqs 994 IO::AIO::flush
328 Returns the number of requests currently outstanding (i.e. for which 995 Wait till all outstanding AIO requests have been handled.
329 their callback has not been invoked yet).
330 996
331 Example: wait till there are no outstanding requests anymore: 997 Strictly equivalent to:
332 998
333 IO::AIO::poll_wait, IO::AIO::poll_cb 999 IO::AIO::poll_wait, IO::AIO::poll_cb
334 while IO::AIO::nreqs; 1000 while IO::AIO::nreqs;
335 1001
336 IO::AIO::flush 1002 IO::AIO::max_poll_reqs $nreqs
337 Wait till all outstanding AIO requests have been handled. 1003 IO::AIO::max_poll_time $seconds
1004 These set the maximum number of requests (default 0, meaning
1005 infinity) that are being processed by "IO::AIO::poll_cb" in one
1006 call, respectively the maximum amount of time (default 0, meaning
1007 infinity) spent in "IO::AIO::poll_cb" to process requests (more
1008 correctly the mininum amount of time "poll_cb" is allowed to use).
338 1009
339 Strictly equivalent to: 1010 Setting "max_poll_time" to a non-zero value creates an overhead of
1011 one syscall per request processed, which is not normally a problem
1012 unless your callbacks are really really fast or your OS is really
1013 really slow (I am not mentioning Solaris here). Using
1014 "max_poll_reqs" incurs no overhead.
340 1015
341 IO::AIO::poll_wait, IO::AIO::poll_cb 1016 Setting these is useful if you want to ensure some level of
342 while IO::AIO::nreqs; 1017 interactiveness when perl is not fast enough to process all requests
1018 in time.
343 1019
344 IO::AIO::poll 1020 For interactive programs, values such as 0.01 to 0.1 should be fine.
345 Waits until some requests have been handled.
346 1021
347 Strictly equivalent to: 1022 Example: Install an Event watcher that automatically calls
1023 IO::AIO::poll_cb with low priority, to ensure that other parts of
1024 the program get the CPU sometimes even under high AIO load.
348 1025
349 IO::AIO::poll_wait, IO::AIO::poll_cb 1026 # try not to spend much more than 0.1s in poll_cb
350 if IO::AIO::nreqs; 1027 IO::AIO::max_poll_time 0.1;
351 1028
1029 # use a low priority so other tasks have priority
1030 Event->io (fd => IO::AIO::poll_fileno,
1031 poll => 'r', nice => 1,
1032 cb => &IO::AIO::poll_cb);
1033
1034 CONTROLLING THE NUMBER OF THREADS
352 IO::AIO::min_parallel $nthreads 1035 IO::AIO::min_parallel $nthreads
353 Set the minimum number of AIO threads to $nthreads. The current 1036 Set the minimum number of AIO threads to $nthreads. The current
354 default is 4, which means four asynchronous operations can be done 1037 default is 8, which means eight asynchronous operations can execute
355 at one time (the number of outstanding operations, however, is 1038 concurrently at any one time (the number of outstanding requests,
356 unlimited). 1039 however, is unlimited).
357 1040
358 IO::AIO starts threads only on demand, when an AIO request is queued 1041 IO::AIO starts threads only on demand, when an AIO request is queued
359 and no free thread exists. 1042 and no free thread exists. Please note that queueing up a hundred
1043 requests can create demand for a hundred threads, even if it turns
1044 out that everything is in the cache and could have been processed
1045 faster by a single thread.
360 1046
361 It is recommended to keep the number of threads low, as some Linux 1047 It is recommended to keep the number of threads relatively low, as
362 kernel versions will scale negatively with the number of threads 1048 some Linux kernel versions will scale negatively with the number of
363 (higher parallelity => MUCH higher latency). With current Linux 2.6 1049 threads (higher parallelity => MUCH higher latency). With current
364 versions, 4-32 threads should be fine. 1050 Linux 2.6 versions, 4-32 threads should be fine.
365 1051
366 Under most circumstances you don't need to call this function, as 1052 Under most circumstances you don't need to call this function, as
367 the module selects a default that is suitable for low to moderate 1053 the module selects a default that is suitable for low to moderate
368 load. 1054 load.
369 1055
… …
379 ensure that all threads are killed and that there are no outstanding 1065 ensure that all threads are killed and that there are no outstanding
380 requests. 1066 requests.
381 1067
382 Under normal circumstances you don't need to call this function. 1068 Under normal circumstances you don't need to call this function.
383 1069
1070 IO::AIO::max_idle $nthreads
1071 Limit the number of threads (default: 4) that are allowed to idle
1072 (i.e., threads that did not get a request to process within 10
1073 seconds). That means if a thread becomes idle while $nthreads other
1074 threads are also idle, it will free its resources and exit.
1075
1076 This is useful when you allow a large number of threads (e.g. 100 or
1077 1000) to allow for extremely high load situations, but want to free
1078 resources under normal circumstances (1000 threads can easily
1079 consume 30MB of RAM).
1080
1081 The default is probably ok in most situations, especially if thread
1082 creation is fast. If thread creation is very slow on your system you
1083 might want to use larger values.
1084
384 $oldnreqs = IO::AIO::max_outstanding $nreqs 1085 IO::AIO::max_outstanding $maxreqs
1086 This is a very bad function to use in interactive programs because
1087 it blocks, and a bad way to reduce concurrency because it is
1088 inexact: Better use an "aio_group" together with a feed callback.
1089
385 Sets the maximum number of outstanding requests to $nreqs. If you 1090 Sets the maximum number of outstanding requests to $nreqs. If you do
386 try to queue up more than this number of requests, the caller will 1091 queue up more than this number of requests, the next call to the
387 block until some requests have been handled. 1092 "poll_cb" (and "poll_some" and other functions calling "poll_cb")
1093 function will block until the limit is no longer exceeded.
388 1094
389 The default is very large, so normally there is no practical limit. 1095 The default value is very large, so there is no practical limit on
390 If you queue up many requests in a loop it often improves speed if 1096 the number of outstanding requests.
391 you set this to a relatively low number, such as 100.
392 1097
393 Under normal circumstances you don't need to call this function. 1098 You can still queue as many requests as you want. Therefore,
1099 "max_outstanding" is mainly useful in simple scripts (with low
1100 values) or as a stop gap to shield against fatal memory overflow
1101 (with large values).
1102
1103 STATISTICAL INFORMATION
1104 IO::AIO::nreqs
1105 Returns the number of requests currently in the ready, execute or
1106 pending states (i.e. for which their callback has not been invoked
1107 yet).
1108
1109 Example: wait till there are no outstanding requests anymore:
1110
1111 IO::AIO::poll_wait, IO::AIO::poll_cb
1112 while IO::AIO::nreqs;
1113
1114 IO::AIO::nready
1115 Returns the number of requests currently in the ready state (not yet
1116 executed).
1117
1118 IO::AIO::npending
1119 Returns the number of requests currently in the pending state
1120 (executed, but not yet processed by poll_cb).
1121
1122 MISCELLANEOUS FUNCTIONS
1123 IO::AIO implements some functions that might be useful, but are not
1124 asynchronous.
1125
1126 IO::AIO::sendfile $ofh, $ifh, $offset, $count
1127 Calls the "eio_sendfile_sync" function, which is like
1128 "aio_sendfile", but is blocking (this makes most sense if you know
1129 the input data is likely cached already and the output filehandle is
1130 set to non-blocking operations).
1131
1132 Returns the number of bytes copied, or -1 on error.
1133
1134 IO::AIO::fadvise $fh, $offset, $len, $advice
1135 Simply calls the "posix_fadvise" function (see it's manpage for
1136 details). The following advice constants are avaiable:
1137 "IO::AIO::FADV_NORMAL", "IO::AIO::FADV_SEQUENTIAL",
1138 "IO::AIO::FADV_RANDOM", "IO::AIO::FADV_NOREUSE",
1139 "IO::AIO::FADV_WILLNEED", "IO::AIO::FADV_DONTNEED".
1140
1141 On systems that do not implement "posix_fadvise", this function
1142 returns ENOSYS, otherwise the return value of "posix_fadvise".
1143
1144 IO::AIO::mmap $scalar, $length, $prot, $flags, $fh[, $offset]
1145 Memory-maps a file (or anonymous memory range) and attaches it to
1146 the given $scalar, which will act like a string scalar.
1147
1148 The only operations allowed on the scalar are "substr"/"vec" that
1149 don't change the string length, and most read-only operations such
1150 as copying it or searching it with regexes and so on.
1151
1152 Anything else is unsafe and will, at best, result in memory leaks.
1153
1154 The memory map associated with the $scalar is automatically removed
1155 when the $scalar is destroyed, or when the "IO::AIO::mmap" or
1156 "IO::AIO::munmap" functions are called.
1157
1158 This calls the "mmap"(2) function internally. See your system's
1159 manual page for details on the $length, $prot and $flags parameters.
1160
1161 The $length must be larger than zero and smaller than the actual
1162 filesize.
1163
1164 $prot is a combination of "IO::AIO::PROT_NONE",
1165 "IO::AIO::PROT_EXEC", "IO::AIO::PROT_READ" and/or
1166 "IO::AIO::PROT_WRITE",
1167
1168 $flags can be a combination of "IO::AIO::MAP_SHARED" or
1169 "IO::AIO::MAP_PRIVATE", or a number of system-specific flags (when
1170 not available, the are defined as 0): "IO::AIO::MAP_ANONYMOUS"
1171 (which is set to "MAP_ANON" if your system only provides this
1172 constant), "IO::AIO::MAP_HUGETLB", "IO::AIO::MAP_LOCKED",
1173 "IO::AIO::MAP_NORESERVE", "IO::AIO::MAP_POPULATE" or
1174 "IO::AIO::MAP_NONBLOCK"
1175
1176 If $fh is "undef", then a file descriptor of -1 is passed.
1177
1178 $offset is the offset from the start of the file - it generally must
1179 be a multiple of "IO::AIO::PAGESIZE" and defaults to 0.
1180
1181 Example:
1182
1183 use Digest::MD5;
1184 use IO::AIO;
1185
1186 open my $fh, "<verybigfile"
1187 or die "$!";
1188
1189 IO::AIO::mmap my $data, -s $fh, IO::AIO::PROT_READ, IO::AIO::MAP_SHARED, $fh
1190 or die "verybigfile: $!";
1191
1192 my $fast_md5 = md5 $data;
1193
1194 IO::AIO::munmap $scalar
1195 Removes a previous mmap and undefines the $scalar.
1196
1197 IO::AIO::mlockall $flags
1198 Calls the "mlockall" function with the given $flags (a combination
1199 of "IO::AIO::MCL_CURRENT" and "IO::AIO::MCL__FUTURE").
1200
1201 On systems that do not implement "mlockall", this function returns
1202 ENOSYS, otherwise the return value of "mlockall".
1203
1204 IO::AIO::munlockall
1205 Calls the "munlockall" function.
1206
1207 On systems that do not implement "munlockall", this function returns
1208 ENOSYS, otherwise the return value of "munlockall".
1209
1210EVENT LOOP INTEGRATION
1211 It is recommended to use AnyEvent::AIO to integrate IO::AIO
1212 automatically into many event loops:
1213
1214 # AnyEvent integration (EV, Event, Glib, Tk, POE, urxvt, pureperl...)
1215 use AnyEvent::AIO;
1216
1217 You can also integrate IO::AIO manually into many event loops, here are
1218 some examples of how to do this:
1219
1220 # EV integration
1221 my $aio_w = EV::io IO::AIO::poll_fileno, EV::READ, \&IO::AIO::poll_cb;
1222
1223 # Event integration
1224 Event->io (fd => IO::AIO::poll_fileno,
1225 poll => 'r',
1226 cb => \&IO::AIO::poll_cb);
1227
1228 # Glib/Gtk2 integration
1229 add_watch Glib::IO IO::AIO::poll_fileno,
1230 in => sub { IO::AIO::poll_cb; 1 };
1231
1232 # Tk integration
1233 Tk::Event::IO->fileevent (IO::AIO::poll_fileno, "",
1234 readable => \&IO::AIO::poll_cb);
1235
1236 # Danga::Socket integration
1237 Danga::Socket->AddOtherFds (IO::AIO::poll_fileno =>
1238 \&IO::AIO::poll_cb);
394 1239
395 FORK BEHAVIOUR 1240 FORK BEHAVIOUR
1241 This module should do "the right thing" when the process using it forks:
1242
396 Before the fork, IO::AIO enters a quiescent state where no requests can 1243 Before the fork, IO::AIO enters a quiescent state where no requests can
397 be added in other threads and no results will be processed. After the 1244 be added in other threads and no results will be processed. After the
398 fork the parent simply leaves the quiescent state and continues 1245 fork the parent simply leaves the quiescent state and continues
399 request/result processing, while the child clears the request/result 1246 request/result processing, while the child frees the request/result
400 queue (so the requests started before the fork will only be handled in 1247 queue (so that the requests started before the fork will only be handled
401 the parent). Threats will be started on demand until the limit ste in 1248 in the parent). Threads will be started on demand until the limit set in
402 the parent process has been reached again. 1249 the parent process has been reached again.
403 1250
1251 In short: the parent will, after a short pause, continue as if fork had
1252 not been called, while the child will act as if IO::AIO has not been
1253 used yet.
1254
1255 MEMORY USAGE
1256 Per-request usage:
1257
1258 Each aio request uses - depending on your architecture - around 100-200
1259 bytes of memory. In addition, stat requests need a stat buffer (possibly
1260 a few hundred bytes), readdir requires a result buffer and so on. Perl
1261 scalars and other data passed into aio requests will also be locked and
1262 will consume memory till the request has entered the done state.
1263
1264 This is not awfully much, so queuing lots of requests is not usually a
1265 problem.
1266
1267 Per-thread usage:
1268
1269 In the execution phase, some aio requests require more memory for
1270 temporary buffers, and each thread requires a stack and other data
1271 structures (usually around 16k-128k, depending on the OS).
1272
1273KNOWN BUGS
1274 Known bugs will be fixed in the next release.
1275
404SEE ALSO 1276SEE ALSO
405 Coro, Linux::AIO. 1277 AnyEvent::AIO for easy integration into event loops, Coro::AIO for a
1278 more natural syntax.
406 1279
407AUTHOR 1280AUTHOR
408 Marc Lehmann <schmorp@schmorp.de> 1281 Marc Lehmann <schmorp@schmorp.de>
409 http://home.schmorp.de/ 1282 http://home.schmorp.de/
410 1283

Diff Legend

– Removed lines
+ Added lines
< Changed lines
> Changed lines